GHB: a cost-effective and energy-efficient data center network structure with greater incremental scalability

被引:0
|
作者
Zhou, Peng [1 ]
Lin, Longxin [2 ]
Zhang, Zhen [1 ,3 ]
Deng, Yuhui [1 ]
He, Tengjiao [2 ]
机构
[1] Jinan Univ, Dept Comp Sci, 601 Huangpu Rd West, Guangzhou 510632, Guangdong, Peoples R China
[2] Jinan Univ, Coll Informat Sci & Technol, 601 Huangpu Rd West, Guangzhou 510632, Guangdong, Peoples R China
[3] Natl Joint Engn Res Ctr Network Secur Detect & Pro, Guangzhou 510632, Guangdong, Peoples R China
关键词
Data center network; Interconnection network; Hypercube; Incremental scalability; Multi-port server; ARCHITECTURE;
D O I
10.1007/s10586-022-03849-z
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Designing a cost-effective, energy-efficient and highly scalable network for data centers that can deliver sufficient bandwidth has drawn tremendous attentions recently. The data center networks constructed by using multi-port servers can provide sufficient bandwidth, such as BCube, DCell and GBC3. As the volume of data keeps growing rapidly, more and more servers are continuously added into data centers. In order to reduce the cost and energy consumption, data center networks can be expanded gradually by adding a small number of servers from time to time instead of adding a huge number of servers at a time. This paper proposes a new type of data center network structure called GHB, which is constructed by using commercial switches and multi-port servers. Two types of incomplete GHB structures are also proposed. A small number of servers can be gradually added into the incomplete structures without changing their topological properties. As shown in the experimental results, the throughput of GHB is comparable to that of BCube, and is larger than that of GBC3 and DCell. The analysis results indicate that GHB strikes a good balance among diameter, bisection width, incremental scalability, cost, and energy consumption in contrast to BCube, DCell and GBC3. Compared with the BCube and GBC3, GHB reduces the cost and energy consumption by about 6% and 18%, respectively. The highest throughput of GHB is higher than that of DCell and GBC3 by about 3.4% and 8.35%, respectively.
引用
收藏
页码:91 / 107
页数:17
相关论文
共 50 条
  • [31] An Energy-Efficient Cost-Effective Transient Batch Rectifier with Bottom Flashing: Process Dynamics and Control
    Jana, Amiya K.
    AICHE JOURNAL, 2015, 61 (11) : 3699 - 3707
  • [32] A Cost-effective and Energy-efficient Architecture for Die-stacked DRAM/NVM Memory Systems
    Guo, Yuhua
    Xiao, Weijun
    Liu, Qing
    He, Xubin
    2018 IEEE 37TH INTERNATIONAL PERFORMANCE COMPUTING AND COMMUNICATIONS CONFERENCE (IPCCC), 2018,
  • [33] Cost-effective, Energy-efficient, and Scalable Storage Computing for Large-scale AI Applications
    Do, Jaeyoung
    Ferreira, Victor C.
    Bobarshad, Hossein
    Torabzadehkashi, Mahdi
    Rezaei, Siavash
    Heydarigorji, Ali
    Souza, Diego
    Goldstein, Brunno F.
    Santiago, Leandro
    Kim, Min Soo
    Lima, Priscila M., V
    Franca, Felipe M. G.
    Alves, Vladimir
    ACM TRANSACTIONS ON STORAGE, 2020, 16 (04)
  • [34] Toward cost-effective and energy-efficient heat recovery systems in buildings: Thermal performance monitoring
    Cuce, Pinar Mert
    Cuce, Erdem
    ENERGY, 2017, 137 : 487 - 494
  • [35] An IMS-Based Middleware Solution for Energy-Efficient and Cost-Effective Mobile Multimedia Services
    Bellavista, Paolo
    Corradi, Antonio
    Foschini, Luca
    MOBILE WIRELESS MIDDLEWARE, OPERATING SYSTEMS, AND APPLICATIONS, 2009, 7 : 280 - 294
  • [36] GHDC: a dual-centric data center network architecture by using multi-port servers with greater incremental scalability
    Zhou, Peng
    Lin, Longxin
    He, Tengjiao
    Zhang, Zhen
    JOURNAL OF SUPERCOMPUTING, 2023, 79 (09): : 9932 - 9963
  • [37] GHDC: a dual-centric data center network architecture by using multi-port servers with greater incremental scalability
    Peng Zhou
    Longxin Lin
    Tengjiao He
    Zhen Zhang
    The Journal of Supercomputing, 2023, 79 : 9932 - 9963
  • [38] Towards an energy-efficient Data Center Network based on deep reinforcement learning
    Wang, Yang
    Li, Yutong
    Wang, Ting
    Liu, Gang
    COMPUTER NETWORKS, 2022, 210
  • [39] Towards an energy-efficient Data Center Network based on deep reinforcement learning
    Wang, Yang
    Li, Yutong
    Wang, Ting
    Liu, Gang
    Computer Networks, 2022, 210
  • [40] Joint Host-Network Optimization for Energy-Efficient Data Center Networking
    Jin, Hao
    Cheocherngngarn, Tosmate
    Levy, Dmita
    Smith, Alex
    Pan, Deng
    Liu, Jason
    Pissinou, Niki
    IEEE 27TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS 2013), 2013, : 623 - 634