无人机群辅助边缘计算系统的任务卸载和资源分配联合优化  

Joint optimization of task offloading and resource allocation for UAV swarm-assisted edge computing systems

作　　者：刘世豪 黄仰超[1] 胡航 司江勃[2] 韩蕙竹 安琪 LIU Shihao;HUANG Yangchao;HU Hang;SI Jiangbo;HAN Huizhu;AN Qi(College of Information and Navigation,Air Force Engineering University,Xi’an 710077,China;State Key Laboratory of Integrated Services Network,Xidian University,Xi’an 710071,China)

机构地区：[1]空军工程大学信息与导航学院,陕西西安710077 [2]西安电子科技大学综合业务网理论及关键技术国家重点实验室,陕西西安710071

出　　处：《系统工程与电子技术》2024年第2期751-760,共10页Systems Engineering and Electronics

基　　金：国家自然科学基金(61901509);空军工程大学校长基金(XZJK2019033)资助课题。

摘　　要：为提升无人机群辅助边缘计算系统在负载不均衡场景下的性能,构建了一种新的无人机群边缘计算系统,利用无人机之间卸载数据来提高计算资源的利用率,通过联合优化多架无人机的卸载方案、部署和资源分配,使得系统的时延和能耗加权和最小。该问题高度非凸,为此提出一种高效的双层优化算法——启发最优评价算法,上层使用粒子群算法优化无人机位置,下层在确定位置的情况下使用块坐标下降算法优化无人机的数据卸载和资源分配。仿真结果表明,所提方案可有效降低系统成本,与基准策略相比优势明显。To improve the performance of unmanned aerial vehicle swarm-assisted edge computing systems under load imbalancing scenarios,a new unmanned aerial vehicle swarm edge computing system is constructed to improve the utilization of computing resources by using offloading data among unmanned aerial vehicle.The weighted sum of the system’s delay and energy consumption are minimized by jointly optimizing the offloading scheme,deployment,and resource allocation of multiple unmanned aerial vehicle.The problem is highly nonconvex,and a two-layer optimization scheme is proposed to solve the problem,i.e.,the heuristic optimal evaluation algorithm.The upper layer uses a particle swarm algorithm to optimize the unmanned aerial vehicle locations.The lower layer uses a block coordinate descent algorithm to optimize the unmanned aerial vehicle data offloading and resource allocation under the determined locations.The simulation results show that the proposed scheme can effectively reduce the system cost and has obvious advantages over the benchmark strategies.

关 键 词：边缘计算 无人机群 任务卸载 资源分配 位置优化 

分 类 号：TN925[电子电信—通信与信息系统]