Artificial neural network based optimized control of condenser water temperature set-point

Tae Young Kim; Jong Man Lee; Sung Hyup Hong; Jong Min Choi; Kwang Ho Lee

doi:10.1115/ES2021-63735

Artificial neural network based optimized control of condenser water temperature set-point

Tae Young Kim
, Jong Man Lee
, Sung Hyup Hong
, Jong Min Choi
, Kwang Ho Lee

Department of Architecture

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

In this study, we developed an artificial neural network based real-time predictive control and optimization model to compare and analyze the difference in total energy consumption when the condenser water outlet temperature coming out of the cooling tower is fixed and when real-time control of the condenser water outlet temperature through the optimal ANN model is applied. An ANN model was developed through MATLAB's built-in neural network toolbox functionality to predict total energy consumption. The model accuracy of the ANN was examined by applying Cv(RMSE), a statistical concept that shows the overall accuracy of the predicted values, and as a result, it was found to have a Cv(RMSE) value of approximately 25%. In addition, the predictive control algorithm was able to reduce cooling energy consumption by about 5.6% compared to the conventional control strategy that fix condenser water temperature set-point to constantly 30°C.

Original language	English
Title of host publication	Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021
Publisher	American Society of Mechanical Engineers (ASME)
ISBN (Electronic)	9780791884881
DOIs	https://doi.org/10.1115/ES2021-63735
Publication status	Published - 2021
Event	ASME 2021 15th International Conference on Energy Sustainability, ES 2021 - Virtual, Online Duration: 2021 Jun 16 → 2021 Jun 18

Publication series

Name	Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021

Conference

Conference	ASME 2021 15th International Conference on Energy Sustainability, ES 2021
City	Virtual, Online
Period	21/6/16 → 21/6/18

Bibliographical note

Publisher Copyright:
Copyright © 2021 by ASME.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

ANN (artificial neural network)
BCVTB (building controls virtual test bed)
Chiller
Condenser water temperature
Cooling tower
EnergyPlus
HVAC (heating, ventilation, and air conditioning) system
MATLAB

ASJC Scopus subject areas

Fuel Technology
Renewable Energy, Sustainability and the Environment
Energy Engineering and Power Technology

Access to Document

10.1115/ES2021-63735

Cite this

Kim, T. Y., Lee, J. M., Hong, S. H., Choi, J. M., & Lee, K. H. (2021). Artificial neural network based optimized control of condenser water temperature set-point. In Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021 Article V001T15A002 (Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021). American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/ES2021-63735

Artificial neural network based optimized control of condenser water temperature set-point. / Kim, Tae Young; Lee, Jong Man; Hong, Sung Hyup et al.
Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021. American Society of Mechanical Engineers (ASME), 2021. V001T15A002 (Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kim, TY, Lee, JM, Hong, SH, Choi, JM & Lee, KH 2021, Artificial neural network based optimized control of condenser water temperature set-point. in Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021., V001T15A002, Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021, American Society of Mechanical Engineers (ASME), ASME 2021 15th International Conference on Energy Sustainability, ES 2021, Virtual, Online, 21/6/16. https://doi.org/10.1115/ES2021-63735

Kim TY, Lee JM, Hong SH, Choi JM, Lee KH. Artificial neural network based optimized control of condenser water temperature set-point. In Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021. American Society of Mechanical Engineers (ASME). 2021. V001T15A002. (Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021). doi: 10.1115/ES2021-63735

Kim, Tae Young ; Lee, Jong Man ; Hong, Sung Hyup et al. / Artificial neural network based optimized control of condenser water temperature set-point. Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021. American Society of Mechanical Engineers (ASME), 2021. (Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021).

