Evaluating the Impact of Renewable Energy on Power Generation Costs: A Hybrid ANN and SCA Approach

This study investigates the integration of renewable energy sources-specifically wind, hydro, and solar power-into a traditional power generation system comprising six thermal units, assessing their impact on fuel and emission costs. Using artificial neural networks (ANNs), synthetic data for renewable generation was generated based on environmental factors such as temperature, humidity, and historical data. Two scenarios were analyzed: the first considering only conventional power generation, and the second incorporating predictions of renewable energy output. The ANN models were trained on the generated datasets, allowing for accurate predictions of renewable energy contributions. Additionally, the optimization of power generation was performed using the Sine Cosine Algorithm implemented in MATLAB. The results indicated significant reductions in both total fuel cost and emissions when renewables were utilized. In Scenario 1, the total costs reflected the operational expenses of conventional generators, while Scenario 2 demonstrated the cost advantages of integrating renewable resources, highlighting their potential to mitigate environmental impacts. This study provides valuable insights into the economic feasibility of renewable energy integration, supporting the transition towards more sustainable energy systems.