[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120954-en":3,"doc-seo-120954-105":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},120954,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Machine Learning Applications in Day-Ahead Electricity Price Forecasting - Thesis Methods and Results","Machine learning based time series forecasting approaches are reviewed and applied to the day-ahead electricity price forecasting problem. The work surveys transformer models for time series forecasting and also covers two MLP-based methods, NBEATSx and NHiTS, along with XGBoost. Four models—NBEATSx, NHiTS, Temporal Fusion Transformer, and XGBoost—are tested on PJM electricity price data, and adaptive conformal inference is used to construct prediction intervals. NBEATSx and NHiTS achieve the strongest performance, and small model ensembles improve accuracy.","UCLA  \nUCLA Electronic Theses and Dissertations  \nTitle  \nMachine Learning Applications in Day-Ahead Electricity Price Forecasting  \nPermalink  \n[https://escholarship.org/uc/item/2k24j8jz](https://escholarship.org/uc/item/2k24j8jz)  \nAuthor  \nBell, Vincent  \nPublication Date  \n2024  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA  \nLos Angeles  \nMachine Learning Applications in Day-Ahead Electricity Price Forecasting  \nA thesis submitted in partial satisfaction of the requirements for the degree  \nMaster of Science in Statistics  \nby  \nVincent Matthew Bell  \n2024  \n© Copyright by Vincent Matthew Bell  \n2024  \nABSTRACT OF THE THESIS  \nMachine Learning Applications in Day-Ahead Electricity Price Forecasting  \nby  \nVincent Matthew Bell  \nMaster of Science in Statistics  \nUniversity of California, Los Angeles, 2024  \nProfessor Yingnian Wu, Chair  \nThis study reviews machine learning based time series forecasting approaches and applies them to the day-ahead electricity price forecasting problem. We review the literature on transformer models for time series forecasting, in addition to two MLP-based methods, NBEATSx and NHiTS, and XGBoost. Four models are chosen and implemented: NBEATSx, NHiTS, Temporal Fusion Transformer, XGBoost. They are tested on electricity price data from the PJM market. We product prediction intervals using adaptive conformal inference. We find that NBEATSx and NHiTS perform best on this dataset. We find that by averaging as few as two models, we are able to significantly improve prediction accuracy.  \nThe thesis of Vincent Matthew Bell is approved.  \nOscar Hernan Madrid Padilla Frederic R. Paik Schoenberg Yingnian Wu, Committee Chair  \nUniversity of California, Los Angeles 2024  \nTABLE OF CONTENTS  \n1 Electricity Price Forecasting ............................ 1  \n2 Background: Machine Learning Models for Forecasting .......... 4  \n2.1 Transformers for Time Series Forecasting .................... 4  \n2.1.1 Attention ................................. 5  \n2.1.2 Transformer ................................ 7  \n2.1.3 Log Sparse Transformer ......................... 9  \n2.1.4 Informer .................................. 10  \n2.1.5 Autoformer ................................ 12  \n2.1.6 FEDFormer ................................ 15  \n2.1.7 Temporal Fusion Transformer ...................... 16  \n2.2 MLP-Based Time Series Methods ........................ 18  \n2.2.1 NBEATS and NBEATSx ......................... 18  \n2.2.2 NHITS ................................... 19  \n2.3 Gradient Boosted Trees .............................. 20  \n2.3.1 Regression Trees ............................. 20  \n2.3.2 Boosted Tree Models ........................... 21  \n2.3.3 Gradient Boosted Tree Models and XGBoost .............. 22  \n2.4 Conformal Inference ............................... 23  \n3 Methods ........................................ 27  \n3.1 Experiments and Methodology .......................... 27  \n4 Conclusion ....................................... 36  \nReferences ......................................... 38  \nLIST OF FIGURES  \n3.1 Train Val Test Split .................................. 27  \n3.2 A low-error week and high-error week for each model ............... 33  \n3.3 Model predictions with ACI prediction intervals .................. 35  \nLIST OF TABLES  \n3.1 Hyperparameter search space for XGBoost models ................. 30  \n3.2 Hyperparameter search space for NBEATSx model with optimal values ..... 31  \n3.3 Hyperparameter search space for NHiTS model with optimal values ....... 32  \n3.4 Hyperparameter search space for TFT model with optimal values ........ 33  \n3.5 Model Test Error ................................... 33  \n3.6 Best Model Combinations for rMSE and MAE. XGB1 represents the XGBoost model with only d − 1 lags on the target variable; XGB2 is the XGBoost model with all lags; XGB3 is the XGBoos","cbCaieGM5oBMtk4F","https://ap.wps.com/l/cbCaieGM5oBMtk4F","pdf",11446230,1,49,"English","en",105,"# Electricity Price Forecasting\n# Background: Machine Learning Models for Forecasting\n## Transformers for Time Series Forecasting\n## MLP-Based Time Series Methods\n## Gradient Boosted Trees\n## Conformal Inference\n# Methods\n## Experiments and Methodology\n# Conclusion","[{\"question\":\"Which forecasting models are implemented in the thesis?\",\"answer\":\"NBEATSx, NHiTS, Temporal Fusion Transformer, and XGBoost are selected and implemented for comparison on PJM electricity price data.\"},{\"question\":\"How are prediction intervals produced in this study?\",\"answer\":\"The study uses adaptive conformal inference to construct prediction intervals for the day-ahead electricity price forecasts.\"},{\"question\":\"What dataset and evaluation result are reported for model performance?\",\"answer\":\"Models are tested on electricity price data from the PJM market, where NBEATSx and NHiTS perform best on the dataset.\"}]","Machine Learning Applications in Day-Ahead Electricity Price Forecasting - Thesis Methods and Results | PDF",1785733039,123,{"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-applications-in-day-ahead-electricity-price-forecasting-thesis-methods-and-results","",{"@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-applications-in-day-ahead-electricity-price-forecasting-thesis-methods-and-results/120954/",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","2026-08-03",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},"Which forecasting models are implemented in the thesis?","Question",{"text":75,"@type":76},"NBEATSx, NHiTS, Temporal Fusion Transformer, and XGBoost are selected and implemented for comparison on PJM electricity price data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are prediction intervals produced in this study?",{"text":80,"@type":76},"The study uses adaptive conformal inference to construct prediction intervals for the day-ahead electricity price forecasts.",{"name":82,"@type":73,"acceptedAnswer":83},"What dataset and evaluation result are reported for model performance?",{"text":84,"@type":76},"Models are tested on electricity price data from the PJM market, where NBEATSx and NHiTS perform best on the dataset.","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"]