Nonparametric short-term probabilistic forecasting for solar radiation

Abstract

The current deep concerns on energy independence and global society's security at the face of climate change have empowered the new ''green energy" paradigm and led to a rapid development of new methodology for modeling sustainable energy resources. However, clean renewables such as wind and solar energies are inherently intermittent, and their integration into a electric power grid require accurate and reliable estimation of uncertainties. And, if probabilistic forecasting of wind power is generally well developed, probabilistic forecasting of solar power is still in its infancy. In this paper we propose a new data-driven method for constructing a full predictive density of solar radiance based on a nonparametric bootstrap. We illustrate utility of the new bootstrapped statistical ensembles for probabilistic one-hour ahead forecasting in Mildura, Australia. We show that the new approach delivers sharp and calibrated ensembles of one-hour forecasts, and is computationally inexpensive and easily tractable.

Probabilistic Solar Forecasting Using Quantile Regression Models

“…For instance, in the case of GHI, the level of uncertainty may vary according the Sun's position in the sky (see for the instance the work of [3]). …”

“…Grantham et al [3] proposed a non-parametric approach based on a specific bootstrap method to build predictive global horizontal solar irradiance (GHI) distributions for a forecast horizon of 1 h. Chu and Coimbra [4] developed models based on the k-nearest-neighbors (kNN) algorithm for generating very short-term (from 5 min-20 min) direct normal solar irradiance (DNI) probabilistic forecasts. Golestaneh et al [5] used an extreme machine learning method to produce very short-term PV power predictive densities for lead times between a few minutes to one hour ahead.…”

Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation

“…Our proposed method is district from the existing probabilistic solar forecasting methods like [6,7] because we use literally different base regression models rather than using a single base model with different parameters or bootstrapping. The good results offered by it can be attributed to the soundness of the seven base regression models themselves and the effectiveness of our carefully-crafted ensemble strategies, especially in the case of the normal distribution with additional features method.…”

Mathematical Tools for Maximising Renewable Energy Use in Electricity Supply

“…Renewable energy sources such as wind and solar irradiance are inherently intermittent, and so their integration into an electric power grid requires accurate and reliable estimation of uncertainties. We present a new data-driven method for constructing a full predictive density of solar irradiation, based on a nonparametric A. Grantham [2] bootstrap technique. We also develop a method for spatio-temporal probabilistic forecasting of wind farm output.…”

“…We also develop a method for spatio-temporal probabilistic forecasting of wind farm output. The results have been published in [2]. A number of studies in the literature on 100% renewable energy use a short period of historical weather data, or a typical meteorological year (TMY), to determine the potential energy supply.…”