att_abstract={{Home security and automation — temperature, lighting and energy management, access control, and alarming — is an area of growth in residential and office settings. These sys- tems typically include a number of sensors and actuators connected to a controller that runs the automation soft- ware. For cost reasons, these home controllers are often resource constrained devices that are not easy to upgrade or replace at scale. But with the emergence of more ca- pable sensors, there is a need for applications that require significant amount of computing resources, e.g., video feeds from cameras being used to identify people and their activ- ities. The limited resources at the home controller makes it hard to deploy such applications, especially when numerous ones are being used concurrently. This problem is reminis- cent of applications on mobile phones that necessitate cloud off-load. However, we posit that home control applications pose a new set of requirements unique to this domain. In this paper, we motivate a few such requirements including the need for disconnected operation and an offload decision engine with system-wide visibility, and propose an architec- ture to address them.
	att_authors={kj2681, rs2497, mh7921, yi1436},
	att_copyright_notice={{(c) ACM, 2014 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 2014 {{, 2014-06-16}}.
	att_tags={Cloud,  Home automation,  NFV},
	author={Kaustubh Joshi and Richard Schlichting and Matti Hiltunen and Yuichi Igarashi},
	institution={{The Fifth ACM Workshop on Mobile Cloud Computing and Services (MCS)}},
	title={{Vision: Towards an Extensible App Ecosystem for Home Automation through Cloud-Offload}},