Task Proactive Caching Based Computation Offloading and Resource Allocation in Mobile-Edge Computing Systems

For the recent emerging applications such as augmented reality (AR), delay is a key performance evaluating the quality of user experience (QoE). Caching the execution results of the popular AR applications' computational tasks can significantly reduce the execution delay. In this paper, we consider the mobile edge computing (MEC) server and the cloud can proactively cache the execution results of computational tasks. Then, in our proposed scenario, there are four optional ways to process a task. They are, respectively, computing tasks locally, offloading tasks to the MEC server to computing, returning the task's computation results directly from the MEC server's cache, and returning the task's computation results from the cloud's cache. The computation offloading, resource allocation and task proactive caching are jointly optimized to minimize the execution latency subject to the constraints of the radio, computation and storage resources. To solve this complex mixed-integer nonlinear programming (MINLP) problem, we first propose a proactive caching algorithm for collaboration between the cloud and the MEC server to determine the task's caching status. Then, we propose a heuristic algorithm based on greedy strategy to solve the remaining problem, which includes resource allocation and the selections of task's execution mode. By analyzing the simulation results and comparing with an exhaustive algorithm, effectiveness and optimality of our proposed schemes are verified.