A Review on ANN Based Model for Solar Ra

Wind speed and solar radiation are fundamental inputs used as a renewable energy source. Both parameters are highly non-linear and environmental dependent. Hence, accurate prediction of these parameters is necessary for various applications in agriculture, industry, transport, and environmental sectors as they help reduce greenhouse gases and are environmentally friendly. This study indicates that accurate solar forecasting and wind speed prediction using machine learning methodology can yield correct data pertaining to temperature, relative humidity, solar radiations, precipitation, and wind speed. The study analyzes and compares the benefits and constraints of various artificial neural network (ANN) algorithms including the RP, Levenberg Marquardt, Polak-Ribière update gradient, and OSS gradient to enhance the prediction accuracy of wind speed and solar radiation. Findings suggest that the Levenberg–Marquardt and Bayesian regulation algorithms are more resilient and effective at predicting highly non-linear characteristics, such as solar radiation and wind speed. Additionally, the IoT is highlighted as a better platform for real-time data analysis, improving energy efficiency and optimizing production through the use of sensors and protocols.