Model-Agnostic Hybrid Numerical Weather Prediction and Machine Learning Paradigm for Solar Forecasting in the Tropics

Numerical weather prediction (NWP) and machine learning (ML) methods are popular for solar forecasting. However, NWP models have multiple possible physical parameterizations, which requires site-specific NWP optimization. This is further complicated when regional NWP models are used with global climate models with different possible parameterizations. In this study, an alternative approach is proposed and evaluated for four radiation models. Weather Research and Forecasting (WRF) model is run in both global and regional mode to provide an estimate for solar irradiance. This estimate is then post-processed using ML to provide a final prediction. Normalized root-mean-square error from WRF is reduced by up to 40-50% with this ML error correction model. Results obtained using CAM, GFDL, New Goddard and RRTMG radiation models were comparable after this correction, negating the need for WRF parameterization tuning. Other models incorporating nearby locations and sensor data are also evaluated, with the latter being particularly promising.

[1]  Dipti Srinivasan,et al.  Operational solar forecasting for grid integration: Standards, challenges, and outlook , 2021, Solar Energy.

[2]  M. Caldas,et al.  Very short-term solar irradiance forecast using all-sky imaging and real-time irradiance measurements , 2019, Renewable Energy.

[3]  Mark I. Richardson,et al.  PlanetWRF: A general purpose, local to global numerical model for planetary atmospheric and climate dynamics , 2007 .

[4]  M. G. Schultz,et al.  Can deep learning beat numerical weather prediction? , 2021, Philosophical Transactions of the Royal Society A.

[5]  John Boland,et al.  Post-processing of Solar Irradiance Forecasts from WRF Model at Reunion Island☆ , 2014 .

[6]  Sharif Atique,et al.  Forecasting of total daily solar energy generation using ARIMA: A case study , 2019, 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC).

[8]  Paulo Canhoto,et al.  Short-term forecasts of GHI and DNI for solar energy systems operation: assessment of the ECMWF integrated forecasting system in southern Portugal , 2018, Solar Energy.

[9]  Dazhi Yang,et al.  Day-Ahead Solar Irradiance Forecasting in a Tropical Environment , 2015 .

[10]  Robert A. Taylor,et al.  Direct normal irradiance forecasting and its application to concentrated solar thermal output forecasting - A review , 2014 .

[11]  S. Freitas,et al.  A scale and aerosol aware stochastic convective parameterization for weather and air quality modeling , 2013 .

[12]  F. Creutzig,et al.  The underestimated potential of solar energy to mitigate climate change , 2017, Nature Energy.

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

[14]  Kevin W. Manning,et al.  The community Noah land surface model with multiparameterization options (Noah-MP): 1. Model description and evaluation with local-scale measurements , 2011 .

[15]  Minzhu Xie,et al.  XGBFEMF: An XGBoost-Based Framework for Essential Protein Prediction , 2018, IEEE Transactions on NanoBioscience.

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

[17]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[18]  Soo Chin Liew,et al.  Customization of the Advanced Research Weather Research and Forecasting model over the Singapore region: impact of planetary boundary layer schemes, land use, land cover and model horizontal grid resolution , 2019, Meteorological Applications.

[19]  Hadrien Verbois,et al.  Solar irradiance forecasting in the tropics using numerical weather prediction and statistical learning , 2018 .

[20]  Dong Huang,et al.  3D cloud detection and tracking system for solar forecast using multiple sky imagers , 2015 .

[21]  T. Hoff,et al.  Validation of short and medium term operational solar radiation forecasts in the US , 2010 .

[22]  Jan Kleissl,et al.  Operational solar forecasting for the real-time market , 2019, International Journal of Forecasting.

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

[24]  G. Powers,et al.  A Description of the Advanced Research WRF Version 3 , 2008 .

[25]  Thomas de Quincey.  [C] , 2000, The Works of Thomas De Quincey, Vol. 1: Writings, 1799–1820.

[26]  L. Chaar,et al.  Review of photovoltaic technologies , 2011 .

[27]  W. Collins,et al.  Description of the NCAR Community Atmosphere Model (CAM 3.0) , 2004 .

[28]  J. A. Ruiz-Arias,et al.  Comparison of numerical weather prediction solar irradiance forecasts in the US, Canada and Europe , 2013 .

[29]  P. Alam.  ‘E’ , 2021, Composites Engineering: An A–Z Guide.

[30]  Kevin W. Manning,et al.  The community Noah land surface model with multiparameterization options (Noah-MP): 2. Evaluation over global river basins , 2011 .

[31]  A. Hammer,et al.  Short term forecasting of solar radiation based on satellite data , 2004 .

[32]  Dazhi Yang,et al.  On post-processing day-ahead NWP forecasts using Kalman filtering , 2019, Solar Energy.

[33]  Max J. Suarez,et al.  A Solar Radiation Parameterization for Atmospheric Studies , 2013 .

[34]  D. Maksimovic,et al.  Mitigation of Solar Irradiance Intermittency in Photovoltaic Power Systems With Integrated Electric-Vehicle Charging Functionality , 2013, IEEE Transactions on Power Electronics.

[35]  S. E. Haupt,et al.  WRF-Solar: Description and Clear-Sky Assessment of an Augmented NWP Model for Solar Power Prediction , 2016 .

[36]  Fahad H. Al-Qahtani,et al.  Multivariate k-nearest neighbour regression for time series data — A novel algorithm for forecasting UK electricity demand , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[37]  Maher Chaabene,et al.  Neuro-fuzzy dynamic model with Kalman filter to forecast irradiance and temperature for solar energy systems , 2008 .

