Data driven chiller plant energy optimization with domain knowledge

Hoang Dung Vu, Kok Soon Chai, Bryan Keating, Nurislam Tursynbek, Boyan Xu, Kaige Yang, Xiaoyan Yang, Zhenjie Zhang

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

1 Citation (Scopus)

Abstract

Refrigeration and chiller optimization is an important and well studied topic in mechanical engineering, mostly taking advantage of physical models, designed on top of oversimplified assumptions, over the equipments. Conventional optimization techniques using physical models make decisions of online parameter tuning, based on very limited information of hardware specifications and external conditions, e.g., outdoor weather. In recent years, new generation of sensors is becoming essential part of new chiller plants, for the first time allowing the system administrators to continuously monitor the running status of all equipments in a timely and accurate way. The explosive growth of data owing to databases, driven by the increasing analytical power by machine learning and data mining, unveils new possibilities of data-driven approaches for real-time chiller plant optimization. This paper presents our research and industrial experience on the adoption of data models and optimizations on chiller plant and discusses the lessons learnt from our practice on real world plants. Instead of employing complex machine learning models, we emphasize the incorporation of appropriate domain knowledge into data analysis tools, which turns out to be the key performance improver over state-of-the-art deep learning techniques by a significant margin. Our empirical evaluation on a real world chiller plant achieves savings by more than 7% on daily power consumption.

Original languageEnglish
Title of host publicationCIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery
Pages1309-1317
Number of pages9
VolumePart F131841
ISBN (Electronic)9781450349185
DOIs
Publication statusPublished - Nov 6 2017
Externally publishedYes
Event26th ACM International Conference on Information and Knowledge Management, CIKM 2017 - Singapore, Singapore
Duration: Nov 6 2017Nov 10 2017

Conference

Conference26th ACM International Conference on Information and Knowledge Management, CIKM 2017
CountrySingapore
CitySingapore
Period11/6/1711/10/17

Fingerprint

Energy
Domain knowledge
Machine learning
Sensor
Empirical evaluation
Weather
Refrigeration
Mechanical engineering
Deep learning
Margin
Savings
Data base
Limited information
Learning model
Optimization techniques
Data mining

ASJC Scopus subject areas

  • Business, Management and Accounting(all)
  • Decision Sciences(all)

Cite this

Vu, H. D., Chai, K. S., Keating, B., Tursynbek, N., Xu, B., Yang, K., ... Zhang, Z. (2017). Data driven chiller plant energy optimization with domain knowledge. In CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management (Vol. Part F131841, pp. 1309-1317). Association for Computing Machinery. https://doi.org/10.1145/3132847.3132860

Data driven chiller plant energy optimization with domain knowledge. / Vu, Hoang Dung; Chai, Kok Soon; Keating, Bryan; Tursynbek, Nurislam; Xu, Boyan; Yang, Kaige; Yang, Xiaoyan; Zhang, Zhenjie.

CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management. Vol. Part F131841 Association for Computing Machinery, 2017. p. 1309-1317.

