[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121913-en":3,"doc-seo-121913-105":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":20,"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},121913,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Machine Learning Approaches for Efficient Forecasting of LEED Accredited Building Energy","Traditional fossil-fuel-based energy sources are limited and have significant environmental impacts, driving climate change. Reducing global CO2 emissions to net zero by 2050 is essential, with building operations responsible for large shares of energy use and greenhouse-gas emissions. This thesis develops advanced machine learning models to forecast building energy consumption using University of California, Irvine campus data. Artificial Neural Networks and a Long Short-Term Memory model are evaluated with optimized training functions, parameters, and early stopping criteria to improve efficiency, accuracy, and practical interpretability under limited data.","UC Irvine  \nUC Irvine Electronic Theses and Dissertations  \nTitle  \nMachine Learning Approaches for Efficient Forecasting of LEED Accredited Building Energy  \nPermalink  \n[https://escholarship.org/uc/item/5h3389b9](https://escholarship.org/uc/item/5h3389b9)  \nAuthor  \nWu, Yu-Ping  \nPublication Date  \n2024  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA,  \nIRVINE  \nMachine Learning Approaches for Efficient Forecasting of LEED Accredited Building Energy  \nTHESIS  \nsubmitted in partial satisfaction of the requirements  \nfor the degree of  \nMASTER OF SCIENCE  \nin Mechanical and Aerospace Engineering  \nby  \nYu-Ping Wu  \nThesis Committee: Professor Yun Wang, Chair Professor David Copp Professor Penghui Cao  \n2024  \n© 2024 Yu-Ping Wu  \nDEDICATION  \nThis study is dedicated to Professor Yun Wang for his unwavering support and guidance. Professor Wang not only supported my thesis journey but also ignited my interest in the field of renewable energy since my undergraduate studies.  \nI would like to express my gratitude to my thesis committee members, Professor Penghui Cao and Professor David Copp, for their invaluable suggestions and support throughout  \nthis process.  \nThanks to my friends and family, especially my parents, for their unconditional love and support, which carried me through to the completion of this thesis. Special thanks to my dog Kiru for being my constant emotional support, offering unlimited furry hugs.  \nFinally, I dedicate this work to all the researchers working on bringing advanced technology to renewable energy and green technology, making the world a cleaner place.  \nTABLE OF CONTENTS  \nPage  \nDEDICATION i  \nTABLE OF CONTENTS ii  \nLIST OF FIGURES iii  \nLIST OF TABLES iv  \nACKNOWLEDGEMENTS v  \nABSTRACT OF THE THESIS vi  \nChapter 1. Introduction 1  \n1.1 Background 1  \n1.2 Objectives 3  \nChapter 2. LEED-Certified Building Profile and Energy Data Analysis 6  \n2.1 LEED-Certified Building 6  \n2.2 Data Analysis 8  \nChapter 3. Neural Network Architecture 10  \n3.1 Artificial Neural Network (ANN) 10  \n3.1.1 Levenberg-Marquardt Algorithm 13  \n3.1.2 Bayesian Regularization Algorithm 16  \n3.2 Long Short-Term Memory (LSTM) network 10  \n3.3 Model Performance and Regularization Methods 18  \n3.4 Forecasting Method 21  \nChapter 4: Results and Discussion 23  \n4.1 Optimizing Early Stopping Criteria for ANN Models 23  \n4.2 Forecast Evaluation Using ANN Models 25  \n4.3 Prediction of LSTM Model 28  \nChapter 5: Conclusion 31  \nREFERENCES 33  \nLIST OF FIGURES  \nFigure 1: The BioSci3 building(left) and the location (right) 7  \nFigure 2: Hourly data in 2019 8  \nFigure 3: Daily average in the 4 seasons and the entire year (in 24 hours) 9  \nFigure 4: Artificial Neural Network Node 11  \nFigure 5: ANN Model Architecture 12  \nFigure 6: RNNs