180 Park Ave - Building 103
Florham Park, NJ
http://www.research.att.com/~kkrama
Subject matter expert in Architecture, protocols and performance of communication networks.
I joined AT&T Bell Labs in 1994 and have been with AT&T Labs-Research since its inception in 1996. Prior to 1994, I was a Technical Director and Consulting Engineer in Networking at Digital Equipment Corporation. I received my MS from the Indian Institute of Science (1978), an MS (1981) and Ph.D. (1983) in Computer Science from the University of Maryland, College Park, Maryland, USA.
Current Work
I work on architecture, protocols and performance of communication networks. My current work is on a range of topics spanning from overlay networks and multimedia distribution to transport and link layer protocols to be robust against loss and disruption and cloud computing and VPNs.
I am currently working on the following issues with several collaborators and students:
1. Adaptive VoD using cooperative peer-assists and multicasts. Caching in a service provider context for VoD, understanding user behavior and providing anonymity in a service provider context for peer-based content distribution.
2. Information dissemination and Recommendation Systems: Our proposal, XTreeNet, integrates both the publish/subscribe and query/response models over a single overlay network. This has motivated the need for large scale multicast and our architecture Multicast with Adaptive Dual State. We are now working on Recommendation Systems.
3. Improving the performance of Transport protocols over lossy and Disruption-prone wireless networks: We have developed Loss-Tolerant TCP (LT-TCP) that uses a combination of packet-level FEC, adaptive MSS and exploits Explicit Congestion Notification (ECN) to make TCP robust against losses of even 50 percent over multi-hop wireless networks. We have a proposed Multipath variant of TCP (MPLOT) which exploits FEC to work exeptionally well in such environments. We are currently working on dealing with disruption-prone links. Another project I have been involved in is to enhance TCP to be usable by P2P applications. We have developed a variant called NF-TCP, which is a Network Friendly Transport protocol for delay-insensitive background traffic (see: http://www.net.informatik.uni-goettingen.de/research_projects/nft )
4. Robust protection and restoration mechanisms of IP backbones to be capable of supporting multimedia distribution.
5. Integration of Cloud Computing and Storage with Virtual Private Networks for transparent and secure use of Cloud resources for Enterprises.
6. The value of Quality of Service Support in IP networks.
Professional activitiesand Recognition
I am an IEEE Fellow (2005), recognized “For contributions to congestion control and traffic management in communication networks".
I am an AT&T Fellow (2006), recognized for "fundamental contributions to communications networks with lasting impact on AT&T and the industry, including congestion control, traffic management and VPN services".
In October 2003, I received the AT&T Strategic Patent Award, in recognition of the patent significantly contributing to AT&T's business, for Patent No. 6,324,279 — Method for Exchanging Signaling Message in Two Phases. (see the web page: http://www.research.att.com/innovators.cfm?portal=17)
My paper “A Binary Feedback Scheme for Congestion Avoidance in Computer Networks with a Connectionless Network Layer” published in the Proceedings of the ACM Sigcomm 1988 received the ACM Sigcomm Test of Time Paper Award in 2006 (see the web page: http://www.sigcomm.org/tot/index.html ). This paper also received recognition in 1995 from ACM Sigcomm for being one of the top innovations in networking in the last 25 years and was republished by ACM SIGCOMM Computer Communications Review in its 25th Anniversary Issue (Jan. 1995).
I am a General Co-Chair for COMSNETS 2012.
I was a TPC Co-Chair and a Vice-Chair for ACM Sigcomm 2010.
I was a General Co-Chair for the IEEE LANMAN 2007 Workshop (http://www.ieee-lanman.org/), held in June 2007.
I was the Technical Program Committee Chair for the LANMAN 2005 Workshop.
I was a Technical Program Co-Chair for the 3rd ACM/IEEE Symposium on Architectures for Networking and Communications Systems (ANCS 2007).
I was a Technical Program Co-Chair for ICNP 2008 (http://www.ieee-icnp.org/).
I was a General Co-Chair for ICNP 2009 (http://www.ieee-icnp.org/) and ANCS 2009 (http://www.ancsconf.org).
I have participated, and continue to participate, in a variety of networking and communications standards bodies such as the IETF, IEEE, WiMAX Forum, ATM Forum etc.
Publications:
A list of some of my publications from our current database appears below. More details, including a (somewhat outdated) publication list (with links to some papers), may be found on my 'old' home page:
This version of the work is reprinted here with permission of IEEE for your personal use. Not for redistribution. The definitive version was published in 2012. , 2013-01-01
{Virtualized cloud-based services can take advantage of statistical
multiplexing across applications to yield significant cost savings. However, achieving similar savings with real-time services can be a challenge. In this paper, we seek to lower a provider's costs for real-time IPTV services through a virtualized IPTV architecture and through intelligent time-shifting of selected services.
Using Live TV and Video-on-Demand (VoD) as examples, we show that we can
take advantage of the different deadlines associated with each service to effectively multiplex these services. We provide a generalized framework for computing the amount of resources needed to support multiple services, without missing the deadline for any service. We construct the problem as an optimization formulation that uses a generic cost function. We consider multiple forms for the cost function (e.g., maximum, convex and concave functions) reflecting the cost of providing the service. The solution to this formulation gives the number of servers needed at different time instants to support these services. We implement a simple mechanism for time-shifting scheduled jobs in a simulator and study the reduction in server load using real traces from an operational IPTV network. Our results show that we are able to reduce the load by $sim24\%$ (compared to a possible $sim31.3\%$ as predicted by the optimization framework). We also show that there are interesting open problems in designing mechanisms that allow time-shifting of load in such environments.}
{Modern day enterprises have a large IT infrastructure
comprising thousands of applications running on
servers housed in tens of data centers geographically spread
out. These enterprises periodically perform a transformation of
their entire IT infrastructure to simplify, decrease operational
costs and enable easier management. However, the large
number of different kinds of applications and data centers
involved and the variety of constraints make the task of
data center transformation challenging. The state-of-the-art
technique for performing this transformation is simplistic, often
unable to account for all but the simplest of constraints. We
present eTransform, a system for generating a transformation
and consolidation plan for the IT infrastructure of large
scale enterprises. We devise a linear programming based
approach that simultaneously optimizes all the costs involved
in enterprise data centers taking into account the constraints
of applications groups. Our algorithm handles the various
idiosyncrasies of enterprise data centers like volume discounts
in pricing, wide-area network costs, traffic matrices, latency
constraints, distribution of users accessing the data etc. We
include a disaster recovery (DR) plan, so that eTransform, thus
provides an integrated disaster recovery and consolidation plan
to transform the enterprise IT infrastructure.
We use eTransform to perform case studies based on real
data from three different large scale enterprises. In our
experiments, eTransform is able to suggest a plan to reduce the
operational costs by more than 50% from the �as-is� state of
these enterprise to the consolidated enterprise IT environment.
Even including the DR capability, eTransform is still able to
reduce the operational costs by more than 25% from the
simple �as-is� state. In our experiments, eTransform is able to
simultaneously optimize multiple parameters and constraints
and discover solutions that are 7x cheaper than other solutions.}
This version of the work is reprinted here with permission of IEEE for your personal use. Not for redistribution. The definitive version was published in FOURTH INTERNATIONAL CONFERENCE ON COMMUNICATION SYSTEMS AND NETWORKS. , 2012-01-04
{Virtualized cloud-based services can take advantage of statistical multiplexing
across applications to yield significant cost savings to the operator. However,
achieving similar benefits with real-time services can be a challenge. In this
paper, we seek to lower a provider's costs of real-time IPTV services through a
virtualized IPTV architecture and through intelligent time-shifting of service
delivery. We take advantage of the differences in the deadlines associated with
Live TV versus Video-on-Demand (VoD) to effectively multiplex these services.
We provide a generalized framework for computing the amount of resources needed
to support multiple services, without missing the deadline for any service. We
construct the problem as an optimization formulation that uses a generic
cost function. We consider multiple forms for the cost function (e.g., maximum,
convex and concave functions) to reflect the different pricing options. The
solution to this formulation gives the number of servers needed at different time instants to support these
services. We implement a simple mechanism for time-shifting scheduled jobs in a
simulator and study the reduction in server load using real traces from an
operational IPTV network. Our results show that we are able to reduce the load
by $sim24\%$ (compared to a possible $sim31\%$). We also show that there
are interesting open problems in designing mechanisms that allow time-shifting
of load in such environments.}
This version of the work is reprinted here with permission of IEEE for your personal use. Not for redistribution. The definitive version was published in IEEE International Conference on Distributed Computing Systems (ICDCS). , 2012-06-18, http://icdcs-2012.org/
{Information-Centric Networking provides substantial
flexibility for users to obtain information without
knowing the source of information or its current location. With
users increasingly focused on an online world, an emerging
challenge for the network infrastructure is to support Massively
Multiplayer Online Role Playing Game (MMORPG).
Currently, MMORPG is built on IP infrastructure with the
primary responsibility resting on servers for disseminating
control messages and predicting/retrieving objects belonging to
each player�s view. Scale and timeliness are major challenges
of such a server-oriented gaming architecture. Limited server
resources significantly impair the user�s interactive experience,
requiring game implementations to limit the number of players
in a single game instance. We propose Gaming over COPSS (GCOPSS),
a distributed communication infrastructure using a
Content-Oriented Pub/Sub System (COPSS) to enable efficient
decentralized information dissemination in MMORPG, jointly
exploiting the network and end-systems for player management
and information dissemination. G-COPSS aims to scale well in
the number of players in a single game, while still meeting
users� response time requirements.
We have implemented G-COPSS on top of the open-source
CCNx implementation. We use a simple game with a hierarchical
map to carefully microbenchmark the implementation and
the processing involved in managing game dynamics. We have
also microbenchmarked the game based on NDN and a server
with an IP infrastructure. We emulate an application that is
particularly emblematic of MMORPG � Counter-Strike � but
one in which all players share a hierarchical structured map.
