Abstract:

In view of the increasing demand for user experience quality， the difficulty in obtaining link status caused by highly mobile vehicles， and the time-varying problem of heterogeneous edge nodes providing resources to vehicles in Vehicle Edge Computing （VEC）， a VEC scheme based on Joint Task Offloading and Resource Optimization （JTO-RO） was developed. Firstly， without loss of the generality， a Vehicle-to-Infrastructure （V2I） transmission model was proposed by considering the intra-edge and inter-edge interference comprehensively. In the model， by introducing Non-Orthogonal Multiple Access （NOMA） technology， edge nodes did not rely on link status information and improved the channel capacity at the same time. Secondly， in order to enhance performance and efficiency of the system， a Multi-Agent Twin Delayed Deep Deterministic policy gradient （MATD3） algorithm was designed to formulate task offloading strategies， which were able to be adjusted dynamically through interactive learning with the environment. Thirdly， the synergies of the two strategies were considered jointly， and an optimization scheme was formulated with the goal of maximizing the task service ratio to meet the increasing user experience quality requirements. Finally， simulation was carried out on a real vehicle trajectory dataset. The results show that compared with three current representative schemes （the schemes using Random Offloading （RO） algorithm， D4PG （Distributed Distributional Deep Deterministic Policy Gradient） algorithm， and MADDPG （Multi-Agent Deep Deterministic Policy Gradient） algorithm as task offloading algorithms as task offloading algorithm， respectively）， the proposed scheme has the average service ratio improved by more than 20%， 10%， and 29%， respectively， in three scenarios （normal scenario， task-intensive scenario and delay-sensitive scenario）， verifying the advantages and effectiveness of the scheme.

Key words: Vehicular Edge Computing (VEC), Non-Orthogonal Multiple Access (NOMA), Deep Reinforcement Learning (DRL), task offloading, resource allocation

摘要：

针对车辆边缘计算（VEC）中存在的用户体验质量需求不断增加、高度移动车辆引起的链路状态获取困难和异构边缘节点为车辆提供资源的时变性等问题，制定一种联合任务卸载和资源优化（JTO-RO）的VEC方案。首先，在不失一般性的前提下，综合考虑边缘内和边缘间干扰，提出一种车辆到基础设施（V2I）的传输模型，该模型通过引入非正交多址接入（NOMA）技术使边缘节点不仅无需依赖链路状态信息，还可以提升信道容量；其次，为了提高系统的性能和效率，设计一种多智能体双延迟深度确定性（MATD3）算法用于制定任务卸载策略，这些策略可通过与环境的交互学习进行动态调整；再次，联合考虑2种策略的协同作用，并制定将最大化任务服务比率作为目标的优化方案，从而满足不断提升的用户体验质量需求；最后，对真实车辆轨迹数据集进行仿真实验。结果表明，相较于当前具有代表性的3种方案（分别以随机卸载（RO）算法、D4PG （Distributed Distributional Deep Deterministic Policy Gradient）算法和MADDPG （Multi-Agent Deep Deterministic Policy Gradient）算法为任务卸载算法的方案）在3类场景下（普通场景、任务密集型场景和时延敏感型场景），所提方案的平均服务比率分别提高了20%、10%和29%以上，验证了该方案的优势和有效性。

关键词: 车辆边缘计算, 非正交多址接入, 深度强化学习, 任务卸载, 资源分配