Context-Aware Mobility Management in HetNets: A Reinforcement Learning Approach
This addresses mobility management challenges in 4G+ networks for improved user throughput and fairness, but it is incremental as it builds on existing reinforcement learning methods for a specific domain problem.
The paper tackles handover performance issues for high-velocity user equipment in dense heterogeneous networks by proposing a reinforcement learning-based mobility management approach, achieving up to 80% gain in UE throughput and reducing handover failure probability by up to a factor of three.
The use of small cell deployments in heterogeneous network (HetNet) environments is expected to be a key feature of 4G networks and beyond, and essential for providing higher user throughput and cell-edge coverage. However, due to different coverage sizes of macro and pico base stations (BSs), such a paradigm shift introduces additional requirements and challenges in dense networks. Among these challenges is the handover performance of user equipment (UEs), which will be impacted especially when high velocity UEs traverse picocells. In this paper, we propose a coordination-based and context-aware mobility management (MM) procedure for small cell networks using tools from reinforcement learning. Here, macro and pico BSs jointly learn their long-term traffic loads and optimal cell range expansion, and schedule their UEs based on their velocities and historical rates (exchanged among tiers). The proposed approach is shown to not only outperform the classical MM in terms of UE throughput, but also to enable better fairness. In average, a gain of up to 80\% is achieved for UE throughput, while the handover failure probability is reduced up to a factor of three by the proposed learning based MM approaches.