Using trace-driven simulation, we demonstrate that G-COPSS
can achieve high scalability and tight timeliness requirements
of MMORPG. The simulator is parameterized based on microbenchmarks
of our implementation. Our evaluations show
that G-COPSS provides orders of magnitude improvement in
update latency and a factor of two reduction in aggregate
network load compared to a server-based implementation.}
The definitive version was published in 2012 , 2012-06-01, http://comjnl.oxfordjournals.org
{Cloud computing platforms such as Amazon EC2 provide customers with flexible,
on demand resources at low cost. However, while existing offerings are useful for
providing basic computation and storage resources, they have not provided the
transparency, security and network controls that many enterpise customers would
like. While cloud computing has a great potential to change how enterprises
run and manage their IT systems, a more comprehensive control over network
resources and security needs to be provided for such users. Towards this goal, we
propose a Virtual Cloud Pool abstraction to logically unify cloud and enterprise
data center resources, and present the vision behind CloudNet, a cloud platform
architecture which utilizes virtual private networks to securely and seamlessly
link cloud and enterprise sites. It also enables the pooling of resources across
data centers to provide enterprises the capability to have cloud resources that
are dynamic and adaptive to their needs. We describe several usage scenarios for
virtual cloud pools and discuss the benefits of using this abstraction in enterprise
settings.}
(c) ACM, 2012. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in 2012 , 2012-10-29, http://www.ancsconf.org/.
{Content-Centric Networking (CCN) seeks to meet the content-
centric needs of users. In this paper, we propose hybrid-
COPSS, a hybrid content-centric architecture. We build on
the previously proposed Content-Oriented Publish/Subscribe
System (COPSS) to address incremental deployment of CCN
and elegantly combine the functionality of content-centric
networks with the efficiency of IP-based forwarding including
IP multicast. Furthermore, we propose an approach for
incremental deployment of caches in generic query/response
CCN environments that optimizes latency and network load.
To overcome the lack of inter-domain IP multicast, hybrid-
COPSS uses COPSS multicast with shortcuts in the CCN
overlay. Our hybrid approach would also be applicable to
the Named Data Networking framework.
To demonstrate the benefits of hybrid-COPSS, we use a
multiplayer online gaming trace in our lab test-bed and microbenchmark
the forwarding performance and queuing for
both COPSS and hybrid-COPSS. A large scale trace-driven
simulation (parameterized by the microbenchmark) on a representative
ISP topology was used to evaluate the response
latency and aggregate network load. Our results show that
hybrid-COPSS performs better in terms of response latency
in a single domain. In a multi-domain environment, hybrid-
COPSS significantly reduces inter-domain traffic with only
a small increase in the average response latency.}
(c) ACM, 2012. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in 2012 , 2012-08-17, http://conferences.sigcomm.org/sigcomm/2012/icn.php.
{Content Centric Networking (CCN) is a new paradigm that
addresses the gap between the content-centric needs of a
user and the current widespread location-centric IP network
architecture. In this paper, we propose a hybrid content centric
architecture based on our pub/sub enhancement to CCN,
Content-Oriented Publish/Subscribe System (COPSS). Our
hybrid architecture (hybrid-COPSS) addresses both the need
for incremental deployment of CCN and also elegantly combines
the functionality of content centric networks and the
efficiency of IP forwarding. Our architecture integrates IP
multicast to achieve forwarding efficiency by taking advantage
of shortest path routing. To overcome the lack of interdomain
IP multicast, hybrid-COPSS uses COPSS multicast
with shortcuts as an overlay and IP multicast as the underlay
to achieve inter-domain COPSS multicast.
To demonstrate the benefits of our hybrid-COPSS architecture,
we study its applicability for online gaming, which
typically requires low latency. We use a gaming trace in
our lab test-bed and microbenchmark the forwarding performance
and queuing for a pure COPSS (representative of a
pure CCN) based network versus hybrid-COPSS. Also, a
large scale simulation (parameterized by the microbenchmark)
on a representative ISP topology was used to evaluate
the response latency and aggregate network load for the
multi-player online gaming scenario. Our preliminary results
show that hybrid-COPSS performs better in terms of
response latency compare to pure COPSS in a single domain.
In a multi-domain environment, hybrid-COPSS can
significantly reduce inter-domain traffic while causing only
a small increase in the average response latency.}
(c) ACM, 2011. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in IMC 2011, 2011-11-02.
{We investigate how consumers view content using Video on
Demand (VoD) in the context of an IP-based video distribution
environment. Users today can use advanced stream
control functions like skip and replay in addition to play,
fast-forward, rewind, pause etc., to interactively control their
viewing. Such stream control, however, places additional
demands on the distribution infrastructure (servers, network,
and set top boxes) and can be challenging to manage with a
large subscriber base. A model of user-interaction is useful
to provide key insights on their impact on server and bandwidth
requirements, client responsiveness, etc.
We capture user activity in their natural setting of viewing
video at home. We first develop a model for the arrival
process of requests for content. We then develop two stream
control models that accurately capture user interaction. We
show that stream control events can be characterized by a finite
state machine and a sojourn time model, parametrized
for major periods of usage (weekend and weekday). Our
semi-Markov (SM)model for the sojourn time in each stream
control state uses a novel technique based on a polynomial fit
to the logarithm of the Inverse CDF. A second Constrained
model (CM) uses a stick-breaking approach familiar in machine
learning to model the individual state sojourn time
distributions. The SM model seeks to preserve the sojourn
time distribution for each state while the CM model puts a
greater emphasis on preserving the overall session duration
distribution. Using traces across a period of 2 years from
a large-scale operational IPTV environment we validate the
proposed model and show that we are able to faithfully predict
the workload presented to a video server. We also provide
a synthetic trace developed from the model enabling
researchers to also study other problems of interest.}
(c) ACM, 2011. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in [ACM Symposium on Cloud Computing , 2011-10-27.
{Disaster Recovery (DR) is a desirable feature for all enterprises, and a crucial one for many. However, adoption of DR remains limited due to the stark tradeoffs it imposes. To be able to recover an application to the point of crash, one is limited by financial considerations, substantial application overhead, or minimal geographical separation between the primary and recovery sites. In this paper, we argue for cloud-based DR and pipelined synchronous replication as an antidote to these problems. Cloud hosting promises economies of scale and on-demand provisioning that are a perfect fit for the infrequent yet urgent needs of DR. However the WAN latency between a cloud site and an enterprise can become a major performance bottleneck when synchronously replicating an application's data into the cloud. Pipelined synchrony addresses this problem by tracking the causal consequences of the disk modifications that are persisted to a recovery site, while allowing the application to make forward progress in its handling of client requests. In this manner, we efficiently overlap replication delay with application processing for multi-tier distributed servers, while retaining full consistency guarantees for application state in the event of a disaster. PipeCloud, our prototype, is able to sustain these guarantees for multi-node servers composed of black-box VMs, with no need of application modification, resulting in a perfect fit for the arbitrary nature of VM-based cloud hosting. Our extensive evaluation shows that PipeCloud achieves significant performance improvements over existing replication strategies, and demonstrates proper disaster failover to the Amazon EC2 platform. PipeCloud can increase throughput by an order of magnitude and reduces response times by more than half compared to synchronous replication, all while providing the same zero data loss consistency guarantees.}
(c) ACM, 20XX. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in Proc. of ACM Internet Measurement Conference (IMC). , 2011-11-01.
{Cellular networks have witnessed tremendous traffic growth
recently, fueled by smartphones, tablets and new high speed
broadband cellular access technologies. A key application
driving that growth is video streaming. Yet very little is
known about the characteristics of this traffic class. In this
paper, we examine video traffic generated by three million
users across one of the world�s largest 3G cellular networks.
This first deep dive into cellular video streaming shows that
HLS, an adaptive bitrate streaming protocol, accounts for
one third of the streaming video traffic and that it is common
to see changes in encoding bitrates within a session. We also
observe that most of the content is streamed at less than 255
Kbps and that only 40% of the videos are fully downloaded.
Another key finding is that there exists significant potential
for caching to deliver this content.}
Nemor: A Congestion-Aware Protocol for Anonymous Peer-based Content Distribution Fang Yu, Vijay Gopalakrishnan, David Lee, K. K. Ramakrishnan
Proceedings of IEEE P2P,
Submitted to IEEE International conference on Peer-to-Peer Computing (P2P 2011),
2011.
[PDF][BIB]
IEEE Copyright
This version of the work is reprinted here with permission of IEEE for your personal use. Not for redistribution. The definitive version was published in IEEE International conference on Peer-to-Peer Computing (P2P 2011). , 2011-08-31
As content providers adopt peer-to-peer approaches for content sharing and distribution, they face new challenges in guaranteeing privacy to their clients. Participating peers can glean information from their communication with other peers, such as their identities or the shared data and use this information for malicious purposes. We present Nemor, a protocol that allows a requesting peer and a corresponding serving peer to communicate anonymously with each other and from other participating peers, while protecting the identity of the content being exchanged. Nemor relies on a trusted intermediary, such as a provider-managed tracker, to identify a potential serving peer. A peer in Nemor joins one or more trees. Using a combination of a random walk, a probabilistic jump from one tree to another and constrained flooding, the requesting and serving peer dynamically construct an overlay path between them. A key differentiator of Nemor is the integrated design of a congestion avoidance mechanism that yields significant performance benefits without compromising on anonymity. Using experimental results from PlanetLab and simulations with traces from an operational VoD system, we demonstrate that Nemor outperforms state of the art approaches like TOR and OneSwarm. Our results confirm that Nemor, while being resilient to attacks on anonymity, achieves high performance and scalability and is suitable for a range of applications, including distribution of large volume content, such as streaming video.
