Collaborative Computing for Internet of Vehicles

Abstract

In this chapter, a collaborative edge computing framework is presented to reduce computing service latency and improve service reliability for vehicular networks. First, a task partition and scheduling algorithm is proposed to decide the workload allocation and the execution order of tasks offloaded to edge servers. Second, an artificial intelligence based collaborative computing approach is developed to determine the task offloading, computing, and result delivery policy for vehicles. Specifically, the offloading and computing problem is formulated as a Markov decision process. A deep reinforcement learning technique, i.e., deep deterministic policy gradient, is adopted to find the optimal solution for a complex urban transportation network. Our approach minimizes the service cost, which includes computing service latency and service failure penalty, via the optimal workload assignment and server selection in collaborative computing. Simulation results show that the proposed learning-based collaborative computing approach can adapt to a highly dynamic environment and perform well.