Enabling Demand Response in a computer cluster

Demand Response(DR) is a method for stimulating end-users to adjust consumption to support the change in the electricity market. DR can be used to improve the stability of power supply including the power generation, transmission and distribution. It can also be used to improve electricity market operation. Furthermore, significant cost savings can be made on the consumer side via the financial incentives in a range of DR programs. As the cloud computing paradigm gains popularity, there is an associated rapid growth of public and private data centers. Data center energy consumption increases significantly. Putting data center energy consumption in the context of power grid becomes important. In this paper, we propose an architecture to integrate data centre computer clusters with a DR service. The resource manager of a cluster can therefore take DR events into account when allocating resources. We particularly focus on resource provisioning for parallel workloads in such a cluster, and propose a DR strategy that is capable of balancing energy savings and user satisfaction.

[1]  Edward D. Lazowska,et al.  Speedup Versus Efficiency in Parallel Systems , 1989, IEEE Trans. Computers.

[2]  Guofei Jiang,et al.  Effective VM sizing in virtualized data centers , 2011, 12th IFIP/IEEE International Symposium on Integrated Network Management (IM 2011) and Workshops.

[3]  Thu D. Nguyen,et al.  Cost-and Energy-Aware Load Distribution Across Data Centers , 2009 .

[4]  Yefu Wang,et al.  GreenWare: Greening Cloud-Scale Data Centers to Maximize the Use of Renewable Energy , 2011, Middleware.

[5]  Thomas F. Wenisch,et al.  PowerNap: eliminating server idle power , 2009, ASPLOS.

[6]  David G. Andersen,et al.  Energy-efficient cluster computing with FAWN: workloads and implications , 2010, e-Energy.

[7]  Lachlan L. H. Andrew,et al.  Greening geographical load balancing , 2011, PERV.

[8]  Amar Phanishayee,et al.  FAWN: a fast array of wimpy nodes , 2009, SOSP '09.

[9]  Randy H. Katz,et al.  NapSAC: design and implementation of a power-proportional web cluster , 2010, CCRV.

[10]  Alexandru Iosup,et al.  Scheduling Strategies for Cycle Scavenging in Multicluster Grid Systems , 2009, 2009 9th IEEE/ACM International Symposium on Cluster Computing and the Grid.

[11]  Luiz André Barroso,et al.  The Case for Energy-Proportional Computing , 2007, Computer.

[12]  Sila Kiliccote,et al.  Open Automated Demand Response Communications Specification (Version 1.0) , 2009 .

[13]  Chen Wang,et al.  Demand Response aware cluster resource provisioning for parallel applications , 2012, 2012 IEEE Third International Conference on Smart Grid Communications (SmartGridComm).

[14]  David A. Lifka,et al.  The ANL/IBM SP Scheduling System , 1995, JSSPP.

[15]  Sujata Banerjee,et al.  ElasticTree: Saving Energy in Data Center Networks , 2010, NSDI.

[16]  Dan Tsafrir,et al.  A Short Survey of Commercial Cluster Batch Schedulers , 2005 .

[17]  Alex Delis,et al.  Flexible use of cloud resources through profit maximization and price discrimination , 2011, 2011 IEEE 27th International Conference on Data Engineering.

[18]  Anand Sivasubramaniam,et al.  Optimal power cost management using stored energy in data centers , 2011, PERV.

[19]  Bruce M. Maggs,et al.  Cutting the electric bill for internet-scale systems , 2009, SIGCOMM '09.

[20]  Amin Vahdat,et al.  Managing energy and server resources in hosting centers , 2001, SOSP.