Computation offloading has been widely used to alleviate the performance and energy limitations of smartphones by sending computationally intensive applications to the cloud. However, mobile devices with poor cellular service quality may incur high communication latency and high energy consumption for offloading, which will reduce the benefits of computation offloading. In this paper, we propose a peer-assisted computation offloading (PACO) framework to address this problem. In PACO, a client experiencing poor service quality can choose a neighbor with better service quality to be the offloading proxy. Through peer to peer interface such as WiFi direct, the client can offload computation tasks to the proxy which further transmits them to the cloud server through cellular networks. We propose algorithms to decide which tasks should be offloaded to minimize the energy consumption. We have implemented PACO on Android and have implemented three computationally intensive applications to evaluate its performance. Experimental results and simulation results show that PACO makes it possible for users with poor cellular service quality to benefit from computation offloading and PACO significantly reduces the delay and energy consumption compared to existing schemes.
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Electrical and Electronic Engineering
- Applied Mathematics