Delay-Efficient Joint Offloading and Resource Allocation Strategy in Multi-MEC Server Edge Cloud Combination Systems

Abstract

With the Internet of Things devices becoming more intelligent, the emergence of large-scale cloud edge collaborative computing networks has made many emerging applications such as online monitoring, simulation reality possible. However, online processing of large-scale computing tasks brings huge delay between cloud, edge and terminal devices. In order to meet the demand of delay sensitive tasks, a cloud side cooperation mode of multi-user and multi MEC servers is considered in this paper. An optimization model with the goal of minimizing the average system delay is proposed, and a joint offloading and resource allocation algorithm based on bi-level particle swarm optimization (BLPSO-JRAA) is proposed to solve the above problems. The algorithm divides the optimization problem into two levels: offloading strategy and resource allocation, and applies the improved particle swarm optimization algorithm to solve the problem iteratively. It is can be show that BLPSO-JRAA reduces the average computing and communication delay by 38% compared with the average communication resource allocation algorithm when users are dense by the simulation results.