Proficiency Assessment of Adaptive Neuro-Fuzzy Inference System to Predict Wind Power: A Case Study of Malaysia

Abstract

Wind power prediction is necessary for proficiency assessment of a potential wind site and can improve the technical and economic integration of wind energy into the existing electricity grid. The aim of the study is to compare the analysis of the wind power prediction between Kuala Lumpur and Melaka in Malaysia for potential place selection of wind power generation. Field data are collected from two places in Malaysia over a period of three years each place from December 2013 to December 2015. The model has been developed by an Adaptive Neuro-Fuzzy Interface System (ANFIS). In addition, the utility of soft computing ANFIS has been applied for wind power prediction. It involves four input variable-temperature, humidity, pressure and wind speed and output variable wind power has done using MATLAB. To obtain wind power, wind speed is collected from the Meteorological Department of Malaysia. The proposed predicted model of ANFIS is clearly indicated high capability and reliability based on error values of estimated wind power. Therefore, ANFIS model shows excellent results in the analysis the mean absolute error (MAE), root means square error (RMSE), mean absolute percentage error (MAPE) and coefficient of determination (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ).