面向车联网的多资源集成驱动任务卸载:从无线干扰的视角
摘要
任务卸载技术在车联网 (IoV) 中发挥着关键作用,通过满足车辆的多样化需求,如计算任务的能耗和处理延迟。与现有工作不同之处在于:一方面,它们忽略了车辆间 (V2V) 以及车辆与路侧单元 (RSU) 之间通信的无线干扰;另一方面,也忽略了停靠在路边车辆和道路上其他移动车辆的可用资源。本文首先采用截断正态分布来建模车辆移动速度,而不是先前研究中使用的简单平均速度模型。随后,考虑到 V2V 和 RSU 之间存在的无线干扰以及有效通信时长,建立了以能耗和处理延迟为特征的任务卸载分析框架,集成了停靠车辆、移动车辆和 RSU 的计算资源。进一步地,受多智能体确定性策略梯度 (MADDPG) 方法的启发,我们解决计算任务能耗和处理延迟的联合优化问题,同时确保资源的负载均衡。最后,仿真结果表明了所提出方法的有效性和正确性。特别是地方法在任务卸载方面,MADDPG 在收敛速度、能耗和处理延迟方面表现最佳。
引用
@article{arxiv.2405.16078,
title = {An Multi-resources Integration Empowered Task Offloading in Internet of Vehicles: From the Perspective of Wireless Interference},
author = {Xiaowu Liu and Yun Wang and Kan Yu and Dianxia Chen and Dong Li and Qixun Zhang and Zhiyong Feng},
journal= {arXiv preprint arXiv:2405.16078},
year = {2024}
}
备注
The paper has been rejected by IEEE Transactions on Communications, apart from the Reviewers' comments, we need reconsider that inaccuracies in the data or results were identified post-submission, necessitating a withdrawal for correction. In addition, considering the plausibility of the simulations, one or more of the authors requested the withdrawal of the manuscript