{"title":"基于软件定义网络平台的q -学习路由算法","authors":"Pingliang Yuan, Zhengrui Bao, Liandan Wang, Ding Gao, Yutong Wang, Qian Qu, Beilun Li","doi":"10.1109/EEI59236.2023.10212950","DOIUrl":null,"url":null,"abstract":"This paper proposes a Q-learning-based routing algorithm for the routing optimization problem in wireless communication networks. The algorithm utilizes an agent to take actions in the transmission environment, change the corresponding state to obtain rewards, and update the Q-matrix. Through iterative steps, the Q-matrix eventually converges. After learning, the optimal routing strategy can be obtained relying on the Q-table. In addition, this paper solves the consensus problem and routing loop problem between nodes using the SDN network architecture. To meet different quality of service requirements, a new reward function is proposed for the Q-learning algorithm, which considers both transmission bandwidth, communication delay, packet loss rate, and transmission service type. Simulation experiments demonstrate that the proposed Q-learning-based routing optimization algorithm outperforms traditional routing algorithms in terms of communication quality.","PeriodicalId":363603,"journal":{"name":"2023 5th International Conference on Electronic Engineering and Informatics (EEI)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Q-Learning Routing Algorithm Based on Software Defined Networking Platform\",\"authors\":\"Pingliang Yuan, Zhengrui Bao, Liandan Wang, Ding Gao, Yutong Wang, Qian Qu, Beilun Li\",\"doi\":\"10.1109/EEI59236.2023.10212950\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper proposes a Q-learning-based routing algorithm for the routing optimization problem in wireless communication networks. The algorithm utilizes an agent to take actions in the transmission environment, change the corresponding state to obtain rewards, and update the Q-matrix. Through iterative steps, the Q-matrix eventually converges. After learning, the optimal routing strategy can be obtained relying on the Q-table. In addition, this paper solves the consensus problem and routing loop problem between nodes using the SDN network architecture. To meet different quality of service requirements, a new reward function is proposed for the Q-learning algorithm, which considers both transmission bandwidth, communication delay, packet loss rate, and transmission service type. Simulation experiments demonstrate that the proposed Q-learning-based routing optimization algorithm outperforms traditional routing algorithms in terms of communication quality.\",\"PeriodicalId\":363603,\"journal\":{\"name\":\"2023 5th International Conference on Electronic Engineering and Informatics (EEI)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 5th International Conference on Electronic Engineering and Informatics (EEI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/EEI59236.2023.10212950\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 5th International Conference on Electronic Engineering and Informatics (EEI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EEI59236.2023.10212950","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Q-Learning Routing Algorithm Based on Software Defined Networking Platform
This paper proposes a Q-learning-based routing algorithm for the routing optimization problem in wireless communication networks. The algorithm utilizes an agent to take actions in the transmission environment, change the corresponding state to obtain rewards, and update the Q-matrix. Through iterative steps, the Q-matrix eventually converges. After learning, the optimal routing strategy can be obtained relying on the Q-table. In addition, this paper solves the consensus problem and routing loop problem between nodes using the SDN network architecture. To meet different quality of service requirements, a new reward function is proposed for the Q-learning algorithm, which considers both transmission bandwidth, communication delay, packet loss rate, and transmission service type. Simulation experiments demonstrate that the proposed Q-learning-based routing optimization algorithm outperforms traditional routing algorithms in terms of communication quality.