A Markov process approach to ensemble control of smart buildings

Roman Pop, Ali Hassan, Kenneth Bruninx, Michael Chertkov, Yury Dvorkin

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

Abstract

This paper describes a step-by-step procedure that converts a physical model of a building into a Markov Process that characterizes energy consumption of this building. Relative to existing thermo-physics-based building models, the proposed procedure reduces model complexity and depends on fewer parameters, while also maintaining accuracy and feasibility sufficient for system-level analyses. Furthermore, the proposed Markov Process approach makes it possible to leverage real-time data streams available from intelligent building data acquisition systems, which are readily available in smart buildings, and merge it with physics-based and statistical models. Construction of the Markov Process naturally leads to a Markov Decision Process formulation, which describes optimal probabilistic control of a collection of similar buildings. The approach is illustrated using validated building data from Belgium.

Original languageEnglish (US)
Title of host publication2019 IEEE Milan PowerTech, PowerTech 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538647226
DOIs
StatePublished - Jun 1 2019
Event2019 IEEE Milan PowerTech, PowerTech 2019 - Milan, Italy
Duration: Jun 23 2019Jun 27 2019

Publication series

Name2019 IEEE Milan PowerTech, PowerTech 2019

Conference

Conference2019 IEEE Milan PowerTech, PowerTech 2019
CountryItaly
CityMilan
Period6/23/196/27/19

Fingerprint

Intelligent buildings
Markov processes
Physics
Data acquisition
Energy utilization

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Energy Engineering and Power Technology
  • Renewable Energy, Sustainability and the Environment
  • Safety, Risk, Reliability and Quality

Cite this

Pop, R., Hassan, A., Bruninx, K., Chertkov, M., & Dvorkin, Y. (2019). A Markov process approach to ensemble control of smart buildings. In 2019 IEEE Milan PowerTech, PowerTech 2019 [8810505] (2019 IEEE Milan PowerTech, PowerTech 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PTC.2019.8810505

A Markov process approach to ensemble control of smart buildings. / Pop, Roman; Hassan, Ali; Bruninx, Kenneth; Chertkov, Michael; Dvorkin, Yury.

2019 IEEE Milan PowerTech, PowerTech 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8810505 (2019 IEEE Milan PowerTech, PowerTech 2019).

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

Pop, R, Hassan, A, Bruninx, K, Chertkov, M & Dvorkin, Y 2019, A Markov process approach to ensemble control of smart buildings. in 2019 IEEE Milan PowerTech, PowerTech 2019., 8810505, 2019 IEEE Milan PowerTech, PowerTech 2019, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE Milan PowerTech, PowerTech 2019, Milan, Italy, 6/23/19. https://doi.org/10.1109/PTC.2019.8810505
Pop R, Hassan A, Bruninx K, Chertkov M, Dvorkin Y. A Markov process approach to ensemble control of smart buildings. In 2019 IEEE Milan PowerTech, PowerTech 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8810505. (2019 IEEE Milan PowerTech, PowerTech 2019). https://doi.org/10.1109/PTC.2019.8810505
Pop, Roman ; Hassan, Ali ; Bruninx, Kenneth ; Chertkov, Michael ; Dvorkin, Yury. / A Markov process approach to ensemble control of smart buildings. 2019 IEEE Milan PowerTech, PowerTech 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 IEEE Milan PowerTech, PowerTech 2019).
@inproceedings{c003254b235442d9a5afa658b5bdc795,
title = "A Markov process approach to ensemble control of smart buildings",
abstract = "This paper describes a step-by-step procedure that converts a physical model of a building into a Markov Process that characterizes energy consumption of this building. Relative to existing thermo-physics-based building models, the proposed procedure reduces model complexity and depends on fewer parameters, while also maintaining accuracy and feasibility sufficient for system-level analyses. Furthermore, the proposed Markov Process approach makes it possible to leverage real-time data streams available from intelligent building data acquisition systems, which are readily available in smart buildings, and merge it with physics-based and statistical models. Construction of the Markov Process naturally leads to a Markov Decision Process formulation, which describes optimal probabilistic control of a collection of similar buildings. The approach is illustrated using validated building data from Belgium.",
author = "Roman Pop and Ali Hassan and Kenneth Bruninx and Michael Chertkov and Yury Dvorkin",
year = "2019",
month = "6",
day = "1",
doi = "10.1109/PTC.2019.8810505",
language = "English (US)",
series = "2019 IEEE Milan PowerTech, PowerTech 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE Milan PowerTech, PowerTech 2019",

}

TY - GEN

T1 - A Markov process approach to ensemble control of smart buildings

AU - Pop, Roman

AU - Hassan, Ali

AU - Bruninx, Kenneth

AU - Chertkov, Michael

AU - Dvorkin, Yury

PY - 2019/6/1

Y1 - 2019/6/1

N2 - This paper describes a step-by-step procedure that converts a physical model of a building into a Markov Process that characterizes energy consumption of this building. Relative to existing thermo-physics-based building models, the proposed procedure reduces model complexity and depends on fewer parameters, while also maintaining accuracy and feasibility sufficient for system-level analyses. Furthermore, the proposed Markov Process approach makes it possible to leverage real-time data streams available from intelligent building data acquisition systems, which are readily available in smart buildings, and merge it with physics-based and statistical models. Construction of the Markov Process naturally leads to a Markov Decision Process formulation, which describes optimal probabilistic control of a collection of similar buildings. The approach is illustrated using validated building data from Belgium.

AB - This paper describes a step-by-step procedure that converts a physical model of a building into a Markov Process that characterizes energy consumption of this building. Relative to existing thermo-physics-based building models, the proposed procedure reduces model complexity and depends on fewer parameters, while also maintaining accuracy and feasibility sufficient for system-level analyses. Furthermore, the proposed Markov Process approach makes it possible to leverage real-time data streams available from intelligent building data acquisition systems, which are readily available in smart buildings, and merge it with physics-based and statistical models. Construction of the Markov Process naturally leads to a Markov Decision Process formulation, which describes optimal probabilistic control of a collection of similar buildings. The approach is illustrated using validated building data from Belgium.

UR - http://www.scopus.com/inward/record.url?scp=85072339949&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072339949&partnerID=8YFLogxK

U2 - 10.1109/PTC.2019.8810505

DO - 10.1109/PTC.2019.8810505

M3 - Conference contribution

AN - SCOPUS:85072339949

T3 - 2019 IEEE Milan PowerTech, PowerTech 2019

BT - 2019 IEEE Milan PowerTech, PowerTech 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -