DocumentCode :
3532810
Title :
Real-time power control of data centers for providing Regulation Service
Author :
Hao Chen ; Coskun, Ayse K. ; Caramanis, Michael C.
Author_Institution :
Dept. of Electr. & Comput. Eng., Boston Univ., Boston, MA, USA
fYear :
2013
fDate :
10-13 Dec. 2013
Firstpage :
4314
Lastpage :
4321
Abstract :
Data centers account for 3% of the national electricity consumption today. Recent advances in power capping enable data centers to provide Regulation Service (RS) reserves to power markets. RS reserve requirements are expected to increase with the integration of substantial environmentally sustainable, albeit volatile and intermittent, renewable generation. We investigate the ability of server clusters to provide RS reserves while meeting contractual Quality-of-Service (QoS) guarantees for user applications running on the cluster. We propose a dynamic server power regulation policy for processing randomly arriving applications within probabilistic QoS constraints while tracking dynamically broadcasted RS requests by the power market Independent System Operator (ISO). Numerical results demonstrate the ability to select optimal RS reserve and average energy consumption levels that allow data centers to both deliver probabilistic QoS guarantees to customers and track real time ISO RS requests. Finally, we argue that simulated optimal policy performance statistics can enable data centers to bid for energy and to offer RS reserves in the the hour-ahead power markets.
Keywords :
computer centres; power consumption; power control; power markets; probability; quality of service; random processes; real-time systems; QoS guarantees; average energy consumption levels; contractual quality-of-service; data centers; dynamic server power regulation policy; dynamically broadcasted RS request tracking; hour-ahead power markets; national electricity consumption; power capping; power market independent system operator; probabilistic QoS constraints; random arriving processing; real-time ISO RS request tracking; real-time power control; regulation service; renewable generation; server clusters; simulated optimal policy performance statistics; ISO; Power demand; Power markets; Program processors; Quality of service; Real-time systems; Servers;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Decision and Control (CDC), 2013 IEEE 52nd Annual Conference on
Conference_Location :
Firenze
ISSN :
0743-1546
Print_ISBN :
978-1-4673-5714-2
Type :
conf
DOI :
10.1109/CDC.2013.6760553
Filename :
6760553
Link To Document :
بازگشت