R.A. Resende, S. Rossi, A. Yamakami, L. H. Bonani, E. Moschim
{"title":"Traffic engineering with MPLS using fuzzy logic for application in IP networks","authors":"R.A. Resende, S. Rossi, A. Yamakami, L. H. Bonani, E. Moschim","doi":"10.1109/FUZZ.2003.1206593","DOIUrl":null,"url":null,"abstract":"One of the great challenges nowadays when managing IP networks is to guarantee proper Quality of Service, using network infrastructure on optimized way. One of the proposed solutions is traffic engineering with MPLS. However, the characterization of the demands and of the network state are difficult tasks, considering that the demands and the data traffic are random, consequently, the network state changes dynamically and in a random way. In this work we propose a connection admission controller that uses fuzzy logic based on linguistic rules to treat the inaccurate information in IP over MPLS networks with the purpose of offering Quality of Service to the users. In accordance with the simulation results, we concluded that the use of fuzzy logic allows a large flexibility in the connection admission process and the possibility to include more network and traffic information when making a decision without increasing considerably the controller complexity.","PeriodicalId":212172,"journal":{"name":"The 12th IEEE International Conference on Fuzzy Systems, 2003. FUZZ '03.","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2003-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"The 12th IEEE International Conference on Fuzzy Systems, 2003. FUZZ '03.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/FUZZ.2003.1206593","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
One of the great challenges nowadays when managing IP networks is to guarantee proper Quality of Service, using network infrastructure on optimized way. One of the proposed solutions is traffic engineering with MPLS. However, the characterization of the demands and of the network state are difficult tasks, considering that the demands and the data traffic are random, consequently, the network state changes dynamically and in a random way. In this work we propose a connection admission controller that uses fuzzy logic based on linguistic rules to treat the inaccurate information in IP over MPLS networks with the purpose of offering Quality of Service to the users. In accordance with the simulation results, we concluded that the use of fuzzy logic allows a large flexibility in the connection admission process and the possibility to include more network and traffic information when making a decision without increasing considerably the controller complexity.
当前IP网络管理面临的一大挑战是如何保证适当的服务质量,优化利用网络基础设施。提出的解决方案之一是利用MPLS进行流量工程。然而,由于需求和数据流量是随机的,因此网络状态是动态随机变化的,因此需求和网络状态的表征是一项艰巨的任务。在这项工作中,我们提出了一种使用基于语言规则的模糊逻辑来处理IP over MPLS网络中的不准确信息的连接允许控制器,目的是为用户提供服务质量。根据仿真结果,我们得出结论,使用模糊逻辑可以在连接接纳过程中具有很大的灵活性,并且在做出决策时可以包含更多的网络和流量信息,而不会大大增加控制器的复杂性。