Application of artificial neural networks for optimized AHU discharge air temperature set-point and minimized cooling energy in VAV system

Jong Man Lee, Sung Hyup Hong, Byeong Mo Seo, Kwang Ho Lee

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Chillers and boilers based air handling unit (AHU) system is one of the most widely used heating and cooling systems in office buildings in Korea. However, in most conventional forced-air systems, the guidelines for the AHU discharge air temperature (DAT) are not fully established and thus AHU DAT are constantly fixed to a particular set-point, regardless of dynamic changes of operating variables. In this circumstance, this study aimed at developing a control algorithm that can operate a conventional VAV system with optimal set-points for the AHU DAT. Three-story office building was modeled using co-simulation technique between EnergyPlus and Matlab via BCVTB (Building Controls Virtual Test Bed). In addition, artificial neural network (ANN) model, which was designed to predict the cooling energy consumption for the upcoming next time-step, was embedded into the control algorithm using neural network toolbox within Matlab. By comparing the predicted energy for the different set-points of the AHU DAT, the control algorithm can determine the most energy-effective AHU DAT set-point to minimize the cooling energy. The results showed that the prediction accuracy between simulated and predicted outcomes turned out to have a low coefficient of variation root mean square error (CvRMSE) value of approximately 24%. In addition, the predictive control algorithm was able to significantly reduce cooling energy consumption by approximately 10%, compared to a conventional control strategy of fixing AHU DAT to 14 °C. These findings suggest that the ANN model and the control algorithm showed energy saving potential for various types of forced air systems by taking dynamic operating conditions into account in each time-step.

Original languageEnglish
Pages (from-to)726-738
Number of pages13
JournalApplied Thermal Engineering
DOIs
Publication statusPublished - 2019 May 5

Fingerprint

Discharge (fluid mechanics)
Cooling
Neural networks
Air
Temperature
Office buildings
Energy utilization
Cooling systems
Mean square error
Boilers
Energy conservation

Keywords

  • AHU (Air Handling Unit)
  • AHU Discharge Air Temperature (DAT)
  • ANN (Artificial Neural Network)
  • BCVTB (Building Controls Virtual Test Bed)
  • EnergyPlus
  • Matlab

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Industrial and Manufacturing Engineering

Cite this

Application of artificial neural networks for optimized AHU discharge air temperature set-point and minimized cooling energy in VAV system. / Lee, Jong Man; Hong, Sung Hyup; Seo, Byeong Mo; Lee, Kwang Ho.

In: Applied Thermal Engineering, 05.05.2019, p. 726-738.

Research output: Contribution to journalArticle

@article{05bfc0dc6cd84a4a9e21bca25289f5bf,
title = "Application of artificial neural networks for optimized AHU discharge air temperature set-point and minimized cooling energy in VAV system",
abstract = "Chillers and boilers based air handling unit (AHU) system is one of the most widely used heating and cooling systems in office buildings in Korea. However, in most conventional forced-air systems, the guidelines for the AHU discharge air temperature (DAT) are not fully established and thus AHU DAT are constantly fixed to a particular set-point, regardless of dynamic changes of operating variables. In this circumstance, this study aimed at developing a control algorithm that can operate a conventional VAV system with optimal set-points for the AHU DAT. Three-story office building was modeled using co-simulation technique between EnergyPlus and Matlab via BCVTB (Building Controls Virtual Test Bed). In addition, artificial neural network (ANN) model, which was designed to predict the cooling energy consumption for the upcoming next time-step, was embedded into the control algorithm using neural network toolbox within Matlab. By comparing the predicted energy for the different set-points of the AHU DAT, the control algorithm can determine the most energy-effective AHU DAT set-point to minimize the cooling energy. The results showed that the prediction accuracy between simulated and predicted outcomes turned out to have a low coefficient of variation root mean square error (CvRMSE) value of approximately 24{\%}. In addition, the predictive control algorithm was able to significantly reduce cooling energy consumption by approximately 10{\%}, compared to a conventional control strategy of fixing AHU DAT to 14 °C. These findings suggest that the ANN model and the control algorithm showed energy saving potential for various types of forced air systems by taking dynamic operating conditions into account in each time-step.",
keywords = "AHU (Air Handling Unit), AHU Discharge Air Temperature (DAT), ANN (Artificial Neural Network), BCVTB (Building Controls Virtual Test Bed), EnergyPlus, Matlab",
author = "Lee, {Jong Man} and Hong, {Sung Hyup} and Seo, {Byeong Mo} and Lee, {Kwang Ho}",
year = "2019",
month = "5",
day = "5",
doi = "10.1016/j.applthermaleng.2019.03.061",
language = "English",
pages = "726--738",
journal = "Applied Thermal Engineering",
issn = "1359-4311",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Application of artificial neural networks for optimized AHU discharge air temperature set-point and minimized cooling energy in VAV system

