DocumentCode :
3426552
Title :
Allocation of Discrete Energy on a Cloud-Computing Datacenter Using a Digital Power Grid
Author :
Yifei Xu ; Rojas-Cessa, Roberto ; Grebel, Haim
Author_Institution :
Electr. & Comput. Eng., New Jersey Inst. of Technol., Newark, NJ, USA
fYear :
2012
fDate :
20-23 Nov. 2012
Firstpage :
615
Lastpage :
618
Abstract :
Electrical power supply of data centers constitutes major operational costs. In this paper, we focus on providing the supplying energy to exact match the consumption demands by using the properties of a digital power grid. Different from the present power grid, where energy is supplied continuously and in amounts to satisfy large demands, the digital power grid supplies energy in the form of packets and upon request. Energy packets are specifically addressed to one, or multiple servers and to no others, and they carry the amount of energy that has been requested. To evaluate the level of energy supply, we model the consumption time of a server as an ON-OFF Markov chain. Through simulation, we show that the digital grid not only reduces the energy safety margins used by current energy providers to assure system stability but it also highly satisfies the energy requests of data center servers when the capacity of the power grid equals the average energy request and without a safety margin.
Keywords :
Markov processes; cloud computing; computer centres; network servers; power aware computing; power consumption; power grids; power supplies to apparatus; resource allocation; On-Off Markov chain; average energy request; cloud-computing data center; consumption demands; digital power grid; discrete energy allocation; energy packets; energy safety margins; energy supply level; multiple servers; server consumption time; system stability; Cloud computing; Conferences; Power grids; Resource management; Servers; Substations; Switches; Carbon Footprint; Cloud computing; Datacenters; Green Cloud; Resource Sharing; Task Scheduling;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Green Computing and Communications (GreenCom), 2012 IEEE International Conference on
Conference_Location :
Besancon
Print_ISBN :
978-1-4673-5146-1
Type :
conf
DOI :
10.1109/GreenCom.2012.94
Filename :
6468374
Link To Document :
بازگشت