{"title":"Low Control Latency SD-WANs for Metaverse","authors":"Liang Qi, Songshi Dou, Zehua Guo, Changlin Li, Yang Li, Tengteng Zhu","doi":"10.1109/ICDCSW56584.2022.00057","DOIUrl":null,"url":null,"abstract":"Metaverse is a shared virtual environment to provide users with an immersive experience and the same feeling as reality. In Software-Defined Wide Area Networks (SD-WANs), the controller dynamically routes flows from metaverse applications to maintain good performance by sending control messages to underlying switches. Thus, the control latency between controllers and switches for rerouting flows is one critical factor for metaverse's performance. However, existing works may introduce high control latency between switches and controllers since they do not consider the dynamic state of each switch in the real world situation. In this paper, we propose to optimize the control latency in SD-WANs by solving a critical programmability-aware problem. Inspired by critical flows, which have a critical impact on network performance, our proposed solution considers the programmability of critical flows at switches to decide the placement of controllers and mapping between switches and controllers. Simulation results show that our work can reduce the control latency by up to 27.5% compared with the baseline algorithms.","PeriodicalId":357138,"journal":{"name":"2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops (ICDCSW)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops (ICDCSW)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICDCSW56584.2022.00057","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
Metaverse is a shared virtual environment to provide users with an immersive experience and the same feeling as reality. In Software-Defined Wide Area Networks (SD-WANs), the controller dynamically routes flows from metaverse applications to maintain good performance by sending control messages to underlying switches. Thus, the control latency between controllers and switches for rerouting flows is one critical factor for metaverse's performance. However, existing works may introduce high control latency between switches and controllers since they do not consider the dynamic state of each switch in the real world situation. In this paper, we propose to optimize the control latency in SD-WANs by solving a critical programmability-aware problem. Inspired by critical flows, which have a critical impact on network performance, our proposed solution considers the programmability of critical flows at switches to decide the placement of controllers and mapping between switches and controllers. Simulation results show that our work can reduce the control latency by up to 27.5% compared with the baseline algorithms.