An Internet of Things compliant model identification methodology for smart buildings

Korkut Bekiroglu, Seshadhri Srinivasan, Ethan Png, Rong Su, Kameshwar Poolla, Constantino Manuel Lagoa

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

3 Citations (Scopus)

Abstract

Identifying building thermal model with communication imperfections (data-loss and -corruption) is emerging as a major challenge in deploying Internet of Things (IoT) based building automation systems. Further, the building thermal model is influenced by multiple inputs - cooling energy, stray heating, and weather, leading to a multi-input and single output (MISO) system, compounding the challenge further. This investigation presents an approach for identifying high fidelity, yet simple building thermal model suitable for designing predictive controllers for heating, ventilation and air-conditioning systems with IoT induced imperfections. By construction, the problem of finding the lowest order MISO model is a cardinality optimization problem, known to be non-convex and NP-hard. To solve this problem, we first define an atomic norm suitable to relax the cardinality reduction problem for simplifying the identification. Then the resulting problem is solved by employing a randomized version of the Frank-Wolfe algorithm. The performance of the proposed identification algorithm is illustrated on a MISO building thermal model. Our results show that the proposed approach is more suitable for identifying the lowest order building thermal models with missing and corrupted data due to the network.

Original languageEnglish (US)
Title of host publication2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4440-4445
Number of pages6
ISBN (Electronic)9781509028733
DOIs
StatePublished - Jan 18 2018
Event56th IEEE Annual Conference on Decision and Control, CDC 2017 - Melbourne, Australia
Duration: Dec 12 2017Dec 15 2017

Publication series

Name2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017
Volume2018-January

Other

Other56th IEEE Annual Conference on Decision and Control, CDC 2017
CountryAustralia
CityMelbourne
Period12/12/1712/15/17

Fingerprint

Intelligent buildings
Internet of Things
Thermal Model
Model Identification
Identification (control systems)
Methodology
Imperfections
Heating
Output
Cardinality
Lowest
Ventilation
Defects
Conditioning
Weather
Fidelity
Automation
Cooling
Air conditioning
NP-complete problem

All Science Journal Classification (ASJC) codes

  • Decision Sciences (miscellaneous)
  • Industrial and Manufacturing Engineering
  • Control and Optimization

Cite this

Bekiroglu, K., Srinivasan, S., Png, E., Su, R., Poolla, K., & Lagoa, C. M. (2018). An Internet of Things compliant model identification methodology for smart buildings. In 2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017 (pp. 4440-4445). (2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CDC.2017.8264314
Bekiroglu, Korkut ; Srinivasan, Seshadhri ; Png, Ethan ; Su, Rong ; Poolla, Kameshwar ; Lagoa, Constantino Manuel. / An Internet of Things compliant model identification methodology for smart buildings. 2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 4440-4445 (2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017).
@inproceedings{0774ae187c7d47ad8f9ffd3eee997822,
title = "An Internet of Things compliant model identification methodology for smart buildings",
abstract = "Identifying building thermal model with communication imperfections (data-loss and -corruption) is emerging as a major challenge in deploying Internet of Things (IoT) based building automation systems. Further, the building thermal model is influenced by multiple inputs - cooling energy, stray heating, and weather, leading to a multi-input and single output (MISO) system, compounding the challenge further. This investigation presents an approach for identifying high fidelity, yet simple building thermal model suitable for designing predictive controllers for heating, ventilation and air-conditioning systems with IoT induced imperfections. By construction, the problem of finding the lowest order MISO model is a cardinality optimization problem, known to be non-convex and NP-hard. To solve this problem, we first define an atomic norm suitable to relax the cardinality reduction problem for simplifying the identification. Then the resulting problem is solved by employing a randomized version of the Frank-Wolfe algorithm. The performance of the proposed identification algorithm is illustrated on a MISO building thermal model. Our results show that the proposed approach is more suitable for identifying the lowest order building thermal models with missing and corrupted data due to the network.",
author = "Korkut Bekiroglu and Seshadhri Srinivasan and Ethan Png and Rong Su and Kameshwar Poolla and Lagoa, {Constantino Manuel}",
year = "2018",
month = "1",
day = "18",
doi = "10.1109/CDC.2017.8264314",
language = "English (US)",
series = "2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "4440--4445",
booktitle = "2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017",
address = "United States",

