Mobile Edge Computing via Wireless Power Transfer Over Multiple Fading Blocks: An Optimal Stopping Approach

To support wireless Internet of things (IoT) devices, this paper presents a new solution which combines wireless power transfer and mobile edge computing. Specifically, we consider one mobile device, which first harvests energy from radio frequency signals sent by a base station and then offloads all or part of its data to be processed to the base station. The process of energy harvesting and offloading span over multiple fading blocks. The target is to maximize the average amount of processed data in unit time. To achieve this target, we optimize the stopping rule for energy harvesting (i.e., when to stop energy harvesting and start offloading) and the number of fading blocks for data offloading. To solve the formulated problem optimally, we decompose it into two levels. In the lower level, the stopping rule for energy harvesting is optimized given a fixed number of fading blocks for offloading. The associated lower-level problem is solved optimally based on a series of special properties of the problem. In the upper level, the number of fading blocks for offloading is optimized. Efficiency of our work with fully offloading mode and partially offloading mode is shown by using simulation.