5G Handover using Reinforcement Learning

In typical wireless cellular systems, the handover mechanism involves reassigning an ongoing session handled by one cell into another. In order to support increased capacity requirement and to enable newer use cases, the next generation wireless systems will have a very dense deployment with advanced beam-forming capability. In such systems, providing a better mobility along with enhanced throughput performance requires an improved handover strategy. In this paper, we will detail a novel method for handover optimization in a 5G cellular network using reinforcement learning (RL). In contrast to the conventional method, we propose to control the handovers between base-stations (BSs) using a centralized RL agent. This agent handles the radio measurement reports from the UEs and choose appropriate handover actions in accordance with the RL framework to maximize a long-term utility. We show that the handover mechanism can be posed as a contextual multi-armed bandit problem and solve it using Q-learning method. We analyze the performance of the methods using different propagation and deployment environment and compare the results with the state-of-the-art algorithms. Results indicate a link-beam performance gain of about 0:3 to 0:7 dB for practical propagation environments.