Prediction of wind power with fuzzy logic and artificial neural networks

Nowadays, as technology develops, most countries in the world meet their energy needs from fossil fuels and nuclear power plants. However, due to the gradual decrease of these fuels and causing significant negative effects on the environment, the need to turn to alternative energy applications has come to the fore with academic studies on this subject. The development of renewable energy sources is important in terms of ensuring energy diversity and eliminating energy deficiency. Wind energy has become one of the most important forms of renewable energy. In order to use the potential of wind energy efficiently, the estimation of wind power is very important. Artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) have been proposed for the estimation of wind power. In the study, data sets were created by taking the wind speeds of the selected wind turbine, the power values it produces and the wind speed values of the Velimeşe region. By creating single-layer and multi-layer ANN models, the network was trained multiple times with different activation functions and different neuron numbers, and wind power estimation was made. In the ANFIS model, the number of membership functions is kept constant and wind power estimation is made using different membership functions. The errors reported in the created models are within acceptable limits, and it has been seen that the ANFIS model produces better results than the ANN model. This shows that ANFIS can be used for wind energy forecasting.