سامانه همایش های دانشگاه آزاد اسلامی واحد نجف آباد

صفحه اصلی / International Conference on Artificial Intelligence; City, Industry and Health

The Application of Artificial Intelligence in Optimizing and Forecasting the Performance of Renewable Energy Systems

نویسندگان :

Behzad Ghadiri¹

1- Faculty of Art, Architecture, urban planning, Najafabad Branch, Islamic Azad University, Najafabad, Iran

کلمات کلیدی :

Artificial Intelligence،Deep Learning،Renewable Energy،Energy Forecasting

چکیده :

With the growing global demand for energy and the environmental consequences of fossil fuel consumption, the utilization of renewable energy sources has become essential. However, the intermittent and complex nature of resources such as solar irradiance and wind poses significant challenges for accurate prediction and optimal utilization. This paper proposes a three-stage framework using advanced Artificial Intelligence (AI) algorithms—particularly Artificial Neural Networks (ANNs), Machine Learning (ML) models, and Long Short-Term Memory (LSTM) networks—to forecast and optimize the performance of photovoltaic (PV) and wind energy systems. In the first stage, meteorological, thermophysical, and geometric data were collected and pre-processed to identify key influencing variables. Subsequently, prediction models such as Support Vector Regression (SVR), XGBoost, CatBoost, and hybrid models like BiLSTM and Voting-Average were employed for forecasting solar irradiance and energy output. Results indicate that deep and ensemble models offer superior prediction accuracy compared to traditional methods, effectively capturing complex temporal patterns in the data. Furthermore, the Non-dominated Sorting Genetic Algorithm II (NSGA-II) was applied for multi-objective optimization in PV/T system design. Emphasizing the integration of AI with renewable energy technologies, this study demonstrates that intelligent approaches can significantly enhance efficiency, reliability, and sustainability in modern energy systems.