DDPG-Based Radio Resource Management for User Interactive Mobile Edge Networks

Abstract

The development of the fifth-generation (5G) system on capability and flexibility enables emerging applications with stringent requirements, such as ultra-high-resolution video streaming and online interactive virtual reality (VR) gaming. Hence, the resource management problem becomes more complicated than in the past, and machine learning can be a powerful tool to provide solutions. In this article, the Deep Deterministic Policy Gradient (DDPG) is used to schedule resources in an edge network environment. We integrate a 3D radio resource structure with componentized Markov decision process (MDP) actions to work on user interactivity-based groups. From the simulation results, we can see that more users are satisfied with DDPG-based radio resource management, especially in bandwidth and latency demanding situations.