Efficiently operating wind turbines is becoming more important as the demand for green energy sources continues to rise. This paper presents a prognostic model for predicting wind turbine power generation using operational and meteorological data, based on a neural network. Input layers, hidden layers that are activated by the Rectified Linear Unit (ReLU) function, and a regression output layer are the components that make up the structure of our model. This particular model is a feed-forward neural network that has a great deal of layers. These non-linear characteristics of the dataset, which include variables such as dew point, temperature, humidity, wind speed, and direction at varying heights, were explicitly taken into consideration when developing this approach, which was especially adapted to accommodate those characteristics. The model was trained using a dataset that was divided into 70% for training and 30% for testing. Normalizing the feature columns enhanced the efficiency of the learning process. By employing an appropriate learning rate and regularization techniques to avoid overfitting, the training process consisting of 100 epochs using the Adam optimizer successfully reached convergence. The root mean squared error (RMSE) metric was utilized in order to evaluate the performance of the model, and it was found to have produced a satisfactory result of 0.170 on the standard set. This is advantageous for operational planning and enhancing efficiency in wind energy generation, as precise power production predictions are essential. The results demonstrate that neural networks and other deep learning models provide essential forecasts and understandings for renewable energy systems, therefore facilitating the development of power generation that is both more dependable and efficient.