Probabilistic Forecasts of Solar Irradiance by Stochastic Differential Equations

TL;DR

This paper introduces a stochastic differential equation framework to generate probabilistic forecasts of solar irradiance, capturing uncertainty and error interdependence, which enhances decision-making for renewable energy management.

Contribution

It presents a novel SDE-based modeling approach for probabilistic solar irradiance forecasting, addressing the limitations of traditional point forecasts.

Findings

The SDE models effectively characterize prediction error structures.

The proposed model provides reliable probabilistic forecasts.

Evaluation shows improved uncertainty quantification.

Abstract

Probabilistic forecasts of renewable energy production provide users with valuable information about the uncertainty associated with the expected generation. Current state-of-the-art forecasts for solar irradiance have focused on producing reliable \emph{point} forecasts. The additional information included in probabilistic forecasts may be paramount for decision makers to efficiently make use of this uncertain and variable generation. In this paper, a stochastic differential equation (SDE) framework for modeling the uncertainty associated with the solar irradiance point forecast is proposed. This modeling approach allows for characterizing both the interdependence structure of prediction errors of short-term solar irradiance and their predictive distribution. A series of different SDE models are fitted to a training set and subsequently evaluated on a one-year test set. The final model proposed is defined on a bounded and time-varying state space with zero probability almost surely of events outside this space.