Learning Based Interference Coordination for Maritime Communications  

作　　者：Liu Chuhuan Xiao Liang Chen Yifan Li Siyao Yang Helin Lyu Zefang 

机构地区：[1]Department of Information and Communication Engineering,Xiamen University,Xiamen 361005,China [2]Key Laboratory of Multimedia Trusted Perception and Efficient Computing,Ministry of Education of China,Xiamen University,Xiamen 361005,China

出　　处：《China Communications》2025年第4期356-374,共19页中国通信(英文版)

摘　　要：With the boom in maritime activities,the need for highly reliable maritime communication is becoming urgent,which is an important component of 5G/6G communication networks.However,the bandwidth reuse characteristic of 5G/6G networks will inevitably lead to severe interference,resulting in degradation in the communication performance of maritime users.In this paper,we propose a safe deep reinforcement learning based interference coordination scheme to jointly optimize the power control and bandwidth allocation in maritime communication systems,and exploit the quality-of-service requirements of users as the risk value references to evaluate the communication policies.In particular,this scheme designs a deep neural network to select the communication policies through the evaluation network and update the parameters using the target network,which improves the communication performance and speeds up the convergence rate.Moreover,the Nash equilibrium of the interference coordination game and the computational complexity of the proposed scheme are analyzed.Simulation and experimental results verify the performance gain of the proposed scheme compared with benchmarks.

关 键 词：bandwidth allocation interference coordination maritime communication power control rein-forcement learning 

分 类 号：TN929.5[电子电信—通信与信息系统]