Data-Driven Cellular Mobility Management via Bayesian Optimization and Reinforcement Learning

TL;DR

This paper introduces data-driven methods using Bayesian optimization and reinforcement learning to optimize cellular handover parameters, improving mobility management performance in complex, real-world network scenarios.

Contribution

It presents novel HD-BO and DRL approaches for adaptive mobility management, outperforming traditional fixed-parameter benchmarks and enabling transfer learning for diverse user speeds.

Findings

HD-BO and DRL outperform 3GPP benchmarks in real-world scenarios.

Transfer learning enhances adaptability to different user speeds.

HD-BO is more sample-efficient than DRL, suitable for limited data scenarios.

Abstract

Mobility management in cellular networks faces increasing complexity due to network densification and heterogeneous user mobility characteristics. Traditional handover (HO) mechanisms, which rely on predefined parameters such as A3-offset and time-to-trigger (TTT), often fail to optimize mobility performance across varying speeds and deployment conditions. Fixed A3-offset and TTT configurations either delay HOs, increasing radio link failures (RLFs), or accelerate them, leading to excessive ping-pong effects. To address these challenges, we propose two data-driven mobility management approaches leveraging high-dimensional Bayesian optimization (HD-BO) and deep reinforcement learning (DRL). HD-BO optimizes HO parameters such as A3-offset and TTT, striking a desired trade-off between ping-pongs vs. RLF. DRL provides a non-parameter-based approach, allowing an agent to select serving cells based on real-time network conditions. We validate our approach using a real-world cellular deployment scenario, and employing Sionna ray tracing for site-specific channel propagation modeling. Results show that both HD-BO and DRL outperform 3GPP set-1 (TTT of 480 ms and A3-offset of 3 dB) and set-5 (TTT of 40 ms and A3-offset of -1 dB) benchmarks. We augment HD-BO with transfer learning so it can generalize across a range of user speeds. Applying the same transfer-learning strategy to the DRL method reduces its training time by a factor of 2.5 while preserving optimal HO performance, showing that it adapts efficiently to the mobility of aerial users such as UAVs. Simulations further reveal that HD-BO remains more sample-efficient than DRL, making it more suitable for scenarios with limited training data.