[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126375-en":3,"doc-seo-126375-105":30,"detail-sidebar-cat-0-en-105":92},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":20,"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},126375,962085564549,"Genevieve","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Quantifying and Predicting Residential Building Flexibility Using Machine Learning Methods","Residential buildings represent a substantial share of electricity demand, and increasing deployment of distributed energy resources strengthens buildings’ ability to provide grid flexibility. Aggregators and operators require metrics that quantify and forecasting approaches that predict when flexibility is available and how it evolves over time. This work introduces two complementary flexibility metrics—power and energy flexibility—and evaluates mainstream machine learning models for forecasting residential flexibility across 4-hour and 24-hour horizons, showing that LSTM performs best for power while energy flexibility remains difficult, especially for HVAC-related loads.","Quantifying and Predicting Residential Building Flexibility Using Machine Learning Methods  \nPatrick Salter, Qiuhua Huang  \nDepartment of Electrical Engineering Colorado School of Mines Golden, USA psalter, [qiuhuahuang@mines.edu](qiuhuahuang@mines.edu)  \nPaulo Cesar Tabares-Velasco  \nDepartment of Mechanical Engineering Colorado School of Mines Golden, USA [tabares@mines.edu](tabares@mines.edu)  \narXiv :2403 .0 1669v 1 [ cs .LG] 4 Mar 2024  \nAbstract—Residential buildings account for a significant portion (35%) of the total electricity consumption in [the U.S. as](the U.S. as) of 2022. As more distributed energy resources are installed in buildings, their potential to provide flexibility to the grid increases. To tap into that flexibility provided by buildings, aggregatorsor system operators need to quantify and forecast flexibility. Previous works in this area primarily focused on commercial buildings, with little work on residential buildings. To address the gap, this paper first proposes two complementary flexibility metrics (i.e., power and energy flexibility) and then investigates several mainstream machine learning-based models for predicting the time-variant and sporadic flexibility of residential buildings at four-hour and 24-hour forecast horizons. The long-short-termmemory (LSTM) model achieves the best performance and can predict power flexibility for up to 24 hours ahead with the average error around 0.7 kW. However, for energy flexibility, the LSTM model is only successful for loads with consistent operational patterns throughout the year and faces challenges when predicting energy flexibility associated with HVAC systems.  \nIndex Terms—Flexibility, residential buildings, machine learning, long short term memory  \nI. INTRODUCTION  \nPower systems in many countries are facing growing challenges posed by the stochastic and intermittent nature of renewable energy resources. As a result, there has been a push for more flexibility from the demand side of the grid. In the United States, buildings make up the majority of electricity end-use consumption with about 75% of the nation’s electricity consumed in residential and commercial buildings [1] . Buildings usually have some controllable devices and flexible loads and can change consumption patterns to benefit both the grid and the building owners. In order to plan control schemes and respond to requests from the grid, the energy management system (EMS) or controller needs to know how much flexibility the building has and when it is available. Flexibility metrics aim to quantify the flexibility of load and consolidate the various sources of flexibility into a common framework.  \nExisting work has quantified building load flexibility through a variety of different metrics, but typically the focus is on power, energy, or cost [2] . Power metrics, like those shown in [3] and [4], aim to quantify the possible power change that  \nFunding for this work was provided through the Sloan Foundation  \ncould be achieved at a given time. The most prominent of these metrics is peak reduction since reducing consumption during the most congested hours of the day is a well-established topic of research. Because these metrics are simple and just look at power, they are good for predictions further into the future. This simplicity comes at the cost of not providing information on how long the load change can be maintained and what the rebound energy effect of the change will be. Energy metrics, on the other hand, are typically short-term in order to provide this time-dependent information. There are many forms of these metrics, but a common goal is to quantify a building’s ability to respond to a demand response event and how efficiently it can do so [5] . Cost metrics, like the flexibility index in [6], are particularly useful for evaluating the cost of a building using its flexibility. These metrics are more evaluative than predictive, mostly used for determining ifa load change provides","cbCaijJqc4VyHqFu","https://ap.wps.com/l/cbCaijJqc4VyHqFu","pdf",645650,5,1,"English","en",105,"# Introduction\n## Flexibility metrics and forecasting needs\n## Power, energy, and cost metrics\n## Focus on residential vs. commercial buildings\n# Methods\n## Proposed flexibility metrics\n## Machine learning models and forecast horizons\n# Results and discussion\n## Power flexibility prediction performance\n## Energy flexibility challenges (HVAC loads)","[{\"question\":\"What flexibility metrics does the paper propose for residential buildings?\",\"answer\":\"The paper proposes two complementary metrics: power flexibility and energy flexibility, designed to quantify different aspects of how loads can change and be sustained during demand response.\"},{\"question\":\"Which machine learning model shows the best overall performance?\",\"answer\":\"The long short-term memory (LSTM) model achieves the best performance, particularly for predicting time-variant power flexibility up to a 24-hour horizon.\"},{\"question\":\"Why is energy flexibility prediction more challenging than power flexibility?\",\"answer\":\"Energy flexibility prediction succeeds mainly for loads with consistent operational patterns across the year, and it becomes difficult for energy flexibility associated with HVAC systems.\"}]","Quantifying and Predicting Residential Building Flexibility Using Machine Learning Methods | PDF",1785904732,13,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"quantifying-and-predicting-residential-building-flexibility-using-machine-learning-methods","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"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/quantifying-and-predicting-residential-building-flexibility-using-machine-learning-methods/126375/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What flexibility metrics does the paper propose for residential buildings?","Question",{"text":76,"@type":77},"The paper proposes two complementary metrics: power flexibility and energy flexibility, designed to quantify different aspects of how loads can change and be sustained during demand response.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which machine learning model shows the best overall performance?",{"text":81,"@type":77},"The long short-term memory (LSTM) model achieves the best performance, particularly for predicting time-variant power flexibility up to a 24-hour horizon.",{"name":83,"@type":74,"acceptedAnswer":84},"Why is energy flexibility prediction more challenging than power flexibility?",{"text":85,"@type":77},"Energy flexibility prediction succeeds mainly for loads with consistent operational patterns across the year, and it becomes difficult for energy flexibility associated with HVAC systems.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"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":20,"slug":138},19,"General","general"]