基于机器学习的网络拥塞控制研究

拥塞控制是网络研究的经典课题，可以避免网络因拥塞而性能下降。其在互联网的发展中扮演着重要的角色。近年来，随着机器学习、深度学习和强化学习的兴起，给拥塞控制提供了新的思路。对网络拥塞控制的机制进行了详细分析，阐述了国内外对于该领域的研究现状及进展，将有代表性的解决方案分为基于规则的解决方案、基于路由反馈的解决方案和智能解决方案3类，并详细分析了各方案的原理及优缺点。

Survey on Network Congestion Control Based on Machine Learning

Congestion control is a classic network research topic which can avoid network performance degradation due to congestion.It plays an important role in the development of the Internet.In recent years,the emergence of machine learning,deep learning and reinforcement learning has provided new ideas for congestion control.In this survey,the network congestion control mechanisms are analyzed in detail.In addition,the research status and progress of this field at home and abroad are described in detail.The proposed protocols will be divided into typical solution based on rule schemes,on the routing schemes and on intelligent schemes.The advantages and disadvantages of detailed analysis schemes are also shown in this paper.