TY - JOUR
T1 - Short-term electricity load forecasting with machine learning
AU - Aguilar Madrid, Ernesto
AU - António, Nuno
N1 - Aguilar Madrid, E., & Antonio, N. (2021). Short-term electricity load forecasting with machine learning. Information (Switzerland), 12(2), 1-21. [50]. https://doi.org/10.3390/info12020050
PY - 2021/2/20
Y1 - 2021/2/20
N2 - An accurate short-term load forecasting (STLF) is one of the most critical inputs for power plant units’ planning commitment. STLF reduces the overall planning uncertainty added by the intermittent production of renewable sources; thus, it helps to minimize the hydrothermal electricity production costs in a power grid. Although there is some research in the field and even several research applications, there is a continual need to improve forecasts. This research proposes a set of machine learning (ML) models to improve the accuracy of 168 h forecasts. The developed models employ features from multiple sources, such as historical load, weather, and holidays. Of the five ML models developed and tested in various load profile contexts, the Extreme Gradient Boosting Regressor (XGBoost) algorithm showed the best results, surpassing previous historical weekly predictions based on neural networks. Additionally, because XGBoost models are based on an ensemble of decision trees, it facilitated the model’s interpretation, which provided a relevant additional result, the features’ importance in the forecasting.
AB - An accurate short-term load forecasting (STLF) is one of the most critical inputs for power plant units’ planning commitment. STLF reduces the overall planning uncertainty added by the intermittent production of renewable sources; thus, it helps to minimize the hydrothermal electricity production costs in a power grid. Although there is some research in the field and even several research applications, there is a continual need to improve forecasts. This research proposes a set of machine learning (ML) models to improve the accuracy of 168 h forecasts. The developed models employ features from multiple sources, such as historical load, weather, and holidays. Of the five ML models developed and tested in various load profile contexts, the Extreme Gradient Boosting Regressor (XGBoost) algorithm showed the best results, surpassing previous historical weekly predictions based on neural networks. Additionally, because XGBoost models are based on an ensemble of decision trees, it facilitated the model’s interpretation, which provided a relevant additional result, the features’ importance in the forecasting.
KW - Electricity
KW - Electricity market
KW - Machine learning
KW - Short-term load forecasting
KW - Weekly forecast
UR - http://www.scopus.com/inward/record.url?scp=85100582142&partnerID=8YFLogxK
UR - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS_CPL&DestLinkType=FullRecord&UT=WOS:000622570500001
UR - http://doi.org/10.17632/tcmmj4t6f4.1
U2 - 10.3390/info12020050
DO - 10.3390/info12020050
M3 - Article
AN - SCOPUS:85100582142
SN - 2078-2489
VL - 12
SP - 1
EP - 21
JO - Information (Switzerland)
JF - Information (Switzerland)
IS - 2
M1 - 50
ER -