首页|基于深度强化学习的车载边缘计算功率分配方法

基于深度强化学习的车载边缘计算功率分配方法

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
针对车载边缘计算环境下车辆移动引起的车载时变信道和任务随机到达问题,提出了一种基于深度强化学习的计算卸载和功率分配方法.首先,设计了双向车道场景下基于非正交多址的"端-边-云"三层卸载模型;接着,结合该模型的通信、计算、缓存资源以及车辆的移动性,进一步确立了车载用户功率和缓存延迟长期累积总成本最小化的联合优化问题;最后,考虑到车载边缘计算网络的动态、时变和随机特性,提出了基于深度确定性策略梯度的分布式智能算法,以获取最优功率分配机制.仿真实验结果显示,相较于传统方法,所提方法在减少总成本方面具有显著优势.
A Power Allocation Algorithm in Vehicular Edge Computing Networks Based on Deep Reinforcement Learning
To address the time-varying channel and stochastic task arrival problems caused by the mobility of vehicle in the vehicular edge computing environment, a deep reinforcement learning-based computation offloading and power allocation algorithm is proposed.First, we build a three-layer system model for end-edge-cloud orchestrated computing based on non-orthogonal multiple access in a two-way lane scenario.Then, by combining the communication, computing, cache resources and the mobility of vehicle, a joint optimization problem is designed to minimize the long-term cumulative total system cost consisting of power consumption and cache latency.Finally, considering the dynamics, time-varying and stochastic characteristics in vehicular edge computing networks, a decentralized intelligent algorithm based on deep deterministic policy gradient is proposed for obtaining the power allocation optimization.Compared with conventional baseline algorithms, the simulation results demonstrate that the proposed algorithm can achieve a superior performance in reducing the cost of the total system.

vehicular edge computingcomputation offloadingpower allocationservice cachingdeep deterministic policy gradient

邱斌、王云霄、肖海林

展开 >

桂林理工大学 信息科学与工程学院, 桂林541004

广西嵌入式技术与智能系统重点实验室,桂林541004

湖北大学 计算机与信息工程学院, 武汉430062

车载边缘计算 计算卸载 功率分配 服务缓存 深度确定性策略梯度

国家自然科学基金广西壮族自治区重点研发计划广西壮族自治区重点研发计划湖北省高等学校优秀中青年科技创新团队项目

62341117桂科AB23026034桂科AB23075175T2021001

2024

10.13190/j.jbupt.2023-032

北京邮电大学学报
北京邮电大学

北京邮电大学学报

CSTPCD北大核心
影响因子：0.592
ISSN：1007-5321
年,卷(期)：2024.47(2)
  • 2