A Reinforcement Learning Framework for Mobility Control of gNBs in Dynamic Radio Access Networks

TL;DR

This paper introduces a simulation environment and a reinforcement learning-based approach for mobile base stations to dynamically maintain LoS connectivity in complex wireless environments, demonstrating significant blockage reduction.

Contribution

It presents the CONVERGE Chamber Simulator (CC-SIM) and a Deep Q-Network agent for autonomous mobility control of gNBs in dynamic wireless settings.

Findings

Reinforcement learning reduces LoS blockage by up to 42%.

CC-SIM models realistic mobility, occlusion, and RF behavior.

The approach improves network QoS in dynamic environments.

Abstract

The increasing complexity of wireless environments, characterized by user mobility and dynamic obstructions, poses challenges for the maintenance of Line-of-Sight (LoS) connectivity. Mobile base stations (gNBs) stand as a promising solution by physically relocating to restore or sustain LoS, thereby necessitating the development of intelligent algorithms for autonomous movement control. As part of the CONVERGE research project, which is developing an experimental chamber to integrate computer vision (CV) into mobile networks and enhance Quality of Service (QoS) in dynamic wireless environments, this paper presents two key contributions. First, we introduce the CONVERGE Chamber Simulator (CC-SIM), a 3D simulation environment for developing, training, and validating mobility control algorithms for mobile gNBs. CC-SIM models user and obstacle mobility, visual occlusion, and Radio Frequency (RF) propagation behavior. It supports both offline reinforcement learning and real-time testing through tight integration with a standalone 5G system via the OpenAirInterface (OAI) RF simulator, enabling validation under realistic network conditions. Second, leveraging CC-SIM, we develop a Deep Q-Network (DQN) agent that learns to reposition the gNB proactively in response to dynamic environmental changes. Experiments across three representative use cases show that the trained agent significantly reduces LoS blockage time - by up to 42% - when compared to static deployments. These results highlight the effectiveness of learning-based mobility control in adaptive next-generation wireless networks.