Vehicular Ad hoc NETworks (VANETs) have become an important part of a smart city environment. Vehicles are equipped with On-Board Units (OBUs) which allow them to run applications and communicate with Road Side Units (RSUs). RSUs can be connected to a local server with some amount of storage and computing resources to run Virtual Machines (VMs) to run application requests generated by vehicles. The tasks generated by vehicles may have different data generation rates and deadlines for completion. Running all the VMs to process the application requests at RSUs may make some of the RSUs overloaded, especially near road intersections where a larger number of vehicles are present. Hence, load balancing by migrating some VMs from overloaded RSUs to other RSUs with spare resources is needed to ensure that the applications complete within their deadlines. However, migration is costly and introduces additional delays, and hence it is important to reduce the migration cost. In this paper, we propose an algorithm called Application Aware Load Balancing (AALB) that schedules the VMs for the applications efficiently among the RSUs so as to try to maximize the number of VMs that complete while reducing the migration cost. Detailed simulation results are presented to evaluate the performance of AALB and compare it with three other existing algorithms. The results indicate that AALB performs better than the existing algorithms with respect to both the percentage of VMs completed and the migration cost.

车载自组织网络 (VANET) 已成为智慧城市环境的重要组成部分。车辆配备车载单元 (OBU)，允许它们运行应用程序并与路边单元 (RSU) 通信。RSU 可以连接到具有一定数量存储和计算资源的本地服务器，以运行虚拟机 (VM) 来运行车辆生成的应用程序请求。车辆生成的任务可能具有不同的数据生成率和完成期限。运行所有 VM 来处理 RSU 处的应用程序请求可能会使一些 RSU 过载，尤其是在存在大量车辆的道路交叉口附近。因此，需要通过将一些 VM 从过载的 RSU 迁移到具有备用资源的其他 RSU 来实现负载平衡，以确保应用程序在其期限内完成。然而，迁移成本高昂并引入了额外的延迟，因此降低迁移成本很重要。在本文中，我们提出了一种称为应用程序感知负载平衡 (AALB) 的算法，该算法有效地在 RSU 之间为应用程序调度虚拟机，以便在降低迁移成本的同时尝试最大化完成的虚拟机数量。详细的仿真结果用于评估 AALB 的性能，并将其与其他三种现有算法进行比较。结果表明，AALB 在完成的虚拟机百分比和迁移成本方面都优于现有算法。我们提出了一种称为应用程序感知负载平衡 (AALB) 的算法，该算法有效地在 RSU 之间为应用程序调度虚拟机，以便在降低迁移成本的同时尝试最大化完成的虚拟机数量。详细的仿真结果用于评估 AALB 的性能，并将其与其他三种现有算法进行比较。结果表明，AALB 在完成的虚拟机百分比和迁移成本方面都优于现有算法。我们提出了一种称为应用程序感知负载平衡 (AALB) 的算法，该算法有效地在 RSU 之间为应用程序调度虚拟机，以便在降低迁移成本的同时尝试最大化完成的虚拟机数量。详细的仿真结果用于评估 AALB 的性能，并将其与其他三种现有算法进行比较。结果表明，AALB 在完成的虚拟机百分比和迁移成本方面都优于现有算法。