{Practical network coding systems for wireless networks employ network coding across unicast sessions to improve throughput. In this paper, we propose an approach, I2NC, that combines inter- and intra-session network coding to improve performance in lossy wireless environments. I2NC provides resilience to loss thanks to the error-correcting capabilities of intra-session network coding. Furthermore, redundancy allows intermediate nodes to operate without the knowledge of the decoding buffers at their neighbors. Based only on the knowledge of average
loss rates on the direct and overhearing links, intermediate nodes can make decisions for both intra-session (i.e., how much redundancy to add in each flow) and inter-session (i.e., what percentage of flows to code together) coding. Our approach is
grounded on a network utility maximization formulation of the problem. We propose two practical schemes, I2NC-state and I2NC-stateless, that mimic the structure of the NUM optimal solution and implement the properties mentioned above. We also address the interaction of our approach with the transport layer. We demonstrate the benefits of our schemes (in terms of error resilience, and thereby throughput) compared to COPE, through simulation in GloMoSim.}
This version of the work is reprinted here with permission of IEEE for your personal use. Not for redistribution. The definitive version was published in 18th IEEE International Workshop on Local and Metropolitan Area Networks. , 2011-10-13
{With users increasingly focused on an online world,
an emerging challenge for the network infrastructure is the need
to support Massively Multiplayer Online Role Playing Games
(MMORPG). This is an application domain that is attracting
more players than ever before, very often with players distributed
over a metropolitan area. Currently, MMORPG are built on
an IP infrastructure with the primary responsibility on servers
to do the work of disseminating control messages and having
to predict/retrieve objects in each player�s view. Limited server
resources significantly impair the user�s interactive experience.
Modern fast-paced action games that run on a client/server
architecture limit the number of players who can interact
simultaneously since the server needs to handle the frequent
updates and disseminate them. Scale and timeliness are major
challenges of such a server-oriented gaming architecture.
We propose Gaming over COPS (GCOPS), a communication
infrastructure using a Content-Oriented Pub/Sub system (COPS)
to enable efficient decentralized information dissemination in
MMORPG, exploiting the network and the end-systems for
player management and information dissemination. We emulate
an application that is particularly emblematic of MMORPG
� Counter-Strike � but one in which all the players share
a hierarchical structured map. Using trace-driven simulation,
we demonstrate that GCOPS can achieve high scalability and
tight timeliness requirements of MMORPG. The simulator is
parameterized using the results of careful microbenchmarking
of the open-source CCN implementation and of standard IPbased
forwarding. Our evaluations show that GCOPS provides
considerable performance improvement in terms of aggregate
network load and update latency compared to that of a traditional
IP server-based infrastructure.}
The definitive version was published in IEEE INFOCOM Cloud Computing Workshop , 2011-04-10
{Cloud computing is a new infrastructure environment
that delivers on the promise of supporting on-demand
services in a flexible manner by scheduling bandwidth, storage
and compute resources on the fly. IPTV services like Video
On Demand (VoD) and Live broadcast TV requires substantial
bandwidth and compute resources to meet the real time requirements
and to handle the very bursty resource requirements
for each of these services. To meet the needs of the bursts of
requests, each with a deadline constraint for both VoD and
LiveTV channel changes, we propose a resource provisioning
framework that allows these services to co-exist on a common
infrastructure by taking advantage of virtualization. We propose
an optimal algorithm that provides the minimum number of
servers needed to fulfill all requests for these services. We prove this
optimality in a general setting for any number of services with
general deadline constraints. By using real world data from an
operational IPTV environment, our results show that anticipating
and thereby enabling the delaying of VoD requests by up to 30
seconds gives significant resource savings even under conservative
environmental assumptions. We also experiment with different
scenarios (by varying the deadline constraints, changing the peak
to average ratios of the constituent services) to compute the
overall savings.}
Cost and Reliability Considerations in Designing the Next-Generation IP over WDM Backbone Networks Byrav Ramamurthy, Kadangode Ramakrishnan, Rakesh Sinha
International Conference on Computer Communication Networks (IEEE ICCCN 2011),
2011.
[PDF][BIB]
IEEE Copyright
This version of the work is reprinted here with permission of IEEE for your personal use. Not for redistribution. The definitive version was published in International Conference on Computer Communication Networks (IEEE ICCCN 2011). , 2011-07-31, http://icccn.org/icccn11/
To accommodate the increasing demands for bandwidth,
Internet Service Providers (ISPs) have deployed higherspeed
links and reconfigurable optical add drop multiplexers
(ROADMs) in their backbone networks. To address the reliability
challenges due to failures and planned outages, ISPs typically
use two backbone routers at each central office in a dualhome
configuration. Thus at the IP layer, redundant backbone
routers as well as redundant transport equipment to interconnect
them are deployed to provide reliability through node and path
diversity. However, adding such redundant resources increases
the overall cost of the network. Hence, a fundamental redesign
of the backbone network which avoids such redundant resources
by leveraging the capabilities of an intelligent optical transport
network is a highly desirable objective. It is clear that such a
redesign must lower costs without compromising on the reliability
achieved by today�s backbone networks. Modeling the costs and
reliability of the network at all layers is an important step in
achieving this objective. In this paper, we undertake an in-depth
investigation of the cost and reliability considerations involved
in designing the next-generation backbone network. Our work
includes a detailed analysis of the operation, cost and reliability
of the network at the IP layer and the multiple layers below it.
We discuss alternative backbone network designs which use only
a single router at each central office but use the optical transport
layer to carry traffic to routers at other offices in order to survive
failures or outages of the single local router. We discuss trade-offs
involved in using these designs.
{Cloud computing platforms are growing from clusters of machines within a data center to networks of data centers with resources spread across the globe. Virtual machine migration within the LAN has changed the scale of resource management from allocating resources on a single server to manipulating pools of resources within a data center. We expect WAN migration to likewise transform the scope of provisioning from a single data center to multiple data centers spread across the country or around the world. In this paper we propose a cloud computing platform linked with a VPN based network infrastructure that provides seamless connectivity between enterprise and data center sites, as well as support for live WAN migration of virtual machines. We describe a set of optimizations that minimize the cost of transferring persistent storage and moving virtual machine memory during migrations over low bandwidth, high latency Internet links. Our evaluation on both a lo- cal testbed and across multiple geographically distributed data center sites demonstrates that these improvements can reduce total migration and pause time by over 30%. During simultaneous migrations of four VMs between Texas and Illinois, Cloud- Net?s optimizations can reduce memory migration time by 65% and lower total bandwidth utilization for the storage and memory transfer by 20GB }
This version of the work is reprinted here with permission of IEEE for your personal use. Not for redistribution. The definitive version was published in IEEE LANMAN 2011. , 2011-10-13
{The end to end system data performance over a 3G cellular network depends on many factors such as the number of users, interference, multipath propagation, radio resource management techniques as well as the interaction between these mechanisms and the transport protocol's flow and congestion mechanisms. Using controlled experiments in a public cell site, we investigate the interaction between TCP and the 3G UMTS/HSPA network's resource allocation, and its effect on fairness in the throughput achieved across multiple (up to 26) TCP flows in a loaded cell sector. Our field measurement results indicate that TCP fairness fluctuates significantly when the air interface (radio link) is the bottleneck. We also observe that TCP fairness is substantially better when the backhaul link (a fixed wired link) is the bottleneck, instead of the air interface. We speculate that the fairness of TCP flows is adversely impacted by the mismatch between the resource allocation mechanisms of TCP's flow and congestion control and that of the Radio Access Network (RAN).}
The definitive version was published in COMSNETS 2011. , 2011-01-05, http://www.comsnets.org/
{Service providers are evolving to provide more video content on-demand. Customers like to watch a variety of entertainment content of their choice and at a time conducive
to their schedules. Catering to this ever-increasing user base requires careful provisioning by the providers to accommodate for both scale and interactivity. In this paper, we examine the usage pattern of several hundreds of thousands of consumers of a nationwide IPTV service, and confirm that viewers are indeed
migrating to what is called �time-shifted� viewing of television programming and movies using digital video recorders or on demand viewing. We also show how users of on-demand content interactively control their viewing experience using �stream control� functions such as fast-forward, rewind, skip, replay, etc. Through careful measurements on an IPTV server, we compute the load due to streaming and handling these stream control events. We then extrapolate from these micro-benchmark
measurement to predict the processing load imposed by users that would resort to using a �network-based� DVR capability if such a service were offered. We use both detailed trace-driven simulations and a simple operational-analysis based model to
predict the capacity requirements of the server complex in the VHO to serve a large population of customers (e.g. a densely populated city like Mumbai). We provide insights on the number of requests serviced by the server, the average time to service
these requests and the response time as perceived by the client.}
(c) ACM, 2011. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ANCS 2011: ACM/IEEE Symposium on Architectures for Networking and Communications SystemsANCS 2011: ACM/IEEE Symposium on Architectures for Networking and Communications SystemsANCS 2011: ACM/IEEE Symposium on Architectures for Networking and Communications SystemsANCS 2011: ACM/IEEE Symposium on Architectures for Networking and Communications SystemsANCS 2011: ACM/IEEE Symposium on Architectures for Networking and Communications Systems. , 2011-10-03.
{Content-Centric Networks (CCN) provide substantial flexibility
for users to obtain information without regard to the
source of the information or its current location. Publish/
subscribe (pub/sub) systems have gained popularity in society
to provide the convenience of removing the temporal dependency
of the user having to indicate an interest each time
he or she wants to receive a particular piece of related information.
Currently, on the Internet, such pub/sub systems
have been built on top of an IP-based network with the additional
responsibility placed on the end-systems and servers
to do the work of getting a piece of information to interested
recipients. We propose Content-Oriented Pub/Sub system
(COPS) to achieve an efficient pub/sub capability for CCN.
COPS enhances the heretofore inherently pull-based CCN
architectures proposed by integrating push based multicast
at the content-centric layer.
We emulate an application that is particularly emblematic
of a pub/sub environment�Twitter�but one where subscribers
are interested in content (e.g., identified by keywords),
rather than tweets from a particular individual. Using
trace-driven simulation, we demonstrate that our architecture
can achieve a scalable and efficient pub/sub content
centric network. The simulator is parameterized using the
results of careful microbenchmarking of the open source CCN
implementation and of standard IP based forwarding.
