[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118515-en":3,"doc-seo-118515-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118515,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Machine Learning and Weather Model Combination for PV Production Forecasting","Accurate photovoltaic generation forecasts are essential for reliable power system operation under highly variable solar radiation, especially in microgrids and grids where generation, load, and storage must be balanced to prevent grid imbalance conditions. The study evaluates machine learning methods combined with photovoltaic forecasts produced by weather models. Linear models are benchmarked against approaches including LSTM, XGBoost, and LightGBM, showing linear models as most effective, delivering at least a 3.7% RMSE improvement over numerical weather prediction baselines, including in low-data settings for recently established plants.","energies   \nArticle  \nMachine Learning and Weather Model Combination for PV Production Forecasting  \nAmedeo Buonanno , Giampaolo Caputo *, Irena Balog , Salvatore Fabozzi , Giovanna Adinolfi, Francesco Pascarella, Gianni Leanza, Giorgio Graditi  and Maria Valenti  \nCitation: Buonanno, A.; Caputo, G.; Balog, I.; Fabozzi, S.; Adinolfi, G.; Pascarella, F.; Leanza, G.; Graditi, G.; Valenti, M. Machine Learning and Weather Model Combination for PV Production Forecasting. Energies 2024, 17, 2203. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)en17092203  \nAcademic Editor: Younes Mohammadi  \nReceived: 22 March 2024  \nRevised: 24 April 2024  \nAccepted: 25 April 2024  \nPublished: 3 May 2024  \nCopyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \nItalian National Agency for New Technologies, Energy and Sustainable Economic Development (ENEA),  \n00196 Rome, Italy; [amedeo.buonanno@enea.it](amedeo.buonanno@enea.it) (A.B.); [irena.balog@enea.it](irena.balog@enea.it) (I.B.); [salvatore.fabozzi@enea.it](salvatore.fabozzi@enea.it) (S.F.); giovanna.adinolfi@enea.it (G.A.); francesco.pascarella@enea.it (F.P.); gianni.leanza@enea.it (G.L.);  \ngiorgio.graditi@enea.it (G.G.); [maria.valenti@enea.it](maria.valenti@enea.it) (M.V.)  \n* Correspondence: [giampaolo.caputo@enea.it](giampaolo.caputo@enea.it)  \nAbstract: Accurate predictions of photovoltaic generation are essential for effectively managing power system resources, particularly in the face of high variability in solar radiation. This is especially crucial in microgrids and grids, where the proper operation of generation, load, and storage resources is necessary to avoid grid imbalance conditions. Therefore, the availability of reliable prediction models is of utmost importance. Authors address this issue investigating the potential benefits of a machine learning approach in combination with photovoltaic power forecasts generated using weather models. Several machine learning methods have been tested for the combined approach (linear model, Long Short-Term Memory, eXtreme Gradient Boosting, and the Light Gradient Boosting Machine) . Among them, the linear models were demonstrated to be the most effective with at least an RMSE improvement of 3.7% in photovoltaic production forecasting, with respect to two numerical weather prediction based baseline methods. The conducted analysis shows how machine learning models can be used to refine the prediction of an already established PV generation forecast model and highlights the efficacy of linear models, even in a low-data regime as in the case of recently established plants.  \nKeywords: machine learning; PV forecasting; microgrids; signal processing  \n1. Introduction  \nClimate change is deeply related to anthropic activities on earth, especially those of the industrial, agriculture, energy production, and transport sectors. Decarbonization is a challenging task in such contexts. It requires novel methods, technologies, strategies, and systems. In the last few decades, considerable efforts have been made by scientists and researchers to facilitate the decarbonization pathway. This is particularly true in the energy sector with numerous implemented initiatives to reduce its Greenhouse Gas (GHG) emissions [1] . These initiatives increasingly also have an economic assessment of the problem [2] underlining how the effects of global warming have negative repercussions on local or global economies, and also how risk mitigation interventions are much less expensive than the consequences of possible extreme events due to ongoing climate change [3] . From apolitical point of view, both national and international energy trans","cbCaik1eWJOqzCUb","https://ap.wps.com/l/cbCaik1eWJOqzCUb","pdf",2988153,1,15,"English","en",105,"# Introduction\n## Microgrids and renewable integration\n## Climate change, decarbonization, and electrification\n# Method and Approach\n## Machine learning combined with weather-based PV forecasts\n## Evaluated models and baseline comparisons\n# Results and Discussion\n## RMSE improvement over numerical weather prediction baselines\n## Effectiveness in low-data regimes\n# Conclusion","[{\"question\":\"Why are accurate photovoltaic (PV) production forecasts important in microgrids?\",\"answer\":\"They support proper operation of generation, load, and storage resources, helping avoid grid imbalance conditions caused by variable solar radiation.\"},{\"question\":\"Which machine learning methods are tested for combining with weather-model PV forecasts?\",\"answer\":\"The study tests linear models, Long Short-Term Memory (LSTM), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM).\"},{\"question\":\"How do the results compare to numerical weather prediction baseline methods?\",\"answer\":\"Linear models provide at least a 3.7% RMSE improvement in PV production forecasting compared with two numerical weather prediction-based baselines.\"}]","Machine Learning and Weather Model Combination for PV Production Forecasting | PDF",1785683948,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-and-weather-model-combination-for-pv-production-forecasting","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-and-weather-model-combination-for-pv-production-forecasting/118515/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are accurate photovoltaic (PV) production forecasts important in microgrids?","Question",{"text":75,"@type":76},"They support proper operation of generation, load, and storage resources, helping avoid grid imbalance conditions caused by variable solar radiation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning methods are tested for combining with weather-model PV forecasts?",{"text":80,"@type":76},"The study tests linear models, Long Short-Term Memory (LSTM), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM).",{"name":82,"@type":73,"acceptedAnswer":83},"How do the results compare to numerical weather prediction baseline methods?",{"text":84,"@type":76},"Linear models provide at least a 3.7% RMSE improvement in PV production forecasting compared with two numerical weather prediction-based baselines.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]