A short-term solar radiation forecasting system for the Iberian Peninsula. Part 2: Model blending approaches based on machine learning

Abstract In this article we explore the blending of the four models (Satellite, WRF-Solar, Smart Persistence and CIADCast) studied in Part 1 by means of Support Vector Machines with the aim of improving GHI and DNI forecasts. Two blending approaches that use the four models as predictors have been studied: the horizon approach constructs a different blending model for each forecast horizon, while the general approach trains a single model valid for all horizons. The influence on the blending models of adding information about weather types is also studied. The approaches have been evaluated in the same four Iberian Peninsula stations of Part 1. Blending approaches have been extended to a regional context with the goal of obtaining improved regional forecasts. In general, results show that blending greatly outperforms the individual predictors, with no large differences between the blending approaches themselves. Horizon approaches were more suitable to minimize rRMSE and general approaches work better for rMAE. The relative improvement in rRMSE obtained by model blending was up to 17% for GHI (16% for DNI), and up to 15% for rMAE. Similar improvements were observed for the regional forecast. An analysis of performance depending on the horizon shows that while the advantage of blending for GHI remains more or less constant along horizons, it tends to increase with horizon for DNI, with the largest improvements occurring at 6 h. The knowledge of weather conditions helped to slightly improve further the forecasts (up to 3%), but only at some locations and for rRMSE.

[1]  Adel Mellit,et al.  Artificial Intelligence technique for modelling and forecasting of solar radiation data: a review , 2008, Int. J. Artif. Intell. Soft Comput..

[2]  Jianzhou Wang,et al.  Combined forecasting models for wind energy forecasting: A case study in China , 2015 .

[3]  Francisco J. Santos-Alamillos,et al.  Evaluation of the WRF model solar irradiance forecasts in Andalusia (southern Spain) , 2012 .

[4]  Matteo De Felice,et al.  Data-driven upscaling methods for regional photovoltaic power estimation and forecast using satellite and numerical weather prediction data , 2017 .

[5]  Olivier Pannekoucke,et al.  A benchmark of statistical regression methods for short-term forecasting of photovoltaic electricity production, part I: Deterministic forecast of hourly production , 2014 .

[6]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[7]  S. E. Haupt,et al.  A regime-dependent artificial neural network technique for short-range solar irradiance forecasting , 2016 .

[8]  Robert L. Vislocky,et al.  Improved Model Output Statistics Forecasts through Model Consensus , 1995 .

[9]  Francisco J. Santos-Alamillos,et al.  Analysis of the intra-day solar resource variability in the Iberian Peninsula , 2018, Solar Energy.

[10]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[11]  D. Renné.  Emerging Meteorological Requirements to Support High Penetrations of Variable Renewable Energy Sources: Solar Energy , 2014 .

[12]  Jan Kühnert.  Development of a photovoltaic power prediction system for forecast horizons of several hours , 2016 .

[13]  Soteris A. Kalogirou,et al.  Machine learning methods for solar radiation forecasting: A review , 2017 .

[14]  Dorit Hammerling,et al.  Comparing and Blending Regional Climate Model Predictions for the American Southwest , 2011 .

[15]  Jie Zhang,et al.  Machine learning based multi-physical-model blending for enhancing renewable energy forecast - improvement via situation dependent error correction , 2015, 2015 European Control Conference (ECC).

[16]  Alexander J. Smola,et al.  Learning with Kernels: support vector machines, regularization, optimization, and beyond , 2001, Adaptive computation and machine learning series.

[17]  Mathieu David,et al.  Combining solar irradiance measurements, satellite-derived data and a numerical weather prediction model to improve intra-day solar forecasting , 2016 .

[18]  Sue Ellen Haupt,et al.  Solar Forecasting: Methods, Challenges, and Performance , 2015, IEEE Power and Energy Magazine.

[19]  Max Kuhn,et al.  Building Predictive Models in R Using the caret Package , 2008 .

[20]  Oliver Kramer,et al.  Comparing support vector regression for PV power forecasting to a physical modeling approach using measurement, numerical weather prediction, and cloud motion data , 2016 .

[21]  Akin Tascikaraoglu,et al.  A review of combined approaches for prediction of short-term wind speed and power , 2014 .

[22]  Phillip A. Arkin,et al.  Analyses of Global Monthly Precipitation Using Gauge Observations, Satellite Estimates, and Numerical Model Predictions , 1996 .