@inproceedings{3397ff3f62bf45eaa51dd96563d7828f,

title = "Artificial neural network based optimized control of condenser water temperature set-point",

abstract = "In this study, we developed an artificial neural network based real-time predictive control and optimization model to compare and analyze the difference in total energy consumption when the condenser water outlet temperature coming out of the cooling tower is fixed and when real-time control of the condenser water outlet temperature through the optimal ANN model is applied. An ANN model was developed through MATLAB's built-in neural network toolbox functionality to predict total energy consumption. The model accuracy of the ANN was examined by applying Cv(RMSE), a statistical concept that shows the overall accuracy of the predicted values, and as a result, it was found to have a Cv(RMSE) value of approximately 25\%. In addition, the predictive control algorithm was able to reduce cooling energy consumption by about 5.6\% compared to the conventional control strategy that fix condenser water temperature set-point to constantly 30°C.",

keywords = "ANN (artificial neural network), BCVTB (building controls virtual test bed), Chiller, Condenser water temperature, Cooling tower, EnergyPlus, HVAC (heating, ventilation, and air conditioning) system, MATLAB",

author = "Kim, \{Tae Young\} and Lee, \{Jong Man\} and Hong, \{Sung Hyup\} and Choi, \{Jong Min\} and Lee, \{Kwang Ho\}",

note = "Publisher Copyright: Copyright {\textcopyright} 2021 by ASME.; ASME 2021 15th International Conference on Energy Sustainability, ES 2021 ; Conference date: 16-06-2021 Through 18-06-2021",

year = "2021",

doi = "10.1115/ES2021-63735",

language = "English",

series = "Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021",

publisher = "American Society of Mechanical Engineers (ASME)",

booktitle = "Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021",

}

TY - GEN

T1 - Artificial neural network based optimized control of condenser water temperature set-point

AU - Kim, Tae Young

AU - Lee, Jong Man

AU - Hong, Sung Hyup

AU - Choi, Jong Min

AU - Lee, Kwang Ho

PY - 2021

Y1 - 2021

N2 - In this study, we developed an artificial neural network based real-time predictive control and optimization model to compare and analyze the difference in total energy consumption when the condenser water outlet temperature coming out of the cooling tower is fixed and when real-time control of the condenser water outlet temperature through the optimal ANN model is applied. An ANN model was developed through MATLAB's built-in neural network toolbox functionality to predict total energy consumption. The model accuracy of the ANN was examined by applying Cv(RMSE), a statistical concept that shows the overall accuracy of the predicted values, and as a result, it was found to have a Cv(RMSE) value of approximately 25%. In addition, the predictive control algorithm was able to reduce cooling energy consumption by about 5.6% compared to the conventional control strategy that fix condenser water temperature set-point to constantly 30°C.

AB - In this study, we developed an artificial neural network based real-time predictive control and optimization model to compare and analyze the difference in total energy consumption when the condenser water outlet temperature coming out of the cooling tower is fixed and when real-time control of the condenser water outlet temperature through the optimal ANN model is applied. An ANN model was developed through MATLAB's built-in neural network toolbox functionality to predict total energy consumption. The model accuracy of the ANN was examined by applying Cv(RMSE), a statistical concept that shows the overall accuracy of the predicted values, and as a result, it was found to have a Cv(RMSE) value of approximately 25%. In addition, the predictive control algorithm was able to reduce cooling energy consumption by about 5.6% compared to the conventional control strategy that fix condenser water temperature set-point to constantly 30°C.

KW - ANN (artificial neural network)

KW - BCVTB (building controls virtual test bed)

KW - Chiller

KW - Condenser water temperature

KW - Cooling tower

KW - EnergyPlus

KW - HVAC (heating, ventilation, and air conditioning) system

KW - MATLAB

UR - https://www.scopus.com/pages/publications/85111766917

U2 - 10.1115/ES2021-63735

DO - 10.1115/ES2021-63735

M3 - Conference contribution

AN - SCOPUS:85111766917

T3 - Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021

BT - Proceedings of the ASME 2021 15th International Conference on Energy Sustainability, ES 2021

PB - American Society of Mechanical Engineers (ASME)

T2 - ASME 2021 15th International Conference on Energy Sustainability, ES 2021

Y2 - 16 June 2021 through 18 June 2021

ER -

Artificial neural network based optimized control of condenser water temperature set-point

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this