Recurrent Unit 17  \nFigure 7: Example of Early Stopping 20  \nFigure 8: Building Load Forecasting Method 22  \nFigure 9: Early Stopping Criteria: Next 72 Hour Accuracy for ANN-LM 24  \nFigure 10: Early Stopping Criteria: Next 72 Hour Accuracy for ANN-BR 24  \nFigure 11: Next 336 Hour Accuracy of ANN Models by Training Functions 26  \nFigure 12: Next 72 Hour Prediction using the LSTM model 30  \nFigure 13: Next 336 Hour Prediction using the LSTM model 30  \nLIST OF TABLES  \nTable 1: Accuracy of ANN-BR and ANN-LM at Different Time Intervals 27  \nTable 2: Accuracy Results by Timesteps for Batch Size 29  \nTable 3: Accuracy Results by Timesteps for Batch Size 29  \nACKNOWLEDGEMENTS  \nThe author would like to thank the UCI central plant for their support in providing access to building site load data for data analysis and neural network modeling.  \nABSTRACT OF THE THESIS  \nMachine Learning Approaches for Efficient Forecasting of LEED Accredited Building Energy  \nby  \nYu-Ping Wu  \nMaster of Science in Mechanical and Aerospace Engineering  \nUniversity of California, Irvine, 2024  \nProfessor Yun Wang, ","cbCaidI0zeOAhgva","https://ap.wps.com/l/cbCaidI0zeOAhgva","pdf",1432586,1,45,"English","en",105,"# Chapter 1. Introduction\n## 1.1 Background\n## 1.2 Objectives\n# Chapter 2. LEED-Certified Building Profile and Energy Data Analysis\n## 2.1 LEED-Certified Building\n## 2.2 Data Analysis\n# Chapter 3. Neural Network Architecture\n## 3.1 Artificial Neural Network (ANN)\n## 3.2 Long Short-Term Memory (LSTM) network\n## 3.3 Model Performance and Regularization Methods\n## 3.4 Forecasting Method\n# Chapter 4. Results and Discussion\n## 4.1 Optimizing Early Stopping Criteria for ANN Models\n## 4.2 Forecast Evaluation Using ANN Models\n## 4.3 Prediction of LSTM Model\n# Chapter 5. Conclusion","[{\"question\":\"What is the main goal of the thesis?\",\"answer\":\"To develop machine learning models that forecast LEED-accredited building energy consumption efficiently and accurately using UCI campus energy data.\"},{\"question\":\"Which machine learning models are investigated?\",\"answer\":\"Two ANN models based on the Levenberg–Marquardt and Bayesian Regularization algorithms, and a Long Short-Term Memory (LSTM) model.\"},{\"question\":\"How are overfitting and forecast performance addressed?\",\"answer\":\"Early stopping criteria are evaluated for the ANN models, while LSTM training inputs such as timesteps and batch sizes are configured, and forecast evaluation compares short-term (24 hours) and long-term (336 hours) predictions.\"}]","Machine Learning Approaches for Efficient Forecasting of LEED Accredited Building Energy | PDF",1785807709,113,{"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-approaches-for-efficient-forecasting-of-leed-accredited-building-energy","",{"@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-approaches-for-efficient-forecasting-of-leed-accredited-building-energy/121913/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main goal of the thesis?","Question",{"text":75,"@type":76},"To develop machine learning models that forecast LEED-accredited building energy consumption efficiently and accurately using UCI campus energy data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning models are investigated?",{"text":80,"@type":76},"Two ANN models based on the Levenberg–Marquardt and Bayesian Regularization algorithms, and a Long Short-Term Memory (LSTM) model.",{"name":82,"@type":73,"acceptedAnswer":83},"How are overfitting and forecast performance addressed?",{"text":84,"@type":76},"Early stopping criteria are evaluated for the ANN models, while LSTM training inputs such as timesteps and batch sizes are configured, and forecast evaluation compares short-term (24 hours) and long-term (336 hours) predictions.","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"]