TaskAlloc: Online Tasks Allocation for Offloading in Energy Harvesting Mobile Edge Computing

Abstract

MEC (Mobile Edge Computing) is a new computation mobile technology which can greatly reduce the execution latency of tasks as well as energy consumption by offloading the computing workload generated by mobile devices to MEC servers. However, due to limited battery capacity of mobile devices, the computing tasks might be abandoned. In this paper, we present an efficient strategy of tasks allocation in an MEC system with energy harvesting to minimize the weight-sum of computation delay and energy cost for mobile devices. In addition, we design a queue for the coming tasks from which the devices fetch the tasks to execute. Based on the Lyapunov optimization method, an online algorithm named Dynamic Lyapunov Optimizationbased Tasks Allocation (DLOTA) is presented, to determine the strategy by adjusting both the CPU frequency and the offloading transmission power of mobile devices. Its advantage is that the tasks allocation decision only depends on the state of the current system and does not need to predict the future state. Simulation results demonstrate that the presented method can make the battery energy levels stable and achieve the trade off between execution delay and energy cost.