Mobile-edge computing (MEC) is an emerging paradigm to meet theever-increasing computation demands from mobile applications. By offloading thecomputationally intensive workloads to the MEC server, the quality ofcomputation experience, e.g., the execution latency, could be greatly improved.Nevertheless, as the on-device battery capacities are limited, computationwould be interrupted when the battery energy runs out. To provide satisfactorycomputation performance as well as achieving green computing, it is ofsignificant importance to seek renewable energy sources to power mobile devicesvia energy harvesting (EH) technologies. In this paper, we will investigate agreen MEC system with EH devices and develop an effective computationoffloading strategy. The execution cost, which addresses both the executionlatency and task failure, is adopted as the performance metric. Alow-complexity online algorithm, namely, the Lyapunov optimization-baseddynamic computation offloading (LODCO) algorithm is proposed, which jointlydecides the offloading decision, the CPU-cycle frequencies for mobileexecution, and the transmit power for computation offloading. A uniqueadvantage of this algorithm is that the decisions depend only on theinstantaneous side information without requiring distribution information ofthe computation task request, the wireless channel, and EH processes. Theimplementation of the algorithm only requires to solve a deterministic problemin each time slot, for which the optimal solution can be obtained either inclosed form or by bisection search. Moreover, the proposed algorithm is shownto be asymptotically optimal via rigorous analysis. Sample simulation resultsshall be presented to verify the theoretical analysis as well as validate theeffectiveness of the proposed algorithm.
展开▼
