Multi-objective Joint Optimization of Communication-Computation-Caching Resources in Mobile Edge Computing

Abstract

With the development of the commercial scale of 5G, the explosive growth of smart mobile devices has promoted the emergence of new applications. How to reasonably design and allocate computing resources and improve users' experience quality with the limited computing and storage capabilities of mobile devices is a challenging problem. The existing work about joint optimization either minimizes the execution delay or the energy consumption of communication, computation, and caching resources of all the devices. However, the single-objective optimization may not be a practical solution given the heterogeneous capabilities and service requirements of mobile devices. This paper proposes a multi-objective joint optimization of communication-computation-caching resources to satisfy the various devices' requirements for execution delay and energy consumption. We reformulate to optimize the tradeoff between energy consumption and latency with the limited computing and storage resources. Then, the problem is transferred to a multi-objective problem and solved by the multi optimization method of non-dominated sorting genetic algorithm II (NSGA-II). Simulation results demonstrate that the proposed approach can achieve the tradeoff between energy consumption and latency with different practical scenarios.