[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84135-en":3,"doc-seo-84135-105":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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},84135,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Creating Power Distribution Network Layouts Using Generative Adversarial Networks and Image-Based Representations","Utilities increasingly depend on planning and operational tools to manage higher penetrations of distributed energy resources, but benchmarking is hindered by the lack of realistic, openly available datasets. The paper presents a data-driven generative framework using Generative Adversarial Networks (GANs) to create power distribution network layouts from image-based representations. Training uses rasterised views from GIS sources and supports unconditional and conditional (geography-aware) generation. Experiments across LV, MV, and HV cases reproduce feeder topologies and align layouts with underlying street and consumer distributions, while revealing limits in stability, resolution artifacts, and missing explicit electrical constraints.","Creating Power Distribution Network Layouts Using Generative Adversarial Networks and Image-Based Representations  \nJuan Manuel García-Pérez1, Carlos Mateo2  \n1 School of Engineering (ICAI), Comillas Pontifical University, Spain  \n2 Institute for Research in Technology (IIT), School of Engineering (ICAI), Comillas Pontifical University, Spain Corresponding author: Carlos Mateo ([cmateo@comillas.edu](cmateo@comillas.edu))  \nABSTRACT: Utilities increasingly rely on planning and operational tools to cope with the increased penetrations of distributed energy resources, yet the lack of realistic, openly available datasets remains a major barrier for benchmarking and comparison. Traditional test feeders, and recently proposed large-scale synthetic networks alleviate this issue but are typically based on heuristic rules and do not learn directly from data. This paper proposes a generative framework based on Generative Adversarial Networks (GANs) to create power distribution network layouts using image-based representations. The model is trained on rasterised views of distribution systems and can operate in two modes: an unconditional configuration that learns layout patterns from the training dataset, and conditional configurations that incorporate geographical context such as street maps and the spatial distribution of consumers. The methodology includes dataset preparation from Geographic Information System (GIS) sources, GAN architecture design, and the analysis of training stability and image resolution. Results from three representative cases show that the proposed approach can reproduce the topologies of low (LV), medium (MV) and high voltage (HV) feeders and align generated layouts with underlying geographical structures. At the same time, the study reveals limitations related to training stability, resolution-dependent artefacts and limits, and the absence of explicit electrical constraints. The proposed framework constitutes a data-driven complement to existing synthetic network generation methods, and could be applied to propose distribution network layouts for the electrification of new areas. This would require future extensions towards power flow, electrically validated models.  \nKEYWORDS: Generative adversarial networks, power distribution, networks, test feeders, image processing, artificial intelligence  \nI. INTRODUCTION  \nElectric distribution networks are undergoing a profound transformation driven by the rapid deployment of distributed energy resources (DERs), the electrification of other sectors (e.g. , electric vehicles and heat pumps), and increasing digitalization. The growing penetration of distributed generation introduces additional uncertainty into distribution networks, which can be mitigated through flexibility provided by distributed storage or flexible loads. This evolution requires enhanced digitalization and the development of new planning and operation tools capable of operating under increasingly uncertainty.  \nThe validation of such tools requires datasets to test and benchmark solutions proposed by different authors. However, real distribution network data is rarely accessible due to confidentiality concerns and the critical infrastructure nature of electrical grids. For decades, this has forced researchers to rely on publicly available benchmark systems such as the IEEE test feeders [1], [2],[3], the PNNL Taxonomy Feeders [4], and the EPRI representative feeders [5] . Although these models have been essential for algorithm comparison and reproducibility, they exhibit several limitations, including reduced scale, limited topological diversity, lack of  \ngeospatial information, and simplified operating conditions [6] .  \nIn response to these limitations, recent efforts have produced a new generation of large-scale synthetic networks. Among them, the synthetic distribution systems created with the U.S. Reference Network Model (RNMUS) represent a major advancement, synthesizing very large-scale distr","cbCaitGIqjeAHOHb","https://ap.wps.com/l/cbCaitGIqjeAHOHb","pdf",530899,3,1,9,"English","en",105,"# Introduction\n# Problem: dataset scarcity and benchmarking limits\n# Existing synthetic network approaches\n# Deep learning and GAN-based image synthesis\n# Proposed generative framework","[{\"question\":\"Why is dataset availability a barrier for distribution network planning tool benchmarking?\",\"answer\":\"Real distribution network data is rarely accessible due to confidentiality and the critical nature of electrical infrastructure, limiting researchers to benchmark systems.\"},{\"question\":\"How does the proposed method generate power distribution network layouts?\",\"answer\":\"It trains a GAN on rasterised views of distribution systems derived from GIS sources, producing layouts either unconditionally or conditionally with geographic context.\"},{\"question\":\"What were the main findings from the case studies across LV, MV, and HV feeders?\",\"answer\":\"The approach reproduced feeder topologies and matched generated layouts with underlying geographic structures, while highlighting limitations in training stability, resolution-dependent artifacts, and the absence of explicit electrical constraints.\"}]",1784193231,23,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"creating-power-distribution-network-layouts-using-generative-adversarial-networks-and-image-based-representations","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"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":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/creating-power-distribution-network-layouts-using-generative-adversarial-networks-and-image-based-representations/84135/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",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},"Why is dataset availability a barrier for distribution network planning tool benchmarking?","Question",{"text":75,"@type":76},"Real distribution network data is rarely accessible due to confidentiality and the critical nature of electrical infrastructure, limiting researchers to benchmark systems.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method generate power distribution network layouts?",{"text":80,"@type":76},"It trains a GAN on rasterised views of distribution systems derived from GIS sources, producing layouts either unconditionally or conditionally with geographic context.",{"name":82,"@type":73,"acceptedAnswer":83},"What were the main findings from the case studies across LV, MV, and HV feeders?",{"text":84,"@type":76},"The approach reproduced feeder topologies and matched generated layouts with underlying geographic structures, while highlighting limitations in training stability, resolution-dependent artifacts, and the absence of explicit electrical constraints.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":21,"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":52,"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":22,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]