Office Building’s Occupancy Prediction Using Extreme Learning Machine Model with Different Optimization Algorithms

Increasing energy efficiency requirements lead to lower energy consumption in buildings, but at the same time occupants’ influence on the energy balance of the building during the use phase becomes more crucial. The randomness of the building’s occupancy often leads to the mismatch of the predicted...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Motuzienė Violeta, Bielskus Jonas, Lapinskienė Vilūnė, Rynkun Genrika
Formato:	article
Lenguaje:	EN
Publicado:	Sciendo 2021
Materias:	co2 (carbon dioxide) genetic algorithm (ga) office simulated annealing (sa) Renewable energy sources TJ807-830
Acceso en línea:	https://doaj.org/article/7f2a437f108047ecbf0bc2afdc064e1f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7f2a437f108047ecbf0bc2afdc064e1f
record_format	dspace
spelling	oai:doaj.org-article:7f2a437f108047ecbf0bc2afdc064e1f2021-12-05T14:11:11ZOffice Building’s Occupancy Prediction Using Extreme Learning Machine Model with Different Optimization Algorithms2255-883710.2478/rtuect-2021-0038https://doaj.org/article/7f2a437f108047ecbf0bc2afdc064e1f2021-01-01T00:00:00Zhttps://doi.org/10.2478/rtuect-2021-0038https://doaj.org/toc/2255-8837Increasing energy efficiency requirements lead to lower energy consumption in buildings, but at the same time occupants’ influence on the energy balance of the building during the use phase becomes more crucial. The randomness of the building’s occupancy often leads to the mismatch of the predicted and measured energy demand, also called Energy Performance Gap. Therefore, prediction of occupancy is important both in the design and use phases of the building. The goal of the study is to apply Extreme Learning Machine (ELM) models with different optimisation algorithms – Genetic (GA-ELM) and Simulated Annealing (SA–ELM) for occupancy prediction in an office building based on measured CO2 concentrations. Both models show similar and high accuracy of prediction: R2 – 0.73–0.74 and RMSE – 1.8–1.9 for the whole measured period. Influence of population size, number of neurons, and number of iterations on results accuracy was also analysed and recommendations are given. It was concluded that both methods are suitable for occupancy prediction, but because of different simulation times, SA-ELM is recommended for the Building Management Systems (BMS), where higher speed is required.Motuzienė VioletaBielskus JonasLapinskienė VilūnėRynkun GenrikaSciendoarticleco2 (carbon dioxide)genetic algorithm (ga)officesimulated annealing (sa)Renewable energy sourcesTJ807-830ENEnvironmental and Climate Technologies, Vol 25, Iss 1, Pp 525-536 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	co2 (carbon dioxide) genetic algorithm (ga) office simulated annealing (sa) Renewable energy sources TJ807-830
spellingShingle	co2 (carbon dioxide) genetic algorithm (ga) office simulated annealing (sa) Renewable energy sources TJ807-830 Motuzienė Violeta Bielskus Jonas Lapinskienė Vilūnė Rynkun Genrika Office Building’s Occupancy Prediction Using Extreme Learning Machine Model with Different Optimization Algorithms
description	Increasing energy efficiency requirements lead to lower energy consumption in buildings, but at the same time occupants’ influence on the energy balance of the building during the use phase becomes more crucial. The randomness of the building’s occupancy often leads to the mismatch of the predicted and measured energy demand, also called Energy Performance Gap. Therefore, prediction of occupancy is important both in the design and use phases of the building. The goal of the study is to apply Extreme Learning Machine (ELM) models with different optimisation algorithms – Genetic (GA-ELM) and Simulated Annealing (SA–ELM) for occupancy prediction in an office building based on measured CO2 concentrations. Both models show similar and high accuracy of prediction: R2 – 0.73–0.74 and RMSE – 1.8–1.9 for the whole measured period. Influence of population size, number of neurons, and number of iterations on results accuracy was also analysed and recommendations are given. It was concluded that both methods are suitable for occupancy prediction, but because of different simulation times, SA-ELM is recommended for the Building Management Systems (BMS), where higher speed is required.
format	article
author	Motuzienė Violeta Bielskus Jonas Lapinskienė Vilūnė Rynkun Genrika
author_facet	Motuzienė Violeta Bielskus Jonas Lapinskienė Vilūnė Rynkun Genrika
author_sort	Motuzienė Violeta
title	Office Building’s Occupancy Prediction Using Extreme Learning Machine Model with Different Optimization Algorithms
title_short	Office Building’s Occupancy Prediction Using Extreme Learning Machine Model with Different Optimization Algorithms
title_full	Office Building’s Occupancy Prediction Using Extreme Learning Machine Model with Different Optimization Algorithms
title_fullStr	Office Building’s Occupancy Prediction Using Extreme Learning Machine Model with Different Optimization Algorithms
title_full_unstemmed	Office Building’s Occupancy Prediction Using Extreme Learning Machine Model with Different Optimization Algorithms
title_sort	office building’s occupancy prediction using extreme learning machine model with different optimization algorithms
publisher	Sciendo
publishDate	2021
url	https://doaj.org/article/7f2a437f108047ecbf0bc2afdc064e1f
work_keys_str_mv	AT motuzienevioleta officebuildingsoccupancypredictionusingextremelearningmachinemodelwithdifferentoptimizationalgorithms AT bielskusjonas officebuildingsoccupancypredictionusingextremelearningmachinemodelwithdifferentoptimizationalgorithms AT lapinskienevilune officebuildingsoccupancypredictionusingextremelearningmachinemodelwithdifferentoptimizationalgorithms AT rynkungenrika officebuildingsoccupancypredictionusingextremelearningmachinemodelwithdifferentoptimizationalgorithms
_version_	1718371307155881984

Office Building’s Occupancy Prediction Using Extreme Learning Machine Model with Different Optimization Algorithms

Ejemplares similares