Study on wind energy forecasting of Quang Tri region using artificial neural networks NARX

Abstract

Quang Tri Province has a rich source of wind energy, but effectively harnessing this valuable resource requires consideration of several factors. One of these is wind forecast databases, which are crucial to optimizing wind energy utilization. The purpose of this study is to develop a wind speed forecasting model based on artificial neural networks using the NARX structure. Our model was constructed using historical data on wind speed and meteorological factors in Quang Tri.  A local monitoring station's wind speed is used as an input variable for the NARX model. The MAPE and MAE metrics indicate that the forecasting model is highly effective, even under changing weather conditions. The proposed model has also been compared with models that use additional correlated input data, including wind direction, temperature, pressure and humidity, at various altitudes of 40m, 60m, 80m. The study also shows that choosing appropriate NARX model parameters can potentially expand the early forecast range up to 7 days. As a result of this validation, not only is the accuracy of the model determined, but also how the model can be used in order to harness wind energy efficiently and sustainably. Local wind energy management systems can benefit from this forecasting model by improving resource utilization and minimizing risks.