Photovoltaic Power Forecasting Methods

Abstract

The rapid growth in grid penetration of photovoltaic (PV) calls for more accurate methods to forecast the performance and reliability of PV. Several methods have been proposed to forecast the PV power generation at different temporal horizons. In this chapter the different methods used in PV power forecasting are described with an example on their applications and related uncertainty. The methods discussed include physical, heuristic, statistical and machine learning methods. When benchmarked, it is shown that physical method showed the highest uncertainties compared to other methods. In the chapter, the effect of degradation on lifetime PV power and energy forecast is also assessed using linear and non-linear degradation scenarios. It is shown that the relative difference in lifetime yield prediction is over 5% between linear and non-linear scenarios.

Assessing the impact of PV panel climate-based degradation rates on inverter reliability in grid-connected solar energy systems

“…To evaluate the yearly degradation rates or lifetime of the modules, we utilized a physics-based approach that considers various factors that may impact PV reliability [ 21 ]. The degradation model is embedded into a bottom-up physics-based energy yield simulation framework, as illustrated in the schematic Fig.…”

“…To model the degradation, the electrical model is evaluated as time and climate/stress factors using the degradation rate and reliability models as in Ref. [ 21 ]. The output is a timeseries of electrical parameters: short-circuit current, open-circuit voltage, power at maximum power point ( P max ), current at maximum power point ( I max ) and voltage at maximum power point ( V max ) with degradation.…”

Global Solar Radiation Forecasting with Artificial Neural Networks

“…It has been observed from satellite measurements that the absolute value of the amount of solar radiation coming from outside the earth is 1361 W/m 2 and that the solar radiation value should be significantly lower than the value of 1365 W/m 2 observed in conventional radiometers [2]. But when solar radiation from the outer planets encounters the atmosphere, it weakens and ceases to be constant.…”

How Does Neural Network Model Capacity Affect Photovoltaic Power Prediction? A Study Case

“…As the name implies, the physical method is based on the physical characteristics that influence PV generation, such as PV system metadata and meteorological data. Therefore, the great advantage over data-driven models is that physical models can be implemented even before the photovoltaic system is in operation, although they generally have lower accuracy [ 19 ].…”