Mobile Edge Computing Task Offloading Based on ADPSO Algorithm in Multi-user Environment
Ming‐Liang Wei, Zhaoyuan Liu, Wei Tao Hu, Suiyan Geng, Xiongwen Zhao · 2021
Mobile edge computing (MEC) is envisioned as a promising approach to enhance computation capability of user equipment and reduce energy consumption due to the growing popularity of mobile applications. In this paper, a system cost model combining time delay and energy consumption in multiuser MEC environment is studied, the task offloading method based on adaptive discrete particle swarm optimization (ADPSO) algorithm is proposed, the relationships between parameters like system computation cost, number of user equipment and number of channels are investigated. Results show that the proposed ADPSO model can achieve lower computation cost and support more user equipment for task offloading compared with other algorithms of random strategy selection (RSS), best response (BR) and multi-agent stochastic learning (MASL). The present results are useful for the design of MEC system in 5G wireless communications.