Reliability Evaluation of DCell Networks

被引:0
|
作者
Wang, Xi [1 ,2 ]
He, Funan [1 ]
Han, Yuejuan [2 ]
You, Lantao [3 ]
机构
[1] Suzhou Inst Ind Technol, Sch Software & Serv Outsourcing, Suzhou 215104, Peoples R China
[2] Soochow Univ, Sch Comp Sci & Technol, Suzhou 215006, Peoples R China
[3] Suzhou Ind Pk Inst Serv Outsourcing, Sch Informat Engn, Suzhou 215000, Peoples R China
来源
基金
中国博士后科学基金; 中国国家自然科学基金;
关键词
DCell network; Reliability; Extra connectivity; Data center network; EXTRACONNECTIVITY; CONNECTIVITY;
D O I
10.1007/978-3-319-73317-3_26
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Recently, the reliability evaluation of data center network (DCN) is important to the design and operation of DCNs. Extra connectivity determination and faulty networks structure analysis are two significant aspects for the reliability evaluation of DCNs. The DCell network is suitable for a massive data centers with high network capacity by only using cheap switches. A k-dimensional DCell built with n-port switches, denoted by D-k,D-n, is an (n + k - 1)-regular graph. In this paper, we firstly prove that the extra-h connectivity of D-k,D-n for n >= 2, kappa(h)(D-k,D-n) = (k - 1)(h + 1) + n if k >= 2 and 0 <= h = n - 1, and kappa(h) (D-k,D-n) = (k - 1)(h + 1) + 2n - 2 if k >= n + 1 and n <= h <= 2n - 1, respectively. What's more, for any faulty node set F subset of V (D-k,D-n) with vertical bar F vertical bar <= kappa(h)(D-k,D-n) - 1, we obtain that there contains a large connected component in D-k,D-n - F, and the rest of small connected components have not more than h nodes in total if k >= 2 and 0 <= h <= n - 1 (resp. k >= n + 1 and n <= h <= 2n - 1). Our result can provide a proper measure for the reliability evaluation of the DCell network when it is used to model the topological structure of a large-scale DCN.
引用
收藏
页码:213 / 225
页数:13
相关论文
共 50 条
  • [41] Disjointing Technique for Reliability Evaluation of Computer Communication Networks
    Kaushik, Kriti
    Pahuja, G. L.
    PROCEEDINGS OF THE 4TH INTERNATIONAL CONFERENCE ON ECO-FRIENDLY COMPUTING AND COMMUNICATION SYSTEMS, 2015, 70 : 205 - 211
  • [42] Reliability evaluation of a multicast over coded packet networks
    Raayatpanah, M. A.
    Pardalos, P. M.
    JOURNAL OF COMBINATORIAL OPTIMIZATION, 2018, 35 (03) : 921 - 940
  • [43] Evaluation and improvement of supply reliability indices for distribution networks
    Rosendo, Jose A.
    Gomez-Exposito, Antonio
    Tevar, Gabriel
    Rodriguez, Manuel
    2008 IEEE/PES TRANSMISSION & DISTRIBUTION CONFERENCE & EXPOSITION, VOLS 1-3, 2008, : 175 - +
  • [44] Power systems reliability evaluation using neural networks
    Schilling, MT
    Souza, JCS
    da Silva, APA
    Do Coutto, MB
    ENGINEERING INTELLIGENT SYSTEMS FOR ELECTRICAL ENGINEERING AND COMMUNICATIONS, 2001, 9 (04): : 219 - 226
  • [45] Evaluation of Network Reliability for Computer Networks with Multiple Sources
    Lin, Yi-Kuei
    Yeng, Louis Cheng-Lu
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2012, 2012
  • [46] Interruption flows for reliability evaluation of power distribution networks
    Fábio Luiz Usberti
    Celso Cavellucci
    Christiano Lyra
    Operational Research, 2023, 23
  • [47] Reliability evaluation for distributed computing networks with imperfect nodes
    Ke, WJ
    Wang, SD
    IEEE TRANSACTIONS ON RELIABILITY, 1997, 46 (03) : 342 - 349
  • [48] Interruption flows for reliability evaluation of power distribution networks
    Usberti, Fabio Luiz
    Cavellucci, Celso
    Lyra, Christiano
    OPERATIONAL RESEARCH, 2023, 23 (01)
  • [49] A New Algorithm for Reliability Evaluation of Radial Distribution Networks
    Sepehry, Mojtaba
    Heidari-Kapourchali, Mohammad
    Banajiger, Avinash
    Aravinthan, Visvakumar
    2014 NORTH AMERICAN POWER SYMPOSIUM (NAPS), 2014,
  • [50] Reliability evaluation of a multicast over coded packet networks
    M. A. Raayatpanah
    P. M. Pardalos
    Journal of Combinatorial Optimization, 2018, 35 : 921 - 940