Technology Category
Search and Optimization: Sampling/Simulation-based SearchMachine Learning: Online Learning & BanditsGame Theory and Economic Paradigms: Adversarial Learning
A Deep Reinforcement Learning-based Approach for Adaptive Handover Protocols
🤖 AI Summary
High-frequency communications necessitate ultra-dense small-cell deployments, leading to frequent handovers and consequently elevated wireless link failure rates and degraded user throughput. To address this challenge, we propose an adaptive handover protocol based on Proximal Policy Optimization (PPO), the first to deploy PPO directly at the base station for real-time, online handover decision-making—significantly enhancing robustness against highly dynamic user mobility. Our approach integrates deep reinforcement learning with a high-fidelity 5G NR system model and realistic mobility simulation. Evaluated against the 3GPP-standardized 5G handover mechanism, our solution achieves a 21.4% average increase in user data rate and a 38.7% reduction in wireless link failure rate. This work establishes a practical, deployable paradigm for reliable mobility management in high-frequency, ultra-dense 5G networks.
Technology Category
Application Category
📝 Abstract
The use of higher frequencies in mobile communication systems leads to smaller cell sizes, resulting in the deployment of more base stations and an increase in handovers to support user mobility. This can lead to frequent radio link failures and reduced data rates. In this work, we propose a handover optimization method using proximal policy optimization (PPO) to develop an adaptive handover protocol. Our PPO-based agent, implemented in the base stations, is highly adaptive to varying user equipment speeds and outperforms the 3GPP-standardized 5G NR handover procedure in terms of average data rate and radio link failure rate. Additionally, our simulation environment is carefully designed to ensure high accuracy, realistic user movements, and fair benchmarking against the 3GPP handover method.
Problem
Research questions and friction points this paper is trying to address.
Optimizing handover protocols for small cell networks
Reducing radio link failures in mobile communications
Improving data rates with adaptive reinforcement learning
Innovation
Methods, ideas, or system contributions that make the work stand out.
PPO-based adaptive handover protocol
Agent adapts to varying UE speeds
Simulation ensures accuracy and fairness
🔎 Similar Papers
2024-08-03arXiv.orgCitations: 0
