{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T14:36:27Z","timestamp":1759674987960,"version":"3.41.0"},"reference-count":33,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2017,10,11]],"date-time":"2017-10-11T00:00:00Z","timestamp":1507680000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGMETRICS Perform. Eval. Rev."],"published-print":{"date-parts":[[2017,10,11]]},"abstract":"<jats:p>The increasing penetration of solar power in the grid has motivated a strong interest in developing real-time performance models that estimate solar output based on a deployment's unique location, physical characteristics, and weather conditions. Solar models are useful for a variety of solar energy analytics, including indirect monitoring, forecasting, disaggregation, anonymous localization, and fault detection. Significant recent work focuses on learning \"black box\" models, primarily for forecasting, using machine learning (ML) techniques, which leverage only historical energy and weather data for training. Interestingly, these ML techniques are often \"off the shelf\" and do not incorporate well-known physical models of solar generation based on fundamental properties. Instead, prior work on physical modeling generally takes a \"white box\" approach that assumes detailed knowledge of a deployment. In this paper, we survey existing work on solar modeling, and then compare black-box solar modeling using ML versus physical approaches. We then i) present a configurable hybrid approach that combines the benefits of both by enabling users to select the parameters they physically model versus learn via ML, and ii) show that it significantly improves model accuracy across 6 deployments.<\/jats:p>","DOI":"10.1145\/3152042.3152067","type":"journal-article","created":{"date-parts":[[2017,10,12]],"date-time":"2017-10-12T12:52:50Z","timestamp":1507812770000},"page":"79-84","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Black-box Solar Performance Modeling"],"prefix":"10.1145","volume":"45","author":[{"given":"Dong","family":"Chen","sequence":"first","affiliation":[{"name":"University of Massachusetts Amherst"}]},{"given":"David","family":"Irwin","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst"}]}],"member":"320","published-online":{"date-parts":[[2017,10,11]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Bird Simple Spectral Model. http:\/\/rredc.nrel.gov\/solar\/models\/spectral\/.  Bird Simple Spectral Model. http:\/\/rredc.nrel.gov\/solar\/models\/spectral\/."},{"key":"e_1_2_1_2_1","unstructured":"PVWatts. http:\/\/pvwatts.nrel.gov\/.  PVWatts. http:\/\/pvwatts.nrel.gov\/."},{"key":"e_1_2_1_3_1","unstructured":"PySolar. http:\/\/pysolar.org\/.  PySolar. http:\/\/pysolar.org\/."},{"key":"e_1_2_1_4_1","unstructured":"Solar Radiation Cloud Cover Adjustment Calculator. http:\/\/www.shodor.org\/os411\/courses\/_master\/tools\/calculators\/solarrad  Solar Radiation Cloud Cover Adjustment Calculator. http:\/\/www.shodor.org\/os411\/courses\/_master\/tools\/calculators\/solarrad"},{"key":"e_1_2_1_5_1","unstructured":"System Advisor Model. https:\/\/sam.nrel.gov\/.  System Advisor Model. https:\/\/sam.nrel.gov\/."},{"key":"e_1_2_1_6_1","unstructured":"Weather.gov Forecast Terms. http:\/\/www.weather.gov\/bgm\/forecast_terms.  Weather.gov Forecast Terms. http:\/\/www.weather.gov\/bgm\/forecast_terms."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/AINA.2015.198"},{"key":"e_1_2_1_8_1","volume-title":"IEEE Photovoltaic Specialist Conference","author":"Andrews R.","year":"2014","unstructured":"R. Andrews , J. Stein , C. Hansen , and D. Riley . Introduction to the Open Source pvlib for Python Photovoltaic System Modelling Package . In IEEE Photovoltaic Specialist Conference , 2014 . R. Andrews, J. Stein, C. Hansen, and D. Riley. Introduction to the Open Source pvlib for Python Photovoltaic System Modelling Package. In IEEE Photovoltaic Specialist Conference, 2014."