Our evaluations show that COPS provides considerable performance
improvements in terms of aggregate network load,
publisher load and subscriber experience compared to that
of a traditional IP infrastructure.}
{Consumer communications and entertainment services, including broadcast TV and VoIP require service providers to meet stringent availability and latency constraints. When a packet technology, such as IP, is used to transport these services, this also poses stringent packet loss requirement on the network. This aspect of IPTV, where impairments have consumer-visible impact and potential public relations consequences, creates new challenges in protocol design, as well as network management. The key to operating an effective network is to expand beyond the typical ?reactive? network management approach to be able to anticipate and manage potential network problems. This paper describes network management techniques deployed in a production IPTV network with over 2 million customers. }
(c) ACM, 2010. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ACM CoNext 2010 , 2010-12-01
IPTV service providers offering Video-on-Demand (VoD) typically have many servers at each metropolitan office to store all the videos in the library. With the rapid increase in the VoD library size, it will soon become infeasible to replicate the entire library at each office. We present an approach for intelligent content placement that scales to large VoD library sizes (e.g., 100Ks of videos). We formulate the problem as a mixed integer program (MIP) that takes into account constraints
such as disk space, link bandwidth, and the skew in content popularity. To overcome the challenges of scale, we employ a Lagrangian relaxation-based decomposition technique that can find a near-optimal solution (e.g., within 1-2%) with orders of magnitude speedup, relative to solving even the LP relaxation via standard software. We also present simple strategies to address practical issues such as popularity estimation, content updates, short-term popularity fluctuation, and frequency
of placement updates. Using traces from an operational system, we show that our approach significantly outperforms simpler placement strategies. For instance, our MIP-based solution can serve all requests using only half the link bandwidth used by LRU cache replacement policy. We also investigate the trade-off between disk space and network bandwidth.
{Delay-insensitive applications such as P2P file sharing,
data center backups and software updates, generate substantial
amounts of traffic. This traffic, transported potentially
over multiple TCP connections, competes with traffic from other
possibly interactive applications. Today, with TCP, they compete
on an equal footing for each individual connection. In this
paper, we propose a new TCP variant for such delay-insensitive
applications, which we call Network Friendly TCP (NF-TCP).
NF-TCP is responsive to available bandwidth, seeking to quickly
and efficiently utilize available bandwidth in a congestion-free
situation, while backing-off more aggressively than standard TCP
when encountering competing traffic that results in even incipient
congestion. NF-TCP uses a novel combination of utilizing
measurement of available bandwidth and ECN-based congestion
avoidance techniques to ensure that it is truly friendly to existing
TCP connections. We evaluate the performance of NF-TCP
through ns-2 simulations and present initial results showing the
friendly nature of NF-TCP compared to standard TCP.}
The definitive version was published in 2nd USENIX Workshop on Hot Topics in Cloud Computing (HotCloud '10)., 2010-06-22
{Many businesses rely on Disaster Recovery (DR) services to prevent either manmade or natural disasters from causing ex- pensive service disruptions. Unfortunately, current DR services come either at very high cost, or with only weak guarantees about the amount of data lost or time required to restart opera- tion after a failure. In this work, we argue that cloud comput- ing platforms are well suited for offering DR as a service due to their pay-as-you-go pricing model that can lower costs, and their use of automated virtual platforms that can minimize the recovery time after a failure. To this end, we perform a pricing analysis to estimate the cost of running a public cloud based DR service and show significant cost reductions compared to using privately owned resources. Further, we explore what additional functionality must be exposed by current cloud platforms and describe what challenges remain in order to minimize cost, data loss, and recovery time in cloud based DR services.}
{Interactivity is promised by IP-based content distribution, particularly with IPTV. We investigate the user viewing activity for broadcast TV, pre-recorded content using Digital Video Recording (DVR) and video on demand (VoD). Advanced stream control functions (play, pause, skip, rewind, etc.) provide users with a high level of interactivity, but place demands on the distribution infrastructure (servers, network, home-network) that can be difficult to manage at large scale. To support system design as well as network capacity planning, it is necessary to have a good model of user interaction. Using traces from a well-provisioned operational environment with a large user population, we first characterize interactivity for broadcast TV, DVR and VoD. We then develop parametric models of individual users stream control operations for VoD. Our analysis shows that interactive behavior is adequately characterized by two semi-Markov models, one for weekdays and another for weekends. We propose a parametric model for the underlying sojourn time distributions and show that it results in a superior fit compared to well known distributions (generalized Pareto and Weibull). In order to validate that our models faithfully capture user behavior, we compare the workload that a VoD server experiences in response to actual traces and synthetic data generated from our proposed models. }
{Multicast has seen a resurgence in the recent past, driven by the need to efficiently disseminate large volumes of real-time content, especially with the growth of IPTV. Video-on-Demand (VoD) delivery by multicasting still remains a challenge. Requests for popular content can be aggregated and served by multicast groups, but it has always been uncertain as to how much aggregation can be achieved. In this paper, we show that combining a good data model and an intelligent scheduler can help us realize significant benefits through multicast. Our design investigates an Earliest Deadline First-like (EDF) scheduler that aims to schedule the transmission of video ``chunks" according to their deadlines over multicast groups. We show through analysis that a dynamic multicast approach we term EDF-D is optimal, and minimizes the number of chunks sent from the VoD server. We use VoD request data from an operational service to quantify the benefit of multicasting and the amount of aggregation. Specifically, we observe a significant reduction in server bandwidth when compared to traditional techniques like unicast (65\%) and cyclic multicast (58\%). Finally, we show that even with 50\% of the requesting users performing some amount of fast forwarding, there is negligible reduction in the amount of aggregation. Version 3 reflects the changes made to conform for the camera ready manuscript for ACM Multimedia 2009 conference. The technical material in this version has only been slightly modified to account for reveiwers' comments. }
This is the author's version of the work. It is posted here by permission of Usenix for your personal use. Not for redistribution. The definitive version was published in HotCloud '09. , 2009-06-14, http://www.usenix.org/event/hotcloud09/.
{Cloud computing platforms such as Amazon EC2 provide customers
with flexible, on demand resources at low cost. However,
while existing offerings are useful for providing basic
computation and storage resources, they fail to provide the security
and network controls that many customers would like. In
this work we argue that cloud computing has a great potential
to change how enterprises run and manage their IT systems, but
that to achieve this, more comprehensive control over network
resources and security need to be provided for users. Towards
this goal, we propose CloudNet, a cloud platform architecture
which utilizes virtual private networks to securely and seamlessly
link cloud and enterprise sites.}
{The use of peer-to-peer (P2P) mechanisms for content delivery is attractive to content and service providers alike. P2P data transfers offload the demand on servers and reduce the bandwidth requirements, with corresponding benefits of improved scalability and performance. This, however, poses interesting challenges in ensuring content integrity. Peers may be malicious and attempt to send corrupt and/or inappropriate content to disrupt the service. Consequently, service providers must provide clients with the capability to validate the integrity of content delivered from peers. This goal is particularly challenging in the context of streaming video because the content needs to be validated in real time. A practical solution must provide high integrity assurance while incurring low communication and computation overhead. In this paper, we present a packet-based validation approach for ensuring the integrity of data obtained from peers. Our proposed scheme randomly selects packets and validates their correctness. Through detailed experiments, we show that this mechanism is not only lightweight but is also able to detect content corruption with very high probability, thus protecting a service provider's content delivery service. }
{Broadcast TV distribution over an IP network requires stringent QoS constraints, such as low latency and loss. Streaming content in IPTV is typically delivered to the distribution points on the IP backbone using IP multicast protocols such as Protocol Independent Multicast Source Specific Mode (PIM-SSM). Link-restoration using MPLS or layer-2 Fast Reroute (FRR) is a proven failure restoration technique at the IP layer. Link-based FRR creates a pseudo-wire or tunnel in parallel to the IP adjacencies (links); and thus, single link failures are transparent to the Interior Gateway Protocol (IGP). Although one may choose the back-up path?s IGP link weights to avoid traffic overlap during any single physical link failure, multiple failures may still cause traffic overlap with FRR. We present a cross-layer restoration approach that combines both FRR-based restoration for single link failure and ?hitless? (i.e., without loss) PIM tree reconfiguration algorithms to prevent traffic overlap when multiple failures occur. Addl AT&T author: Wang, Dongmei }
{IPTV delivers television content over an IP infrastructure with the potential to enrich the viewing experience of users by integrating data applications with video delivery. From an engineering perspective, IPTV places both significant steady state and transient demands on network bandwidth. Typical IPTV streaming techniques incur delays to fill the play-out buffer. But, when viewers switch or surf channels, it is important to minimize this user-perceived latency. Traditional Instant Channel Change (ICC) techniques reduce this latency by having a separate unicast assist channel for every user changing channels. Instead, we propose a multicast-based approach using a secondary "channel change stream" in association with the multicast of the regular quality stream for the channel requested. During channel change events, the user does a multicast join to this new stream and experiences smaller display latency. In the background, the play-out buffer of the new full-quality multicast stream is filled. Then, the transition to the new channel is complete. We show that this approach has several performance benefits including lower bandwidth consumption even during flash crowds of channel changes, lower display latency (50% lower), and lower variability of network & server load. The tradeoff is a lower quality video during the play-out buffering period of a few seconds. Our results are based upon both synthetic channel change arrival patterns as well as traces collected from an operational IPTV environment. }
{We present CPM, a unified approach that exploits server multicast, assisted by peer downloads, to provide efficient video-on-demand (VoD) in a service provider environment. We describe our architecture and show how CPM is designed to dynamically adapt to a wide range of situations including highly different peer-upload bandwidths, content popularity, user request arrival patterns (including flash-crowds), video library size, and subscriber population. We demonstrate the effectiveness of CPM using simulations (based on the an actual implementation codebase) across the range of situations described above and show that CPM does significantly better than traditional unicast, different forms of multicast, as well as peer-to-peer schemes. Along with synthetic parameters, we augment our experiments using data from a deployed VoD service to evaluate the performance of CPM. Original document was a presentation. This is a paper we have written, and submitted to a conference. The first author has also been changed. }
