VECSim:改进iFogSim2的面向车载边缘计算的建模与仿真模拟器

目前，研究人员着眼于车载边缘计算（vehicular edge computing，VEC）环境下高效应用和资源调度策略的研究，然而，这些应用和策略的实机验证往往受限于成本和时间，无法快速有效地进行。边缘/雾计算仿真器如iFogSim2的出现降低了实验成本，然而，高速移动车辆的连接切换和资源分配需求对边缘/雾计算仿真器在VEC下应用提出了挑战。因此，改进了iFogSim2，设计了支持高速移动的VEC环境仿真器VECSim。集成开源基站数据并构建车辆轨迹数据集，以便研究人员专注于资源分配策略。首先，为了简化实验步骤，改进了移动轨迹数据解析模块并适配了微观交通仿真软件Simulation of Urban Mobility （SUMO）生成的车辆轨迹数据。其次，基于分布式数据流模型对VEC下的分布式应用进行建模，并提供了服务迁移基准策略算法。此外，VECSim还引入了时间性能优化方法，通过并行化操作，加速仿真事件处理，从而提高了仿真工具的时间性能。实验表明，相比于iFogSim2中同类的服务迁移算法，提出的服务迁移算法在大规模机动车轨迹数据集验证下表现出良好的稳定性，时间性能优化方法在执行时间上取得了5.3%的性能提升。代码开源地址：https://github.com/LiuZiyuan-CS/VECSim。

VECSim: improved iFogSim2 modeling and simulation simulator for vehicular edge computing

Currently, researchers are focusing on efficient applications and resource scheduling strategies in vehicular edge computing(VEC) environments, however, the real-world validation of these applications and strategies is often limited by cost and time and cannot be performed quickly and efficiently. The emergence of edge/fog computing simulators such as iFogSim2 reduces the cost of experiments; however, the connection switching and resource allocation requirements of high-speed moving vehicles pose challenges to the application of edge/fog computing simulators under VEC. Therefore, this paper improved iFogSim2 by designing VECSim, a VEC environment simulator that supported high-speed mobility. It integrated open-source base station data and constructed vehicle trajectory datasets so that researchers can focus on resource allocation strategies. Firstly, to simplify the experimental steps, this paper improved the mobile trajectory data parsing module and adapted the vehicle trajectory data generated by Simulation of Urban Mobility(SUMO), a microscopic transportation simulation software. Secondly, this paper modeled distributed applications under VEC based on the distributed data flow model and provided a service migration benchmark policy algorithm. In addition, VECSim introduced a time-performance optimization method to accelerate the simulation event processing by parallelizing the operation, which improved the time performance of the simulation tool. Experiments show that compared with similar service migration algorithms in iFogSim2, the proposed service migration algorithm exhibits good stability under the validation of large-scale motor vehicle trajectory dataset, and the time-performance optimization method achieves a 5.3% performance improvement in execution time. Code is available: https: //github. com/LiuZiyuan-CS/VECSim.