Despite the increased capabilities of mobile devices, mobile application resource requirements can often transcend what can be accomplished on a single device. This has been addressed through several proposals for efficient computation offloading from mobile devices to remote cloud resources or closely located computing resources known as cloudlets. In this paper we consider an environment in which computational offloading is performed among a set of mobile devices. We call this environment a Mobile Device Cloud (MDC). We are interested in MDCs where nodes are highly collaborative. We develop computational offloading schemes that maximize the lifetime of the ensemble of mobile devices where we consider the network to be alive as long as no device has depleted its battery. As a secondary contribution in this work, we develop and use an experimentation platform that allows us to evaluate a range of computational models and profiles derived from a realistic testbed. We use this platform as a first step in an evaluation exercise that demonstrates the effectiveness of our computation offloading algorithms in extending the lifetime of an MDC.
It is common practice for mobile devices to offload computationally heavy tasks off to a cloud, which has greater computational resources. We consider an environment in which computational offloading is made among mobile devices. We call such an environment a mobile device cloud (MDC). In this work, we first highlight the gain in computation time and energy consumption that can be achieved by offloading tasks to nearby devices inside a mobile device cloud. We do this by emulating network conditions that exist for different communication technologies provided by modern mobile devices. We then present a platform that allows creation and offloading of tasks by a mobile devices to nearby devices. Such a platform consists of an API, an accompanying Android application deployable across MDC devices, and a test bed to measure power being consumed by a mobile device. Finally, we create and utilize a testbed, which consists of four Android devices and energy measurement equipment, in order to validate our intuitions and qualify the gain in time and energy which we deduced from the emulation experiments. Using this test bed we show up to 50% gain in time and 26% gain in energy by employing task offload in MDC's versus executing tasks locally. * Funded by the CMUQ Seed Funding
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.