{Abstract. The ability of an IP backbone network to deliver robust and dependable communications relies on quickly restoring service after failures. Service-level agreements (SLAs) between a network service provider and customers typically include overall availability and performance objectives. To achieve the desired SLA, we have developed a methodology for the combined analysis of performance and reliability (performability)of networks across multiple layers by modeling the probabilistic failure state space in detail and analyzing different restoration alternatives. This methodology has been used to analyze large commercial IP-over-Optical layer networks. In this paper we extend our methodology to evaluate restoration approaches for an IP-based satellite backbone network. Because of the environment in which they operate (long delay links, frequent impairments), satellite networks pose an interesting challenge to typical restoration strategies. We describe the potential multi-layer restoration alternatives and compare their performability. Interestingly, while it is commonly thought that SONET ring restoration at the lower layer improves overall reliability, we find that it may not always improve performability in this environment. }
{Multicast is an approach that uses network and server resources efficiently to distribute information to groups. As networks evolve to become information-centric, users will increasingly demand publish-subscribe based access to fine-grained information, and multicast will need to evolve to (i) manage an increasing number of groups, with a distinct group for each piece of distributable content; (ii) support persistent group membership, as group activity can vary over time, with intense activity at some times, and infrequent (but still critical) activity at others. These requirements raise scalability challenges that are not met by today's multicast techniques. }
{In this paper, we propose and study a novel transport protocol that can effectively utilize available bandwidth and diversity gains provided by heterogeneous, highly lossy paths. Our Multi-Path LOss-tolerant Transport (MPLOT) protocol can be used to provide significant gains in the goodput of wireless mesh networks, subject to bursty, correlated losses with average rates as high as 50%, and random outage events. MPLOT makes intelligent use of erasure codes to guard against packets losses, and a Hybrid-ARQ/FEC scheme to reduce packet recovery latency, where the redundancy is adaptively provisioned into both proactive and reactive FECs. MPLOT uses dynamic packet mapping based on current path characteristics, and does not require packets to be delivered in sequence to ensure reliability. We present a theoretical analysis of the diversity gain that can be obtained from the available lossy paths and show that MPLOT makes full use of the diversity gain through simulations, under a variety of test scenarios. We also show that MPLOT co-exists fairly with traditional singlepath protocols like TCP-SACK. }
{A significant concern for Internet-based service providers is the continued operation and availability of services in the face of outages, whether planned or unplanned. In this paper we advocate a cooperative, context-aware approach to data center migration across WANs to deal with outages in a non-disruptive manner. We specifically seek to achieve high availability of data center services in the face of both planned and incidental outages of data center facilities. We make use of server virtualization technologies to enable the replication and migration of server functions. We propose new network functions to enable server migration and replication across wide area networks (i.e., the Internet), and finally show the utility of intelligent and dynamic storage replication technology to ensure applications have access to data in the face of outages with very tight recovery point objectives. }
{Multi-hop wireless meshed networks are being considered as backbones in metro broadband deployments. In such networks, wireless links need to offer low link-latencies, high goodput and low residual loss rates. Due to non-line-of-sight deployments involving fading/interference, such links experience high/bursty errors, especially at higher bit rates. Traditionally, wireless links use retransmissions (ARQ) and adaptive modulation/ coding to overcome loss. The price paid is reduced goodput (affecting bulk applications) and higher per-hop latencies (affecting latency-sensitive applications over multiple hops). Our paper starts with the design of a link-level hybrid ARQ scheme (LLHARQ) to achieve high goodput and low residual loss rate with limited ARQ attempts. While LL-HARQ performs well, it exports a small residual loss rate under high/bursty loss scenarios. Over multiple hops, this small residual loss accumulates and TCPSACK performance suffers. A transport protocol (LT-TCP) designed for loss tolerance achieves the best performance in combination with LL-HARQ, though TCP-SACK is sufficient if residual loss accumulation is under 5%. This suggests a division of reliability functions where link-layer attempts reliability with tight latency constraints, and transport layer support handles residual erasures. We develop insights for structuring FEC, and verify the goodput-loss rate-latency trade-offs and impact of bursty losses and multiple hops through simulations. }
{This paper argues that the network latency due to synchronous replication is no longer tolerable in scenarios where businesses are required by regulation to separate their secondary sites from the primary by hundreds of miles. We propose a semantic-aware remote replication system to meet the contrasting needs of both system efficiency and safe remote replication with tight recovery-point and recovery-time objectives. Using experiments conducted on a commercial replication system and on a Linux file system we show that (i) unlike synchronous replication, asynchronous replication is relatively insensitive to network latency, and (ii) applications such as databases already intelligently deal with the weak persistency semantics offered by modern file systems. Our proposed system attempts to use asynchronous replication whenever possible and uses application/file-system ?signals? to maintain synchrony between the primary and secondary sites. We present a high-level design of our system and discuss several potential challenges that need to be addressed in such a system. }
{Multimedia distribution, especially broadcast TV distribution over an IP network requires high bandwidth combined with tight latency and loss constraints, even under failure conditions. Due to high bandwidth requirements of broadcast TV distribution, use of IP-based multicast to distribute TV content is needed for capacity efficiency. The protection and restoration mechanisms currently adopted in IP backbones use either IGP re-convergence or some form of Fast Reroute. The IGP re-convergence mechanism is too slow for real-time multimedia distribution while a drawback of fast reroute is that since they re-route traffic on a link-basis (instead of end-to-end) they can suffer traffic overlap during failures. Here traffic overlap is defined as the same traffic passing through the same link along the same direction more than once, which requires more link capacity. We propose a method that interacts with Fast Reroute and multicast to minimize traffic overlap during failures. We also present an algorithm for link-weight setting that avoids traffic overlap for any single link failure. Performance analysis shows that the proposed method improves network service availability and significantly reduces the impact of failure events. version 2 record added in error; please see version 1 for paper. }
{Today's metro networks have evolved from the need to support traditional voice and private line services. However, the tremendous growth in access to Frame Relay, ATM, IP and Ethernet services, coupled with the desire of enterprise customers to interconnect via Ethernet interfaces, suggests the need for a new approach. This paper proposes a new architecture for Packet-Aware technologies to provide efficient aggregation and switching of packet traffic in metro networks. The PATN has the potential to provide significant cost savings to carriers by reducing the number of network elements, reducing transport costs through statistical multiplexing, and eliminating the need for redundant multiplexing operations. HB8420000-040104-01TM This is an abstract of the previous version. }
System And Method For Content Validation,
Tue Jan 31 12:50:22 EST 2012
A method of obtaining content includes receiving a playfile. The playfile includes a chunk ID corresponding to a chunk of the content, a packet ID corresponding to a packet of the chunk, and a hash of the packet. The method further includes obtaining the chunk from a peer, determining a calculated hash for the packet, and discarding the chunk when the calculated hash does not match the hash in the playfile.
Multicast With Adaptive Dual-State,
Tue Nov 22 16:06:33 EST 2011
A method and system are described to multicast with an adaptive dual state. The system receives multicast traffic over a membership tree including a first plurality of nodes connected in a first topology destined for a plurality of multicast members of a first multicast group. Next, the system determines a rate of multicast traffic that exceeds a predetermined threshold based on the receiving the multicast traffic. Next, the system generates a dissemination tree including a second plurality of nodes connected in a second topology to reduce a number of hops to communicate the multicast traffic to the plurality of multicast members of the first multicast group. Finally, the system forwards the multicast traffic to the plurality of multicast members of the first multicast group over the dissemination tree.
Methods And Apparatus To Deploy And Monitor Network Layer Functionalities,
Tue Oct 04 16:06:12 EDT 2011
Example methods and apparatus to deploy and monitor network layer functionalities are disclosed. A disclosed example method includes receiving an Internet Protocol (IP) packet at an input of a server, the IP packet being received from a communicatively coupled router, identifying the IP packet as a production IP packet or a non-production IP packets, when the IP packet is the non-production IP packet, manipulating data within the IP packet to monitor network layer functionality, forwarding the manipulated non-production IP packet to the router, and when the IP packet is the production IP packet, forwarding the production IP packet to the router without manipulating data within the IP packet.
Method For Bandwidth Management By Resizing Pipes,
Tue Jun 07 16:05:25 EDT 2011
Signaling messages are exchanged for a call between a calling party to a called party. A setup message for the call is exchanged through at least one gate controller. Network resources are reserved for the call based on the exchanged setup messages. An end-to-end message for the call is exchanged without the end-to-end message being routed through the at least one gate controller.
Methods And Apparatus To Monitor Network Layer Functionalities,
Tue May 17 16:05:10 EDT 2011
Example methods and apparatus to monitor network layer functionalities are disclosed. A disclosed example method includes receiving a first probe packet at an input of a first server, the first probe packet being received from a router, the first probe packet being generated and transmitted from a second server that is one-hop away from the first server in a network, determining if the first server is a final destination of the first probe packet, and if the first server is not the final destination of the first probe packet, generating a second probe packet and transmitting the second probe packet to the router for transmission toward the final destination.
Transport Protocol For Efficient Aggregation Of Heterogeneous Lossy Paths,
Tue Apr 19 16:04:55 EDT 2011
A transport protocol that achieves improved performance in an environment where paths are lossy and a plurality of paths are employed to transfer data, essentially in parallel, from a source to a destination. The protocol is implemented with the aid of an aggregate flow manager (AFM) at the source that considers and controls the data flow through the plurality of paths. With some preselected regularity the AFM determines a number of packets to be included in a Forward Error Correction (FEC) block of packets, creates the block, and transmits the segments of the block over the plurality of paths. As necessary, the destination sends information to the source of what additional information needs to be sent. This additional information might be reactive error correcting (RFEC) packets, or a retransmission of the missed packets.
