基于深度强化学习的软件定义网络QoS优化  

Software-defined networking QoS optimization based on deep reinforcement learning

作　　者：兰巨龙[1] 张学帅 胡宇翔[1] 孙鹏浩[1] LAN Julong;ZHANG Xueshuai;HU Yuxiang;SUN Penghao(National Digital Switching System Engineering&Research Center,Zhengzhou 450001,China)

机构地区：[1]国家数字交换系统工程技术研究中心

出　　处：《通信学报》2019年第12期60-67,共8页Journal on Communications

基　　金：国家重点研发计划基金资助项目(No.2017YFB0803204);国家自然科学基金资助项目(No.61521003,No.61702547,No.61872382);广东省重点领域研发计划基金资助项目(No.2018B010113001)~~

摘　　要：为解决软件定义网络场景中,当前主流的基于启发式算法的QoS优化方案常因参数与网络场景不匹配出现性能下降的问题,提出了基于深度强化学习的软件定义网络QoS优化算法。首先将网络资源和状态信息统一到网络模型中,然后通过长短期记忆网络提升算法的流量感知能力,最后基于深度强化学习生成满足QoS目标的动态流量调度策略。实验结果表明,相对于现有算法,所提算法不但保证了端到端传输时延和分组丢失率,而且提高了22.7%的网络负载均衡程度,增加了8.2%的网络吞吐率。To solve the problem that the QoS optimization schemes which based on heuristic algorithm degraded often due to the mismatch between parameters and network characteristics in software-defined networking scenarios,a software-defined networking QoS optimization algorithm based on deep reinforcement learning was proposed.Firstly,the network resources and state information were integrated into the network model,and then the flow perception capability was improved by the long short-term memory,and finally the dynamic flow scheduling strategy,which satisfied the specific QoS objectives,were generated in combination with deep reinforcement learning.The experimental results show that,compared with the existing algorithms,the proposed algorithm not only ensures the end-to-end delay and packet loss rate,but also improves the network load balancing by 22.7%and increases the throughput by 8.2%.

关 键 词：软件定义网络 深度强化学习 长短期记忆 服务质量 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]