Artificial Neural Networks (ANNs) are useful in the solar energy field because they can learn from data and show nonlinear relationships. This paper looks at some of the most significant ways that ANNs may be used in solar energy, such estimating solar irradiance, modelling and simulating photovoltaic (PV) and solar thermal systems. When modelling, ANNs employ operational data to better imitate how complex PV and thermal systems function than regular physics-based models do. ANN-based fault detection systems are better at discovering flaws in a system. This lets the researchers diagnose problems and conduct preventative maintenance on time. The Internet of Things (IoT), big data analytics, and deep learning are all becoming more widespread. They have improved solar energy applications by adding features like real-time monitoring, adaptive control, and predictive maintenance. The paper also reviews the issues in employing ANN, such as concerns regarding the model’s quality and how easy it is to grasp. It also speaks about what kinds of research may be done in the future and how to use hybrid computational methodologies that combine data-driven and physical modelling frameworks. Overall, ANNs are still highly vital for improving the implementation of solar energy technology.