Machine learning models for prediction of building energy performance

Saleh Seyedzadeh; Farzad Pour Rahimian

doi:10.1007/978-3-030-64751-3_5

Machine learning models for prediction of building energy performance

Saleh Seyedzadeh, Farzad Pour Rahimian

School of Computing, Engineering & Digital Technologies

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

Abstract

This chapter investigates the accuracy of most popular ML models in the prediction of building heating and cooling loads carrying out specific tuning for each ML model and using two simulated building energy data. The use of grid search coupled with cross-validation method in examination of the model parameters is demonstrated. Furthermore, sensitivity analysis techniques are used to evaluate the importance of input variables on the performance of ML models. The accuracy and time complexity of models in predicting heating and cooling loads are demonstrated.

Original language	English
Title of host publication	Data-Driven Modelling of Non-Domestic Buildings Energy Performance
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	77-98
Number of pages	22
ISBN (Electronic)	9783030647513
ISBN (Print)	9783030647506
DOIs	https://doi.org/10.1007/978-3-030-64751-3_5
Publication status	Published - 16 Jan 2021

Publication series

Name	Green Energy and Technology
ISSN (Print)	1865-3529
ISSN (Electronic)	1865-3537

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.

Access to Document

10.1007/978-3-030-64751-3_5

Cite this

@inbook{9e677268d9c14a7c870ee101bbe057ca,

title = "Machine learning models for prediction of building energy performance",

abstract = "This chapter investigates the accuracy of most popular ML models in the prediction of building heating and cooling loads carrying out specific tuning for each ML model and using two simulated building energy data. The use of grid search coupled with cross-validation method in examination of the model parameters is demonstrated. Furthermore, sensitivity analysis techniques are used to evaluate the importance of input variables on the performance of ML models. The accuracy and time complexity of models in predicting heating and cooling loads are demonstrated.",

author = "Saleh Seyedzadeh and {Pour Rahimian}, Farzad",

year = "2021",

month = jan,

day = "16",

doi = "10.1007/978-3-030-64751-3_5",

language = "English",

isbn = "9783030647506",

series = "Green Energy and Technology",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "77--98",

booktitle = "Data-Driven Modelling of Non-Domestic Buildings Energy Performance",

address = "Germany",

}

TY - CHAP

T1 - Machine learning models for prediction of building energy performance

AU - Seyedzadeh, Saleh

AU - Pour Rahimian, Farzad

PY - 2021/1/16

Y1 - 2021/1/16

N2 - This chapter investigates the accuracy of most popular ML models in the prediction of building heating and cooling loads carrying out specific tuning for each ML model and using two simulated building energy data. The use of grid search coupled with cross-validation method in examination of the model parameters is demonstrated. Furthermore, sensitivity analysis techniques are used to evaluate the importance of input variables on the performance of ML models. The accuracy and time complexity of models in predicting heating and cooling loads are demonstrated.

AB - This chapter investigates the accuracy of most popular ML models in the prediction of building heating and cooling loads carrying out specific tuning for each ML model and using two simulated building energy data. The use of grid search coupled with cross-validation method in examination of the model parameters is demonstrated. Furthermore, sensitivity analysis techniques are used to evaluate the importance of input variables on the performance of ML models. The accuracy and time complexity of models in predicting heating and cooling loads are demonstrated.

UR - http://www.scopus.com/inward/record.url?scp=85101092894&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-64751-3_5

DO - 10.1007/978-3-030-64751-3_5

M3 - Chapter

AN - SCOPUS:85101092894

SN - 9783030647506

T3 - Green Energy and Technology

SP - 77

EP - 98

BT - Data-Driven Modelling of Non-Domestic Buildings Energy Performance

PB - Springer Science and Business Media Deutschland GmbH

ER -

Machine learning models for prediction of building energy performance

Abstract

Publication series

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this