Assessment of machine learning techniques for deterministic and probabilistic intra-hour solar forecasts

This work compares the performance of machine learning methods (k-nearest-neighbors (kNN) and gradient boosting (GB)) in intra-hour forecasting of global (GHI) and direct normal (DNI) irradiances. The models predict the GHI and DNI and the corresponding prediction intervals. The data used in this work include pyranometer measurements of GHI and DNI and sky images. Point forecasts are evaluated using bulk error metrics while the performance of the probabilistic forecasts are quantified using metrics such as Prediction Interval Coverage Probability (PICP), Prediction Interval Normalized Averaged Width (PINAW) and the Continuous Ranked Probability Score (CRPS). Graphical verification displays like reliability diagram and rank histogram are used to assess the probabilistic forecasts. Results show that the machine learning models achieve significant forecast improvements over the reference model. The reduction in the RMSE translates into forecasting skills ranging between 8% and 24%, and 10% and 30% for the GHI and DNI testing set, respectively. CRPS skill scores of 42% and 62% are obtained respectively for GHI and DNI probabilistic forecasts. Regarding the point forecasts, the GB method performs better than the kNN method when sky image features are included in the model. Conversely, for probabilistic forecasts the kNN exhibits rather good performance.

[1]  Jing Huang,et al.  A semi-empirical approach using gradient boosting and k-nearest neighbors regression for GEFCom2014 probabilistic solar power forecasting , 2016 .

[2]  Carlos F.M. Coimbra,et al.  Hybrid intra-hour DNI forecasts with sky image processing enhanced by stochastic learning , 2013 .

[3]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[4]  Carlos F.M. Coimbra,et al.  Hybrid solar forecasting method uses satellite imaging and ground telemetry as inputs to ANNs , 2013 .

[5]  Greg Ridgeway,et al.  Generalized Boosted Models: A guide to the gbm package , 2006 .

[6]  L. D. Monache,et al.  An analog ensemble for short-term probabilistic solar power forecast , 2015 .

[7]  P. Ineichen.  A broadband simplified version of the Solis clear sky model , 2008 .

[8]  Carlos F.M. Coimbra,et al.  A Smart Image-Based Cloud Detection System for Intrahour Solar Irradiance Forecasts , 2014 .

[9]  T. Soubdhan,et al.  A benchmarking of machine learning techniques for solar radiation forecasting in an insular context , 2015 .

[10]  John Boland,et al.  Forecasting solar radiation on an hourly time scale using a Coupled AutoRegressive and Dynamical System (CARDS) model , 2013 .

[11]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[12]  P. L. Houtekamer,et al.  Verification of an Ensemble Prediction System against Observations , 2007 .

[13]  Nikos Kourentzes,et al.  Short-term solar irradiation forecasting based on Dynamic Harmonic Regression , 2015 .

[14]  John Boland,et al.  Nonparametric short-term probabilistic forecasting for solar radiation , 2016 .

[15]  T. Hamill.  Interpretation of Rank Histograms for Verifying Ensemble Forecasts , 2001 .

[16]  Rob J Hyndman,et al.  Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyond , 2016 .

[17]  H. Pedro,et al.  Assessment of forecasting techniques for solar power production with no exogenous inputs , 2012 .

[18]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[19]  Carlos F.M. Coimbra,et al.  Forecasting of Global Horizontal Irradiance Using Sky Cover Indices , 2013 .

[20]  Gilles Notton,et al.  Forecasting method for global radiation time series without training phase: Comparison with other well-known prediction methodologies , 2017 .

[21]  Robin Broder Hytowitz,et al.  Managing solar uncertainty in microgrid systems with stochastic unit commitment , 2015 .

[22]  H. Madsen,et al.  Reliability diagrams for non‐parametric density forecasts of continuous variables: Accounting for serial correlation , 2010 .

[23]  Vladimiro Miranda,et al.  Probabilistic solar power forecasting in smart grids using distributed information , 2015 .

[24]  Pierre Pinson,et al.  Wind Energy: Forecasting Challenges for Its Operational Management , 2013, 1312.6471.

[25]  J. Friedman.  Stochastic gradient boosting , 2002 .

[26]  Claudio A. Cañizares,et al.  Stochastic-Predictive Energy Management System for Isolated Microgrids , 2015, IEEE Transactions on Smart Grid.

[27]  J. Kleissl,et al.  Intra-hour forecasting with a total sky imager at the UC San Diego solar energy testbed , 2011 .

[28]  H. Hersbach.  Decomposition of the Continuous Ranked Probability Score for Ensemble Prediction Systems , 2000 .

[29]  Henrik Madsen,et al.  Probabilistic forecasts of solar irradiance using stochastic differential equations , 2014 .

[30]  Philippe Lauret,et al.  Probabilistic forecasting of the solar irradiance with recursive ARMA and GARCH models , 2016 .

[31]  Henrik Madsen,et al.  Online short-term solar power forecasting , 2009 .

[32]  A. Pavlovski,et al.  Solar Power Forecasting Performance – Towards Industry Standards , 2011 .

[33]  R. Inman,et al.  Solar forecasting methods for renewable energy integration , 2013 .

[34]  A. Raftery,et al.  Probabilistic forecasts, calibration and sharpness , 2007 .

[35]  Carlos F.M. Coimbra,et al.  Cloud-tracking methodology for intra-hour DNI forecasting , 2014 .

[36]  Jan Kleissl,et al.  Energy dispatch schedule optimization for demand charge reduction using a photovoltaic-battery storage system with solar forecasting , 2014 .

[37]  Carlos F.M. Coimbra,et al.  Nearest-neighbor methodology for prediction of intra-hour global horizontal and direct normal irradiances , 2015 .

[38]  Daniel S. Wilks,et al.  Statistical Methods in the Atmospheric Sciences: An Introduction , 1995 .

[39]  L. D. Monache,et al.  An application of the ECMWF Ensemble Prediction System for short-term solar power forecasting , 2016 .

[40]  C. Coimbra,et al.  Intra-hour DNI forecasting based on cloud tracking image analysis , 2013 .

[41]  Carlos F.M. Coimbra,et al.  Short-term probabilistic forecasts for Direct Normal Irradiance , 2017 .

[42]  R. Koenker,et al.  Regression Quantiles , 2007 .