Machine learning for estimation of building energy consumption and performance

a review

Saleh Seyedzadeh, Farzad Rahimian, Ivan Glesk, Marc Roper

Research output: Contribution to journalArticleResearchpeer-review

11 Downloads (Pure)

Abstract

Ever growing population and progressive municipal business demands for constructing new buildings are known as the foremost contributor to greenhouse gasses. Therefore, improvement of energy eciency of the building sector has become an essential target to reduce the amount of gas emission as well as fossil fuel consumption. One most eective approach to reducing CO2 emission and energy consumption with regards to new buildings is to consider energy eciency at a very early design stage. On the other hand, ecient energy management and smart refurbishments can enhance energy performance of the existing stock. All these solutions entail accurate energy prediction for optimal decision making. In recent years, articial intelligence (AI) in general and machine learning (ML) techniques in specic terms have been proposed for forecasting of building energy consumption and performance. This paperprovides a substantial review on the four main ML approaches including articial neural network, support vector machine, Gaussian-based regressions and clustering, which have commonly been applied in forecasting and improving building energy performance.
Original languageEnglish
JournalVisualization in Engineering
DOIs
Publication statusPublished - 31 Dec 2018

Fingerprint

Energy Consumption
Learning systems
Machine Learning
Energy utilization
Energy
Greenhouses
Energy management
Forecasting
Gas emissions
Fossil fuels
Fuel consumption
Support vector machines
Decision making
Greenhouse
Energy Management
Neural networks
Support Vector Machine
Sector
Regression
Decision Making

Cite this

@article{33a0a81be4d142e7b909519befc9a9ba,
title = "Machine learning for estimation of building energy consumption and performance: a review",
abstract = "Ever growing population and progressive municipal business demands for constructing new buildings are known as the foremost contributor to greenhouse gasses. Therefore, improvement of energy eciency of the building sector has become an essential target to reduce the amount of gas emission as well as fossil fuel consumption. One most eective approach to reducing CO2 emission and energy consumption with regards to new buildings is to consider energy eciency at a very early design stage. On the other hand, ecient energy management and smart refurbishments can enhance energy performance of the existing stock. All these solutions entail accurate energy prediction for optimal decision making. In recent years, articial intelligence (AI) in general and machine learning (ML) techniques in specic terms have been proposed for forecasting of building energy consumption and performance. This paperprovides a substantial review on the four main ML approaches including articial neural network, support vector machine, Gaussian-based regressions and clustering, which have commonly been applied in forecasting and improving building energy performance.",
author = "Saleh Seyedzadeh and Farzad Rahimian and Ivan Glesk and Marc Roper",
year = "2018",
month = "12",
day = "31",
doi = "10.1186/s40327-018-0064-7",
language = "English",
journal = "Visualization in Engineering",
issn = "2213-7459",
publisher = "Springer Open",

}

Machine learning for estimation of building energy consumption and performance : a review. / Seyedzadeh, Saleh; Rahimian, Farzad; Glesk, Ivan; Roper, Marc.

In: Visualization in Engineering, 31.12.2018.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Machine learning for estimation of building energy consumption and performance

T2 - a review

AU - Seyedzadeh, Saleh

AU - Rahimian, Farzad

AU - Glesk, Ivan

AU - Roper, Marc

PY - 2018/12/31

Y1 - 2018/12/31

N2 - Ever growing population and progressive municipal business demands for constructing new buildings are known as the foremost contributor to greenhouse gasses. Therefore, improvement of energy eciency of the building sector has become an essential target to reduce the amount of gas emission as well as fossil fuel consumption. One most eective approach to reducing CO2 emission and energy consumption with regards to new buildings is to consider energy eciency at a very early design stage. On the other hand, ecient energy management and smart refurbishments can enhance energy performance of the existing stock. All these solutions entail accurate energy prediction for optimal decision making. In recent years, articial intelligence (AI) in general and machine learning (ML) techniques in specic terms have been proposed for forecasting of building energy consumption and performance. This paperprovides a substantial review on the four main ML approaches including articial neural network, support vector machine, Gaussian-based regressions and clustering, which have commonly been applied in forecasting and improving building energy performance.

AB - Ever growing population and progressive municipal business demands for constructing new buildings are known as the foremost contributor to greenhouse gasses. Therefore, improvement of energy eciency of the building sector has become an essential target to reduce the amount of gas emission as well as fossil fuel consumption. One most eective approach to reducing CO2 emission and energy consumption with regards to new buildings is to consider energy eciency at a very early design stage. On the other hand, ecient energy management and smart refurbishments can enhance energy performance of the existing stock. All these solutions entail accurate energy prediction for optimal decision making. In recent years, articial intelligence (AI) in general and machine learning (ML) techniques in specic terms have been proposed for forecasting of building energy consumption and performance. This paperprovides a substantial review on the four main ML approaches including articial neural network, support vector machine, Gaussian-based regressions and clustering, which have commonly been applied in forecasting and improving building energy performance.

UR - https://pureportal.strath.ac.uk/en/publications/8a7ab0c4-e9f1-4da8-83db-51364a10b654

U2 - 10.1186/s40327-018-0064-7

DO - 10.1186/s40327-018-0064-7

M3 - Article

JO - Visualization in Engineering

JF - Visualization in Engineering

SN - 2213-7459

ER -