AU - Lee, Jong Man

AU - Hong, Sung Hyup

AU - Seo, Byeong Mo

AU - Lee, Kwang Ho

PY - 2019/5/5

Y1 - 2019/5/5

N2 - Chillers and boilers based air handling unit (AHU) system is one of the most widely used heating and cooling systems in office buildings in Korea. However, in most conventional forced-air systems, the guidelines for the AHU discharge air temperature (DAT) are not fully established and thus AHU DAT are constantly fixed to a particular set-point, regardless of dynamic changes of operating variables. In this circumstance, this study aimed at developing a control algorithm that can operate a conventional VAV system with optimal set-points for the AHU DAT. Three-story office building was modeled using co-simulation technique between EnergyPlus and Matlab via BCVTB (Building Controls Virtual Test Bed). In addition, artificial neural network (ANN) model, which was designed to predict the cooling energy consumption for the upcoming next time-step, was embedded into the control algorithm using neural network toolbox within Matlab. By comparing the predicted energy for the different set-points of the AHU DAT, the control algorithm can determine the most energy-effective AHU DAT set-point to minimize the cooling energy. The results showed that the prediction accuracy between simulated and predicted outcomes turned out to have a low coefficient of variation root mean square error (CvRMSE) value of approximately 24%. In addition, the predictive control algorithm was able to significantly reduce cooling energy consumption by approximately 10%, compared to a conventional control strategy of fixing AHU DAT to 14 °C. These findings suggest that the ANN model and the control algorithm showed energy saving potential for various types of forced air systems by taking dynamic operating conditions into account in each time-step.

AB - Chillers and boilers based air handling unit (AHU) system is one of the most widely used heating and cooling systems in office buildings in Korea. However, in most conventional forced-air systems, the guidelines for the AHU discharge air temperature (DAT) are not fully established and thus AHU DAT are constantly fixed to a particular set-point, regardless of dynamic changes of operating variables. In this circumstance, this study aimed at developing a control algorithm that can operate a conventional VAV system with optimal set-points for the AHU DAT. Three-story office building was modeled using co-simulation technique between EnergyPlus and Matlab via BCVTB (Building Controls Virtual Test Bed). In addition, artificial neural network (ANN) model, which was designed to predict the cooling energy consumption for the upcoming next time-step, was embedded into the control algorithm using neural network toolbox within Matlab. By comparing the predicted energy for the different set-points of the AHU DAT, the control algorithm can determine the most energy-effective AHU DAT set-point to minimize the cooling energy. The results showed that the prediction accuracy between simulated and predicted outcomes turned out to have a low coefficient of variation root mean square error (CvRMSE) value of approximately 24%. In addition, the predictive control algorithm was able to significantly reduce cooling energy consumption by approximately 10%, compared to a conventional control strategy of fixing AHU DAT to 14 °C. These findings suggest that the ANN model and the control algorithm showed energy saving potential for various types of forced air systems by taking dynamic operating conditions into account in each time-step.

KW - AHU (Air Handling Unit)

KW - AHU Discharge Air Temperature (DAT)

KW - ANN (Artificial Neural Network)

KW - BCVTB (Building Controls Virtual Test Bed)

KW - EnergyPlus

KW - Matlab

UR - http://www.scopus.com/inward/record.url?scp=85062848087&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062848087&partnerID=8YFLogxK

U2 - 10.1016/j.applthermaleng.2019.03.061

DO - 10.1016/j.applthermaleng.2019.03.061

M3 - Article

SP - 726

EP - 738

JO - Applied Thermal Engineering

JF - Applied Thermal Engineering

SN - 1359-4311

ER -