[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122699-en":3,"doc-seo-122699-105":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},122699,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Machine Learning models for the estimation of the production of large utility-scale photovoltaic plants - Hyperparameter optimization and Random Forest comparison","Photovoltaic energy development has accelerated through deployment of large utility-scale plants characterized by extensive panel fields and high-power inverters. Accurate production forecasting supports failure detection, identification of deviations, and stable grid integration. This work builds machine learning estimators for large plants using measured non-uniform radiation represented across multiple meteorological stations. Systematic hyperparameter optimization improves performance over multiple linear regression, with Random Forest achieving RMS errors from 1.9% to 5.4% and outperforming models reported for smaller PV systems.","Solar Energy 254 (2023) 88–101  \n| Machine Learning models for the estimation of the production of large utility-scale photovoltaic plants\u003Cbr>Ana P. Talayero, Julio J. Melero ∗, Andrés Llombart, Nurseda Y. Yürüşen\u003Cbr>Instituto Universitario de Investigación Mixto CIRCE (Fundación CIRCE - Universidad de Zaragoza), C/ Mariano Esquillor 15, 50018, Zaragoza, Spain |  |  |  |\n| --- | --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| Keywords:\u003Cbr>Photovoltaics\u003Cbr>Utility-scale PV plants Hyperparameters optimisation Machine Learning models PV power estimation |  | Photovoltaic (PV) energy development has increased in the last years mainly based on large utility-scale plants. These plants are characterised by a huge number of panels connected to high-power inverters occupying a large land area. An accurate estimation of the power production of the PV plants is needed for failure detection, identifying production deviations, and the integration of the plants into the power grid. Various studies have used Machine Learning estimation techniques developed on very small PV plants. This paper deals with large utility-scale plants and uses all the available information to represent the non-uniform radiation over the whole studied solar field. Variables measured in up to four meteorological stations and distributed across the plant are used. Three PV plants with 1, 2 and 4 meteorological stations have been used to develop Machine Learning models. The hyperparameters were systematically optimised, demonstrating the improvements by comparing with a simple model based on Multiple Linear Regression. The best results were obtained with the Random Forest technique for the three PV plants, providing a RMS error value ranging from 1.9% to 5.4%. The final models were compared with those found in the literature for tiny PV plants showing in general much better performance. |  |\n\n1. Introduction  \nSolar photovoltaic (PV) is an ever-expanding technology, with an annual growth rate in recent years of more than 20%(International Renewable Energy Agency - IRENA, 2021). The global PV capacity atthe end of 2020 was 714 GW (International Renewable Energy AgencyIRENA, 2021), and this figure will be doubled in the next five years. Its growth potential and lower generation costs will enable PV to become the most competitive energy source globally in the coming years.  \nThe modularity of this technology allows an easy and quick installation of different plant sizes, from a few watts for self-consumption to hundreds of megawatts for large utility-scale grid-connected plants. Large utility-scale PV plants are characterised by a huge number of panels (hundreds of thousands) connected to high-power inverters (megawatts of power) and occupying a large land area (tens of hectares). Its size makes finding malfunctioning parts more complicated, and the time to do that can be considerable. So, energy losses due to failures and unavailability can become significant in large plants.  \nThe availability and energy losses of the plants have been evaluated through reliability studies (Spertino et al., 2021b,a; Ketjoy et al., 2021), analysing the root causes of failures, and finding that inverters are  \nresponsible for the highest losses and unavailability. It was also concluded that availability in large plants was better due to advantageous maintenance contracts. Energy losses in utility-scale PV plants have also been estimated using performance analysis (Bansal et al., 2022; Dahmoun et al., 2021; Jed et al., 2021). Different climatic zones provided PR values ranging from 70% in hot climate (India) to 87% in cold climate (France) with yearly degradation rates varying from 0.2% to around 1%. It can be concluded that accurate knowledge of the photovoltaic production is essential not only to determine the performance of the plants and its evolution in time but also to characterise energy losses associated with possible component failures and to ensure the integ","cbCaijwSLtV1xtYa","https://ap.wps.com/l/cbCaijwSLtV1xtYa","pdf",3751894,1,14,"English","en",105,"# Introduction\n## Motivation for accurate PV production estimation\n## Reliability and energy-loss evaluation in large utility-scale plants\n## Modeling approaches: parametric vs. non-parametric","[{\"question\":\"Why is accurate power production estimation important for large utility-scale PV plants?\",\"answer\":\"It enables failure detection, identifies production deviations, supports performance tracking over time, characterizes energy losses linked to component failures, and improves grid integration.\"},{\"question\":\"What data setup is used to represent radiation variability in this study?\",\"answer\":\"The study uses measurements from up to four meteorological stations distributed across the solar field to capture non-uniform radiation over the plant.\"},{\"question\":\"How do the machine learning models compare with a simpler baseline?\",\"answer\":\"Hyperparameters are systematically optimized, and results are compared against a multiple linear regression model, showing measurable improvements.\"}]","Machine Learning models for the estimation of the production of large utility-scale photovoltaic plants - Hyperparameter optimization and Random Forest comparison | PDF",1785812328,35,{"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-models-for-the-estimation-of-the-production-of-large-utility-scale-photovoltaic-plants-hyperparameter-optimization-and-random-forest-comparison","",{"@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-models-for-the-estimation-of-the-production-of-large-utility-scale-photovoltaic-plants-hyperparameter-optimization-and-random-forest-comparison/122699/",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","2026-08-04",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 is accurate power production estimation important for large utility-scale PV plants?","Question",{"text":75,"@type":76},"It enables failure detection, identifies production deviations, supports performance tracking over time, characterizes energy losses linked to component failures, and improves grid integration.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data setup is used to represent radiation variability in this study?",{"text":80,"@type":76},"The study uses measurements from up to four meteorological stations distributed across the solar field to capture non-uniform radiation over the plant.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the machine learning models compare with a simpler baseline?",{"text":84,"@type":76},"Hyperparameters are systematically optimized, and results are compared against a multiple linear regression model, showing measurable improvements.","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"]