Machine learning based multi-physical-model blending for enhancing renewable energy forecast - improvement via situation dependent error correction
Authors:
- 1 July 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 283-290
Abstract
With increasing penetration of solar and wind energy to the total energy supply mix, the pressing need for accurate energy forecasting has become well-recognized. Here we report the development of a machine-learning based model blending approach for statistically combining multiple meteorological models for improving the accuracy of solar/wind power forecast. Importantly, we demonstrate that in addition to parameters to be predicted (such as solar irradiance and power), including additional atmospheric state parameters which collectively define weather situations as machine learning input provides further enhanced accuracy for the blended result. Functional analysis of variance shows that the error of individual model has substantial dependence on the weather situation. The machine-learning approach effectively reduces such situation dependent error thus produces more accurate results compared to conventional multi-model ensemble approaches based on simplistic equally or unequally weighted model averaging. Validation over an extended period of time results show over 30% improvement in solar irradiance/power forecast accuracy compared to forecasts based on the best individual model.Keywords
This publication has 26 references indexed in Scilit:
- Intra-hour DNI forecasting based on cloud tracking image analysisSolar Energy, 2013
- Online 24-h solar power forecasting based on weather type classification using artificial neural networkSolar Energy, 2011
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- Forecasting of preprocessed daily solar radiation time series using neural networksSolar Energy, 2010
- Generalized Functional ANOVA Diagnostics for High-Dimensional Functions of Dependent VariablesJournal of Computational and Graphical Statistics, 2007
- Using Bayesian Model Averaging to Calibrate Forecast EnsemblesMonthly Weather Review, 2005
- Greedy function approximation: A gradient boosting machine.The Annals of Statistics, 2001
- Support vector machinesACM SIGKDD Explorations Newsletter, 2000
- Improved Weather and Seasonal Climate Forecasts from Multimodel SuperensembleScience, 1999
- Tools for atmospheric radiative transfer: Streamer and FluxNetComputers & Geosciences, 1998