Energy Delay Tradeoff in Cloud Offloading for Multi-Core Mobile Devices

Cloud offloading is considered a promising approach for both energy conservation and storage/computation enhancement for resource-limited mobile devices. In this paper, we present a Lyapunov optimization-based scheme for cloud offloading scheduling, as well as download scheduling for cloud execution output, for multiple applications running in a mobile device with a multi-core CPU. We derive an online algorithm and prove performance bounds for the proposed algorithm with respect to average power consumption and average queue length, which is indicative of delay, and reveal the fundamental tradeoff between the two optimization goals. The performance of the proposed online scheduling scheme is validated with trace-driven simulations.