摘要
减少网络能耗和建立绿色网络已经成为学术界和工业界研究的关键科学问题。已有的节能方案均在已知流量矩阵的前提下展开研究,但是获得实时流量数据并不容易。因此,文中研究了如何在未知流量矩阵的情况下降低网络能耗,提出了一种基于网络熵的域内节能路由方案(Intra-domain Energy Efficiency Routing Scheme Based on Network Entropy,EERSBNE),该方案通过关闭网络中的链路来实现节能的效果。首先提出了链路关键度模型和网络熵模型,然后根据链路关键度计算网络中所有链路的重要程度,最后根据链路的重要性和网络熵模型依次关闭网络中的链路。实验结果表明,该算法在降低网络能耗的同时不会引入较大的路径拉伸度。
The reduction of network energy consumption and the building of green network have become key scientific problems in academic and industrial research.All the existing energy efficiency schemes carry out researches on the premise of knowing the traffic matrix,but it's not easy to get real-time traffic data.Therefore,this paper studied how to reduce the network energy consumption without knowing real-time traffic matrix,and presented an intra-domain energy efficiency routing scheme based on network entropy.This scheme achieves energy efficiency by turning off the links in network.Firstly,the link criticality model and the network entropy model are proposed.Then,the importance of all links in the network is calculated according to the link criticality.Finally,the links in the network are turned off in turn according to the importance of link and the network entropy model.The experimental results show that the proposed algorithm does not introduce larger path stretch when reducing the energy consumption of network.
引文
[1] GUPTA M,SINGH S.Greening of the internet[C]∥Proceedings of ACM Special Interest Group on Data Communication.Karlsruhe,Germany:ACM Press,2003:19-26.
[2] XU M,SHANG Y,LI D,et al.Greening data center networks with throughput-guaranteed power-aware routing[J].Computer Networks,2013,57(15):2880-2899.
[3] YANG Y,WANG D,PAN D,et al.Wind blows,traffic flows:Green Internet routing under renewable energy[C]∥Proceedings of IEEE International Conference on Computer Communications.San Francisco,CA:IEEE Press,2016:1-9.
[4] MINERAUD J,WANG L,BALASUBRAMANIAM S,et al.Hybrid renewable energy routing for ISP networks[C]∥Proceedings of IEEE International Conference on Computer Communications.San Francisco,CA:IEEE Press,2016:1-9.
[5] ZHANG G Q,XU Z Q,LIU Z.Research on Green Network Theory and Technology[J].Journal of Software,2016,27(3):736-759.(in Chinese)张国强,许自取,刘真.绿色网络理论与技术研究[J].软件学报,2016,27(3):736-759.
[6] BOLLA R,BRUSCHI R,CIANFRANI A,et al.Enabling backbone networks to sleep[J].IEEE Network,2011,25(2):26-31.
[7] CHABAREK J,SOMMERS J,BARFORD P,et al.Power Awareness in Network Design and Routing[C]∥Proceedings of IEEE International Conference on Computer Communications.Honolulu,USA:IEEE Press,2008:457-465.
[8] CHIARAVIGLIO L,CIULLO D,MELLIA M,et al.Modeling sleep mode gains in energy-aware networks[J].Computer Networks,2013,57(15):3051-3066.
[9] ANDREWS M,ANTA A F,ZHANG L,et al.Routing for Energy Minimization in the Speed Scaling Model[C]∥Conference on Information Communications.IEEE Press,2010:2435-2443.
[10]CHIARAVIGLIO L,MELLIA M,NERI F.Minimizing ISP Network Energy Cost:Formulation and Solutions[J].IEEE/ACM Transactions on Networking,2012,20(2):463-476.
[11]YANG Y,XU M,WANG D,et al.A Hop-by-hop Routing Mechanism for Green Internet[J].IEEE Transactions on Parallel&Distributed Systems,2015,27(1):2-16.
[12]CHIARAVIGLIO L,CIANFRANI A,ROUZIC E L,et al.Sleep modes effectiveness in backbone networks with limited configurations[J].Computer Networks the International Journal of Computer&Telecommunications Networking,2013,57(15):2931-2948.
[13]ZHANG M,YI C,LIU B,et al.GreenTE:Power-aware traffic engineering[C]∥Proceedings of IEEE International Conference on Network Protocols.Kyoto,Japan:IEEE Press,2010:21-30.
[14]WU L S.Research on the Network Reliability Based on Network Entropy[D].Nanjing:Nanjing University of Aeronautics and Astronautics,2014.(in Chinese)吴六三.基于网络熵的网络可靠性研究[D].南京:南京航空航天大学,2014.
[15]KREUTZ D,RAMOS F M V,ESTEVES V P,et al.SoftwareDefined Networking:A Comprehensive Survey[J].Proceedings of the IEEE,2015,103(1):14-76.