Method And Apparatus For Increasing Survivability In IP Networks,
Tue Mar 08 16:04:38 EST 2011
A method and apparatus for increasing the capability of a network topology model having a plurality of nodes connected by existing links to maintain service continuity in the presence of faults. The steps of the method include adding new links to the network topology model to protect against single node failures, and adjusting link weights for the network topology model to reduce at least one of a cost of network operation and an imbalance in link utilizations. Preferably, the link weights are adjusted to reduce the imbalance in link utilizations without deteriorating the cost of network operation. The link weights are preferably adjusted to reduce the cost of network operation without increasing the imbalance in link utilizations. Preferably, the link weights are adjusted to reduce the cost of network operation without increasing the imbalance in link utilizations while keeping the utilization for each link below a specific threshold. In addition, links can be added to the network topology model to reduce the cost of network operation.
Loss Tolerant Transmission Control Protocol,
Tue Feb 15 16:04:30 EST 2011
Provided are apparatuses and methods for transmitting or receiving data packets in a data block in a communication network with a transport protocol. In one example, a loss tolerant TCP protocol is used in which a maximum segment size (MSS) may be adapted to a minimum granularity of a congestion window. Also, proactive forward error correction (FEC) packets may be added to a window of the data block. The number of proactive FEC packets may be determined, for example, based on an estimate erasure rate. In addition, reactive FEC packets may be added to the data block. Also, a receiver may receive data packets in a data block and process a selective acknowledgment (SACK) responsive to the data packets received.
Methods For Determining Non-Broadcast Multiple Access (NBMA) Connectivity For Routers Having Multiple Local NBMA Interfaces,
Tue Oct 05 15:04:51 EDT 2010
The present invention discloses an efficient architecture for routing in a very large autonomous system where many of the layer 3 routers are attached to a common connection-oriented layer 2 subnetwork, such as an ATM network. In a preferred embodiment of the invention, a permanent topology of routers coupled to the subnetwork is connected by permanent virtual circuits. The routers can further take advantage of both intra-area and inter-area shortcuts through the layer 2 network to improve network performance. The routers pre-calculate shortcuts using information from link state packets broadcast by other routers and store the shortcuts to a given destination in a forwarding table, along with corresponding entries for a next hop along the permanent topology. The present invention allows the network to continue to operate correctly if layer 2 resource limitations preclude the setup of additional shortcuts.
Method And Apparatus For Coordinating A Change In Service Provider Between A Client And A Server
With Identity Based Service Access Management,
Tue Sep 21 15:04:47 EDT 2010
A method of configuring a network access device connected to an access network connected to a plurality of service networks, the network device having a first network address allocated to a subscriber of services of a first service provider provided by a first service network, with a new network address allocated to a second subscriber of services of either the first service provider, or a second service provider provided by a second service network. The method comprises the steps of: sending a request from the network access device to the access network with user credentials for the second subscriber requesting access to the first service provider or a change to the second service provider; receiving a response from the access network; and initiating a network address change request using a configuration protocol. In this manner, a second network address allocated to the second subscriber of services of either the first or second service providers is assigned to the network access device to enable the network access device to communicate data packets to the service network providing the selected service.
Method For Performing Gate Coordination On A Per-Call Basis,
Tue Aug 17 15:04:25 EDT 2010
Network resources for a call between a calling party and a called party are allocated. The network resources for the call are reserved based on a reservation request. The network resources are reserved before any one network resource from the reserved network resources is committed. The reserved network resources for the call are committed when a called party indicates acceptance for the call.
Method For Performing Segmented Resource Reservation,
Tue Jun 22 15:04:07 EDT 2010
Segmented resource reservation is performed for at least one call. network resources associated with a first network are reserved according to that network's own reservation policy and based on an indication from a calling party. For the at least one call, network resources associated with a second network are reserved according to its own reservation policy and based on an indication from a called party. The second network is coupled to the first network.
Method For Call Forwarding Without Hairpinning And With Split Billing,
Tue May 04 15:03:46 EDT 2010
A call is forwarded by connecting the call between an originating location and a forwarding location without connecting the call through a terminating location. The originating location is associated with a calling party. The terminating location is associated with a dialed number. The terminating location and the forwarding location is associated with the called party. A bill for the call is apportioned between the calling party and the called party. The bill portion for the calling party is a function of the originating location and the terminating location. The bill portion for the called party is a function of the terminating location and the forwarding location.
Method And Apparatus For Increasing Survivability In IP Networks,
Tue Mar 16 15:03:38 EDT 2010
A method and apparatus for increasing the capability of a network topology model having a plurality of nodes connected by existing links to maintain service continuity in the presence of faults. The steps of the method include adding new links to the network topology model to protect against single node failures, and adjusting link weights for the network topology model to reduce at least one of a cost of network operation and an imbalance in link utilizations. Preferably, the link weights are adjusted to reduce the imbalance in link utilizations without deteriorating the cost of network operation. The link weights are preferably adjusted to reduce the cost of network operation without increasing the imbalance in link utilizations. Preferably, the link weights are adjusted to reduce the cost of network operation without increasing the imbalance in link utilizations while keeping the utilization for each link below a specific threshold. In addition, links can be added to the network topology model to reduce the cost of network operation.
System And Method For Improving Transport Protocol Performance In Communication Networks Having Lossy Links,
Tue Dec 01 16:08:17 EST 2009
Providing transport protocol within a communication network having a lossy link. The receiver distinguishes between packets received with non-congestion bit errors and packets having been not at all received due to congestion. When packets are received with non-congestion bit errors, the receiver sends selective acknowledgments indicating that the packets were received with bit errors while suppressing duplicate acknowledgments to prevent the invocation of a congestion mechanism.
Method For Allocating Network Resources,
Tue Feb 17 16:07:17 EST 2009
Network resources for a call between a calling party and a called party are allocated. The network resources for the call are reserved based on a reservation request. In particular, the network resources for the call are reserved based on a reservation request. Prior to the reservation request being made, one or more operational parameters for the call are established by a gate controller and sent to a network edge device or other routing entity associated with one of the parties. An identifier, illustratively a so-called gate identification, is sent to that party. Thereafter the routing entity receives the identifier from the associated party in, for example, the aforementioned resource reservation request. The routing entity is able to use the identifier to determine the one or more parameters established for the call and to thereupon cause the call to be established--including the reserving of resources--in a way that is consistent with the one or more parameters.
Loss tolerant transmission control protocol,
Tue Apr 29 18:12:45 EDT 2008
Provided are apparatuses and methods for transmitting or receiving data packets in a data block in a communication network with a transport protocol. In one example, a loss tolerant TCP protocol is used in which a maximum segment size (MSS) may be adapted to a minimum granularity of a congestion window. Also, proactive forward error correction (FEC) packets may be added to a window of the data block. The number of proactive FEC packets may be determined, for example, based on an estimate erasure rate. In addition, reactive FEC packets may be added to the data block. Also, a receiver may receive data packets in a data block and process a selective acknowledgment (SACK) responsive to the data packets received.
Method for exchanging signaling messages in two phases,
Tue Dec 04 18:12:29 EST 2007
Signaling messages are exchanged for a call between a calling party to a called party. A setup message for the call is exchanged through at least one gate controller. Network resources are reserved for the call based on the exchanged setup messages. An end-to-end message for the call is exchanged without the end-to-end message being routed through the at least one gate controller.
Method for bandwidth management by resizing pipes,
Tue Nov 27 18:12:28 EST 2007
Signaling messages are exchanged for a call between a calling party to a called party. A setup message for the call is exchanged through at least one gate controller. Network resources are reserved for the call based on the exchanged setup messages. An end-to-end message for the call is exchanged without the end-to-end message being routed through the at least one gate controller.
Method for performing gate coordination on a per-call basis,
Tue Oct 30 18:12:20 EDT 2007
Gates for a call between a calling party and a called party are coordinated. A timer associated with a first gate opened at an originating network edge device is initiated. A first gate open message is sent from the originating network edge device to the terminating network edge device. The first gate at the originating network edge device is released if the timer expires before at least one from the group of: (1) an acknowledgment based on the sent first gate open message is received from the terminating network edge device, and (2) a second gate open message is received at the originating network edge device from the terminating network edge device after the terminating network edge device has opened a second gate associated with the called party.
Segmented resource reservation is performed for at least one call. Network resources associated with a first network are reserved according to that network's own reservation policy and based on an indication from a calling party. For the at least one call, network resources associated with a second network are reserved according to its own reservation policy and based on an indication from a called party. The second network is coupled to the first network.
Method for performing gate coordination on a per-call basis,
Tue Jul 17 18:12:08 EDT 2007
Gates a call between a calling party and a called party are coordinated. A timer associated with a first opened at an originating network edge device is initiated. A first gate open message is sent from the originating network edge device to the terminating network edge device. The first gate at the originating network edge device is released if the timer expires before at least one from the group of: (1) an acknowledgment based on the sent first gate open message is received from the terminating network edge device, and (2) a second gate open message is received at the originating network edge device from the terminating network edge device after the terminating network edge device has opened a second gate associated with the called party.
Network resources for a call between a calling party and a called party are allocated. The network resources for the call are reserved based on a reservation request. In particular, the network resources for the call are reserved based on a reservation request. Prior to the reservation request being made, one or more operational parameters for the call are established by a gate controller and sent to a network edge device or other routing entity associated with one of the parties. An identifier, illustratively a so-called gate identification, is sent to that party. Thereafter the routing entity receives the identifier from the associated party in, for example, the aforementioned resource reservation request. The routing entity is able is able to use the identifier to determine the one or more parameters established for the call and to thereupon cause the call to be established--including the reserving of resources--in a way that is consistent with the one or more parameters.
Virtual private network,
Tue Mar 27 17:08:41 EDT 2007
The invention provides apparatus and methods for a Virtual Private Network (VPN) in a network that offers a simple user interface for efficient utilization of network resources. The VPN is defined for a specified set of endpoints each of which is associated with a single hose. A hose provides access to the VPN through an access point which may be a node of the network, for example. The hose is a single interface to the VPN for communication to all other endpoints of the VPN. The VPN achieves network resource allocation efficiency by exploiting resource sharing possibilities via multiplexing routing paths between endpoints and dynamic resource allocation techniques that permit real time resource allocation resizing. When a VPN is established with a VPN service provider, the routing paths between the endpoints of the VPN is optimized for multiplexing opportunities so that resource allocations between nodes along routing paths within the IP network is reduced to a minimum.
