Research on Edge Computing and Caching Resource Allocation Mechanism for Multi-view Video

Abstract

Multi-View Video (MVV) is an emerging video technology that allows users to freely change their viewing angle when watching. Compared with traditional video transmission, multi-view video transmission requires large bandwidth and high computing power, which brings great challenges to multi-view video transmission under wireless networks. With the rapid development of Mobile Edge Computing (MEC) technology, this technology has become one of the potential solutions to the problem of multi-view video transmission in wireless networks by using edge caching and computing technology. This paper firstly establishes a communication model for multi-view video transmission, models different transmission paths in the process of multi-view video transmission, and jointly optimizes the design of edge computing and storage resources to maximize the hit rate of edge caching and computing. Further, a deep reinforcement learning algorithm is designed for the resource allocation mechanism of edge computing and storage. Finally, the simulation results verify that the algorithm can significantly improve the hit rate of edge computing and storage.