Resource Allocation Algorithm with Multi-Platform Intelligent Offloading in D2D-Enabled Vehicular Networks

Abstract

The latest research of network and computing contributes greatly to the development of vehicular networks. However, in existing works, these two important enabling technologies are studied separately. To reduce the delay, in this paper, we propose a multi-platform intelligent offloading and resource allocation algorithm which can dynamically organize the computing resources to improve the performance of the next-generation vehicular networks. Considering the task calculation problem, the K-nearest neighbor algorithm is used to select the task offloading platform (i.e., cloud computing, mobile edge computing, or local computing). For the computational resource allocation problem and system complexity in non-local computing, reinforcement learning is used to solve the optimization problem of resource allocation. The simulation results show that compared with the baseline algorithm that all tasks are offloaded to the local or mobile edge computing server, the resource allocation scheme achieves a significant reduction in latency cost, and the average system cost can be saved by 80%.