A Review on Prediction of Solar Energy using Artificial Neural Network

Global acceptance of sustainable development and renewable energy is rising as a result of climate change's growing effect on national and local governments. The EU 2030 agenda, which aspires to give everyone access to affordable, dependable, and sustainable energy in the future, reflects this. A barrier to achieving this goal is some renewable energy sources' limited reliability. While both private citizens and governmental organizations work to produce enough renewable energy to meet their needs, it is unclear how much investment will be needed to lessen the unreliability caused by environmental factors such seasonal variations in wind speed and daylight. In this regard, a tool that helps predict the energy output of sustainable sources throughout the course of the year for a particular location can significantly help in boosting the efficiency of sustainable energy investments. In this study, we use Internet of Things (IoT) sensors, installations spread across Europe, and open data sources to build such a tool utilizing artificial neural networks. We investigate the effects of various factors on the estimation of energy production as well as the potential use of public data to predict the expected output of sustainable sources. We give users the information they need to decide what investments to make based on the necessary energy production for their particular location. Our method offers an abstraction layer that is focused on energy production rather than radiation statistics and can be taught and customized for different locations using open data, in contrast to cutting-edge alternatives