Extreme learning machine for prediction of heat load in district heating systems

Shahin Sajjadi, Shahaboddin Shamshirband, Meysam Alizamir, Por Lip Yee, Zulkefli Mansor, Azizah Abdul Manaf, Torki A. Altameem, Ali Mostafaeipour

Research output: Contribution to journalArticle

63 Citations (Scopus)

Abstract

District heating systems are important utility systems. If these systems are properly managed, they can ensure economic and environmental friendly provision of heat to connected customers. Potentials for further improvement of district heating systems' operation lie in improvement of present control strategies. One of the options is introduction of model predictive control. Multistep ahead predictive models of consumers' heat load are starting point for creating successful model predictive strategy. In this article, short-term, multistep ahead predictive models of heat load of consumer attached to district heating system were created. Models were developed using the novel method based on Extreme Learning Machine (ELM). Nine different ELM predictive models, for time horizon from 1 to 24 h ahead, were developed. Estimation and prediction results of ELM models were compared with genetic programming (GP) and artificial neural networks (ANNs) models. The experimental results show that an improvement in predictive accuracy and capability of generalization can be achieved by the ELM approach in comparison with GP and ANN. Moreover, achieved results indicate that developed ELM models can be used with confidence for further work on formulating novel model predictive strategy in district heating systems. The experimental results show that the new algorithm can produce good generalization performance in most cases and can learn thousands of times faster than conventional popular learning algorithms.

Original languageEnglish
Pages (from-to)222-227
Number of pages6
JournalEnergy and Buildings
Volume122
DOIs
Publication statusPublished - 15 Jun 2016

Fingerprint

District heating
Thermal load
Learning systems
Genetic programming
Neural networks
Model predictive control
Learning algorithms
Economics

Keywords

  • District heating systems
  • Estimation
  • Extreme Learning Machine (ELM)
  • Heat load
  • Prediction

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction
  • Mechanical Engineering
  • Electrical and Electronic Engineering

Cite this

Sajjadi, S., Shamshirband, S., Alizamir, M., Yee, P. L., Mansor, Z., Manaf, A. A., ... Mostafaeipour, A. (2016). Extreme learning machine for prediction of heat load in district heating systems. Energy and Buildings, 122, 222-227. https://doi.org/10.1016/j.enbuild.2016.04.021

Extreme learning machine for prediction of heat load in district heating systems. / Sajjadi, Shahin; Shamshirband, Shahaboddin; Alizamir, Meysam; Yee, Por Lip; Mansor, Zulkefli; Manaf, Azizah Abdul; Altameem, Torki A.; Mostafaeipour, Ali.

In: Energy and Buildings, Vol. 122, 15.06.2016, p. 222-227.

Research output: Contribution to journalArticle

Sajjadi, S, Shamshirband, S, Alizamir, M, Yee, PL, Mansor, Z, Manaf, AA, Altameem, TA & Mostafaeipour, A 2016, 'Extreme learning machine for prediction of heat load in district heating systems', Energy and Buildings, vol. 122, pp. 222-227. https://doi.org/10.1016/j.enbuild.2016.04.021
Sajjadi, Shahin ; Shamshirband, Shahaboddin ; Alizamir, Meysam ; Yee, Por Lip ; Mansor, Zulkefli ; Manaf, Azizah Abdul ; Altameem, Torki A. ; Mostafaeipour, Ali. / Extreme learning machine for prediction of heat load in district heating systems. In: Energy and Buildings. 2016 ; Vol. 122. pp. 222-227.
@article{fec9dcde4d7140438560719316bc295c,
title = "Extreme learning machine for prediction of heat load in district heating systems",
abstract = "District heating systems are important utility systems. If these systems are properly managed, they can ensure economic and environmental friendly provision of heat to connected customers. Potentials for further improvement of district heating systems' operation lie in improvement of present control strategies. One of the options is introduction of model predictive control. Multistep ahead predictive models of consumers' heat load are starting point for creating successful model predictive strategy. In this article, short-term, multistep ahead predictive models of heat load of consumer attached to district heating system were created. Models were developed using the novel method based on Extreme Learning Machine (ELM). Nine different ELM predictive models, for time horizon from 1 to 24 h ahead, were developed. Estimation and prediction results of ELM models were compared with genetic programming (GP) and artificial neural networks (ANNs) models. The experimental results show that an improvement in predictive accuracy and capability of generalization can be achieved by the ELM approach in comparison with GP and ANN. Moreover, achieved results indicate that developed ELM models can be used with confidence for further work on formulating novel model predictive strategy in district heating systems. The experimental results show that the new algorithm can produce good generalization performance in most cases and can learn thousands of times faster than conventional popular learning algorithms.",
keywords = "District heating systems, Estimation, Extreme Learning Machine (ELM), Heat load, Prediction",
author = "Shahin Sajjadi and Shahaboddin Shamshirband and Meysam Alizamir and Yee, {Por Lip} and Zulkefli Mansor and Manaf, {Azizah Abdul} and Altameem, {Torki A.} and Ali Mostafaeipour",
year = "2016",
month = "6",
day = "15",
doi = "10.1016/j.enbuild.2016.04.021",
language = "English",
volume = "122",
pages = "222--227",
journal = "Energy and Buildings",
issn = "0378-7788",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Extreme learning machine for prediction of heat load in district heating systems

