Saquib Amjad, Amir Varasteh, N. Deric, C. M. Machuca
{"title":"虚拟化SDN中延迟感知动态管理程序的放置和重新配置","authors":"Saquib Amjad, Amir Varasteh, N. Deric, C. M. Machuca","doi":"10.1109/NoF52522.2021.9609929","DOIUrl":null,"url":null,"abstract":"Software defined networking (SDN) provides different functionality and resource sharing capabilities with the aid of virtualization. In virtualized SDN, multiple SDN tenants can bring their controllers and different functions in the same physical substrate. The SDN hypervisor provides the link between the physical network substrate and its SDN tenants. Distributed hypervisor architecture can handle scalability, virtualization, and reassignment better than a centralized hypervisor architecture. However, distributed hypervisors may require synchronization and load balancing. Due to the dynamic control plane traffic, some network elements may suffer from increase in delay. Controller placement problem (CPP) and hypervisor placement problem (HPP) have tackled the static placement and mapping strategies.In this paper, we design a dynamic hypervisor assignment and reconfiguration with load balancing using integer linear programming. The proposed model focuses on optimizing multiple objectives: control plane latency, processing latency, and load balancing for distributed hypervisors. We provide different heuristics for the model and then perform evaluation on two topologies- Abilene and EU-nobel. The results show the trade off between load balancing and minimizing latency, and comparison of the performance of heuristics and MILP model.","PeriodicalId":314720,"journal":{"name":"2021 12th International Conference on Network of the Future (NoF)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Delay-Aware Dynamic Hypervisor Placement and Reconfiguration in Virtualized SDN\",\"authors\":\"Saquib Amjad, Amir Varasteh, N. Deric, C. M. Machuca\",\"doi\":\"10.1109/NoF52522.2021.9609929\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Software defined networking (SDN) provides different functionality and resource sharing capabilities with the aid of virtualization. In virtualized SDN, multiple SDN tenants can bring their controllers and different functions in the same physical substrate. The SDN hypervisor provides the link between the physical network substrate and its SDN tenants. Distributed hypervisor architecture can handle scalability, virtualization, and reassignment better than a centralized hypervisor architecture. However, distributed hypervisors may require synchronization and load balancing. Due to the dynamic control plane traffic, some network elements may suffer from increase in delay. Controller placement problem (CPP) and hypervisor placement problem (HPP) have tackled the static placement and mapping strategies.In this paper, we design a dynamic hypervisor assignment and reconfiguration with load balancing using integer linear programming. The proposed model focuses on optimizing multiple objectives: control plane latency, processing latency, and load balancing for distributed hypervisors. We provide different heuristics for the model and then perform evaluation on two topologies- Abilene and EU-nobel. The results show the trade off between load balancing and minimizing latency, and comparison of the performance of heuristics and MILP model.\",\"PeriodicalId\":314720,\"journal\":{\"name\":\"2021 12th International Conference on Network of the Future (NoF)\",\"volume\":\"18 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-10-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 12th International Conference on Network of the Future (NoF)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/NoF52522.2021.9609929\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 12th International Conference on Network of the Future (NoF)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NoF52522.2021.9609929","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Delay-Aware Dynamic Hypervisor Placement and Reconfiguration in Virtualized SDN
Software defined networking (SDN) provides different functionality and resource sharing capabilities with the aid of virtualization. In virtualized SDN, multiple SDN tenants can bring their controllers and different functions in the same physical substrate. The SDN hypervisor provides the link between the physical network substrate and its SDN tenants. Distributed hypervisor architecture can handle scalability, virtualization, and reassignment better than a centralized hypervisor architecture. However, distributed hypervisors may require synchronization and load balancing. Due to the dynamic control plane traffic, some network elements may suffer from increase in delay. Controller placement problem (CPP) and hypervisor placement problem (HPP) have tackled the static placement and mapping strategies.In this paper, we design a dynamic hypervisor assignment and reconfiguration with load balancing using integer linear programming. The proposed model focuses on optimizing multiple objectives: control plane latency, processing latency, and load balancing for distributed hypervisors. We provide different heuristics for the model and then perform evaluation on two topologies- Abilene and EU-nobel. The results show the trade off between load balancing and minimizing latency, and comparison of the performance of heuristics and MILP model.