This paper investigates solar PV power generation forecasting techniques presented to date and describes the characteristics of various forecasting techniques. These approaches are compared together in terms of forecast method, time horizon, measurement error, input and output variables, computational time, and benchmark model.
Bacher et al. suggested a two-stage method to predict PV generation online. First, a clear sky model obtains a statistical normalization of solar power. Then, the adaptive linear time series model calculates the prediction of the normalized solar power.
Many researchers have focused on the optimization of solar PV power generation in terms of the number of PV modules, storage and inverter capacity, and controller types . This can improve the operation of renewable energy based power grids by proper energy storage scheduling .
Accurate estimation of solar energy is necessary as the demand and dependency of solar energy in total power is increasing worldwide. Moreover, accurate estimat
In this case, solar photovoltaic power forecasting is a crucial aspect to ensure optimum planning and modelling of the solar photovoltaic plants. Accurate forecasting provides the grid operators and power system designers with significant information to design an optimal solar photovoltaic plant as well as managing the power of demand and supply.
Two types of training methodologies i.e., online and offline are applied to eleven-data driven models in order to evaluate the fitness and flexibility of the forecast models performances as presented in . The solar PV power forecasting method could be deployed to optimize the usage of solar energy.