A Bayesian Network model for predicting cooling load of commercial buildings

Sen Huang, Wangda Zuo, Michael D. Sohn

Research output: Contribution to journalArticle

  • 1 Citations

Abstract

Cooling load prediction is indispensable to many building energy saving strategies. In this paper, we proposed a new method for predicting the cooling load of commercial buildings. The proposed approach employs a Bayesian Network model to relate the cooling load to outdoor weather conditions and internal building activities. The proposed method is computationally efficient and implementable for use in real buildings, as it does not involve sophisticated mathematical theories. In this paper, we described the proposed method and demonstrated its use via a case study. In this case study, we considered three candidate models for cooling load prediction and they are the proposed Bayesian Network model, a Support Vector Machine model, and an Artificial Neural Network model. We trained the three models with fourteen different training data datasets, each of which had varying amounts and quality of data that were sampled on-site. The prediction results for a testing week shows that the Bayesian Network model achieves similar accuracy as the Support Vector Machine model but better accuracy than the Artificial Neural Network model. Notable in this comparison is that the training process of the Bayesian Network model is fifty-eight times faster than that of the Artificial Neural Network model. The results also suggest that all three models will have much larger prediction deviations if the testing data points are not covered by the training dataset for the studied case (The maximum absolute deviation of the predictions that are not covered by the training dataset can be up to seven times larger than that of the predictions covered by the training dataset). In addition, we also found the uncertainties in the weather forecast significantly affected the accuracy of the cooling load prediction for the studied case and the Support Vector Machine model was more sensitive to those uncertainties than the other two models.

LanguageEnglish (US)
Pages87-101
Number of pages15
JournalBuilding Simulation
Volume11
Issue number1
DOIs
StatePublished - Feb 1 2018

Fingerprint

Bayesian networks
Loads (forces)
Cooling
Support vector machines
Neural networks
Testing
Energy conservation

Keywords

  • Bayesian Network model
  • cooling load prediction
  • training dataset
  • uncertainties

ASJC Scopus subject areas

  • Building and Construction
  • Energy (miscellaneous)

Cite this

A Bayesian Network model for predicting cooling load of commercial buildings. / Huang, Sen; Zuo, Wangda; Sohn, Michael D.

In: Building Simulation, Vol. 11, No. 1, 01.02.2018, p. 87-101.

Research output: Contribution to journalArticle

Huang, Sen ; Zuo, Wangda ; Sohn, Michael D. / A Bayesian Network model for predicting cooling load of commercial buildings. In: Building Simulation. 2018 ; Vol. 11, No. 1. pp. 87-101.
@article{5238bc86627b4143b4c91a1bd99742da,
title = "A Bayesian Network model for predicting cooling load of commercial buildings",
abstract = "Cooling load prediction is indispensable to many building energy saving strategies. In this paper, we proposed a new method for predicting the cooling load of commercial buildings. The proposed approach employs a Bayesian Network model to relate the cooling load to outdoor weather conditions and internal building activities. The proposed method is computationally efficient and implementable for use in real buildings, as it does not involve sophisticated mathematical theories. In this paper, we described the proposed method and demonstrated its use via a case study. In this case study, we considered three candidate models for cooling load prediction and they are the proposed Bayesian Network model, a Support Vector Machine model, and an Artificial Neural Network model. We trained the three models with fourteen different training data datasets, each of which had varying amounts and quality of data that were sampled on-site. The prediction results for a testing week shows that the Bayesian Network model achieves similar accuracy as the Support Vector Machine model but better accuracy than the Artificial Neural Network model. Notable in this comparison is that the training process of the Bayesian Network model is fifty-eight times faster than that of the Artificial Neural Network model. The results also suggest that all three models will have much larger prediction deviations if the testing data points are not covered by the training dataset for the studied case (The maximum absolute deviation of the predictions that are not covered by the training dataset can be up to seven times larger than that of the predictions covered by the training dataset). In addition, we also found the uncertainties in the weather forecast significantly affected the accuracy of the cooling load prediction for the studied case and the Support Vector Machine model was more sensitive to those uncertainties than the other two models.",
keywords = "Bayesian Network model, cooling load prediction, training dataset, uncertainties",
author = "Sen Huang and Wangda Zuo and Sohn, {Michael D.}",
year = "2018",
month = "2",
day = "1",
doi = "10.1007/s12273-017-0382-z",
language = "English (US)",
volume = "11",
pages = "87--101",
journal = "Building Simulation",
issn = "1996-3599",
publisher = "Tsing Hua University",
number = "1",

