| 摘要: |
| 当物联网设备(Internet of Things Device,IoTD)面临随机到达且复杂度高的计算任务时，因自身计算资源和能力所限，无法进行实时高效的处理。为了应对此类问题，设计了一种两层无人机辅助的移动边缘计算(Mobile Edge Computing,MEC)模型。在该模型中，考虑到IoTD处理随机计算任务时的局限性，引入多架配备MEC服务器的下层无人机和单架上层无人机进行协同处理。为了实现系统能耗最优化，提出了一种资源优化和多无人机位置部署方案，根据计算任务到达的随机性，应用李雅普诺夫优化方法将能耗最小化问题转化为一个确定性问题，应用差分进化(Differential Evolution,DE)算法进行多次变异、交叉和选择取得无人机的优化部署方案；采用深度确定性策略梯度(Depth Deterministic policy Gradient,DDPG)算法对带宽分配、计算资源分配、传输功率分配和任务卸载分配进行联合优化。实验结果表明，该算法相较于对比算法系统能耗降低35%，充分验证了其可行性和有效性。 |
| 关键词: 无人机（UAV） 能耗优化 移动边缘计算(MEC) 随机计算卸载 |
| DOI：10.20079/j.issn.1001-893x.230104002 |
|
| 基金项目:国家自然科学基金资助项目(62271264) |
|
| A Two-ayer UAV Energy Consumption Optimization Method for Stochastic Computation Offloading |
| TAN Ling,b,CAO Boyuan,XIA Jingming |
| (a.School of Computer Science/School of Cyber Science and Engineering;b.Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology CICAEET;c.School of Artificial Intelligence;d.School of Software,Nanjing University of Information Science and Technology,Nanjing 210044,China) |
| Abstract: |
| Internet of Things device (IoTD) cannot process the randomly and highly complex computing tasks in a timely and efficient manner due to insufficient computing resources and capabilities.To solve such problems,a two-ayer unmanned aerial vehicle (UAV)-ssisted mobile edge computing (MEC) model.It gives sufficient consideration of the limitation of IoTD in handling random computing tasks,and introduces multiple low-ltitude UAVs equipped with MEC servers and a single high-ltitude UAV for assistance.To optimize the system energy consumption,a resource optimization and multi-AV location deployment scheme is proposed.According to the randomness of the calculation task,the Lyapunov optimization method is applied to transform the energy consumption minimization problem into a deterministic problem.To carry out multiple mutations,crossover and selection,the Differential Evolution (DE) algorithm is used to obtain the optimal UAV deployment scheme.Besides,the Depth Deterministic Policy Gradient (DDPG) algorithm is adopted to optimize the bandwidth allocation,computation resource allocation,transmission power allocation and task offload allocation.Experimental results show that compared with the comparison algorithm,the proposed method can significantly reduce the energy consumption by 35 |
| Key words: unmanned aerial vehicle(UAV) energy sumption optimization mobile edge computing(MEC) stochastic calculation offloading |
