Data-Driven Model for Predicting Power Generation in Integrated Turbine Units

Given the increasing demand for energy and the challenges posed by climate change, the depletion of fossil fuel resources, and rising energy demand, optimizing power generation has become a critical priority in the energy industry. Climate change, excessive consumption, and inadequate infrastructure exacerbate energy imbalances. To address these challenges, this paper presents a data-driven approach to predicting power output. We evaluate and compare various state-of-the-art data-driven forecasting models to identify the most reliable approach for both short-term and long-term predictions. In this study, we propose a hybrid deep learning model combining Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN). This model excels at capturing time dependencies and nonlinear, complex patterns in the data. The results show that the hybrid LSTM-CNN model outperforms other machine learning approaches, including single-layer LSTM and Random Forest, with prediction accuracy up to 98 %. This high level of accuracy makes the proposed model a reliable and effective solution for predicting power generation in combinedcycle power plants.