Forecasting the Performance of a Photovoltaic Solar System Installed in other Locations using Artificial Neural Networks. Issue 1 (20th January 2020)

• Record Type: Journal Article
• Authors: Rocha, Amanda Suianny Fernandes; Guerra, Fabiana Karla de O. M. V.; Vale, Marcelo Roberto Bastos Guerra
• Is Part Of: Electric power components and systems. Volume 48:Issue 1/2(2020)
• Page Start: 201
• Page End: 212
• Publication Date: 2020-01-20
• Subjects: solar photovoltaic system -- solar irradiation -- artificial neural network -- feedforward -- power forecasting -- energy efficiency -- distributed generation -- renewable energy -- electrical systems -- root mean square error; Electric machinery -- Periodicals; 621.3104205
• DOI: 10.1080/15325008.2020.1736211
• Languages: English
• ISSNs: 1532-5008

Abstract

Abstract: Photovoltaic solar energy has been spread all over the world, and in Brazil this energy source has been getting considerable space in the last years, being driven mainly by the energy crises. However, when installed in regions with low incidence of solar irradiation, this technology presents a loss of efficiency in the generation of energy. As an alternative to this consideration, a power prediction study could be conducted prior to its installation, based on local climate information that directly influences power generation, verifying the feasibility of system implementation and avoiding unrewarded investment. Therefore, the objective of this work is to predict the viability of the installation of a photovoltaic system of 3kWp in different places, with the assist of an Artificial Neural Network. Thus, the feedforward network was used for the training, being trained and validated with the support of Matlab ®, and inserting samples of temperature and solar irradiation as input variables. Through the performance methods, the results are favorable for this application, presenting validations with RMSE% in the range of 13-20% and R of not less than 0.93. The predictions presented RMSE% around 19-25% and average powers close to the real values generated by the PV system.