Open AccessImportant variable assessment and electricity price forecasting based on regression tree models: classification and regression trees, Bagging and Random Forests
Author(s) -
González Camino,
MiraMcWilliams José,
Juárez Isabel
Publication year - 2015
Publication title -
iet generation, transmission and distribution
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.92
H-Index - 110
eISSN - 1751-8695
pISSN - 1751-8687
DOI - 10.1049/iet-gtd.2014.0655
Subject(s) - random forest , regression , regression analysis , decision tree , econometrics , statistics , variable (mathematics) , tree (set theory) , computer science , machine learning , artificial intelligence , mathematics , mathematical analysis
Electricity price forecasting has become the focus of considerable interest in a deregulated energy market. In this study, regression tree‐based models: classification and regression trees, Bagging and Random Forests have been built and used to identify the variables dominating the marginal price of the commodity as well as for short‐term (one hour and day ahead) electricity price forecasting for the Spanish–Iberian market. Different prediction models are proposed including the main features of the market such as load, hydro and thermal generation and from available, wind energy production, of strategic interest in the Spanish market. In addition other explanatory variables are considered as lagged prices, as well as hour, day, month and year indicators. In the study, hourly data from 2000–2011 corresponding to 22 variables have been used. The results show the effectiveness of the proposed ensemble of tree‐based models which emerge as an alternative and promising tool, competitive with other existing methods.