Optimal Peak Shaving Using Batteries at Datacenters: Characterizing the Risks and Benefits

Neda Nasiriani, George Kesidis, Di Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

A datacenter's power consumption is a major contributor to its operational expenditures (op-ex) and one-time capital expenditures (cap-ex). The recurring electricity cost is often in large determined by datacenter peak-demand under peak-based pricing which is employed by major electric utility providers. There is a growing interest in reducing a datacenter's electricity costs by using throttling techniques and/or energy storage devices (batteries) which are readily available at most datacenters as a backup energy source. A datacenter's power-demand uncertainty makes this a challenging problem, which is largely neglected in existing work, by assuming perfect predictability of power demand. We model this inherent uncertainty as a Markov chain and also evaluate the risk of over/under charging batteries as a result of the randomness in power demand. We design an online optimization framework for peak shaving which considers Conditional Value at Risk and allows for navigating cost-risk trade-offs of datacenters based on their energy infrastructure and workload characteristics. We show that this framework offers significantly higher (up to 2X) cost-savings with small risks of over/under charging batteries, compared to existing stochastic optimization techniques. This framework leverages Markov Decision Processes to perform online dynamic peak shaving, considering battery degradation costs under peak-based pricing.

Original languageEnglish (US)
Title of host publicationProceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages164-174
Number of pages11
ISBN (Electronic)9781538627631
DOIs
StatePublished - Nov 13 2017
Event25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017 - Banff, Canada
Duration: Sep 20 2017Sep 22 2017

Publication series

NameProceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017

Other

Other25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017
CountryCanada
CityBanff
Period9/20/179/22/17

Fingerprint

Battery
Costs
Electricity
Charging (batteries)
Pricing
Online Optimization
Demand Uncertainty
Conditional Value at Risk
Energy Storage
Stochastic Optimization
Markov Decision Process
Predictability
Energy
Leverage
Randomness
Optimization Techniques
Power Consumption
Workload
Markov chain
Degradation

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Hardware and Architecture
  • Modeling and Simulation

Cite this

Nasiriani, N., Kesidis, G., & Wang, D. (2017). Optimal Peak Shaving Using Batteries at Datacenters: Characterizing the Risks and Benefits. In Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017 (pp. 164-174). [8107443] (Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MASCOTS.2017.27
Nasiriani, Neda ; Kesidis, George ; Wang, Di. / Optimal Peak Shaving Using Batteries at Datacenters : Characterizing the Risks and Benefits. Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 164-174 (Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017).
@inproceedings{8e38592be7224317a3405a359ba3b2df,
title = "Optimal Peak Shaving Using Batteries at Datacenters: Characterizing the Risks and Benefits",
abstract = "A datacenter's power consumption is a major contributor to its operational expenditures (op-ex) and one-time capital expenditures (cap-ex). The recurring electricity cost is often in large determined by datacenter peak-demand under peak-based pricing which is employed by major electric utility providers. There is a growing interest in reducing a datacenter's electricity costs by using throttling techniques and/or energy storage devices (batteries) which are readily available at most datacenters as a backup energy source. A datacenter's power-demand uncertainty makes this a challenging problem, which is largely neglected in existing work, by assuming perfect predictability of power demand. We model this inherent uncertainty as a Markov chain and also evaluate the risk of over/under charging batteries as a result of the randomness in power demand. We design an online optimization framework for peak shaving which considers Conditional Value at Risk and allows for navigating cost-risk trade-offs of datacenters based on their energy infrastructure and workload characteristics. We show that this framework offers significantly higher (up to 2X) cost-savings with small risks of over/under charging batteries, compared to existing stochastic optimization techniques. This framework leverages Markov Decision Processes to perform online dynamic peak shaving, considering battery degradation costs under peak-based pricing.",
author = "Neda Nasiriani and George Kesidis and Di Wang",
year = "2017",
month = "11",
day = "13",
doi = "10.1109/MASCOTS.2017.27",
language = "English (US)",
series = "Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "164--174",
booktitle = "Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017",
address = "United States",

}

Nasiriani, N, Kesidis, G & Wang, D 2017, Optimal Peak Shaving Using Batteries at Datacenters: Characterizing the Risks and Benefits. in Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017., 8107443, Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017, Institute of Electrical and Electronics Engineers Inc., pp. 164-174, 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017, Banff, Canada, 9/20/17. https://doi.org/10.1109/MASCOTS.2017.27

Optimal Peak Shaving Using Batteries at Datacenters : Characterizing the Risks and Benefits. / Nasiriani, Neda; Kesidis, George; Wang, Di.

Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 164-174 8107443 (Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Optimal Peak Shaving Using Batteries at Datacenters

T2 - Characterizing the Risks and Benefits

AU - Nasiriani, Neda

AU - Kesidis, George

AU - Wang, Di

PY - 2017/11/13

Y1 - 2017/11/13

N2 - A datacenter's power consumption is a major contributor to its operational expenditures (op-ex) and one-time capital expenditures (cap-ex). The recurring electricity cost is often in large determined by datacenter peak-demand under peak-based pricing which is employed by major electric utility providers. There is a growing interest in reducing a datacenter's electricity costs by using throttling techniques and/or energy storage devices (batteries) which are readily available at most datacenters as a backup energy source. A datacenter's power-demand uncertainty makes this a challenging problem, which is largely neglected in existing work, by assuming perfect predictability of power demand. We model this inherent uncertainty as a Markov chain and also evaluate the risk of over/under charging batteries as a result of the randomness in power demand. We design an online optimization framework for peak shaving which considers Conditional Value at Risk and allows for navigating cost-risk trade-offs of datacenters based on their energy infrastructure and workload characteristics. We show that this framework offers significantly higher (up to 2X) cost-savings with small risks of over/under charging batteries, compared to existing stochastic optimization techniques. This framework leverages Markov Decision Processes to perform online dynamic peak shaving, considering battery degradation costs under peak-based pricing.

AB - A datacenter's power consumption is a major contributor to its operational expenditures (op-ex) and one-time capital expenditures (cap-ex). The recurring electricity cost is often in large determined by datacenter peak-demand under peak-based pricing which is employed by major electric utility providers. There is a growing interest in reducing a datacenter's electricity costs by using throttling techniques and/or energy storage devices (batteries) which are readily available at most datacenters as a backup energy source. A datacenter's power-demand uncertainty makes this a challenging problem, which is largely neglected in existing work, by assuming perfect predictability of power demand. We model this inherent uncertainty as a Markov chain and also evaluate the risk of over/under charging batteries as a result of the randomness in power demand. We design an online optimization framework for peak shaving which considers Conditional Value at Risk and allows for navigating cost-risk trade-offs of datacenters based on their energy infrastructure and workload characteristics. We show that this framework offers significantly higher (up to 2X) cost-savings with small risks of over/under charging batteries, compared to existing stochastic optimization techniques. This framework leverages Markov Decision Processes to perform online dynamic peak shaving, considering battery degradation costs under peak-based pricing.

UR - http://www.scopus.com/inward/record.url?scp=85040530819&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040530819&partnerID=8YFLogxK

U2 - 10.1109/MASCOTS.2017.27

DO - 10.1109/MASCOTS.2017.27

M3 - Conference contribution

AN - SCOPUS:85040530819

T3 - Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017

SP - 164

EP - 174

BT - Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Nasiriani N, Kesidis G, Wang D. Optimal Peak Shaving Using Batteries at Datacenters: Characterizing the Risks and Benefits. In Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 164-174. 8107443. (Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017). https://doi.org/10.1109/MASCOTS.2017.27