Abstract
Solar energy forecasting is an active research problem and a key issue to increase the competitiveness of solar power plants in the energy market. However, using meteorological, production, or irradiance data from the past is not enough to produce accurate forecasts. This article aims to integrate a prediction algorithm (Smart Persistence), irradiance, and past production data, using a state-of-the-art machine learning technique (Random Forests). Three years of data from six solar PV modules at Faro (Portugal) are analyzed. A set of features that combines past data, predictions, averages, and variances is proposed for training and validation. The experimental results show that using Smart Persistence as a Machine Learning input greatly improves the accuracy of short-term forecasts, achieving an NRMSE of 0.25 on the best panels at short horizons and 0.33 on a 6 h horizon.
Highlights
Solar energy forecasting is a key issue in the development of renewable energy sources
Machine learning is playing an important role in the development of many new technologies, and solar forecasting techniques are no exception
The main advantage of machine learning algorithms is the automatic detection of hidden patterns in large amounts of data, allowing the identification of unknown synergies and integration of varied sources of information
Summary
Solar energy forecasting is a key issue in the development of renewable energy sources. Improving the reliability and accuracy of forecasts can increase the competitiveness of solar electricity in power markets. Several methods have been proposed in recent years aiming to improve the accuracy of forecasts [1] and the solar photovoltaic grid efficiency [2,3,4,5]. Machine learning is playing an important role in the development of many new technologies, and solar forecasting techniques are no exception. Forecasting solar resources requires addressing several challenges [6]. Many advances have been made applying machine learning techniques [7,8] to solar forecasting. The main advantage of machine learning algorithms is the automatic detection of hidden patterns in large amounts of data, allowing the identification of unknown synergies and integration of varied sources of information
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.
