Please use this identifier to cite or link to this item:
|Title:||Energy-Aware Computation Offloading in Wearable Computing||Authors:||Mariam Jawad Safar||Supervisor:||Prof. Imtiaz Ahmad||Keywords:||Energy-Aware||Issue Date:||2017||Publisher:||Kuwait university - college of graduate studies||Abstract:||Wearable technology is an emerging computing paradigm with a broad range of applications including consumer market, healthcare, entertainment, military, and body area networks to name a few of them. Numerous researchers have proven that wearable devices are equipped with limited compute capability, storage and battery lifetime, which hinder their use for compute-intensive applications such as image recognition in a fast and an energy efficient manner. To support advanced applications on wearable devices with enhanced performance and energy efficiency. Therefore, offloading some of the workload to the neighboring mobile devices or cloud with unlimited computation prosperities, is an attractive approach. In this study, we propose a lightweight computation offloading technique in which some of the workload is transferred to nearby more resourceful mobile devices in order to enhance performance and save energy of wearable devices. The computation-offloading problem is modeled as heterogeneous system scheduling problem, where an application is represented as a Directed Acyclic Graph (DAG) and devices (wearable and mobile) are considered as heterogeneous computing system, since the computation capabilities of these devices are different. The proposed solution is based on priority based list scheduling algorithm, which is of low-complexity to suit the wearable computing paradigm requirements and generate the most effective schedules. A key feature of the proposed list scheduling technique that it intelligently exploits task duplication to achieve both the objectives of saving energy consumption and enhancing performance. The effectiveness of the proposed technique for a wearable device and a mobile device connected through a Wi- Fi network is demonstrated by comparing the results with a well-known technique for randomly generated DAGs. Experimental results reveal that the proposed approach provides a significant reduction in energy and schedule over existing approach. Furthermore, for online computation offloading two types of models are simulated based on queueing theory (M/M/1). The two models differ in the communication interfaces: Wi-Fi and Bluetooth.||URI:||http://hdl.handle.net/123456789/670|
|Appears in Programs:||0612 Computer Engineering|
Show full item record
Files in This Item:
|Energy-Aware Computation Offloading in Wearable Computing .pdf||508,95 kB||Adobe PDF||View/Open Request a copy|
checked on Sep 20, 2020
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.