TY - JOUR

T1 - Comparison and explanation of forecasting algorithms for energy time series

AU - Zhang, Yuyi

AU - Ma, Ruimin

AU - Liu, Jing

AU - Liu, Xiuxiu

AU - Petrosian, Ovanes

AU - Krinkin, Kirill

N1 - Publisher Copyright: © 2021 by the authors. Licensee MDPI, Basel, Switzerland.

PY - 2021/11/1

Y1 - 2021/11/1

N2 - 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.

AB - 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.

KW - Ensemble model

KW - Explainable AI

KW - Neural network

KW - Time series forecasting

UR - http://www.scopus.com/inward/record.url?scp=85118692127&partnerID=8YFLogxK

U2 - 10.3390/math9212794

DO - 10.3390/math9212794

M3 - Article

AN - SCOPUS:85118692127

VL - 9

JO - Mathematics

JF - Mathematics

SN - 2227-7390

IS - 21

M1 - 2794

ER -