ExCCC-DCN: A Highly Scalable, Cost-Effective and Energy-Efficient Data Center Structure

Over the past decade, many data centers have been constructed around the world due to the explosive growth of data volume and type. The cost and energy consumption have become the most important challenges of building those data centers. Data centers today use commodity computers and switches instead of high-end servers and interconnections for cost-effectiveness. In this paper, we propose a new type of interconnection networks called <italic>Exchanged Cube-Connected Cycles (ExCCC)</italic>. The <italic>ExCCC</italic> network is an extension of <italic>Exchanged Hypercube (EH)</italic> network by replacing each node with a cycle. The <italic>EH</italic> network is based on link removal from a <italic>Hypercube</italic> network, which makes the <italic>EH</italic> network more cost-effective as it scales up. After analyzing the topological properties of <italic>ExCCC</italic>, we employ commodity switches to construct a new class of data center network models, namely <italic>ExCCC-DCN</italic>, by leveraging the advantages of the <italic>ExCCC</italic> architecture. The analysis and experimental results demonstrate that the proposed <italic>ExCCC-DCN</italic> models significantly outperform four state-of-the-art data center network models in terms of the total cost, power consumption, scalability, and other static characteristics. It achieves the goals of low cost, low energy consumption, high network throughput, and high scalability simultaneously.

[1]  Haitao Wu,et al.  BCube: a high performance, server-centric network architecture for modular data centers , 2009, SIGCOMM '09.

[2]  Yan Zhang,et al.  On Architecture Design, Congestion Notification, TCP Incast and Power Consumption in Data Centers , 2013, IEEE Communications Surveys & Tutorials.

[3]  Dharma P. Agrawal,et al.  Generalized Hypercube and Hyperbus Structures for a Computer Network , 1984, IEEE Transactions on Computers.

[4]  Baochun Li,et al.  Temperature Aware Workload Managementin Geo-Distributed Data Centers , 2013, IEEE Transactions on Parallel and Distributed Systems.

[5]  Kaishun Wu,et al.  Rethinking the architecture design of data center networks , 2012, Frontiers of Computer Science.

[6]  P. S. Nagendra Rao,et al.  Properties and performance of folded cube-connected cycles , 1998, J. Syst. Archit..

[7]  GhemawatSanjay,et al.  The Google file system , 2003 .

[8]  Magdy A. Bayoumi,et al.  The Extended Cube Connected Cycles: An Efficient Interconnection for Massively Parallel Systems , 1996, IEEE Trans. Computers.

[9]  Albert G. Greenberg,et al.  The cost of a cloud: research problems in data center networks , 2008, CCRV.

[10]  Yuhui Deng,et al.  mtCloudSim: A Flow-Level Network Simulator for Multi-Tenant Cloud , 2016, 2016 IEEE 22nd International Conference on Parallel and Distributed Systems (ICPADS).

[11]  Albert G. Greenberg,et al.  Data center TCP (DCTCP) , 2010, SIGCOMM '10.

[12]  Lei Shi,et al.  Dcell: a scalable and fault-tolerant network structure for data centers , 2008, SIGCOMM '08.

[13]  David A. Maltz,et al.  Network traffic characteristics of data centers in the wild , 2010, IMC '10.

[14]  Bohn Stafleu van Loghum,et al.  Online … , 2002, LOG IN.

[15]  Tao Jiang,et al.  Energy Cost Minimization for Distributed Internet Data Centers in Smart Microgrids Considering Power Outages , 2015, IEEE Transactions on Parallel and Distributed Systems.

[16]  Amin Vahdat,et al.  Hedera: Dynamic Flow Scheduling for Data Center Networks , 2010, NSDI.

[17]  Amin Vahdat,et al.  A scalable, commodity data center network architecture , 2008, SIGCOMM '08.

[18]  Yi Pan,et al.  The exchanged hypercube , 2005, IEEE Transactions on Parallel and Distributed Systems.

[19]  Kemal Efe,et al.  The Crossed Cube Architecture for Parallel Computation , 1992, IEEE Trans. Parallel Distributed Syst..

[20]  Lionel M. Ni,et al.  The Twisted N-Cube with Application to Multiprocessing , 1991, IEEE Trans. Computers.

[21]  Muthu Dayalan,et al.  MapReduce : Simplified Data Processing on Large Cluster , 2018 .

[22]  Haitao Wu,et al.  FiConn: Using Backup Port for Server Interconnection in Data Centers , 2009, IEEE INFOCOM 2009.

[23]  Franco P. Preparata,et al.  The cube-connected-cycles: A versatile network for parallel computation , 1979, 20th Annual Symposium on Foundations of Computer Science (sfcs 1979).

[24]  Yuan Yu,et al.  Dryad: distributed data-parallel programs from sequential building blocks , 2007, EuroSys '07.

[25]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[26]  Shahram Latifi,et al.  Properties and Performance of Folded Hypercubes , 1991, IEEE Trans. Parallel Distributed Syst..

[27]  Hong Liu,et al.  Jupiter Rising: A Decade of Clos Topologies and Centralized Control in Google's Datacenter Network , 2015, Comput. Commun. Rev..

[28]  Anthony A. Maciejewski,et al.  Power and Thermal-Aware Workload Allocation in Heterogeneous Data Centers , 2015, IEEE Transactions on Computers.

[29]  Ivan Fris,et al.  The Diameter of the Cube-Connected Cycles , 1997, Inf. Process. Lett..