“Forecasting wind speed presents significant challenges due to its inherent uncertainties and fluctuating nature. Previous research has explored various techniques to enhance wind speed estimation. This study aims to evaluate the performance of deep learning algorithms in forecasting wind speed using data from Ensit’s SIME lab acquisition chain. By implementing a deep neural network (DNN), we aimed to overcome the limitations of traditional wind speed forecasting methods and achieve greater accuracy and reliability. The results of this study demonstrate the efficacy of using a DNN for wind speed forecasting. The DNN model outperformed traditional forecasting algorithms, exhibiting a lower mean absolute error and a lower root mean square error of 0.08. It also achieved a high R-squared value of 0.92 and a higher coefficient of determination. These findings support the use of DNN-based models in various fields that rely on accurate wind speed forecasting, including renewable energy management, environmental monitoring, and disaster preparedness.”