Tasks-Oriented Joint Resource Allocation Scheme for the Internet of Vehicles with Sensing, Communication and Computing Integration

With the development of artificial intel-ligence (AI) and 5G technology, the integration of sensing, communication and computing in the Inter-net of Vehicles (IoV) is becoming a trend. However, the large amount of data transmission and the comput-ing requirements of intelligent tasks lead to the com-plex resource management problems. In view of the above challenges, this paper proposes a tasks-oriented joint resource allocation scheme (TOJRAS) in the sce-nario of IoV. First, this paper proposes a system model with sensing, communication, and computing integra-tion for multiple intelligent tasks with different re-quirements in the IoV. Secondly, joint resource allo-cation problems for real-time tasks and delay-tolerant tasks in the IoV are constructed respectively, includ-ing communication, computing and caching resources. Thirdly, a distributed deep Q-network (DDQN) based algorithm is proposed to solve the optimization prob-lems, and the convergence and complexity of the al-gorithm are discussed. Finally, the experimental re-sults based on real data sets verify the performance ad-vantages of the proposed resource allocation scheme, compared to the existing ones. The exploration ef-ficiency of our proposed DDQN-based algorithm is improved by at least about 5%, and our proposed re-source allocation scheme improves the mAP perfor-mance by about 0.15 under resource constraints.