Boltzmann optimized Q-learning algorithm for high-speed railway handover control
CHEN Yong
KANG Jie
Abstract：Aiming at the problem of using a fixed handover threshold for 5G-R high-speed railway cross section han-dover and ignoring the effects of same frequency interference and ping-pong handover,which leads to a low success rate of cross section handover,a cross section handover control algorithm based on Boltzmann optimized Q-learning is proposed.Firstly,a Q-table with train position action as the index was designed,and a Q-learning algorithm return function was con-structed by comprehensively considering ping pong handover,bit error rate,and other factors.Then,a Boltzmann search strategy is proposed to optimize action selection and improve the convergence performance of the handover algorithm.Finally,taking into account the impact of co frequency interference of base stations,the Q-table is updated to obtain the handover decision parameters,thereby controlling the handover execution.The simulation results show that the improved algorithm can effectively enhance the handover success rate compared to traditional algorithms under different operating speeds and scenarios,and meet the Quality of Service(QoS)requirements of wireless communication systems.
Keywords：handover5G-RQ-learning algorithmBoltzmann optimize strategy
Publication Date：2025-04-30
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：7( 688-694 )