}

Bekiroglu, K, Srinivasan, S, Png, E, Su, R, Poolla, K & Lagoa, CM 2018, An Internet of Things compliant model identification methodology for smart buildings. in 2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017. 2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 4440-4445, 56th IEEE Annual Conference on Decision and Control, CDC 2017, Melbourne, Australia, 12/12/17. https://doi.org/10.1109/CDC.2017.8264314

An Internet of Things compliant model identification methodology for smart buildings. / Bekiroglu, Korkut; Srinivasan, Seshadhri; Png, Ethan; Su, Rong; Poolla, Kameshwar; Lagoa, Constantino Manuel.

2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017. Institute of Electrical and Electronics Engineers Inc., 2018. p. 4440-4445 (2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017; Vol. 2018-January).

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

TY - GEN

T1 - An Internet of Things compliant model identification methodology for smart buildings

AU - Bekiroglu, Korkut

AU - Srinivasan, Seshadhri

AU - Png, Ethan

AU - Su, Rong

AU - Poolla, Kameshwar

AU - Lagoa, Constantino Manuel

PY - 2018/1/18

Y1 - 2018/1/18

N2 - Identifying building thermal model with communication imperfections (data-loss and -corruption) is emerging as a major challenge in deploying Internet of Things (IoT) based building automation systems. Further, the building thermal model is influenced by multiple inputs - cooling energy, stray heating, and weather, leading to a multi-input and single output (MISO) system, compounding the challenge further. This investigation presents an approach for identifying high fidelity, yet simple building thermal model suitable for designing predictive controllers for heating, ventilation and air-conditioning systems with IoT induced imperfections. By construction, the problem of finding the lowest order MISO model is a cardinality optimization problem, known to be non-convex and NP-hard. To solve this problem, we first define an atomic norm suitable to relax the cardinality reduction problem for simplifying the identification. Then the resulting problem is solved by employing a randomized version of the Frank-Wolfe algorithm. The performance of the proposed identification algorithm is illustrated on a MISO building thermal model. Our results show that the proposed approach is more suitable for identifying the lowest order building thermal models with missing and corrupted data due to the network.

AB - Identifying building thermal model with communication imperfections (data-loss and -corruption) is emerging as a major challenge in deploying Internet of Things (IoT) based building automation systems. Further, the building thermal model is influenced by multiple inputs - cooling energy, stray heating, and weather, leading to a multi-input and single output (MISO) system, compounding the challenge further. This investigation presents an approach for identifying high fidelity, yet simple building thermal model suitable for designing predictive controllers for heating, ventilation and air-conditioning systems with IoT induced imperfections. By construction, the problem of finding the lowest order MISO model is a cardinality optimization problem, known to be non-convex and NP-hard. To solve this problem, we first define an atomic norm suitable to relax the cardinality reduction problem for simplifying the identification. Then the resulting problem is solved by employing a randomized version of the Frank-Wolfe algorithm. The performance of the proposed identification algorithm is illustrated on a MISO building thermal model. Our results show that the proposed approach is more suitable for identifying the lowest order building thermal models with missing and corrupted data due to the network.

UR - http://www.scopus.com/inward/record.url?scp=85046143634&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046143634&partnerID=8YFLogxK

U2 - 10.1109/CDC.2017.8264314

DO - 10.1109/CDC.2017.8264314

M3 - Conference contribution

AN - SCOPUS:85046143634

T3 - 2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017

SP - 4440

EP - 4445

BT - 2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Bekiroglu K, Srinivasan S, Png E, Su R, Poolla K, Lagoa CM. An Internet of Things compliant model identification methodology for smart buildings. In 2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017. Institute of Electrical and Electronics Engineers Inc. 2018. p. 4440-4445. (2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017). https://doi.org/10.1109/CDC.2017.8264314