Energy and Delay Tradeoff for Application Offloading in Mobile Cloud Computing

Abstract

Recent work shows that offloading a mobile application from mobile devices to cloud servers can significantly reduce the energy consumption of mobile devices, thus extending 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. However, offloading to cloud servers may incur a large execution delay because of the waiting time at the servers or the communication delay from the mobile devices to the servers. Thus, to balance the tradeoff between energy consumption 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 first formulate a joint optimization problem, which minimizes both the energy consumption at the mobile devices and the execution delay of mobile applications. We prove that the proposed problem is NP-hard. For a special case with unlimited residual energy at the mobile device and the same amount of resources required by each mobile application, we present 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.