Heat demand forecasting in District Heating Network using XGBoost algorithm

Forecasting an hourly heat demand during different periods of district heating network operation is essential to optimize heat production in the CHP plant. The paper presents the heat demand model in the real district heating system with a peak load of 200 MW. The predictive model was developed with...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Bujalski Maciej, Madejski Paweł, Fuzowski Krzysztof
Formato:	article
Lenguaje:	EN FR
Publicado:	EDP Sciences 2021
Materias:	Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/81c8026fe87040349a1deb42d6ddc4dd
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:81c8026fe87040349a1deb42d6ddc4dd
record_format	dspace
spelling	oai:doaj.org-article:81c8026fe87040349a1deb42d6ddc4dd2021-11-12T11:44:46ZHeat demand forecasting in District Heating Network using XGBoost algorithm2267-124210.1051/e3sconf/202132300004https://doaj.org/article/81c8026fe87040349a1deb42d6ddc4dd2021-01-01T00:00:00Zhttps://www.e3s-conferences.org/articles/e3sconf/pdf/2021/99/e3sconf_mpsu2021_00004.pdfhttps://doaj.org/toc/2267-1242Forecasting an hourly heat demand during different periods of district heating network operation is essential to optimize heat production in the CHP plant. The paper presents the heat demand model in the real district heating system with a peak load of 200 MW. The predictive model was developed with the use of the machine learning method based on the historical data. The XGBoost (Extreme Gradient Boosting) algorithm was applied to find the relation between actual heat demand and predictors such as weather data and behavioral parameters like an hour of the day, day of week, and month. The method of model training and evaluating was discussed. The results were assessed by comparing hourly heat demand forecasts with actual values from a measuring system located in the CHP plant. The RMSE and MAPE error for the analysed time period were calculated and then benchmarked with an exponential regression model supplied with ambient air temperature. It was found that the machine learning method allows to obtain more accurate results due to the incorporation of additional predictors. The MAPE and RMSE for the XGBoost model in the day-ahead horizon were 6.9% and 8.7MW, respectively.Bujalski MaciejMadejski PawełFuzowski KrzysztofEDP SciencesarticleEnvironmental sciencesGE1-350ENFRE3S Web of Conferences, Vol 323, p 00004 (2021)
institution	DOAJ
collection	DOAJ
language	EN FR
topic	Environmental sciences GE1-350
spellingShingle	Environmental sciences GE1-350 Bujalski Maciej Madejski Paweł Fuzowski Krzysztof Heat demand forecasting in District Heating Network using XGBoost algorithm
description	Forecasting an hourly heat demand during different periods of district heating network operation is essential to optimize heat production in the CHP plant. The paper presents the heat demand model in the real district heating system with a peak load of 200 MW. The predictive model was developed with the use of the machine learning method based on the historical data. The XGBoost (Extreme Gradient Boosting) algorithm was applied to find the relation between actual heat demand and predictors such as weather data and behavioral parameters like an hour of the day, day of week, and month. The method of model training and evaluating was discussed. The results were assessed by comparing hourly heat demand forecasts with actual values from a measuring system located in the CHP plant. The RMSE and MAPE error for the analysed time period were calculated and then benchmarked with an exponential regression model supplied with ambient air temperature. It was found that the machine learning method allows to obtain more accurate results due to the incorporation of additional predictors. The MAPE and RMSE for the XGBoost model in the day-ahead horizon were 6.9% and 8.7MW, respectively.
format	article
author	Bujalski Maciej Madejski Paweł Fuzowski Krzysztof
author_facet	Bujalski Maciej Madejski Paweł Fuzowski Krzysztof
author_sort	Bujalski Maciej
title	Heat demand forecasting in District Heating Network using XGBoost algorithm
title_short	Heat demand forecasting in District Heating Network using XGBoost algorithm
title_full	Heat demand forecasting in District Heating Network using XGBoost algorithm
title_fullStr	Heat demand forecasting in District Heating Network using XGBoost algorithm
title_full_unstemmed	Heat demand forecasting in District Heating Network using XGBoost algorithm
title_sort	heat demand forecasting in district heating network using xgboost algorithm
publisher	EDP Sciences
publishDate	2021
url	https://doaj.org/article/81c8026fe87040349a1deb42d6ddc4dd
work_keys_str_mv	AT bujalskimaciej heatdemandforecastingindistrictheatingnetworkusingxgboostalgorithm AT madejskipaweł heatdemandforecastingindistrictheatingnetworkusingxgboostalgorithm AT fuzowskikrzysztof heatdemandforecastingindistrictheatingnetworkusingxgboostalgorithm
_version_	1718430561980121088

Heat demand forecasting in District Heating Network using XGBoost algorithm

Ejemplares similares