Application of artificial neural networks for determining energy-efficient operating set-points of the VRF cooling system

Min Hee Chung, Young Kwon Yang, Kwang Ho Lee, Je Hyeon Lee, Jin Woo Moon

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

The aim of this study was to develop an Artificial Neural Network (ANN) model that can predict the amount of cooling energy consumption for the different settings of the variable refrigerant flow (VRF) cooling system's control variables. Matrix laboratory (MATLAB) and its neural network toolbox were used for the ANN model development and test performance. For the model training and performance evaluation, data sets were collected through the field measurement. Four steps were conducted in the development process: initial model development, input variable selection, model optimization, and performance evaluation. In the initial model development and input variable selection process, seven input variables were selected as input neurons: TEMPOUT, HUMIDOUT, TEMPIN, LOADCOOL, TEMPSA, TEMPCOND, and PRESCOND. In addition, the initial model was optimized to have 2 hidden layers, 15 hidden neurons in each hidden layer, a learning rate of 0.3, and a momentum of 0.3. The optimized model demonstrated its prediction accuracy within the recommended level, thus proved its potential for application in the control algorithm for creating a comfortable indoor thermal environment in an energy-efficient manner.

Original languageEnglish
Pages (from-to)77-87
Number of pages11
JournalBuilding and Environment
Volume125
DOIs
Publication statusPublished - 2017 Nov 15
Externally publishedYes

Fingerprint

Cooling systems
neural network
artificial neural network
Flow of fluids
development model
cooling
Neural networks
energy
performance
system control
optimization model
energy consumption
Neurons
data analysis
control system
momentum
learning
refrigerant
evaluation
matrix

Keywords

  • Artificial neural network
  • Condenser fluid pressure set-point
  • Condenser fluid temperature set-point
  • Predictive controls
  • Refrigeration evaporation temperature set-point
  • Supply air temperature set-point

ASJC Scopus subject areas

  • Environmental Engineering
  • Geography, Planning and Development
  • Civil and Structural Engineering
  • Building and Construction

Cite this

Application of artificial neural networks for determining energy-efficient operating set-points of the VRF cooling system. / Chung, Min Hee; Yang, Young Kwon; Lee, Kwang Ho; Lee, Je Hyeon; Moon, Jin Woo.

In: Building and Environment, Vol. 125, 15.11.2017, p. 77-87.

Research output: Contribution to journalArticle

@article{2c003e2d98254735a79065db3921b825,
title = "Application of artificial neural networks for determining energy-efficient operating set-points of the VRF cooling system",
abstract = "The aim of this study was to develop an Artificial Neural Network (ANN) model that can predict the amount of cooling energy consumption for the different settings of the variable refrigerant flow (VRF) cooling system's control variables. Matrix laboratory (MATLAB) and its neural network toolbox were used for the ANN model development and test performance. For the model training and performance evaluation, data sets were collected through the field measurement. Four steps were conducted in the development process: initial model development, input variable selection, model optimization, and performance evaluation. In the initial model development and input variable selection process, seven input variables were selected as input neurons: TEMPOUT, HUMIDOUT, TEMPIN, LOADCOOL, TEMPSA, TEMPCOND, and PRESCOND. In addition, the initial model was optimized to have 2 hidden layers, 15 hidden neurons in each hidden layer, a learning rate of 0.3, and a momentum of 0.3. The optimized model demonstrated its prediction accuracy within the recommended level, thus proved its potential for application in the control algorithm for creating a comfortable indoor thermal environment in an energy-efficient manner.",
keywords = "Artificial neural network, Condenser fluid pressure set-point, Condenser fluid temperature set-point, Predictive controls, Refrigeration evaporation temperature set-point, Supply air temperature set-point",
author = "Chung, {Min Hee} and Yang, {Young Kwon} and Lee, {Kwang Ho} and Lee, {Je Hyeon} and Moon, {Jin Woo}",
year = "2017",
month = "11",
day = "15",
doi = "10.1016/j.buildenv.2017.08.044",
language = "English",
volume = "125",
pages = "77--87",
journal = "Building and Environment",
issn = "0360-1323",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Application of artificial neural networks for determining energy-efficient operating set-points of the VRF cooling system

AU - Chung, Min Hee

AU - Yang, Young Kwon

AU - Lee, Kwang Ho

AU - Lee, Je Hyeon

AU - Moon, Jin Woo

PY - 2017/11/15

Y1 - 2017/11/15

N2 - The aim of this study was to develop an Artificial Neural Network (ANN) model that can predict the amount of cooling energy consumption for the different settings of the variable refrigerant flow (VRF) cooling system's control variables. Matrix laboratory (MATLAB) and its neural network toolbox were used for the ANN model development and test performance. For the model training and performance evaluation, data sets were collected through the field measurement. Four steps were conducted in the development process: initial model development, input variable selection, model optimization, and performance evaluation. In the initial model development and input variable selection process, seven input variables were selected as input neurons: TEMPOUT, HUMIDOUT, TEMPIN, LOADCOOL, TEMPSA, TEMPCOND, and PRESCOND. In addition, the initial model was optimized to have 2 hidden layers, 15 hidden neurons in each hidden layer, a learning rate of 0.3, and a momentum of 0.3. The optimized model demonstrated its prediction accuracy within the recommended level, thus proved its potential for application in the control algorithm for creating a comfortable indoor thermal environment in an energy-efficient manner.

AB - The aim of this study was to develop an Artificial Neural Network (ANN) model that can predict the amount of cooling energy consumption for the different settings of the variable refrigerant flow (VRF) cooling system's control variables. Matrix laboratory (MATLAB) and its neural network toolbox were used for the ANN model development and test performance. For the model training and performance evaluation, data sets were collected through the field measurement. Four steps were conducted in the development process: initial model development, input variable selection, model optimization, and performance evaluation. In the initial model development and input variable selection process, seven input variables were selected as input neurons: TEMPOUT, HUMIDOUT, TEMPIN, LOADCOOL, TEMPSA, TEMPCOND, and PRESCOND. In addition, the initial model was optimized to have 2 hidden layers, 15 hidden neurons in each hidden layer, a learning rate of 0.3, and a momentum of 0.3. The optimized model demonstrated its prediction accuracy within the recommended level, thus proved its potential for application in the control algorithm for creating a comfortable indoor thermal environment in an energy-efficient manner.

KW - Artificial neural network

KW - Condenser fluid pressure set-point

KW - Condenser fluid temperature set-point

KW - Predictive controls

KW - Refrigeration evaporation temperature set-point

KW - Supply air temperature set-point

UR - http://www.scopus.com/inward/record.url?scp=85028565466&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028565466&partnerID=8YFLogxK

U2 - 10.1016/j.buildenv.2017.08.044

DO - 10.1016/j.buildenv.2017.08.044

M3 - Article

AN - SCOPUS:85028565466

VL - 125

SP - 77

EP - 87

JO - Building and Environment

JF - Building and Environment

SN - 0360-1323

ER -