[38]  P. Alam.  ‘S’ , 2021, Composites Engineering: An A–Z Guide.

[39]  Bjørn Petter Jelle,et al.  Building integrated photovoltaic products: A state-of-the-art review and future research opportunities , 2012 .

[40]  Anne-Laure Boulesteix,et al.  Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics , 2012, WIREs Data Mining Knowl. Discov..

[41]  Ali Assi,et al.  Forecasting Solar Radiation Strength Using Machine Learning Ensemble , 2018, 2018 7th International Conference on Renewable Energy Research and Applications (ICRERA).

[42]  J. Dudhia,et al.  A Revised Scheme for the WRF Surface Layer Formulation , 2012 .

[43]  Zeyar Aung,et al.  Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation , 2016 .

[44]  Ilke Celik,et al.  A technoeconomic analysis of perovskite solar module manufacturing with low-cost materials and techniques , 2017 .

[45]  T. Koh,et al.  Improved diagnostics for NWP verification in the tropics , 2009 .

[46]  Xin-Zhong Liang,et al.  A Thermal Infrared Radiation Parameterization for Atmospheric Studies , 2001 .

[47]  Song‐You Hong,et al.  The WRF Single-Moment 6-Class Microphysics Scheme (WSM6) , 2006 .

[48]  Jiahua Pan,et al.  Climate Change--the Chinese Challenge , 2008, Science.

[49]  Jiafeng Zheng,et al.  A Novel Hybrid Model of WRF and Clearness Index-Based Kalman Filter for Day-Ahead Solar Radiation Forecasting , 2019, Applied Sciences.

[50]  J. Kleissl,et al.  Evaluation of numerical weather prediction for intra-day solar forecasting in the continental United States , 2011 .

[51]  Urban Lundin,et al.  Power system flexibility need induced by wind and solar power intermittency on time scales of 1–14 days , 2015 .

[52]  P. Alam.  ‘N’ , 2021, Composites Engineering: An A–Z Guide.

[53]  Mahesh Pal,et al.  Random forest classifier for remote sensing classification , 2005 .

[54]  Danna Zhou,et al.  d. , 1840, Microbial pathogenesis.

[55]  S. P. Srivastava,et al.  SOLAR ENERGY AND ITS FUTURE ROLE IN INDIAN ECONOMY , 2013 .

[56]  Benjamin K. Sovacool,et al.  The intermittency of wind, solar, and renewable electricity generators: Technical barrier or rhetorical excuse? , 2009 .

[57]  Alireza Bahadori,et al.  A review on solar energy utilisation in Australia , 2013 .

[58]  Andreas Kazantzidis,et al.  Evaluation of WRF shortwave radiation parameterizations in predicting Global Horizontal Irradiance in Greece , 2016 .

[59]  W. Collins,et al.  Radiative forcing by long‐lived greenhouse gases: Calculations with the AER radiative transfer models , 2008 .

[60]  Quang Tuyen Le,et al.  Modeling transient fluid simulations with proper orthogonal decomposition and machine learning , 2020 .

[61]  B. Sivaneasan,et al.  Solar Forecasting using ANN with Fuzzy Logic Pre-processing , 2017 .

[62]  P. Alam.  ‘W’ , 2021, Composites Engineering.

[63]  X. Bi,et al.  Validation for a tropical belt version of WRF: sensitivity tests on radiation and cumulus convection parameterizations , 2019, Atmospheric and Oceanic Science Letters.

[64]  Ranko Goic,et al.  review of solar photovoltaic technologies , 2011 .

[65]  M. Diagne,et al.  Review of solar irradiance forecasting methods and a proposition for small-scale insular grids , 2013 .

[66]  Dazhi Yang,et al.  Satellite image analysis and a hybrid ESSS/ANN model to forecast solar irradiance in the tropics , 2014 .

[67]  Dahai Zhang,et al.  A Data-Driven Design for Fault Detection of Wind Turbines Using Random Forests and XGboost , 2018, IEEE Access.

[68]  Wei-Chiang Hong,et al.  Application of the Weighted K-Nearest Neighbor Algorithm for Short-Term Load Forecasting , 2019, Energies.

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

[70]  B. Hodge,et al.  The value of day-ahead solar power forecasting improvement , 2016 .

[71]  H. Zhou,et al.  Impacts of different radiation schemes on the prediction of solar radiation and photovoltaic power , 2017 .

[72]  Jun Wang,et al.  Numerical simulation of seasonal mesoscale atmospheric flow‐field variables using ARW over the Singapore region: impact of land use land cover , 2019, Meteorological Applications.

[73]  Ponnuthurai Nagaratnam Suganthan,et al.  Ensemble methods for wind and solar power forecasting—A state-of-the-art review , 2015 .

[74]  R. Saidur,et al.  Application of support vector machine models for forecasting solar and wind energy resources: A review , 2018, Journal of Cleaner Production.

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

[76]  G. Nagy,et al.  GEFCom2014: Probabilistic solar and wind power forecasting using a generalized additive tree ensemble approach , 2016 .

[77]  J. Dudhia,et al.  A New Vertical Diffusion Package with an Explicit Treatment of Entrainment Processes , 2006 .

[78]  Jianxue Wang,et al.  GEFCom2014 probabilistic solar power forecasting based on k-nearest neighbor and kernel density estimator , 2015, 2015 IEEE Power & Energy Society General Meeting.

[79]  Wilfred M. Walsh,et al.  Comparisons of next-day solar forecasting for Singapore using 3DVAR and 4DVAR data assimilation approaches with the WRF model , 2020 .

[80]  Stephen B. Fels,et al.  An efficient, accurate algorithm for calculating CO2 15 μm band cooling rates , 1981 .