AU - Sajjadi, Shahin

AU - Shamshirband, Shahaboddin

AU - Alizamir, Meysam

AU - Yee, Por Lip

AU - Mansor, Zulkefli

AU - Manaf, Azizah Abdul

AU - Altameem, Torki A.

AU - Mostafaeipour, Ali

PY - 2016/6/15

Y1 - 2016/6/15

N2 - District heating systems are important utility systems. If these systems are properly managed, they can ensure economic and environmental friendly provision of heat to connected customers. Potentials for further improvement of district heating systems' operation lie in improvement of present control strategies. One of the options is introduction of model predictive control. Multistep ahead predictive models of consumers' heat load are starting point for creating successful model predictive strategy. In this article, short-term, multistep ahead predictive models of heat load of consumer attached to district heating system were created. Models were developed using the novel method based on Extreme Learning Machine (ELM). Nine different ELM predictive models, for time horizon from 1 to 24 h ahead, were developed. Estimation and prediction results of ELM models were compared with genetic programming (GP) and artificial neural networks (ANNs) models. The experimental results show that an improvement in predictive accuracy and capability of generalization can be achieved by the ELM approach in comparison with GP and ANN. Moreover, achieved results indicate that developed ELM models can be used with confidence for further work on formulating novel model predictive strategy in district heating systems. The experimental results show that the new algorithm can produce good generalization performance in most cases and can learn thousands of times faster than conventional popular learning algorithms.

AB - District heating systems are important utility systems. If these systems are properly managed, they can ensure economic and environmental friendly provision of heat to connected customers. Potentials for further improvement of district heating systems' operation lie in improvement of present control strategies. One of the options is introduction of model predictive control. Multistep ahead predictive models of consumers' heat load are starting point for creating successful model predictive strategy. In this article, short-term, multistep ahead predictive models of heat load of consumer attached to district heating system were created. Models were developed using the novel method based on Extreme Learning Machine (ELM). Nine different ELM predictive models, for time horizon from 1 to 24 h ahead, were developed. Estimation and prediction results of ELM models were compared with genetic programming (GP) and artificial neural networks (ANNs) models. The experimental results show that an improvement in predictive accuracy and capability of generalization can be achieved by the ELM approach in comparison with GP and ANN. Moreover, achieved results indicate that developed ELM models can be used with confidence for further work on formulating novel model predictive strategy in district heating systems. The experimental results show that the new algorithm can produce good generalization performance in most cases and can learn thousands of times faster than conventional popular learning algorithms.

KW - District heating systems

KW - Estimation

KW - Extreme Learning Machine (ELM)

KW - Heat load

KW - Prediction

UR - http://www.scopus.com/inward/record.url?scp=84971607430&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84971607430&partnerID=8YFLogxK

U2 - 10.1016/j.enbuild.2016.04.021

DO - 10.1016/j.enbuild.2016.04.021

M3 - Article

AN - SCOPUS:84971607430

VL - 122

SP - 222

EP - 227

JO - Energy and Buildings

JF - Energy and Buildings

SN - 0378-7788

ER -