Deep Q-Learning for Routing Schemes in SDN-Based Data Center Networks
Deep Q-Learning for Routing Schemes in SDN-Based Data Center Networks
复制标题
基于 SDN 的数据中心网络中路由方案的深度 Q 学习
DOI：
10.1109/access.2020.2995511
复制
发表时间：
2020-06
期刊：
影响因子：
3.9
通讯作者：
Zhang Yanhua
中科院分区：
文献类型：
--
作者：
Fu Qiongxiao;Sun Enchang;Meng Kang;Li Meng;Zhang Yanhua
为了适应云计算、大数据等技术的快速发展，提出了数据中心网络与SDN的结合，使网络管理更加方便灵活。利用这一优势，路由策略得到了研究人员的广泛研究。然而，控制器中的策略主要依靠人工设计，在动态网络环境下很难得到最优解。因此，基于人工智能（AI）的策略正在考虑之中。本文提出了一种基于深度Q学习（DQL）的路由策略，用于为基于SDN的数据中心网络自主生成最佳路由路径。为了满足数据中心网络中老鼠流和大象流的不同需求，分别为它们训练了深度Q网络，以实现老鼠流的低延迟和低丢包率，大象流的高吞吐量和低丢包率。考虑到数据中心网络和SDN的流量分布和资源有限性，本文选择端口速率和流表利用率来描述网络状态。仿真结果表明，与ECMP路由和SRL +FlowFit路由相比，该路由方案能有效降低微流的平均时延和平均丢包率，同时提高象流的平均吞吐量.
In order to adapt to the rapid development of cloud computing, big data, and other technologies, the combination of data center networks and SDN is proposed to make network management more convenient and flexible. With this advantage, routing strategies have been extensively studied by researchers. However, the strategies in the controller mainly rely on manual design, the optimal solutions are difficult to be obtained in the dynamic network environment. So the strategies based on artificial intelligence (AI) are being considered. This paper proposes a novel routing strategy based on deep Q-learning (DQL) to generate optimal routing paths autonomously for SDN-based data center networks. To satisfy the different demands of mice-flows and elephant-flows in data center networks, deep Q networks are trained for them respectively to achieve low latency and low packet loss rate for mice-flows as well as high throughput and low packet loss rate for elephant-flows. Furthermore, with the consideration of the distribution of traffic and the limitated resources of data center networks and SDN, we choose port rate and flow table utilization to describe the network state. Simulation results show that compared with Equal-Cost Multipath (ECMP) routing and Selective Randomized Load Balancing (SRL)+FlowFit, the proposed routing scheme can reduce both the average delay of mice-flows and average packet loss rate, while increase the average throughput of elephant-flows.
登录
查看更多内容
影响因子：
35.6
作者：
Wenfeng Xia;Peng Zhao;Yonggang Wen;Haiyong Xie
通讯作者：
Wenfeng Xia;Peng Zhao;Yonggang Wen;Haiyong Xie
DOI：
10.1109/wpmc.2014.7014867
发表时间：
2014-09
期刊：
2014 International Symposium on Wireless Personal Multimedia Communications (WPMC)
影响因子：
--
作者：
Jing Liu;Jie Li;Guochu Shou;Yihong Hu;Zhigang Guo;Wei Dai
通讯作者：
Jing Liu;Jie Li;Guochu Shou;Yihong Hu;Zhigang Guo;Wei Dai
DOI：
--
发表时间：
2021
期刊：
--
影响因子：
--
作者：
通讯作者：
--
DOI：
10.1109/netsoft.2015.7116182
发表时间：
2015-04
期刊：
Proceedings of the 2015 1st IEEE Conference on Network Softwarization (NetSoft)
影响因子：
--
作者：
Wile Sehery;Charles Clancy
通讯作者：
Wile Sehery;Charles Clancy
DOI：
10.1145/1402958.1402967
发表时间：
2008-08
期刊：
--
影响因子：
--
作者：
Mohammad Al-Fares;Alexander Loukissas;Amin Vahdat
通讯作者：
Mohammad Al-Fares;Alexander Loukissas;Amin Vahdat