Intelligent resource allocation management for vehicles network: An A3C learning approach

Abstract

With the increasing demand of users for high-speed, low-delay and high-reliability services in connected vehicles network, wireless networks with communication, caching and computing convergence become the trend of network development in the future. To improve the quality of services of vehicles network, we propose a virtualized framework for mobile vehicle services, which using a learning-based resource allocation scheme. The dynamic change processes are modeled as Markov chains without making assumptions about the optimization goal and reducing the complexity of resource allocation computing. A high performance asynchronous advantage actor–critic learning algorithm is proposed to solve the complex dynamic resource allocation problem. Base on software-defined networking and information-centric networking, the method can dynamic orchestration of computing and communication resources to enhance the performance of virtual wireless networks. Simulation results verify that the proposed scheme can converge at a fast speed and improve the network operator’s total rewards.