An energy-efficient method for hybrid mobile cloud computing

Abstract

Many benefits of cloud computing are now well established, as both enterprise and mobile IT have been transformed by its pervasiveness. Backed by the virtually unbounded resources of cloud computing, battery-powered mobile computing systems can meet the demands of even the most resource-intensive applications. However, many existing hybrid mobile-cloud (HMC) applications are inefficient in terms of optimising trade-offs between simultaneously conflicting objectives, such as minimising both battery power consumption and network usage. To tackle this problem, we propose a novel method that can be used not only to instrument HMC applications but also to search for its efficient configurations representing compromise solutions between the objectives. The method is based on a general purpose HMC framework, which provides scalability, and make runtime decisions that are based on: 1) changing of the environment (i.e. WiFi signal level variation), and 2) itself in a changing environment (i.e. actual observed packet loss in the network). Our experimental evaluation considers two Android-based applications for smartphones, and a Python-based foraging task performed by a battery powered and Raspberry Pi controlled Thymio robot. Analysis of our results shows that our method can be used for small to medium size HMC applications to achieve energy efficient computing systems. Furthermore, HMC applications can achieve better optimisation in a changing environment (i.e. signal level variation) than using static off loading or running the applications only on a mobile device. However, a self-adaptive decision would fall behind when the change in the environment happens within the system (i.e.network congestion). In such a case, a self-aware system can perform well, in terms of minimising the two objectives and better performance of applications.

Date of Award	2020
Original language	English
Supervisor	Peter Lewis (Supervisor)