Long short term memory–convolutional neural network based deep hybrid approach for solar irradiance forecasting

A case study of NeuralProphet and nonlinear evaluation for high accuracy prediction in short-term forecasting in PV solar plant

“…(9) and Eq. (10) , [ 10 ]. where: : It is the sequential input from the temperature, irradiance, wind velocity.…”

Short-term forecasting of global solar irradiance in tropical environments with incomplete data

“…There are several approaches to forecast the solar radiation such as persistence methods that assume that the value at time + 1 is equal to value at time [8], autoregressive models that allow modeling stationary and non-stationary variations and describing complex nonlinear atmospheric phenomena [7], e.g., autoregressive moving average (ARMA), and autoregressive integrated moving average (ARIMA); and soft computing techniques, e.g., support vector machine (SVM), artificial neural network (ANN), and fuzzy and genetic algorithms (GA) [9]. The ANN, fuzzy logic, and hybrids are robust for modeling the physical processes' stochastic nature, like the solar irradiance because of their capacity to compensate systematic errors and problematic learnable deviation [10,11].…”

Machine learning techniques for hourly global horizontal irradiance prediction: A case study for smart cities of India

“…Artificial neural netw ork decision tree, support vector machine (SVM), random forest, etc. are a few extensively applied machine learning-based solar irradiance forecasting models [8,9].…”