DDPG-Based Intelligent Computation Offloading and Resource Allocation for LEO Satellite Edge Computing Network  

作　　者：Jia Min Wu Jian Zhang Liang Wang Xinyu Guo Qing 

机构地区：[1]School of Electronics and Information Engineering,Harbin Institute of Technology,Harbin 150000,China

出　　处：《China Communications》2025年第3期1-15,共15页中国通信(英文版)

基　　金：supported by National Natural Science Foundation of China No.62231012;Natural Science Foundation for Outstanding Young Scholars of Heilongjiang Province under Grant YQ2020F001;Heilongjiang Province Postdoctoral General Foundation under Grant AUGA4110004923.

摘　　要：Low earth orbit(LEO)satellites with wide coverage can carry the mobile edge computing(MEC)servers with powerful computing capabilities to form the LEO satellite edge computing system,providing computing services for the global ground users.In this paper,the computation offloading problem and resource allocation problem are formulated as a mixed integer nonlinear program(MINLP)problem.This paper proposes a computation offloading algorithm based on deep deterministic policy gradient(DDPG)to obtain the user offloading decisions and user uplink transmission power.This paper uses the convex optimization algorithm based on Lagrange multiplier method to obtain the optimal MEC server resource allocation scheme.In addition,the expression of suboptimal user local CPU cycles is derived by relaxation method.Simulation results show that the proposed algorithm can achieve excellent convergence effect,and the proposed algorithm significantly reduces the system utility values at considerable time cost compared with other algorithms.

关 键 词：computation offloading deep deterministic policy gradient low earth orbit satellite mobile edge computing resource allocation 

分 类 号：TN929.5[电子电信—通信与信息系统] TN927.2[电子电信—信息与通信工程]