Hierarchical Optimization for Task Execution Cost Minimization in D2D-Assisted Mobile Edge Computing Networks

This paper addresses the coalition formation and the resource allocation in a device-to-device assisted mobile edge computing network, where the user equipments (UEs) collaborate to share the communication bandwidth and the computation resources for the task offloading. Our goal is to minimize the task execution cost, which is defined as the weighted sum of energy consumption and processing delay. In particular, we model waiting time of UEs in a coalition for the task offloading and incorporate it in the task execution cost. Therefore, we propose a three-layer hierarchical optimization framework which integrates the convex optimization, the heuristic algorithm, and the coalition game theory. In particular, we propose a double weighted mutation genetic algorithm to enhance the convergence of the algorithm, which applies weighted mutations to the offloading leader and the offloading order in the coalition. Furthermore, the task execution costs in both middle and upper layers are analytically evaluated. Simulation results validate the effectiveness of our proposed algorithms in reducing the task execution costs and speeding up the convergence.