光通信技术2024，Vol.48Issue(4)：77-82,6.DOI:10.13921/j.cnki.issn1002-5561.2024.04.015
基于强化学习的异构网络接入选择算法
Heterogeneous network access selection algorithm based on reinforcement learning
摘要
Abstract
Aiming at the challenge of enhancing throughput and maintaining high fairness in heterogeneous network access selec-tion,a proximal policy optimization(PPO)algorithm based on reinforcement learning is proposed.This algorithm interacts with the environment and samples data,aiming to maximize users'long-term throughput and satisfaction.It randomly simulates user locations,collects user attribute data for model training,and acquires the optimal network access point allocation strategy.The simulation results show that compared with traditional algorithms,when the number of access users reaches the maximum,the PPO algorithm can increase throughput by 40％to 70％,while the average user satisfaction can still exceed 30％,and the user fairness index can reach 0.82.关键词
强化学习/吞吐量/体验质量/公平指数Key words
reinforcement learning/throughput/quality of experience/fairness indices分类
信息技术与安全科学引用本文复制引用
张慧颖,马成宇,李月月,梁士达,盛美春..基于强化学习的异构网络接入选择算法[J].光通信技术,2024,48(4):77-82,6.基金项目
吉林省科技厅自然科学基金联合基金(No.YDZJ202101ZYTS189)资助. （No.YDZJ202101ZYTS189）
