基于最优运输理论的蜂窝网边缘卸载时延优化研究

Research on edge offloading delay optimization of cellular networks based on optimal transport theory

随着物联网的发展,蜂窝网络中接入了大量的用户设备。由于用户设备空间分布和应用需求的变化,需要对用户设备卸载决策进行动态调整。综合考虑网络中用户设备空间分布、应用需求、基站侧边缘服务器的处理能力等参数信息,从分布角度出发,优化用户设备的卸载决策。基于最优运输理论,提出一种时延优化算法。通过合理规划网络中用户设备的卸载基站,降低用户设备计算任务卸载过程的平均时延。仿真结果表明,所提基于时延优化的卸载机制能使平均时延降低81.06%,并能均衡各基站之间处理的业务量。

With the development of the internet of things,a large number of user device(UD)were connected to cellular network.Since the changes in the spatial distribution of UD and application requirements,it is necessary to dynamically adjust the UD’offloading decision.Comprehensively considering various parameter information in the networks such as the spatial distribution of UD,application requirements,and the processing capability of the edge servers on the base station(BS)side,the offloading decision of UD were optimized from the perspective of distribution.Based on the optimal transport theory,a delay optimization algorithm was proposed to reduce the average delay of the UD’computing tasks offloading process by reasonably planning the offloading BS of the UD in the networks.The simulation results show that the average delay can be reduced by 81.06%using the proposed offloading mechanism based on delay optimization,and the traffic handled by each BS is balanced.