Method for performing lawfully-authorized electronic surveillance,
Tue Dec 19 18:11:46 EST 2006
Lawfully-authorized electronic surveillance is performed. A call associated with a first party to be surveilled is verified, on a per-call basis. Packets associated with the call are multicast to a second party and to a surveillance receiver.
Method and apparatus for coordinating a change in service provider between a client and a server,
Tue Jun 27 18:11:22 EDT 2006
A method of configuring a network access device having a first network address allocated to a subscriber of services of a first service provider provided by a first service network, with a new network address allocated to a subscriber of services of a second service provider provided by a second service network, wherein the network access device is connected to an access network connected to a plurality of service networks. The method comprises the steps of: sending a request from the network access device to the access network requesting a change to a second service provider; receiving a response from the access network; and initiating a network address change request using a configuration protocol. In this manner, a second network address allocated to the subscriber of services of the second service provider is assigned to the network access device to enable the network access device to communicate data packets to the service network providing the selected service. In one preferred embodiment of the invention, the subscriber is authenticated by a service activation system coupled to the access network prior to initiating the configuration protocol. Accordingly, the request to the access network includes an authentication request for the subscriber. The response received from the access network therefore includes an authentication status for the subscriber from the second service provider. If the subscriber is authenticated, the client initiates the network address change request.
Service selection in a shared access network using policy routing,
Tue Jun 20 18:11:18 EDT 2006
It is an object of the invention to enable multiple services or service providers to share the facilities of an access network infrastructure providing physical connectivity to subscribers. A network access device advantageously may be used in communication network services with a service or service provider that is separate from the operator of the access network infrastructure.
Method for exchanging signaling messages in two phases,
Tue Apr 11 18:11:05 EDT 2006
Signaling messages are exchanged for a call between a calling party to a called party. A setup message for the call is exchanged through at least one gate controller. Network resources are reserved for the call based on the exchanged setup messages. An end-to-end message for the call is exchanged without the end-to-end message being routed through the at least one gate controller.
Method and apparatus for coordinating a change in service provider between a client and a server with identity based service access management,
Tue Apr 11 18:11:03 EDT 2006
A method of configuring a network access device connected to an access network connected to a plurality of service networks, the network device having a first network address allocated to a subscriber of services of a first service provider provided by a first service network, with a new network address allocated to a second subscriber of services of either the first service provider, or a second service provider provided by a second service network. The method comprises the steps of: sending a request from the network access device to the access network with user credentials for the second subscriber requesting access to the first service provider or a change to the second service provider; receiving a response from the access network; and initiating a network address change request using a configuration protocol. In this manner, a second network address allocated to the second subscriber of services of either the first or second service providers is assigned to the network access device to enable the network access device to communicate data packets to the service network providing the selected service.
Method for bandwidth management by resizing pipes,
Tue Feb 14 18:10:53 EST 2006
Signaling messages are exchanged for a call between a calling party to a called party. A setup message for the call is exchanged through at least one gate controller. Network resources are reserved for the call based on the exchanged setup messages. An end-to-end message for the call is exchanged without the end-to-end message being routed through the at least one gate controller.
System and method for improving transport protocol performance in communication networks having lossy links,
Tue Jan 24 18:10:48 EST 2006
Providing transport protocol within a communication network having a lossy link. The receiver distinguishes between packets received with non-congestion bit errors and packets having been not at all received due to congestion. When packets are received with non-congestion bit errors, the receiver sends selective acknowledgments indicating that the packets were received with bit errors while suppressing duplicate acknowledgments to prevent the invocation of a congestion mechanism.
Method for call forwarding without hairpinning and with split billing,
Tue Jan 03 18:10:46 EST 2006
A call is forwarded by connecting the call between an originating location and a forwarding location without connecting the call through a terminating location. The originating location is associated with a calling party. The terminating location is associated with a dialed number. The terminating location and the forwarding location is associated with the called party. A bill for the call is apportioned between the calling party and the called party. The bill portion for the calling party is a function of the originating location and the terminating location. The bill portion for the called party is a function of the terminating location and the forwarding location.
Method For Establishing Call State Information Without Maintaining State Information At Gate Controllers,
Tue Jul 05 18:10:26 EDT 2005
State information for a call between a calling party and a called party is established without maintaining the state information at a gate controller. A setup request for the call is received at an originating gate controller. The originating gate controller is connected to a trusted network. The calling party is associated with an originating interface unit coupled to an untrusted network. The setup request for the call is authorized. The authorized setup request is sent to the called party. State information for the call is formatted based on a setup acknowledgment message received from the calling party. The state information for the call is sent from the originating gate controller to the originating interface unit without maintaining the state information at the originating gate controller.
Virtual Private Network,
Tue Jun 28 17:08:39 EDT 2005
The invention provides apparatus and methods for a Virtual Private Network (VPN) in a network that offers a simple user interface for efficient utilization of network resources. The VPN is defined for a specified set of endpoints each of which is associated with a single hose. A hose provides access to the VPN through an access point which may be a node of the network, for example. The hose is a single interface to the VPN for communication to all other endpoints of the VPN. The VPN achieves network resource allocation efficiency by exploiting resource sharing possibilities via multiplexing routing paths between endpoints and dynamic resource allocation techniques that permit real time resource allocation resizing. When a VPN is established with a VPN service provider, the routing paths between the endpoints of the VPN is optimized for multiplexing opportunities so that resource allocations between nodes along routing paths within the IP network is reduced to a minimum.
Method for providing privacy by network address translation,
Tue Mar 22 18:10:20 EST 2005
A call between a first network associated with a calling party and a second network associated with a called party is connected. The source address for packets associated with the call arc translated. The packets are sent from the calling party to the called party without the called party receiving the source address that indicates at least one from the group of a logical identity of the calling party and a geographical identity of the calling party.
Startup Management System And Method For Rate-Based Flow And Congestion Control Within A Network,
Tue Jan 04 18:10:15 EST 2005
A startup management system and method, particularly adapted for use in computer and other communication networks, is presented. Rate-based flow and congestion control mechanisms have been considered desirable, including to deal with the needs of emerging multimedia applications. Explicit rate control mechanisms achieve low loss because of a smooth flow of data from sources, while adjusting source rates through feedback. However, large feedback delays, presence of higher priority traffic and varying network conditions make it difficult to ensure feasibility (i.e., the aggregate arrival rate is below the bottleneck resource's capacity) while also maintaining very high resource utilization. The invention applies entry and early warning techniques which increase the initial connect rate of newly connecting sources.
Method For Allocating Network,
Tue Nov 23 18:10:11 EST 2004
Network resources for a call between a calling party and a called party are allocated. The network resources for the call are reserved based on a reservation request. The network resources are reserved before any one network resource from the reserved network resources is committed. The reserved network resources for the call are committed when a called party indicates acceptance for the call.
Method for bandwidth management by resizing pipes,
Tue Aug 31 18:10:02 EDT 2004
Signaling messages are exchanged for a call between a calling party to a called party. A setup message for the call is exchanged through at least one gate controller. Network resources are reserved for the call based on the exchanged setup messages. An end-to-end message for the call is exchanged without the end-to-end message being routed through the at least one gate controller.
Method for performing gate coordination on a per-call basis,
Tue Jun 29 18:09:55 EDT 2004
Gates for a call between a calling party and a called party are coordinated. A timer associated with a first gate opened at an originating network edge device is initiated. A first gate open message is sent from the originating network edge device to the terminating network edge device. The first gate at the originating network edge device is released if the timer expires before at least one from the group of: (1) an acknowledgment based on the sent first gate open message is received from the terminating network edge device, and (2) a second gate open message is received at the originating network edge device from the terminating network edge device after the terminating network edge device has opened a second gate associated with the called party.
Method and apparatus for dynamically displaying brand information in a user interface,
Tue Jun 22 18:09:53 EDT 2004
Client software may be used in conjunction with services offered by several entities such as network service providers. A user interface of the client software presents brand indicia relating to the network service provider that is currently being used by the software. The software is configured by selecting entities with which the software will be used. Once the entities are selected, an instruction server is queried to determine the location of branding data to be presented to the user, and a branding data server is queried to retrieve the branding data. The brand indicia are presented to the user according to the branding data each time the corresponding entity is accessed.
Method for allocating network resources,
Tue Jun 08 18:09:47 EDT 2004
Network resources for a call between a calling party and a called party are allocated. The network resources for the call are reserved based on a reservation request. The network resources are reserved before any one network resource from the reserved network resources is committed. The reserved network resources for the call are committed when a called party indicates acceptance for the call.
Routing over large clouds,
Tue Mar 23 18:09:41 EST 2004
The present invention discloses an efficient architecture for routing in a very large autonomous system where many of the layer 3 routers are attached to a common connection-oriented layer 2 subnetwork, such as an ATM network. In a preferred embodiment of the invention, a permanent topology of routers coupled to the subnetwork is connected by permanent virtual circuits. The routers can further take advantage of both intra-area and inter-area shortcuts through the layer 2 network to improve network performance. The routers pre-calculate shortcuts using information from link state packets broadcast by other routers and store the shortcuts to a given destination in a forwarding table, along with corresponding entries for a next hop along the permanent topology. The present invention allows the network to continue to operate correctly if layer 2 resource limitations preclude the setup of additional shortcuts.
System and method for improving transport protocol performance in communication networks having lossy links,
Tue Mar 23 18:09:09 EST 2004
Providing transport protocol within a communication network having a lossy link. The receiver distinguishes between packets received with non-congestion bit errors and packets having been not at all received due to congestion. When packets are received with non-congestion bit errors, the receiver sends selective acknowledgments indicating that the packets were received with bit errors while suppressing duplicate acknowledgments to prevent the invocation of a congestion mechanism.
