[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122843-en":3,"doc-seo-122843-105":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},122843,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Fairness-aware Machine Learning in Power Grids - Thesis","Fairness-aware machine learning methods for power grid decision-making are developed and evaluated in this thesis. It introduces fairness-aware user classification frameworks that incorporate fairness regularizers, including accuracy parity and equal opportunity/predictive equality constraints, to address bias across sensitive attributes. The work further studies long-term fairness for real-time decision making under time-varying conditions, providing performance analysis using defined metrics and bounds. An application to a peer-to-peer electricity market is included, supported by experimental evaluations and comparisons.","UC Irvine  \nUC Irvine Electronic Theses and Dissertations  \nTitle  \nFairness-aware Machine Learning in Power Grids  \nPermalink  \n[https://escholarship.org/uc/item/1dc9q857](https://escholarship.org/uc/item/1dc9q857)  \nAuthor  \nDu, Ruijie  \nPublication Date  \n2023  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA,  \nIRVINE  \nFairness-aware Machine Learning in Power Grids  \nTHESIS  \nsubmitted in partial satisfaction of the requirements  \nfor the degree of  \nMASTER OF SCIENCE  \nin Electrical and Computer Engineering  \nby  \nRuijie Du  \nThesis Committee:  \nAssistant Professor Yanning Shen, Chair Professor Pramod Khargonekar Professor A. Lee Swindlehurst  \n© 2023 Ruijie Du  \nTABLE OF CONTENTS  \nPage  \nLIST OF FIGURES iv  \nLIST OF TABLES v  \nLIST OF ALGORITHMS vi  \nACKNOWLEDGMENTS vii  \nVITA viii  \nABSTRACT OF THE THESIS ix  \n1 Introduction 1  \n2 Background 4  \n2.1 Machine Learning in Power Grids ........................ 5  \n2.2 Fairness in Power Systems ............................ 7  \n3 Fairness-aware User Classification in Power Grids 9  \n3.1 Introduction .................................... 9  \n3.2 Fairness-aware High-load Indication ....................... 10  \n3.2.1 Accuracy Parity Regularizer ....................... 11  \n3.2.2 Equal Opportunity and Predictive Equality Regularizers ....... 13  \n3.3 Fairness-aware User Type Identification ..................... 14  \n3.3.1 Accuracy Parity Regularizer ....................... 15  \n3.3.2 Equal Opportunity and Predictive Equality Regularizers ....... 15  \n3.4 Experiments ................................... 16  \n3.4.1 Fariness-aware Measurements ...................... 16  \n3.4.2 High Load Indication ........................... 17  \n3.4.3 User Type Identification ......................... 18  \n3.4.4 Impact of Fairness Regularizers ..................... 19  \n3.5 Summary ..................................... 20  \n4 Long-term Fairness for Real-time Decision Making 21  \n4.1 Introduction .................................... 22  \n4.2 Problem Formulation ............................... 23  \n4.3 Method ...................................... 26  \n4.4 Performance Analysis ............................... 27  \n4.4.1 Performance Metrics ........................... 28  \n4.4.2 Performance Bounds ........................... 29  \n4.5 Application: Peer-to-peer Electricity Market .................. 32  \n4.6 Conclusion ..................................... 35  \n4.7 Experiments .................................... 35  \n4.7.1 Random Setting .............................. 37  \n4.7.2 Time-varying Setting ........................... 37  \n4.7.3 OASIS ................................... 40  \n4.8 Conclusion ..................................... 42  \n4.9 Summary ..................................... 42  \n5 Discussion and Conclusion 43  \n5.1 Future Work .................................... 44  \nBibliography 46  \nAppendix A 50  \nA.1 Proof of Lemma 1 ................................. 50  \nA.2 Proof of Lemma 2 ................................. 55  \nA.3 Proof of Theorem 1 ................................ 58  \nA.4 Proof of Theorem 2 ................................ 59  \nA.4.1 Upper bounds ............................... 63  \nA.5 Upperbound of RoffT ................................ 64  \nA.6 Flow constraint and Transmission utilization fee ................ 67  \nLIST OF FIGURES  \nPage  \n2.1 Concept of smart grid............................... 6  \n3.1 Impact of equal opportunity and predictive equality regularizers. The weight of REO is represented as β2 , and β1 = 0 .8β2 ................... 19  \n3.2 Impact of accuracy parity regularizer. The weight of RAP is represented as α. 20  \n4.1 Experimental results of random setting, time-averaged costs and dynamic regrets, µ = 1e4 ,α = 0 .5.............................. 38  \n4.2 Experimental results of random setting, dynamic fairness and A2 FV , µ = 1e4 ,α = 0 .5","cbCaipmnHfXh3LFU","https://ap.wps.com/l/cbCaipmnHfXh3LFU","pdf",1674414,1,79,"English","en",105,"# Table of Contents\n## 1 Introduction\n## 2 Background\n## 2.1 Machine Learning in Power Grids\n## 2.2 Fairness in Power Systems\n## 3 Fairness-aware User Classification in Power Grids\n## 4 Long-term Fairness for Real-time Decision Making\n## 4.1 Introduction\n## 5 Discussion and Conclusion\n## Bibliography\n## Appendix A","[{\"question\":\"What fairness issues are addressed in machine learning for power grids?\",\"answer\":\"The thesis focuses on fairness within power systems, incorporating constraints such as accuracy parity and equal opportunity/predictive equality to reduce bias across sensitive attributes.\"},{\"question\":\"How does the work perform fairness-aware user classification?\",\"answer\":\"It proposes fairness-aware user classification methods for power grids, using fairness regularizers to guide learning and evaluating the resulting accuracy and fairness trade-offs.\"},{\"question\":\"How is long-term fairness handled for real-time decision making?\",\"answer\":\"A dedicated section formulates the long-term fairness problem for real-time decisions, analyzes performance with metrics and bounds, and tests settings such as time-varying scenarios.\"}]","Fairness-aware Machine Learning in Power Grids - Thesis | PDF",1785813225,199,{"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},"fairness-aware-machine-learning-in-power-grids-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/fairness-aware-machine-learning-in-power-grids-thesis/122843/",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 fairness issues are addressed in machine learning for power grids?","Question",{"text":75,"@type":76},"The thesis focuses on fairness within power systems, incorporating constraints such as accuracy parity and equal opportunity/predictive equality to reduce bias across sensitive attributes.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the work perform fairness-aware user classification?",{"text":80,"@type":76},"It proposes fairness-aware user classification methods for power grids, using fairness regularizers to guide learning and evaluating the resulting accuracy and fairness trade-offs.",{"name":82,"@type":73,"acceptedAnswer":83},"How is long-term fairness handled for real-time decision making?",{"text":84,"@type":76},"A dedicated section formulates the long-term fairness problem for real-time decisions, analyzes performance with metrics and bounds, and tests settings such as time-varying scenarios.","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"]