User Satisfaction-Aware Edge Computation Offloading in 5G Multi-Scenario

作     者：Xiaochuan Sun Xiaoyu Niu Yutong Wang Yingqi Li Xiaochuan Sun;Xiaoyu Niu;Yutong Wang;Yingqi Li

作者机构：College of Artificial IntelligenceNorth China University of Science and TechnologyTangshan 063210China Hebei Key Laboratory of Industrial Intelligent PerceptionTangshan 063210China School of Computer and Communication EngineeringUniversity of Science and Technology BeijingBeijing 100083China 

出 版 物：《Journal of Communications and Information Networks》 (通信与信息网络学报（英文）)

年 卷 期：2023年第8卷第3期

页      面：271-282页

核心收录：

学科分类：080904[工学-电磁场与微波技术] 0810[工学-信息与通信工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 080402[工学-测试计量技术及仪器] 0804[工学-仪器科学与技术] 081001[工学-通信与信息系统] 

基　　金：This work was supported in part by the Science and Technology Project of North China University of Science and Technology under Grant ZD-YG-202317-23 

主　　题：DNN user satisfaction 5G multi-scenario edge computation offloading 

摘      要：Edge computation offloading has made some progress in the fifth generation mobile network(5G).However,load balancing in edge computation offloading is still a challenging ***,with the continuous pursuit of low execution latency in 5G multi-scenario,the functional requirements of edge computation offloading are further *** the above challenges,we raise a unique edge computation offloading method in 5G multi-scenario,and consider user *** method consists of three functional parts:offloading strategy generation,offloading strategy update,and offloading strategy ***,the offloading strategy is generated by means of a deep neural network(DNN),then update the offloading strategy by updating the DNN ***,we optimize the offloading strategy based on changes in user *** summary,compared to existing optimization methods,our proposal can achieve performance close to the *** simulation results indicate the latency of the execution of our method on the CPU is under 0.1 seconds while improving the average computation rate by about 10%.