},{"key":"e_1_2_1_9_1","volume":"136","author":"Antonanzas J.","year":"2016","unstructured":"J. Antonanzas , N. Osorio , R. Escobar , R. Urraca , F. M. de Pison , and F. Antonanzas-Torres. Review of Photovoltaic Power Forecasting. Solar Energy , 136 , October 2016 . J. Antonanzas, N. Osorio, R. Escobar, R. Urraca, F. M. de Pison, and F. Antonanzas-Torres. Review of Photovoltaic Power Forecasting. Solar Energy, 136, October 2016.","journal-title":"Antonanzas-Torres. Review of Photovoltaic Power Forecasting. Solar Energy"},{"issue":"10","key":"e_1_2_1_10_1","first-page":"4086","volume":"35","author":"Ayompe L.","year":"2015","unstructured":"L. Ayompe , A. Duffy , S. McCormack , and M. Conlon . Validated Real-time Energy Models for Small-scale Grid-connected PV-systems. Energy , 35 ( 10 ): 4086 -- 4091 , 2015 . L. Ayompe, A. Duffy, S. McCormack, and M. Conlon. Validated Real-time Energy Models for Small-scale Grid-connected PV-systems. Energy, 35(10):4086--4091, 2015.","journal-title":"Validated Real-time Energy Models for Small-scale Grid-connected PV-systems. Energy"},{"key":"e_1_2_1_11_1","volume-title":"Radial Basis Function Network-based Prediction of Global Solar Radiation Data: Application for Sizing of a Stand-alone Photovoltaic System at Al-Madinah. Energy, 35(9)","author":"Benghanem M.","year":"2010","unstructured":"M. Benghanem and A. Mellit . Radial Basis Function Network-based Prediction of Global Solar Radiation Data: Application for Sizing of a Stand-alone Photovoltaic System at Al-Madinah. Energy, 35(9) , 2010 . M. Benghanem and A. Mellit. Radial Basis Function Network-based Prediction of Global Solar Radiation Data: Application for Sizing of a Stand-alone Photovoltaic System at Al-Madinah. Energy, 35(9), 2010."},{"issue":"5","key":"e_1_2_1_12_1","first-page":"431","volume":"70","author":"Blanco-Muriel M.","year":"2001","unstructured":"M. Blanco-Muriel , D. Alarcon-Padilla , T. Lopez-Moratalla , and M. Lara-Coira. Computing the Solar Vector. Solar Energy , 70 ( 5 ): 431 -- 441 , 2001 . M. Blanco-Muriel, D. Alarcon-Padilla, T. Lopez-Moratalla, and M. Lara-Coira. Computing the Solar Vector. Solar Energy, 70(5):431--441, 2001.","journal-title":"Lara-Coira. Computing the Solar Vector. Solar Energy"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077839.3077848"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993422.2993573"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.solener.2015.06.017"},{"key":"e_1_2_1_16_1","first-page":"670","volume":"105","author":"Engerer N.","year":"2014","unstructured":"N. Engerer and F. Mills . Kpv : A Clear-sky Index for Photovoltaics. Solar Energy , 105 : 670 -- 693 , July 2014 . N. Engerer and F. Mills. Kpv: A Clear-sky Index for Photovoltaics. Solar Energy, 105:670--693, July 2014.","journal-title":"A Clear-sky Index for Photovoltaics. Solar Energy"},{"key":"e_1_2_1_17_1","volume-title":"The Price of Solar Is Declining to Unprecedented Lows, August 27th","author":"Fares R.","year":"2016","unstructured":"R. Fares . Scientific American , The Price of Solar Is Declining to Unprecedented Lows, August 27th 2016 . R. Fares. Scientific American, The Price of Solar Is Declining to Unprecedented Lows, August 27th 2016."},{"key":"e_1_2_1_18_1","first-page":"423","volume":"86","author":"Hammer A.","year":"2003","unstructured":"A. Hammer , D. Heinemann , C. Hoyer , R. Kuhlemann , E. Lorenz , R. Muller , and H. Beyer . Solar Energy Assessment using Remote Sensing Technologies. Remote Sensing of Environment , 86 : 423 -- 432 , 2003 . A. Hammer, D. Heinemann, C. Hoyer, R. Kuhlemann, E. Lorenz, R. Muller, and H. Beyer. Solar Energy Assessment using Remote Sensing Technologies. Remote Sensing of Environment, 86:423--432, 2003.","journal-title":"Solar Energy Assessment using Remote Sensing Technologies. Remote Sensing of Environment"},{"key":"e_1_2_1_19_1","volume-title":"Solar Panel Anomaly Detection and Classification. Technical report","author":"Hu B.","year":"2012","unstructured":"B. Hu . Solar Panel Anomaly Detection and Classification. Technical report , University of Waterloo , 2012 . B. Hu. Solar Panel Anomaly Detection and Classification. Technical report, University of Waterloo, 2012."