山东科学 ›› 2025, Vol. 38 ›› Issue (1): 96-104.doi: 10.3976/j.issn.1002-4026.20240064

• 交通运输 • 上一篇    下一篇

基于车联网的边缘计算低能耗任务卸载方法

李立娟1(), 李研强1,*(), 童星2, 王勇1, 钟志邦1   

  1. 1.齐鲁工业大学(山东省科学院) 山东省科学院自动化研究所,山东 济南 250014
    2.山东高速信息集团有限公司,山东 济南 250002
  • 收稿日期:2024-04-24 出版日期:2025-02-20 发布日期:2025-01-21
  • 通信作者: 李研强(1977—),男,研究员,研究方向为自动驾驶、5G。E-mail: liyq@sdas.org, Tel:15254187758
  • 作者简介:李立娟(1996—),女,硕士研究生,研究方向为车联网边缘计算任务卸载。E-mail: 18805692268@163.com
  • 基金资助:
    山东省自然科学基金面上项目(ZR2021MF103)

Low-energy task-offloading method based on edge computing in internet of vehicles

LI Lijuan1(), LI Yanqiang1,*(), TONG Xing2, WANG Yong1, ZHONG Zhibang1   

  1. 1. Institute of Automation, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, China
    2. Shandong High-speed Information Group Co., Ltd., Jinan 250002, China
  • Received:2024-04-24 Online:2025-02-20 Published:2025-01-21

摘要:

随着智能交通和绿色出行领域的蓬勃发展,针对车辆网络低时延业务需求和能源节约的双重挑战,提出了一种基于车联网通信的边缘计算低能耗卸载方法。在多车单小区场景的公共路段中,探讨了行驶中车辆的任务卸载需求,并对计算资源的分配问题进行了系统研究。为充分利用计算资源,不仅考虑了车辆自身的计算能力,还提出了将任务卸载至同向行驶或路边停放的车辆服务器,以及路边单元的边缘服务器的新思路,实现了计算资源的有效整合与高效共享,显著提升了车辆网络的处理能力。采用了改进的粒子群优化算法,对卸载功率和任务分配比例进行优化。通过大量仿真实验验证,该方法显著降低了车辆处理任务的能耗,同时提升了车辆网络的服务质量和能源使用效率。有助于推动绿色交通和可持续发展,为未来智能交通系统的能源优化和效率提升奠定了坚实的基础。

关键词: 车联网, 边缘计算, 改进粒子群算法, 低能耗

Abstract:

With the extensive development of intelligent transportation and eco-friendly travel, a low-energy task-offloading method based on edge computing in the internet of vehicles (IoV) is proposed to address the dual challenges of low-latency service demands and energy conservation in the IoV. In the context of multivehicle single-cell scenarios on public roads, this study explores the task-offloading requirements of vehicles in motion and systematically investigates the allocation of computational resources. To fully utilize computing resources, this study not only considers the computing power of vehicles but also introduces a new approach for offloading tasks to vehicle servers traveling in the same direction or parked along the roadside as well as to edge servers in roadside units. This enables the effective integration and efficient sharing of computing resources, thereby remarkably enhancing the processing capabilities of the IoV. Furthermore, this study employs an improved particle swarm optimization algorithm to optimize offloading power and task allocation ratios. Extensive simulation tests revealed that the proposed method significantly reduced the energy consumption of vehicle tasks and improved the service quality and energy efficiency of the IoV.It helps to promote green transportation and sustainable development, and lays a solid foundation for energy optimization and efficiency improvement of future intelligent transportation systems.

Key words: internet of vehicles, edge computing, enhanced particle swarm algorithm, low energy

中图分类号: 

  • TN92

开放获取 本文遵循知识共享-署名-非商业性4.0国际许可协议(CC BY-NC 4.0),允许第三方对本刊发表的论文自由共享(即在任何媒介以任何形式复制、发行原文)、演绎(即修改、转换或以原文为基础进行创作),必须给出适当的署名,提供指向本文许可协议的链接,同时表明是否对原文作了修改,不得将本文用于商业目的。CC BY-NC 4.0许可协议详情请访问 https://creativecommons.org/licenses/by-nc/4.0