[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123285-en":3,"doc-seo-123285-105":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},123285,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Photovoltaic Installations - Performance Analysis Based on Machine Learning Techniques","This paper studies performance analysis of photovoltaic (PV) installations using machine learning techniques. It uses a mixed dataset combining power-generation measurements from an experimental PV system at Brunel University London and the corresponding weather data. Sensitivity relationships between PV power output and weather conditions are established with Random Forest-based methods, and model fitness is evaluated through cross-validation across different ML approaches. Results compare effectiveness and identify best-performing techniques to support accurate, reliable forecasting and renewable energy optimization under varying environmental conditions.","This article has been accepted for publication in a future proceedings of this conference, but has not been fully edited. Content may change prior to final publication. Citation information: DOI: 10. 1109/UPEC61344 .2024. 10892390, 2024 59th International Universities Power Engineering Conference (UPEC)  \nPerformance Analysis of Photovoltaic Installations Based on Machine Learning Techniques  \nDaniil Hulak  \nDepartment of Electronic and Electrical Engineering Brunel University London London, UK [Daniil.Hulak@brunel.ac.uk](Daniil.Hulak@brunel.ac.uk)  \nYang Xie  \nSchool of Cyber Science and Engineering Southeast University Nanjing China [Yang.Xie@brunel.ac.uk](Yang.Xie@brunel.ac.uk)  \nGareth Taylor  \nDepartment of Electronic and Electrical Engineering Brunel University London London, UK [Gareth.Taylor@brunel.ac.uk](Gareth.Taylor@brunel.ac.uk)  \nAbstract—This paper investigates the novel performance analysis of photovoltaic (PV) installations by applying machine learning techniques (ML). The data used for the research is a mixed dataset of data from an experimental PV installation located at Brunel University London with correspondingly available weather data. Firstly, the analysis aims to establish various sensitivity relationships between PV power generation and weather conditions using techniques based on Random Forest ML. Secondly, the processing stage is implemented to assess the fitness of the different ML techniques through cross-validation. The results highlight the differing effectiveness of the applied approaches in achieving accurate and reliable results for the PV installations. The best techniques offer valuable insights for optimizing renewable energy usage in diverse environmental conditions.  \nIndex Terms—Generation Forecasting, Machine Learning, Photovoltaic Installation, Solar Irradiance  \nI. INTRODUCTION  \nIn recent years, the global energy profile has changed rapidly, shifting towards the higher penetration of renewable energy sources (RES) . Among these, photovoltaic (PV) installations have emerged as one of the key players, contributing significantly to the power generation mix. Increasing RES penetration aligns with the efforts to address climate change, reaching Net Zero and transitioning towards sustainable energy practices. PV power generation globally increased by a record 270 TWh, up 26% in 2022, reaching almost 1 300 TWh. It demonstrated the largest absolute power generation growth of all renewable technologies in 2022, surpassing wind for the first time in history [1] .  \nThe development of RES, particularly PV installations, creates a significant challenge to the reliable and efficient energy supply for the existing power systems. PV are heavily dependent on meteorological conditions, and predicting their power generation is a complex and dynamic task. As solar power production is linked to weather patterns, accurate forecasting becomes essential to ensure grid stability, optimal resource utilization, and effective energy management.  \nThe rise of distributed generation in the form of residential PV installations also started to be a growing challenge for  \nsystem operators. Unlike centralised power generators, equipped with advanced monitoring systems, individual households typically do not install additional weather monitors simultaneously with their PV installations. As a result, they concentrate data on their power generation, but not on the weather conditions. This data gap creates significant challenges to accurate forecasting of weather-dependent output from these distributed sources. The absence of real-time weather data complicates integrating these decentralised power resources into the overall power system, highlighting the need for innovative approaches.  \nIn response to these challenges, this paper investigates the application of machine learning (ML) models for predicting power generation of distributed PV installations. Using the capabilities of ML, we aim to enhance the accuracy and ","cbCaic3LEJ0Fc3qB","https://ap.wps.com/l/cbCaic3LEJ0Fc3qB","pdf",1038653,1,6,"English","en",105,"# Introduction\n# Data Description\n## PV installation data and general characteristics","[{\"question\":\"What dataset is used for the PV performance analysis?\",\"answer\":\"The study uses power-generation data from an experimental PV installation at Brunel University London together with available weather data. This mixed dataset supports learning relationships between output and meteorological conditions.\"},{\"question\":\"How are weather–power relationships modeled in the paper?\",\"answer\":\"The analysis first establishes sensitivity relationships between PV power generation and weather conditions using Random Forest-based machine learning techniques.\"},{\"question\":\"How is the performance of different ML techniques evaluated?\",\"answer\":\"Model fitness is assessed using cross-validation, and the results compare how effectively each applied approach achieves accurate and reliable predictions for PV installations under different conditions.\"}]","Photovoltaic Installations - Performance Analysis Based on Machine Learning Techniques | PDF",1785815750,15,{"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},"photovoltaic-installations-performance-analysis-based-on-machine-learning-techniques","",{"@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/photovoltaic-installations-performance-analysis-based-on-machine-learning-techniques/123285/",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},"What dataset is used for the PV performance analysis?","Question",{"text":75,"@type":76},"The study uses power-generation data from an experimental PV installation at Brunel University London together with available weather data. This mixed dataset supports learning relationships between output and meteorological conditions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are weather–power relationships modeled in the paper?",{"text":80,"@type":76},"The analysis first establishes sensitivity relationships between PV power generation and weather conditions using Random Forest-based machine learning techniques.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the performance of different ML techniques evaluated?",{"text":84,"@type":76},"Model fitness is assessed using cross-validation, and the results compare how effectively each applied approach achieves accurate and reliable predictions for PV installations under different conditions.","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},[93,97,101,105,110,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]