一种城轨交通车地无线通信网络覆盖优化方法
By constructing a quantitative model and using deep reinforcement learning methods in urban rail transit, and optimizing base station radio frequency parameters, the impact of network coverage quality on train operation efficiency in high-speed mobile scenarios was resolved, achieving adaptive optimization of network coverage and efficiency improvement.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING JIAOTONG UNIV
- Filing Date
- 2025-10-23
- Publication Date
- 2026-07-17
AI Technical Summary
Existing adaptive optimization methods for wireless networks are not suitable for high-speed urban rail transit scenarios, are difficult to deploy based on existing infrastructure, and do not fully consider the impact of network coverage quality on train operation efficiency.
Based on the train braking model, a quantitative model is constructed to calculate the minimum train tracking interval and the line throughput capacity. A state space and reward function of deep reinforcement learning are designed, and the base station radio frequency parameters are optimized through a multi-agent deep deterministic gradient policy algorithm to achieve adaptive optimization of network coverage.
It reduces the probability of unnecessary braking of trains, improves network coverage quality, balances train operation efficiency and communication performance, and dynamically adapts to complex and ever-changing wireless environments.
Smart Images
Figure CN121151833B_ABST