多无人机网络边缘智能计算卸载算法  

Computation Offloading Algorithm for Multi-UAV Network Based on Edge Intelligence

作　　者：王心一[1] 陈志江 雷磊[1] 宋晓勤[1] WANG Xinyi;CHEN Zhijiang;LEI Lei;SONG Xiaoqin(Public Experimental Teaching Department,Nanjing University of Aeronautics&Astronautics,Nanjing 211106,China)

机构地区：[1]南京航空航天大学公共实验教学部,南京211106

出　　处：《数据采集与处理》2023年第6期1286-1298,共13页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(62371232);江苏省教育厅及未来网络创新研究院“未来网络”科研基金(FNSRFP-2021-ZD-4)。

摘　　要：为了解决大规模部署固定边缘计算节点成本高、机动性差和难以应对突发事件等问题,针对计算密集型和延迟敏感型移动业务需求,提出了一种基于深度强化学习的计算任务卸载算法。考虑多架无人机飞行范围、飞行速度和系统公平效益等约束条件,最小化网络平均计算延时与无人机能耗的加权和。将该非凸性、NP(Non-deterministic polynomial)难问题转化为部分观测马尔可夫决策过程,利用多智能体深度确定性策略梯度算法进行移动用户卸载决策和无人机飞行轨迹优化。仿真结果表明,所提算法在移动服务终端的公平性、系统平均时延和多无人机的总能耗等方面的性能均优于基线算法。其中,所提算法能够得到不同计算性能下的最佳功耗控制,当CPU频率为12.5 GHz时,能耗相比基线降低29.16%,相比随机策略梯度算法降低8.67%。In order to solve the problems of high cost,poor mobility and difficulty in coping with emergency in large-scale deployment of fixed edge computing nodes,a computing task offloading algorithm based on deep reinforcement learning is proposed to meet the needs of computing-intensive and delay-sensitive mobile services.Considering constraints such as the flight range,flight speed and system fairness benefits of multiple unmanned aerial vehicles(UAVs),the method aims to minimize the weighted sum of the average computing delay of the network and the UAV energy consumption.This non-convex and non-deterministic polynomial(NP)-hard problem is transformed into a partially observed Markov decision process,and a multi-agent deep deterministic policy gradient algorithm is used for mobile user offloading decision and UAV flight trajectory optimization.Simulation results show that the proposed algorithm outperforms the baseline algorithm in terms of fairness of mobile service terminals,average system delay and total energy consumption of multiple UAVs.Especially,the proposed algorithm can obtain the optimal power consumption control under different computing performance.When the CPU frequency is 12.5 GHz,the energy consumption is 29.16% lower than the Cruise algorithm,and 8.67% lower than the advantage actor-critic(A2C)algorithm.

关 键 词：移动边缘计算 计算卸载策略 无人机轨迹优化 深度确定性策略梯度 用户公平 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]