A Review on ANN Based Model for Solar Radiation and Wind Speed Prediction with Real-Time Data

Wind speed and solar radiation are the 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 the application to various applications in different agriculture, industrial, transport, and environmental sectors because they reduce greenhouse gases and are environmentally friendly. The study indicates that good quality prediction, accurate solar forecasting, and wind speed, using the machine learning methodology, can predict correct data such as temperature, relative moisture, solar radiations, rain, and wind speed. The best way to anticipate extremely nonlinear environmental data, such as wind speed and solar radiation is using the artificial neural system. In this study, the benefits and constraints of various neural artificial network algorithms (RP) are analyzed and compared. These algorithms include the RP, Levenberg Marquardt (LM), Polak-Ribiere update gradient (CGP), and OSS (one step secant) gradient to enhance the accuracy of the wind speed and the predicted solar radiation. All findings suggest that the Levenberg-Marquardt and Bayesian algorithms for regulation are more resilient and effective to anticipate highly non-linear characteristics, such as solar radiation and wind speed. With the aid of components like sensors, actuators, protocols, and gateways to increase energy efficiency, dependability, detection of failures, and production optimization, IoT is after collecting exact data the better platform utilized for real-time data analysis.