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

Vu, HD, Chai, KS, Keating, B, Tursynbek, N, Xu, B, Yang, K, Yang, X & Zhang, Z 2017, Data driven chiller plant energy optimization with domain knowledge. in CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management. vol. Part F131841, Association for Computing Machinery, pp. 1309-1317, 26th ACM International Conference on Information and Knowledge Management, CIKM 2017, Singapore, Singapore, 11/6/17. https://doi.org/10.1145/3132847.3132860
Vu HD, Chai KS, Keating B, Tursynbek N, Xu B, Yang K et al. Data driven chiller plant energy optimization with domain knowledge. In CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management. Vol. Part F131841. Association for Computing Machinery. 2017. p. 1309-1317 https://doi.org/10.1145/3132847.3132860
Vu, Hoang Dung ; Chai, Kok Soon ; Keating, Bryan ; Tursynbek, Nurislam ; Xu, Boyan ; Yang, Kaige ; Yang, Xiaoyan ; Zhang, Zhenjie. / Data driven chiller plant energy optimization with domain knowledge. CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management. Vol. Part F131841 Association for Computing Machinery, 2017. pp. 1309-1317
@inproceedings{ff9914c003544684b3ca2cafa846ebdb,
title = "Data driven chiller plant energy optimization with domain knowledge",
abstract = "Refrigeration and chiller optimization is an important and well studied topic in mechanical engineering, mostly taking advantage of physical models, designed on top of oversimplified assumptions, over the equipments. Conventional optimization techniques using physical models make decisions of online parameter tuning, based on very limited information of hardware specifications and external conditions, e.g., outdoor weather. In recent years, new generation of sensors is becoming essential part of new chiller plants, for the first time allowing the system administrators to continuously monitor the running status of all equipments in a timely and accurate way. The explosive growth of data owing to databases, driven by the increasing analytical power by machine learning and data mining, unveils new possibilities of data-driven approaches for real-time chiller plant optimization. This paper presents our research and industrial experience on the adoption of data models and optimizations on chiller plant and discusses the lessons learnt from our practice on real world plants. Instead of employing complex machine learning models, we emphasize the incorporation of appropriate domain knowledge into data analysis tools, which turns out to be the key performance improver over state-of-the-art deep learning techniques by a significant margin. Our empirical evaluation on a real world chiller plant achieves savings by more than 7{\%} on daily power consumption.",
author = "Vu, {Hoang Dung} and Chai, {Kok Soon} and Bryan Keating and Nurislam Tursynbek and Boyan Xu and Kaige Yang and Xiaoyan Yang and Zhenjie Zhang",
year = "2017",
month = "11",
day = "6",
doi = "10.1145/3132847.3132860",
language = "English",
volume = "Part F131841",
pages = "1309--1317",
booktitle = "CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Data driven chiller plant energy optimization with domain knowledge

AU - Vu, Hoang Dung

AU - Chai, Kok Soon

AU - Keating, Bryan

AU - Tursynbek, Nurislam

AU - Xu, Boyan

AU - Yang, Kaige

AU - Yang, Xiaoyan

AU - Zhang, Zhenjie

PY - 2017/11/6

Y1 - 2017/11/6

N2 - Refrigeration and chiller optimization is an important and well studied topic in mechanical engineering, mostly taking advantage of physical models, designed on top of oversimplified assumptions, over the equipments. Conventional optimization techniques using physical models make decisions of online parameter tuning, based on very limited information of hardware specifications and external conditions, e.g., outdoor weather. In recent years, new generation of sensors is becoming essential part of new chiller plants, for the first time allowing the system administrators to continuously monitor the running status of all equipments in a timely and accurate way. The explosive growth of data owing to databases, driven by the increasing analytical power by machine learning and data mining, unveils new possibilities of data-driven approaches for real-time chiller plant optimization. This paper presents our research and industrial experience on the adoption of data models and optimizations on chiller plant and discusses the lessons learnt from our practice on real world plants. Instead of employing complex machine learning models, we emphasize the incorporation of appropriate domain knowledge into data analysis tools, which turns out to be the key performance improver over state-of-the-art deep learning techniques by a significant margin. Our empirical evaluation on a real world chiller plant achieves savings by more than 7% on daily power consumption.

AB - Refrigeration and chiller optimization is an important and well studied topic in mechanical engineering, mostly taking advantage of physical models, designed on top of oversimplified assumptions, over the equipments. Conventional optimization techniques using physical models make decisions of online parameter tuning, based on very limited information of hardware specifications and external conditions, e.g., outdoor weather. In recent years, new generation of sensors is becoming essential part of new chiller plants, for the first time allowing the system administrators to continuously monitor the running status of all equipments in a timely and accurate way. The explosive growth of data owing to databases, driven by the increasing analytical power by machine learning and data mining, unveils new possibilities of data-driven approaches for real-time chiller plant optimization. This paper presents our research and industrial experience on the adoption of data models and optimizations on chiller plant and discusses the lessons learnt from our practice on real world plants. Instead of employing complex machine learning models, we emphasize the incorporation of appropriate domain knowledge into data analysis tools, which turns out to be the key performance improver over state-of-the-art deep learning techniques by a significant margin. Our empirical evaluation on a real world chiller plant achieves savings by more than 7% on daily power consumption.

UR - http://www.scopus.com/inward/record.url?scp=85037376236&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037376236&partnerID=8YFLogxK

U2 - 10.1145/3132847.3132860

DO - 10.1145/3132847.3132860

M3 - Conference contribution

VL - Part F131841

SP - 1309

EP - 1317

BT - CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management

PB - Association for Computing Machinery

ER -