J. Galán-Jiménez, Marco Polverini, F. Lavacca, Juan Luis Herrera, J. Berrocal
{"title":"混合IP/SDN网络中负载平衡与能源效率的权衡","authors":"J. Galán-Jiménez, Marco Polverini, F. Lavacca, Juan Luis Herrera, J. Berrocal","doi":"10.1109/NoF52522.2021.9609876","DOIUrl":null,"url":null,"abstract":"The flexibility and programmability provided by the Software-Defined Networking (SDN) paradigm allow network operators to upgrade their legacy IP network infrastructures with the aim of improving their control over the network. However, the full migration from IP to SDN is not straightforward, at least, in the short term. Thus, transitory network infrastructures combining IP and SDN nodes (named hybrid IP/SDN networks) are required to coexist, while the correct coordination between paradigms is crucial to maintain the required Quality of Service. In this paper, two optimization problems that are normally solved separately due to their opposite nature: i) traffic load balancing and ii) the reduction of network power consumption, are jointly considered. In particular, an heuristic named Hybrid Spreading Load Algorithm (HSLA), is proposed to jointly minimize the Maximum Link Utilization (MLU) and the network power consumption during the transition from IP to SDN networks. Simulations over topologies of different size considering diverse selection methods for the replacement of the nodes reveal that HSLA outperforms other state-of-the-art approaches that specifically tackle only one objective, either the traffic load balancing or the reduction of the network power consumption.","PeriodicalId":314720,"journal":{"name":"2021 12th International Conference on Network of the Future (NoF)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"On the tradeoff between load balancing and energy-efficiency in hybrid IP/SDN networks\",\"authors\":\"J. Galán-Jiménez, Marco Polverini, F. Lavacca, Juan Luis Herrera, J. Berrocal\",\"doi\":\"10.1109/NoF52522.2021.9609876\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The flexibility and programmability provided by the Software-Defined Networking (SDN) paradigm allow network operators to upgrade their legacy IP network infrastructures with the aim of improving their control over the network. However, the full migration from IP to SDN is not straightforward, at least, in the short term. Thus, transitory network infrastructures combining IP and SDN nodes (named hybrid IP/SDN networks) are required to coexist, while the correct coordination between paradigms is crucial to maintain the required Quality of Service. In this paper, two optimization problems that are normally solved separately due to their opposite nature: i) traffic load balancing and ii) the reduction of network power consumption, are jointly considered. In particular, an heuristic named Hybrid Spreading Load Algorithm (HSLA), is proposed to jointly minimize the Maximum Link Utilization (MLU) and the network power consumption during the transition from IP to SDN networks. Simulations over topologies of different size considering diverse selection methods for the replacement of the nodes reveal that HSLA outperforms other state-of-the-art approaches that specifically tackle only one objective, either the traffic load balancing or the reduction of the network power consumption.\",\"PeriodicalId\":314720,\"journal\":{\"name\":\"2021 12th International Conference on Network of the Future (NoF)\",\"volume\":\"44 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/NoF52522.2021.9609876\",\"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/NoF52522.2021.9609876","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
摘要
软件定义网络(SDN)范例提供的灵活性和可编程性允许网络运营商升级其传统IP网络基础设施,以改善其对网络的控制。然而,从IP到SDN的完全迁移并不简单,至少在短期内是这样。因此,需要IP和SDN节点组合的临时网络基础设施(称为混合IP/SDN网络)共存,而范式之间的正确协调对于维持所需的服务质量至关重要。本文将流量负载均衡和网络功耗降低这两个通常因性质相反而单独解决的优化问题联合考虑。特别提出了一种启发式混合扩展负载算法(Hybrid Spreading Load Algorithm, HSLA),在IP网络向SDN网络过渡的过程中,共同最小化最大链路利用率(Maximum Link Utilization, MLU)和网络功耗。考虑到节点替换的不同选择方法,对不同大小拓扑的模拟表明,HSLA优于其他专门解决一个目标的最先进的方法,即流量负载平衡或降低网络功耗。
On the tradeoff between load balancing and energy-efficiency in hybrid IP/SDN networks
The flexibility and programmability provided by the Software-Defined Networking (SDN) paradigm allow network operators to upgrade their legacy IP network infrastructures with the aim of improving their control over the network. However, the full migration from IP to SDN is not straightforward, at least, in the short term. Thus, transitory network infrastructures combining IP and SDN nodes (named hybrid IP/SDN networks) are required to coexist, while the correct coordination between paradigms is crucial to maintain the required Quality of Service. In this paper, two optimization problems that are normally solved separately due to their opposite nature: i) traffic load balancing and ii) the reduction of network power consumption, are jointly considered. In particular, an heuristic named Hybrid Spreading Load Algorithm (HSLA), is proposed to jointly minimize the Maximum Link Utilization (MLU) and the network power consumption during the transition from IP to SDN networks. Simulations over topologies of different size considering diverse selection methods for the replacement of the nodes reveal that HSLA outperforms other state-of-the-art approaches that specifically tackle only one objective, either the traffic load balancing or the reduction of the network power consumption.