A method designed to create day-ahead, wide-area probabilistic solar power scenarios with control over emphasis of the tails. • Computational experiments are detailed, including comparisons with a method based on quantile regression.
What is the weather scenario generation-based probabilistic solar power forecasting method?
The rest of the paper is organized as follows. Section 2 describes the proposed weather scenario generation-based probabilistic solar power forecasting method, which consists of a deterministic forecasting method, Gaussian mixture model-based marginal weather probability distribution modeling, and a Copula-based Gibbs sampling model.
Can correlated weather scenario generation improve solar power forecasting?
This paper presents an improved probabilistic solar power forecasting framework based on correlated weather scenario generation. Copula is used to model a multivariate joint distribution between predicted weather variables and observed weather variables.
What are the different types of weather scenario generation methods?
Weather scenario generation has been widely used in the literature for probabilistic forecasts due to its simplicity and accessibility. Weather scenario generation methods can be generally classified into three categories : (i) fixed-date method, (ii) shifted-date method, and (iii) bootstrap method.
Massive weather scenarios are obtained by deriving a conditional probability density function given a current weather prediction by using the Bayesian theory. The generated weather scenarios are used as input variables to a machine learning-based multi-model solar power forecasting model, where probabilistic solar power forecasts are obtained.
One of the most popular probabilistic solar forecasting methods is to feed simulated explanatory weather scenarios into a deterministic forecasting model. However, the correlation among different explanatory weather variables are seldom considered during the scenario generation process.
Why do we need probabilistic solar power forecasts?
PV power output is highly dependent on external weather conditions such as solar radiation and temperature . Therefore, it is challenging to get accurate forecasts under different weather conditions. To better account for the solar power uncertainty and variability, probabilistic solar power forecasts are needed.