A VLC-RF network resource matching method based on martingale theory and reinforcement learning
By employing martingale theory and reinforcement learning methods, a handover service mechanism for VLC-RF heterogeneous networks is constructed. Multidimensional QoS indicators are derived and a user satisfaction utility function is established, which solves the problem of singular network performance evaluation in existing technologies and achieves optimal resource allocation and improved network service efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- JILIN INST OF CHEM TECH
- Filing Date
- 2025-02-28
- Publication Date
- 2026-06-26
AI Technical Summary
Existing VLC-RF network resource matching schemes only focus on system latency performance, and do not fully consider the nonlinear mapping relationship between user satisfaction and service quality parameters, resulting in a single network performance evaluation and insufficient guarantee of user QoS requirements.
We employ martingale theory and reinforcement learning to construct a VLC-RF heterogeneous network handover service mechanism. We describe state transitions using a Markov chain model, derive multidimensional QoS indicators, establish a user satisfaction utility function, and utilize reinforcement learning to obtain the optimal service rate combination.
It achieves improved network service efficiency and user satisfaction, and optimized resource allocation, while ensuring diverse QoS requirements of users.
Smart Images

Figure CN120090705B_ABST