Solar Photovoltaic Energy Production Forecast Using Neural Networks. (2016)

• Record Type: Journal Article
• Authors: Dumitru, Cristian-Dragos; Gligor, Adrian; Enachescu, Calin
• Is Part Of: Procedia technology. Volume 22(2016)
• Page Start: 808
• Page End: 815
• Publication Date: 2016
• Subjects: renewable energy -- solar photovoltaic energy -- energy management -- energy forecast -- time-series data -- neural networks -- backpropagation.; Technology -- Congresses; Technology -- Periodicals; Engineering -- Congresses; Engineering -- Periodicals; Engineering; Technology; Conference proceedings; Periodicals; 605
• DOI: 10.1016/j.protcy.2016.01.053
• Languages: English
• ISSNs: 2212-0173

Abstract

Abstract: The management of renewable energy resources plays an important role in the availability, stability and energy quality in the modern power systems. A key role of the energy management policies is played by the primary resource availability adjustment to the required consumption. As the renewable energy resources are variable in time their forecast represents an important issue. In this paper is explored how the use of consecrated artificial intelligence techniques such as feed-forward and Elman neural networks are suitable for such energy production forecasting. The main reason is that artificial intelligence techniques offers a viable solution to correct the behavior of these systems while operating by learning the changes that occur as a result of power systems external and internal factors evolution. In this case the back-propagation learning algorithm was tested in different configurations of the neural networks to find an adequate solution for the specific datasets of solar photovoltaic renewable energy resource availability.