[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119112-en":3,"doc-seo-119112-105":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},119112,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Capturing Uncertainties of Household Decision-Making with Machine Learning in an Agent-based Model - Forecasting Multiple Attributes in a Coupled Energy Systems Model","The work focuses on forecasting multiple household decision attributes under massive uncertainties within a coupled energy systems framework. It addresses geopolitical disruptions that alter prosumer behavior and uncertainty in key assumptions such as fuel prices, while individual reactions remain largely unknown. The approach represents household investment decisions by modeling optimal operation of PV, heat pumps, and electric vehicles, then translating aggregated household outcomes into an agent-based electricity market simulation by coupling AMIRIS with stochastic supply optimization. Machine learning predicts dynamic aggregated behavior from varied inputs like building types, comfort preferences, heat pump types, and weather locations.","1  \nFORECASTING MULTIPLE ATTRIBUTES CONSIDERING UNCERTAINTIES IN A COUPLED ENERGY SYSTEMS MODEL  \nCFE-CMStatistics, 16th of December 2023, Berlin  \nUlrich FREY(1) , A. Achraf EL GHAZI(1) , Evelyn SPERBER(1) , Fabia MIORELLI(1) ,  \nChristoph SCHIMECZEK(1) , Stephanie STUMPF(2) , Anil KAYA(2) , Steffen REBENNACK(2)  \n(1) Deutsches Zentrum für Luft- und Raumfahrt, (2) Karlsruher Institut für Technologie  \nProject: EN4U, FKZ 03EI1029A  \nOVERVIEW  \nMotivation: Massive uncertainties  \n▪ Recent geopolitical disruptions increase uncertainties & change prosumer reactions  \n→Energy systems pathways highly uncertain  \n→ Assumptions (e.g. fuel prices) might be off  \n→Prosumer reactions largely unknown  \n▪ Buy an electric vehicle?  \n▪ Buy PV + storage?  \n▪ Buy a heat pump?  \nResearch  \nquestions  \n▪ How to represent prosumer investment decisions under uncertainty?  \n▪ How to abstract individual decisions of prosumers so they can be integrated in energy systems models?  \nIdea  \n▪ Model individual decisions:  \n▪ Simulate actual optimal operation of PVS, HP, EV  \n▪ Diffusion model of household investment decisions (PVS, HP, EV)  \n▪ Large energy system models:  \n▪ Feed these models into an agent-based simulation of electricity markets, AMIRIS  \n▪ Couple AMIRIS with a stochastic optimization model for the supply side  \n→ Ability to model uncertainties between all these components of the energy system comprehensively  \nMODELING INDIVIDUAL DECISIONS  \nHow to model individual household decisions?  \nProblem  \n▪ Many different households  \n▪ High computational effort per optimization  \n➔ Dispatch optimization of all household types not possible within AMIRIS simulation  \nIdea  \n• Individual household dispatch optimization done for multiple input variations (weather,   )  \n• Aggregate household results  \n• Train Neural Net to predict household aggregated behavior based on given  \ninput variations  \nFrey et al.– Modelling Uncertainty  \n Input variation for heat pump model  \n▪ Exploring various household’s decisions  \n18 building types 3 user comfort types 2 heat pump types 6 weather locations Total demand  \n▪ High computational effort per optimization → Produce training data via input variations  \n▪ Train Neural Nets to predict household aggregated behavior i → dynamic reaction possible in AMIRIS","cbCaiaIgigk0iXm9","https://ap.wps.com/l/cbCaiaIgigk0iXm9","pdf",2346194,1,27,"English","en",105,"# Overview\n## Motivation: Massive uncertainties\n## Research questions and idea\n# Modeling individual decisions\n## Problem and computational challenges\n## Simulation, aggregation, and neural network training\n## Input variations for heat pump model","[{\"question\":\"What uncertainties motivate the proposed modeling approach?\",\"answer\":\"Geopolitical disruptions increase uncertainty, change prosumer reactions, and can invalidate assumptions such as fuel prices. Individual prosumer reactions are also largely unknown, making energy pathways highly uncertain.\"},{\"question\":\"How does the method represent household investment decisions under uncertainty?\",\"answer\":\"It models individual decisions by simulating optimal operation for PV, heat pumps, and electric vehicles, then aggregates results. Neural networks are trained to predict aggregated household behavior from input variations so reactions can be represented inside the AMIRIS agent-based simulation.\"},{\"question\":\"Why is machine learning used instead of direct dispatch optimization for all household types in AMIRIS?\",\"answer\":\"Dispatch optimization across many household types has high computational cost and is not feasible within the AMIRIS simulation. The workflow uses offline input variations to generate training data, then trains neural nets to enable efficient prediction during simulation.\"}]","Capturing Uncertainties of Household Decision-Making with Machine Learning in an Agent-based Model - Forecasting Multiple Attributes in a Coupled Energy Systems Model | PDF",1785722438,68,{"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},"capturing-uncertainties-of-household-decision-making-with-machine-learning-in-an-agent-based-model-forecasting-multiple-attributes-in-a-coupled-energy-systems-model","",{"@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/capturing-uncertainties-of-household-decision-making-with-machine-learning-in-an-agent-based-model-forecasting-multiple-attributes-in-a-coupled-energy-systems-model/119112/",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":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What uncertainties motivate the proposed modeling approach?","Question",{"text":75,"@type":76},"Geopolitical disruptions increase uncertainty, change prosumer reactions, and can invalidate assumptions such as fuel prices. Individual prosumer reactions are also largely unknown, making energy pathways highly uncertain.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the method represent household investment decisions under uncertainty?",{"text":80,"@type":76},"It models individual decisions by simulating optimal operation for PV, heat pumps, and electric vehicles, then aggregates results. Neural networks are trained to predict aggregated household behavior from input variations so reactions can be represented inside the AMIRIS agent-based simulation.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is machine learning used instead of direct dispatch optimization for all household types in AMIRIS?",{"text":84,"@type":76},"Dispatch optimization across many household types has high computational cost and is not feasible within the AMIRIS simulation. The workflow uses offline input variations to generate training data, then trains neural nets to enable efficient prediction during simulation.","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"]