Power Prediction in Combined Cycle Power Plant through ML and DL Regression Techniques

The process of forecasting future power demand is very important to the electric sector since it helps as the basis for decision-making about the operation and planning of power systems. Predicting the need for power may be done in a number of different ways by electrical businesses. These may be used for predicting the short-term, the medium-term, or the long-term. However, the consumption of power results from the intricate interactions that take place between climatological and socioeconomic elements. In such a dynamic environment, conventional methods of predicting are inadequate, and it is necessary to use more advanced approaches. In this research, a Deep Learning (DL) -based method is proposed for power plant power prediction. A power plant dataset from Kaggle is collected, and five machine learning techniques followed by a deep learning algorithm are applied. The experiments showed that deep learning models performed better for power prediction when compared to the existing models. Later, regression analysis was also done to investigate and identify features that are important for power prediction. Proposed DL-based approach significantly enhances accuracy in power prediction, marking a notable advancement in the field.