Neural Network modelling for prediction of energy in hybrid renewable energy systems
J. Femila Roseline, D. Dhanya, Saravana Selvan, M. Yuvaraj, P. Duraipandy, S. Sandeep Kumar, A. Rajendra Prasad, Ravishankar Sathyamurthy, V. Mohanavel
Abstract
When it comes to the expansion of the renewable energy business in today technological age, the ability to predict power and energy output based on shifting weather patterns is crucial. It is possible to support and even improve an economy and quality of life by using renewable energy sources rather than traditional fossil fuels, rather than by using fossil fuels at all. Because global warming and climate change are posing serious challenges to our planet, the findings of this study may be valuable in the development of smart grids that can properly predict future weather conditions. In this study, we develop an artificial neural network (ANN) model to estimate the energy generated at PV and the energy from the hybrid PV and wind energy systems considering several weather factors. The modelling is conducted to potentially predict the energy generation. The results shows that the proposed classifier is efficient in terms of reduced mean squared error with increased accuracy than other methods.