Abstract
Load forecasting models are of great importance in Electricity Markets and a wide range of techniques have been developed according to the objective being pursued. The increase of smart meters in different sectors (residential, commercial, universities, etc.) allows accessing the electricity consumption nearly in real time and provides those customers with large datasets that contain valuable information. In this context, supervised machine learning methods play an essential role. The purpose of the present study is to evaluate the effectiveness of using ensemble methods based on regression trees in short-term load forecasting. To illustrate this task, four methods (bagging, random forest, conditional forest, and boosting) are applied to historical load data of a campus university in Cartagena (Spain). In addition to temperature, calendar variables as well as different types of special days are considered as predictors to improve the predictions. Finally, a real application to the Spanish Electricity Market is developed: 48-h-ahead predictions are used to evaluate the economical savings that the consumer (the campus university) can obtain through the participation as a direct market consumer instead of purchasing the electricity from a retailer.
Highlights
Load forecasting has been a topic of interest for many decades and the literature is plenty with a wide variety of techniques
We propose the using of a particular set of supervised machine learning techniques to predict the hourly electricity consumption of university buildings
We will focus on 48-h-ahead predictions in order to apply them to the context of Direct Market Consumers, different prediction horizons will be considered for the case of XGBoost method
Summary
Load forecasting has been a topic of interest for many decades and the literature is plenty with a wide variety of techniques. Forecasting methods can be divided into three different categories: time-series approaches, regression based, and artificial intelligence methods (see [1]). Regression approaches, see [2,6], are widely used in the field of short-term and medium-term load forecasting, including non-linear regression [7] and nonparametric regression [8]. Several machine learning or computational intelligence techniques have been applied in the field of Short Term Load Forecasting. We propose the using of a particular set of supervised machine learning techniques (called ensemble methods based on decision trees) to predict the hourly electricity consumption of university buildings. There some recent literature regarding random forest and short-term load
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
