Day Ahead Hourly Global Horizontal Irradiance Forecasting—Application to South African Data

Phathutshedzo Mpfumali,Caston Sigauke,Sophie Mulaudzi,Alphonce Bere

doi:10.3390/en12183569

Phathutshedzo Mpfumali, Caston Sigauke + Show 2 more

Open Access

https://doi.org/10.3390/en12183569

Copy DOI

Journal: Energies	Publication Date: Sep 18, 2019
Citations: 24	License type: CC BY 4.0

Affiliation: University of Venda

Abstract

Due to its variability, solar power generation poses challenges to grid energy management. In order to ensure an economic operation of a national grid, including its stability, it is important to have accurate forecasts of solar power. The current paper discusses probabilistic forecasting of twenty-four hours ahead of global horizontal irradiance (GHI) using data from the Tellerie radiometric station in South Africa for the period August 2009 to April 2010. Variables are selected using a least absolute shrinkage and selection operator (Lasso) via hierarchical interactions and the parameters of the developed models are estimated using the Barrodale and Roberts’s algorithm. Two forecast combination methods are used in this study. The first is a convex forecast combination algorithm where the average loss suffered by the models is based on the pinball loss function. A second forecast combination method, which is quantile regression averaging (QRA), is also used. The best set of forecasts is selected based on the prediction interval coverage probability (PICP), prediction interval normalised average width (PINAW) and prediction interval normalised average deviation (PINAD). The results demonstrate that QRA gives more robust prediction intervals than the other models. A comparative analysis is done with two machine learning methods—stochastic gradient boosting and support vector regression—which are used as benchmark models. Empirical results show that the QRA model yields the most accurate forecasts compared to the machine learning methods based on the probabilistic error measures. Results on combining prediction interval limits show that the PMis the best prediction limits combination method as it gives a hit rate of 0.955 which is very close to the target of 0.95. This modelling approach is expected to help in optimising the integration of solar power in the national grid.

Highlights

The first column indicates the main effect, columns indicate the non-zero interactions of the row predictor and the last column indicates whether hierarchy constraint is tight or not, 0 indicate that there is no interactions between the variables
This indicates that the prediction intervals constructed by model M8 are more informative with satisfactory prediction interval coverage probability (PICP)
This paper discussed an application of Partially linear additive quantile regression (PLAQR) models to probabilistic solar irradiance forecasting using South African data

Summary

Introduction

The focus is on probabilistic solar irradiance modelling and forecasting. Probabilistic forecasts take probability distributions of future events into account. They are preferred over deterministic forecasting because they take into account the uncertainties in the predicted values which help in taking effective decisions. It is believed that probabilistic forecasting can become a power trend in solar irradiance forecasting [1]. Providing the full predictive density or providing prediction intervals of the forecasts help decision makers in power utility companies in assessing future uncertainty of the power supply [2,3]

Methods

Results

Discussion

Conclusion