Improving Prediction Intervals Using Measured Solar Power with a Multi-Objective Approach

Ricardo Aler,Javier Huertas-Tato,Inés M Galván,José M Valls

doi:10.3390/en12244713

Ricardo Aler, Javier Huertas-Tato + Show 2 more

Open Access

https://doi.org/10.3390/en12244713

Copy DOI

Journal: Energies	Publication Date: Dec 10, 2019
Citations: 2	License type: CC BY 4.0

Affiliation: Carlos III University of Madrid

Abstract

Prediction Intervals are pairs of lower and upper bounds on point forecasts and are useful to take into account the uncertainty on predictions. This article studies the influence of using measured solar power, available at prediction time, on the quality of prediction intervals. While previous studies have suggested that using measured variables can improve point forecasts, not much research has been done on the usefulness of that additional information, so that prediction intervals with less uncertainty can be obtained. With this aim, a multi-objective particle swarm optimization method was used to train neural networks whose outputs are the interval bounds. The inputs to the network used measured solar power in addition to hourly meteorological forecasts. This study was carried out on data from three different locations and for five forecast horizons, from 1 to 5 h. The results were compared with two benchmark methods (quantile regression and quantile regression forests). The Wilcoxon test was used to assess statistical significance. The results show that using measured power reduces the uncertainty associated to the prediction intervals, but mainly for the short forecasting horizons.

Highlights

IntroductionEnergy, has increased significantly and, a large PV penetration with a rapid growth has taken place in the electricity market [1]
In the last decade, wind and solar energy production, and photovoltaic (PV)energy, has increased significantly and, a large PV penetration with a rapid growth has taken place in the electricity market [1]
To have a first view of the performance of the different methods, Table 2 shows the mean of the ratio values for each method and each horizon, separately for Stations 1–3

Summary

Introduction

Energy, has increased significantly and, a large PV penetration with a rapid growth has taken place in the electricity market [1]. To achieve this high penetration, it is important to have accurate point forecasts and most of the research has focused on this issue. Due to the high variability of several meteorological factors, solar power prediction is inherently uncertain and, it is important to estimate the uncertainty around point forecasts. Nonlinear models can be constructed using this cost function, for example quantile regression neural networks (QRNN) [8] or tree-based ensembles such as Gradient Tree

Objectives

Methods

Results

Conclusion