[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127105-en":3,"doc-seo-127105-105":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},127105,5909887254083,"Miles","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Statistical and Machine Learning Techniques for Predicting Solar Power Generation in a Microgrid - Master of Science in Data Analytics Thesis","This study applies statistical and machine learning models to forecast solar power generation in microgrids, with emphasis on the solar installation at Powell-Focht Bioengineering Hall (University of California San Diego). Because solar output is variable and intermittent, accurate forecasts are essential for optimizing microgrid operations and improving solar power utilization efficiency. Models assessed include SARIMAX, LSTM, Random Forest, and ANN using meteorological and generation time-series features. Results show current meteorological conditions, especially solar radiation, improve short-term forecasting; the Random Forest Auto Regressor is best for 10-day ahead prediction, followed by SARIMAX. The work supports renewable energy forecasting with comparative model insights and practical implications for microgrid energy management, recommending clear-sky radiation combined with ground-level radiation and suggesting future integration into real-time control and weather-aware systems.","CCT College Dublin  \nARC (Academic Research Collection)  \nICT  \n2024  \nStatistical and Machine Learning Techniques for Predicting Solar Power Generation in a Microgrid.  \nConor Dillon  \nCCT College Dublin  \nFollow this and additional works at: [https://arc.cct.ie/ict](https://arc.cct.ie/ict)  \n Part of the Computer Sciences Commons, and the Data Science Commons  \nRecommended Citation  \nDillon, Conor, \"Statistical and Machine Learning Techniques for Predicting Solar Power Generation in a Microgrid.\" (2024) . ICT. 67.  \n[https://arc.cct.ie/ict/67](https://arc.cct.ie/ict/67)  \nThis Capstone Project is brought to you for free and open access by ARC (Academic Research Collection) . It has been accepted for inclusion in ICT by an authorized administrator of ARC (Academic Research Collection) . For more information, please [contact](contact debora@cct.ie)[ debora@cct.ie](contact debora@cct.ie).  \nStatistical and Machine Learning Techniques for Predicting Solar  \nPower Generation in a Microgrid  \nConor Dillon  \nA Thesis Submitted in Partial Fulfilment of the requirements for the  \nDegree of  \nMaster of Science in Data Analytics  \nFebruary 2024  \nSupervisor: David McQuaid  \nStatistical and Machine Learning Methods for Predicting Solar Power  \nGeneration in Microgrids  \nConor Dillon  \nFebruary 23, 2024  \nAbstract  \nThis study explores the application of statistical and machine learning models for forecasting solar power generation within microgrids, with a particular focus on the solar installation at Powell-Focht Bioengineering Hall at the University of California San Diego. Given the inherent variability and intermittency of solar energy, accurate forecasting models are crucial for optimising the operation of microgrids and enhancing the efficiency of solar power utilisation. This research evaluates the performance of Seasonal Autoregressive Integrated Moving Average (SARIMAX), Long Short-Term Memory (LSTM) networks, Random Forest, and Artificial Neural Networks (ANN) in predicting solar power output. The study processes and analyses meteorological and solar power generation time series to identify key features influencing solar power generation. The findings indicate that models utilising current meteorological conditions, particularly solar radiation, are more effective for short-term solar power forecasting compared to those relying more on pattern recognition. The Random Forest Auto Regressor emerged as the most accurate model on this dataset for forecasting 10 day ahead solar power generation, emphasising the significance of instantaneous values over historical patterns in predicting solar power output. The performance of RFAR is closely followed by the SARIMAX model. This research contributes to the field of renewable energy forecasting by providing insights into the comparative advantages of various forecasting models and suggests practical applications for microgrid energy management systems. A recommendation is determined that clear-sky radiation should be used in conjunction with ground-level solar radiation as this isolates solar energy availability from meteorological effects. Future work may explore the integration of these models into real-time control systems and the impact of advanced weather prediction technologies on forecasting accuracy.  \nContents  \n1 Introduction .................................................................................................................................................. 7  \n2 Literature Review.......................................................................................................................................... 7  \n2.1 Innovations in the Energy Grid ................................................................................................................... 7  \n2.2 Time Series Forecasting.............................................................................................................................. 8  \n2.3 Weather Forecasting .............","cbCaiax5b92VwgaW","https://ap.wps.com/l/cbCaiax5b92VwgaW","pdf",1809566,1,43,"English","en",105,"# Contents\n## Introduction\n## Literature Review\n## Research Design\n## Exploratory Data Analysis","[{\"question\":\"Which forecasting models are evaluated for solar power generation in the microgrid?\",\"answer\":\"The research evaluates SARIMAX, LSTM networks, Random Forest, and Artificial Neural Networks (ANN) for predicting solar power output.\"},{\"question\":\"What factors most improve short-term solar power forecasting in this study?\",\"answer\":\"Using current meteorological conditions—especially solar radiation—proves more effective for short-term forecasting than relying primarily on historical pattern recognition.\"},{\"question\":\"Which model performs best for 10-day ahead forecasting on the dataset?\",\"answer\":\"The Random Forest Auto Regressor is the most accurate model for forecasting 10 days ahead, with performance closely followed by SARIMAX.\"}]","Statistical and Machine Learning Techniques for Predicting Solar Power Generation in a Microgrid - Master of Science in Data Analytics Thesis | PDF",1785936865,108,{"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},"statistical-and-machine-learning-techniques-for-predicting-solar-power-generation-in-a-microgrid-master-of-science-in-data-analytics-thesis","",{"@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/statistical-and-machine-learning-techniques-for-predicting-solar-power-generation-in-a-microgrid-master-of-science-in-data-analytics-thesis/127105/",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","2026-08-05",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},"Which forecasting models are evaluated for solar power generation in the microgrid?","Question",{"text":75,"@type":76},"The research evaluates SARIMAX, LSTM networks, Random Forest, and Artificial Neural Networks (ANN) for predicting solar power output.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What factors most improve short-term solar power forecasting in this study?",{"text":80,"@type":76},"Using current meteorological conditions—especially solar radiation—proves more effective for short-term forecasting than relying primarily on historical pattern recognition.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model performs best for 10-day ahead forecasting on the dataset?",{"text":84,"@type":76},"The Random Forest Auto Regressor is the most accurate model for forecasting 10 days ahead, with performance closely followed by SARIMAX.","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"]