Energy and Delay Tradeoff for Application Offloading in Mobile Cloud Computing
Recent work shows that offloading mobile applications,e.g.,computation services,from mobile devices,e.g.,smartphone,to cloud servers,can significantly reduce the energy consumption of mobile devices and thus extend the lifetime of mobile devices.However,previous work only considers the energy saving of mobile devices,while ignoring the execution delay of mobile applications.To reduce the energy consumption of mobile devices,one may offload as many mobile applications as possible,to the cloud servers.However,offloading to cloud servers may incur large execution delay,because of waiting time at servers or the communication delay from mobile devices to the servers.Thus,to balance the tradeoff between energy consumption of mobile devices and execution delay of mobile applications,it is necessary to determine whether the mobile application should be offloaded to the cloud server or run locally at the mobile devices.In this paper,we firstly formulate an optimization problem,which minimizes the sum of energy consumption at mobile devices and execution delay of mobile applications according to a certain weightage.We then prove that the proposed problem is NPhard.For a special case with unlimited residual energy at mobile device and the same size of resources required by each mobile application,we propose a polynomial-time optimal solution.We also propose an efficient heuristic algorithm to solve the general case of the problem.Finally,simulation results demonstrate the effectiveness of the proposed scheme.
Application offloading mobile cloud energy efficient delay tradeoff
Xiumin Wang Jin Wang Xin Wang Xiaoming Chen
School of Computer and Information,Hefei University of Technology,Hefei,China School of Computer Science and Technology,Soochow University,Suzhou,China School of Computer Science,Fudan University,Shanghai,China School of Electronic and Information Engineering,Nanjing University of Aeronautics and Astronautics,
国内会议
北京
英文
1-9
2014-09-13（万方平台首次上网日期，不代表论文的发表时间）