}

TY - JOUR

T1 - A Bayesian Network model for predicting cooling load of commercial buildings

AU - Huang, Sen

AU - Zuo, Wangda

AU - Sohn, Michael D.

PY - 2018/2/1

Y1 - 2018/2/1

N2 - Cooling load prediction is indispensable to many building energy saving strategies. In this paper, we proposed a new method for predicting the cooling load of commercial buildings. The proposed approach employs a Bayesian Network model to relate the cooling load to outdoor weather conditions and internal building activities. The proposed method is computationally efficient and implementable for use in real buildings, as it does not involve sophisticated mathematical theories. In this paper, we described the proposed method and demonstrated its use via a case study. In this case study, we considered three candidate models for cooling load prediction and they are the proposed Bayesian Network model, a Support Vector Machine model, and an Artificial Neural Network model. We trained the three models with fourteen different training data datasets, each of which had varying amounts and quality of data that were sampled on-site. The prediction results for a testing week shows that the Bayesian Network model achieves similar accuracy as the Support Vector Machine model but better accuracy than the Artificial Neural Network model. Notable in this comparison is that the training process of the Bayesian Network model is fifty-eight times faster than that of the Artificial Neural Network model. The results also suggest that all three models will have much larger prediction deviations if the testing data points are not covered by the training dataset for the studied case (The maximum absolute deviation of the predictions that are not covered by the training dataset can be up to seven times larger than that of the predictions covered by the training dataset). In addition, we also found the uncertainties in the weather forecast significantly affected the accuracy of the cooling load prediction for the studied case and the Support Vector Machine model was more sensitive to those uncertainties than the other two models.

AB - Cooling load prediction is indispensable to many building energy saving strategies. In this paper, we proposed a new method for predicting the cooling load of commercial buildings. The proposed approach employs a Bayesian Network model to relate the cooling load to outdoor weather conditions and internal building activities. The proposed method is computationally efficient and implementable for use in real buildings, as it does not involve sophisticated mathematical theories. In this paper, we described the proposed method and demonstrated its use via a case study. In this case study, we considered three candidate models for cooling load prediction and they are the proposed Bayesian Network model, a Support Vector Machine model, and an Artificial Neural Network model. We trained the three models with fourteen different training data datasets, each of which had varying amounts and quality of data that were sampled on-site. The prediction results for a testing week shows that the Bayesian Network model achieves similar accuracy as the Support Vector Machine model but better accuracy than the Artificial Neural Network model. Notable in this comparison is that the training process of the Bayesian Network model is fifty-eight times faster than that of the Artificial Neural Network model. The results also suggest that all three models will have much larger prediction deviations if the testing data points are not covered by the training dataset for the studied case (The maximum absolute deviation of the predictions that are not covered by the training dataset can be up to seven times larger than that of the predictions covered by the training dataset). In addition, we also found the uncertainties in the weather forecast significantly affected the accuracy of the cooling load prediction for the studied case and the Support Vector Machine model was more sensitive to those uncertainties than the other two models.

KW - Bayesian Network model

KW - cooling load prediction

KW - training dataset

KW - uncertainties

UR - http://www.scopus.com/inward/record.url?scp=85037057898&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037057898&partnerID=8YFLogxK

U2 - 10.1007/s12273-017-0382-z

DO - 10.1007/s12273-017-0382-z

M3 - Article

VL - 11

SP - 87

EP - 101

JO - Building Simulation

T2 - Building Simulation

JF - Building Simulation

SN - 1996-3599

IS - 1

ER -