{"title":"Evaluating the controller capacity in software defined networking","authors":"Long Yao, P. Hong, Wei Zhou","doi":"10.1109/ICCCN.2014.6911857","DOIUrl":null,"url":null,"abstract":"The flow-based OpenFlow architecture decouples the control plane and data plane, and it has involved great evolution towards traditional networks. A particular important issue in OpenFlow architecture is controller capacity, which can be defined as the number of switches a controller can manage. In this paper, we model the flow set-up requests from switches to controller as a batch arrival process Mk/M /1. Further, we analyze the controller performance with queuing theory, and derive the expression of average flow service time. Under the circumstance of a limited flow set-up time, the number of switches is determined, this provides a method to evaluate the controller capacity. Moreover, we extend the scene of a single controller to multiple controllers. All of these results are meaningful to large scale OpenFlow network deployment in the future.","PeriodicalId":404048,"journal":{"name":"2014 23rd International Conference on Computer Communication and Networks (ICCCN)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"34","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 23rd International Conference on Computer Communication and Networks (ICCCN)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCCN.2014.6911857","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 34
Abstract
The flow-based OpenFlow architecture decouples the control plane and data plane, and it has involved great evolution towards traditional networks. A particular important issue in OpenFlow architecture is controller capacity, which can be defined as the number of switches a controller can manage. In this paper, we model the flow set-up requests from switches to controller as a batch arrival process Mk/M /1. Further, we analyze the controller performance with queuing theory, and derive the expression of average flow service time. Under the circumstance of a limited flow set-up time, the number of switches is determined, this provides a method to evaluate the controller capacity. Moreover, we extend the scene of a single controller to multiple controllers. All of these results are meaningful to large scale OpenFlow network deployment in the future.