Comparison and Explanation of Forecasting Algorithms for Energy Time Series

In this work, energy time series forecasting competitions from the Schneider Company, the Kaggle Online platform, and the American society ASHRAE were considered. These competitions include power generation and building energy consumption forecasts. The datasets used in these competitions are based...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yuyi Zhang, Ruimin Ma, Jing Liu, Xiuxiu Liu, Ovanes Petrosian, Kirill Krinkin
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	time series forecasting ensemble model neural network explainable AI Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/2fe302a156b44f2b864533cda3e588c2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2fe302a156b44f2b864533cda3e588c2
record_format	dspace
spelling	oai:doaj.org-article:2fe302a156b44f2b864533cda3e588c22021-11-11T18:19:51ZComparison and Explanation of Forecasting Algorithms for Energy Time Series10.3390/math92127942227-7390https://doaj.org/article/2fe302a156b44f2b864533cda3e588c22021-11-01T00:00:00Zhttps://www.mdpi.com/2227-7390/9/21/2794https://doaj.org/toc/2227-7390In this work, energy time series forecasting competitions from the Schneider Company, the Kaggle Online platform, and the American society ASHRAE were considered. These competitions include power generation and building energy consumption forecasts. The datasets used in these competitions are based on reliable and real sensor records. In addition, exogenous variables are accurately added to the dataset. All of these ensure the richness of the information contained in the dataset, which is crucial for energy management. Therefore, (1) We choose to study forecast models suitable for energy management on these energy datasets; (2) Forecast models including popular algorithm structures such as neural network models and ensemble models. In addition, as an innovation, we introduce the Explainable AI method (SHAP) to explain models with excellent performance indicators, thereby strengthening its trust and transparency; (3) The results show that the performance of the integrated model in these competitions is more stable and efficient, and in the integrated model, the advantages of LightGBM are more obvious; (4) Through the interpretation of SHAP, we found that the lagging characteristics of the building area and target variables are important features.Yuyi ZhangRuimin MaJing LiuXiuxiu LiuOvanes PetrosianKirill KrinkinMDPI AGarticletime series forecastingensemble modelneural networkexplainable AIMathematicsQA1-939ENMathematics, Vol 9, Iss 2794, p 2794 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	time series forecasting ensemble model neural network explainable AI Mathematics QA1-939
spellingShingle	time series forecasting ensemble model neural network explainable AI Mathematics QA1-939 Yuyi Zhang Ruimin Ma Jing Liu Xiuxiu Liu Ovanes Petrosian Kirill Krinkin Comparison and Explanation of Forecasting Algorithms for Energy Time Series
description	In this work, energy time series forecasting competitions from the Schneider Company, the Kaggle Online platform, and the American society ASHRAE were considered. These competitions include power generation and building energy consumption forecasts. The datasets used in these competitions are based on reliable and real sensor records. In addition, exogenous variables are accurately added to the dataset. All of these ensure the richness of the information contained in the dataset, which is crucial for energy management. Therefore, (1) We choose to study forecast models suitable for energy management on these energy datasets; (2) Forecast models including popular algorithm structures such as neural network models and ensemble models. In addition, as an innovation, we introduce the Explainable AI method (SHAP) to explain models with excellent performance indicators, thereby strengthening its trust and transparency; (3) The results show that the performance of the integrated model in these competitions is more stable and efficient, and in the integrated model, the advantages of LightGBM are more obvious; (4) Through the interpretation of SHAP, we found that the lagging characteristics of the building area and target variables are important features.
format	article
author	Yuyi Zhang Ruimin Ma Jing Liu Xiuxiu Liu Ovanes Petrosian Kirill Krinkin
author_facet	Yuyi Zhang Ruimin Ma Jing Liu Xiuxiu Liu Ovanes Petrosian Kirill Krinkin
author_sort	Yuyi Zhang
title	Comparison and Explanation of Forecasting Algorithms for Energy Time Series
title_short	Comparison and Explanation of Forecasting Algorithms for Energy Time Series
title_full	Comparison and Explanation of Forecasting Algorithms for Energy Time Series
title_fullStr	Comparison and Explanation of Forecasting Algorithms for Energy Time Series
title_full_unstemmed	Comparison and Explanation of Forecasting Algorithms for Energy Time Series
title_sort	comparison and explanation of forecasting algorithms for energy time series
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/2fe302a156b44f2b864533cda3e588c2
work_keys_str_mv	AT yuyizhang comparisonandexplanationofforecastingalgorithmsforenergytimeseries AT ruiminma comparisonandexplanationofforecastingalgorithmsforenergytimeseries AT jingliu comparisonandexplanationofforecastingalgorithmsforenergytimeseries AT xiuxiuliu comparisonandexplanationofforecastingalgorithmsforenergytimeseries AT ovanespetrosian comparisonandexplanationofforecastingalgorithmsforenergytimeseries AT kirillkrinkin comparisonandexplanationofforecastingalgorithmsforenergytimeseries
_version_	1718431873407909888

Comparison and Explanation of Forecasting Algorithms for Energy Time Series

Ejemplares similares