Application of artificial neural networks for the wind power prediction in Nakhon Pathom

Abstract

This paper uses weather data from the Thai Meteorological Department (TMD), Nakhon Pathom Weather
Station [1]. Weather information includes wind speed, wind direction, temperature, humidity, and atmospheric
pressure. Average data sets were collected on daily basis for 9 months, from January 2017 to September 2017 and converted to a database. Artificial neural networks (ANN) are used to estimate wind power. The mean square error (MSE) is used for measured ANN performance. The experimental results show that the topology of the 3 neurons in the input, 10 neurons in the hidden layer, and a neuron node output is trained by Levenberg–Marquardt algorithm (LM). It has maximum regression and minimum MSE.