A Two-Sided Matching Approach for Distributed Edge Computation Offloading

摘要

Mobile edge computing (MEC) has emerged as a promising technology, that enables real-time information transmission and computing by offloading computation-intensive tasks from mobile devices to the edge of the network, such as base stations (BSs) and access points (APs). In this paper, we consider a MEC system consisting of multiple users and multiple APs, where each AP is equipped with a MEC server. Each user can select one AP to associate for computation offloading and each AP can allocate its resources. We formulate a non-convex problem with the goal of minimizing the system total latency by joint radio-and-computation allocation and user association, subject to the finite computation capacity of each AP. We propose a new algorithm based on the two-sided matching theory to achieve distributed offloading and computing to the problem. Simulation results show the superior performance of the proposed algorithm.