Method and apparatus for the encapsulation of control information in a real-time data stream,
Tue Mar 16 18:09:07 EST 2004
Method and device provide for the encapsulation of control information in a real-time data stream. In one embodiment a method of encapsulating data in an information frame is provided. This information frame has a payload portion and a trailer portion wherein the trailer portion is designated for control data and the payload portion is designated for real-time data. In use control data is inserted into the payload portion of the information frame and an extension bit is used to signify the presence of control data in the payload portion of the information frame. The information frame is then transmited over a virtual circuit.
Method for establishing call state information without maintaining state information at gate controllers,
Tue Feb 17 18:09:04 EST 2004
State information for a call between a calling party and a called party is established without maintaining the state information at a gate controller. A setup request for the call is received at an originating gate controller. The originating gate controller is connected to a trusted network. The calling party is associated with an originating interface unit coupled to an untrusted network. The setup request for the call is authorized. The authorized setup request is sent to the called party. State information for the call is formatted based on a setup acknowledgment message received from the calling party. The state information for the call is sent from the originating gate controller to the originating interface unit without maintaining the state information at the originating gate controller.
Method and system for telephony and high speed data access on a broadband access network,
Tue Dec 16 18:08:57 EST 2003
A system and method for providing telephony and high speed data access over a broadband access network, comprising a network interface unit (NIU) coupled to a backup local exchange carrier (LEC) line, the broadband access network coupled to the NIU, an intermediate point-of-presence (IPOP) coupled to the broadband access network, and at least one external access network coupled to the IPOP. The system also provides for a fail-safe mode in which the NIU supports the LEC line for lifeline services.
Method For Call Forwarding Without Hairpinning And With Split Billing,
Tue Jun 10 18:08:44 EDT 2003
A call is forwarded by connecting the call between an originating location and a forwarding location without connecting the call through a terminating location. The originating location is associated with a calling party. The terminating location is associated with a dialed number. The terminating location and the forwarding location is associated with the called party. A bill for the call is apportioned between the calling party and the called party. The bill portion for the calling party is a function of the originating location and the terminating location. The bill portion for the called party is a function of the terminating location and the forwarding location.
Method For Simulating A Ring Back For A Call Between Parties In Different Communication Networks,
Tue Jun 03 18:08:43 EDT 2003
A ring back signal for a call between a calling party and a called party can be simulated. A ring back message associated with the call is received. The calling party is associated with a first network. The called party is associated with a second network. A prestored ring back signal is selected from a set of prestored ring back signals based on the ring back message and/or a called number for the call. The selected prestored ring back signal is associated with the second network and is different from a second prestored ring back signal associated with the first network. The prestored ring back signal is sent to the calling party.
Architecture For Lightweight Signaling In ATM Networks,
Tue Apr 29 18:08:41 EDT 2003
A method and system provide for a network using lightweight signaling for establishing connections. The method and system establish a best efforts connection between at least two terminals, on a hop-by-hop basis. Data can flow before and quality of service is established. The system enhances processing time for quality of service requirements and provides flexibility in establishing multicast connections.
Method and apparatus for communication services on a network,
Tue Dec 24 18:08:35 EST 2002
A method for performing communications over a network comprises receiving a user record for a first user, receiving a query from a second user with regard to the first user, and sending, to the second user, as a response to the query, a call-handling profile.
Method for allocating network resources,
Tue Nov 19 18:08:32 EST 2002
Network resources for a call between a calling party and a called party are allocated. The network resources for the call are reserved based on a reservation request. The network resources are reserved before any one network resource from the reserved network resources is committed. The reserved network resources for the call are committed when a called party indicates acceptance for the call.
Method and apparatus for managing congestion within an internetwork using window adaptation,
Tue Aug 20 18:08:24 EDT 2002
Congestion is controlled in an internetwork having at least two segments coupled by a router where at least one connection between communication devices passes through the router. Each connection is assumed to use a window-based flow control protocol between its source and destination. On receiving an acknowledgment from a connection in the router, where the acknowledgment contains a window size set by the destination, the router adaptively determines a second window size for the connection based on the router's average buffer occupancy and its instantaneous buffer occupancy. If the window size in the acknowledgment exceeds this second window size, the window size in the acknowledgment is overwritten to select the second window size. The router then forwards the acknowledgment to the source, thereby controlling the window size available to the source as a function of the congestion in the router.
System and method for multipoint-to-multipoint multicasting,
Tue Mar 05 18:07:22 EST 2002
A system and method are provided for a scalable and efficient multipoint-to-multipoint multicast in packet and sub-packet based communications networks. The methodology of the invention incorporates an additional switching feature called cut-through forwarding, which enables the mapping of several incoming virtual channels into one or several outgoing virtual channels. The inventive methodology further provides a shared tree spanning all senders and receivers of the multicast group. Centrally initiated group setup as well as dynamic group membership changes are incorporated into the invention. An additional feature of the invention, designated short-cutting, allows for the transmission of a packet to follow the shortest path along the shared tree. A methodology is also provided for achieving interoperability among switching nodes in a network which are capable of fully implementing the multipoint-to-multipoint multicast method of the invention and other switching nodes which lack that capability.
Method for exchanging signaling messages in two phases,
Tue Nov 27 18:07:17 EST 2001
Signaling messages are exchanged for a call between a calling party to a called party. A setup message for the call is exchanged through at least one gate controller. Network resources are reserved for the call based on the exchanged setup messages. An end-to-end message for the call is exchanged without the end-to-end message being routed through the at least one gate controller
Method and apparatus for smoothing and multiplexing video data flows,
Tue Oct 30 18:07:15 EST 2001
A method and apparatus provide a smoothing and rate adaptation algorithm to facilitate the flow of video data, maintaining video quality while avoiding potentially harmful buffering delays. The invention uses a smoothing interval to determine a rate to request for allocation. The invention also adapts the encoding rate in relation to a target delay for a source buffer.
Method and apparatus for supporting compressed video with explicit rate congestion control,
Tue Jul 31 18:07:10 EDT 2001
A method and system provide for adaptive coding for transporting of compressed video data. The method and system include techniques for predicting the rate which an encoder needs to be able to supply video to a network. The method and system also include the network receiving the demand rate and calculating an allocation rate which is ultimately fed back to the video source setting an explicit rate for the transporting of compressed video. Furthermore, it includes the adaptation of the encoding rate at the video source in accordance with the explicit rate allocated by the network in response to the demand.
Architecture for lightweight signaling in ATM networks,
Tue Jun 05 18:07:05 EDT 2001
A method and system provide for a network using lightweight signaling for establishing connections. The method and system establish a best efforts connection between at least two terminals, on a hop-by-hop basis. Data can flow before and quality of service is established. The system enhances processing time for quality of service requirements and provides flexibility in establishing multicast connections.
Startup management system and method for networks,
Tue Feb 20 18:06:59 EST 2001
A startup management system and method, particularly adapted for use in computer and other communication networks, is presented. Rate-based flow and congestion control mechanisms have been considered desirable, including to deal with the needs of emerging multimedia applications. Explicit rate control mechanisms achieve low loss because of a smooth flow of data from sources, while adjusting source rates through feedback. However, large feedback delays, presence of higher priority traffic and varying network conditions make it difficult to ensure feasibility (i.e., the aggregate arrival rate is below the bottleneck resource's capacity) while also maintaining very high resource utilization. The invention applies entry and early warning techniques which increase the initial connect rate of newly connecting sources.
Load balancing based on queue length, in a network of processor stations,
Tue Oct 03 18:06:35 EDT 2000
A method for distributing a job load from a local processor station to at least one processor station within a plurality of processor stations connected by a multiaccess channel. A job is selected for remote execution from the local processor so that the average load value of the local processor station is reduced to the average load value of the processor station having the lowest average load value from a subset of processor stations. The average load value can be, for example, average utilization or average queue length.
Architecture for lightweight signaling in ATM networks,
Tue Oct 03 18:06:12 EDT 2000
A method and system provide for a network using lightweight signaling for establishing connections. The method and system establish a best efforts connection between at least two terminals, on a hop-by-hop basis. Data can flow before and quality of service is established. The system enhances processing time for quality of service requirements and provides flexibility in establishing multicast connections.
System and method for performing switching in multipoint-to-multipoint multicasting,
Tue Apr 11 18:05:31 EDT 2000
A method for utilizing buffered switches to perform multipoint-to-multipoint multicasting within a telecommunication network. A switching feature known as cut-through forwarding is implemented for output-buffered switches, shared-memory switches and input-buffered switches.
System and method for improving transport protocol performance in communication networks having lossy links,
Tue Oct 26 18:05:24 EDT 1999
Providing transport protocol within a communication network having a lossy link. The receiver distinguishes between packets received with non-congestion bit errors and packets having been not at all received due to congestion. When packets are received with non-congestion bit errors, the receiver sends selective acknowledgments indicating that the packets were received with bit errors while suppressing duplicate acknowledgments to prevent the invocation of a congestion mechanism.
Method for fair allocation of bandwidth,
Tue Aug 31 01:05:20 EDT 1999
A method is provided for allocating the bandwidth of a shared resource. The resource takes into account not only the explicit rates allocated to sources by upstream bottlenecks but also takes into account the original relative demands of the sources either in terms of the actual demand placed into the networks by the respective sources or in terms of some other parameter indicative of the demands of the source, such as a minimum rate necessary to provide useful service for the source.
Adaptive channel allocation system for communication network,
Tue Sep 08 18:05:05 EDT 1998
An adaptive channel allocation system is provided which monitors the actual channel bandwidth used by network sources. Sources which have placed demands for network bandwidth, but not used that bandwidth, have their channel resources down-allocated according to a smoothed exponential function. Sources which are idle are detected by means of an aging function.
Awards
AT&T Fellow, 2006.
IEEE Fellow, 2005.
For contributions to congestion control and traffic management in communication networks.