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2674061.2674071"},{"key":"e_1_2_1_21_1","volume-title":"July 8th","author":"John J. S.","year":"2014","unstructured":"J. S. John . Bidgely Thinks Algorithms Can Replace Hardware to Capture the Impact of Rooftop Solar , July 8th 2014 . J. S. John. Bidgely Thinks Algorithms Can Replace Hardware to Capture the Impact of Rooftop Solar, July 8th 2014."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993422.2996419"},{"key":"e_1_2_1_23_1","volume-title":"Solar Energy Forecasting and Resource Assessment","author":"Kleissl J.","year":"2013","unstructured":"J. Kleissl . Solar Energy Forecasting and Resource Assessment . Academic Press , Waltham, Massachusetts , 2013 . J. Kleissl. Solar Energy Forecasting and Resource Assessment. Academic Press, Waltham, Massachusetts, 2013."},{"key":"e_1_2_1_24_1","unstructured":"S. Marcacci. US Solar Energy Capacity Grew An Astounding 418% From 2010-2014 April 24th 2014.  S. Marcacci. US Solar Energy Capacity Grew An Astounding 418% From 2010-2014 April 24th 2014."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1029\/2000GL011743"},{"key":"e_1_2_1_26_1","volume-title":"Sandia National Laboratories","author":"Reno J. S. S.","year":"2012","unstructured":"J. S. S. Matthew J. Reno , Clifford W. Hansen . Global Horizontal Irradiance Clear Sky Models: Implementation and Analysis. Technical report , Sandia National Laboratories , March 2012 . J. S. S. Matthew J. Reno, Clifford W. Hansen. Global Horizontal Irradiance Clear Sky Models: Implementation and Analysis. Technical report, Sandia National Laboratories, March 2012."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2012.02.012"},{"key":"e_1_2_1_28_1","volume-title":"NILM Workshop","author":"Mohan R.","year":"2014","unstructured":"R. Mohan , T. Cheng , A. Gupta , V. Garud , and Y. He . Solar Energy Disaggregation using Whole-House Consumption Signals . In NILM Workshop , June 2014 . R. Mohan, T. Cheng, A. Gupta, V. Garud, and Y. He. Solar Energy Disaggregation using Whole-House Consumption Signals. In NILM Workshop, June 2014."},{"key":"e_1_2_1_30_1","volume-title":"Broadband Hourly Clear Sky Model. In Annual conference of the American Solar Energy Society (SOLAR)","author":"Myers D.","year":"2006","unstructured":"D. Myers . Cloudy Sky Version of Bird's Broadband Hourly Clear Sky Model. In Annual conference of the American Solar Energy Society (SOLAR) , July 2006 . D. Myers. Cloudy Sky Version of Bird's Broadband Hourly Clear Sky Model. In Annual conference of the American Solar Energy Society (SOLAR), July 2006."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/SmartGridComm.2011.6102379"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/PVSC.2012.6318225"},{"key":"e_1_2_1_33_1","volume-title":"Renewable Energy","author":"Voyant C.","year":"2017","unstructured":"C. Voyant , G. Notton , S. Kalogirou , M. Nivet , C. Paoli , F. Motte , and A. Fouilloy . Machine Learning Methods for Solar Radiation Forecasting: A Review . Renewable Energy , 105, May 2017 . C. Voyant, G. Notton, S. Kalogirou, M. Nivet, C. Paoli, F. Motte, and A. Fouilloy. Machine Learning Methods for Solar Radiation Forecasting: A Review. Renewable Energy, 105, May 2017."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1080\/14786450701549824"}],"container-title":["ACM SIGMETRICS Performance Evaluation Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3152042.3152067","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3152042.3152067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:26:26Z","timestamp":1750213586000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3152042.3152067"}},"subtitle":["Comparing Physical, Machine Learning, and Hybrid Approaches"],"short-title":[],"issued":{"date-parts":[[2017,10,11]]},"references-count":33,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,10,11]]}},"alternative-id":["10.1145\/3152042.3152067"],"URL":"https:\/\/doi.org\/10.1145\/3152042.3152067","relation":{},"ISSN":["0163-5999"],"issn-type":[{"type":"print","value":"0163-5999"}],"subject":[],"published":{"date-parts":[[2017,10,11]]},"assertion":[{"value":"2017-10-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}