Literature Review: Applications of Artificial Intelligence in Solar Radiation Prediction for Photovoltaic Systems

Abstract

Solar Power Plants (SPPs) are gaining more attention as a sustainable and environmentally friendly renewable energy solution. However, the operational efficiency of SPPs is significantly affected by the unpredictable fluctuations in solar radiation. To improve short-term predictions of solar radiation, the use of Artificial Intelligence (AI) presents a promising approach. This study aims to provide a literature review on the various applications of AI in forecasting solar radiation for photovoltaic (PV) systems. The review covers AI techniques such as Machine Learning (ML), Deep Learning (DL), and hybrid models, which have proven effective in enhancing prediction accuracy. Algorithms like Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and their combinations have shown promising results in capturing non-linear patterns in solar radiation data. Additionally, optimization algorithms like Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO) also show significant potential in improving prediction model performance. This research offers insights into the benefits and challenges of applying AI in solar radiation forecasting and provides recommendations for further development to enhance the efficiency of global PV systems.

Keywords: Artificial Intelligence (AI), Solar Radiation Prediction, Photovoltaic Systems