[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121388-en":3,"doc-seo-121388-105":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},121388,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Machine learning-guided optimal power flow for weak hybrid AC-DC grids","This paper introduces a machine learning-guided method for optimal power flow in weak hybrid AC-DC grids, targeting voltage stability issues and the reactive power behavior of LCC-HVDC. A two-factor Taylor series approximation is developed to embed LCC-HVDC reactive power consumption into standard AC OPF models. Pre-trained ML models predict bus voltages with reliability comparable to conventional OPF, while supporting more complex optimization. Validation on Pakistan’s 4 GW embedded LCC-HVDC link shows improved physical fidelity and tractable computation compared with interior-point approaches.","Citation for published version:  \nBanatwala, AZ, Gu, C & Pei, X 2025, 'Machine learning-guided optimal power flow for weak hybrid AC-DC grids', IET Conference Proceedings, vol. 2025, no. 6, pp. 339-343. [https://doi.org/10.1049/icp.2025.1228](https://doi.org/10.1049/icp.2025.1228)  \nDOI:  \n10.1049/icp.2025.1228  \nPublication date:  \n2025  \nDocument Version  \nPeer reviewed version  \nLink to publication  \nUniversity of Bath  \nAlternative formats  \nIf you require this document in an alternative format, please contact: [openaccess@bath.ac.uk](openaccess@bath.ac.uk)  \nGeneral rights  \nCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.  \nTake down policy  \nIf you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.  \nDownload date: 16. Jul. 2025  \nMACHINE LEARNING-GUIDED OPTIMAL POWER FLOW FOR WEAK HYBRID AC-DC GRIDS  \nAli Z Banatwala,1 * Chenghong Gu1, Xiaoze Pei1  \n1 Department of Electronic and Electrical Engineering, University of Bath, Bath, United Kingdom  \n*[E-mail: az343@bath.ac.uk](E-mail: az343@bath.ac.uk)  \nKeywords: MACHINE LEARNING, OPTIMAL POWER FLOW, WEAK GRIDS, EMBEDDED LCC-HVDC  \nAbstract  \nThis paper presents a novel machine learning-guided approach for optimal power flow in weak hybrid AC-DC grids. The methodology addresses two key challenges: voltage stability in weak grids and the integration of LCC-HVDC systems. First, a two-factor Taylor series approximation is developed to incorporate LCC-HVDC reactive power consumption into standard AC OPF models. Second, the paper demonstrates that using pre-trained machine learning models to predict bus voltages can achieve comparable reliability to conventional OPF methods while enabling more complex optimization scenarios. The approach is validated on Pakistan’s transmission network which includes a 4 GW embedded LCC-HVDC link. Results show that the ML-guided quadratic convex programming (QCQP) method better reflects the physical reality of weak grids compared to interior point methods. The model successfully optimizes both AC and DC parameters while maintaining computational tractability, providing a practical solution for operations planning in weak grids with embedded HVDC links.  \n1 Introduction  \nOptimal power flow (OPF) is the bedrock of operations planning models. But OPF models that use DC power flow can lead to inaccurate results, particularly in weak grids where bus voltages can deviate significantly from nominal values. The assumption of perfect voltage profile is the most critical of the DC power flow assumptions and voltage profile is the biggest source of active power estimation error [1] .  \nFig. 1 shows the voltage range for selected 220kV substations in Pakistan in 2023/24 [2] . It can be seen that on average, bus voltage magnitudes deviate up to 10% from their nominal values. Fig. 2 shows a voltage heatmap for the 500kV network during average summer loading of 20 GW. High voltages can be observed, particularly in the south, where load centres are sparse and transmission lines are long and lightly loaded. Winter voltages tend even higher as system demand drops below 10 GW, requiring disconnection of long lines for voltage control [3] .  \nOPF models that solely minimize generation costs may lead to sub-optimal outcomes for high-voltage direct current (HVDC) assets, particularly if converter transformer tap settings need to be regularly updated and reactive power exchange between the AC grid and HVDC systems is contractually limited. The increased use of bulk power transfers over long distances presents significant challenges for system planners and operators, particularly in developing countries with weak transmission grids [4","cbCaiiBUWHcQe3h9","https://ap.wps.com/l/cbCaiiBUWHcQe3h9","pdf",1613391,1,6,"English","en",105,"# Introduction\n# Predicting network parameters","[{\"question\":\"What two main challenges does the paper address for weak hybrid AC-DC grids?\",\"answer\":\"It addresses voltage stability under weak-grid conditions and the integration of LCC-HVDC systems, especially the impact of LCC-HVDC reactive power consumption on AC OPF models.\"},{\"question\":\"How does the proposed method incorporate LCC-HVDC reactive power into AC OPF?\",\"answer\":\"It develops a two-factor Taylor series approximation that integrates LCC-HVDC reactive power consumption into standard AC OPF formulations.\"},{\"question\":\"How is machine learning used, and what benefit does it provide?\",\"answer\":\"Pre-trained ML models predict bus voltages from nodal injections and transmission-line power flows, achieving reliability comparable to conventional OPF while enabling more complex and scalable optimization.\"}]","Machine learning-guided optimal power flow for weak hybrid AC-DC grids | PDF",1785735432,15,{"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-guided-optimal-power-flow-for-weak-hybrid-ac-dc-grids","",{"@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-guided-optimal-power-flow-for-weak-hybrid-ac-dc-grids/121388/",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},"What two main challenges does the paper address for weak hybrid AC-DC grids?","Question",{"text":75,"@type":76},"It addresses voltage stability under weak-grid conditions and the integration of LCC-HVDC systems, especially the impact of LCC-HVDC reactive power consumption on AC OPF models.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method incorporate LCC-HVDC reactive power into AC OPF?",{"text":80,"@type":76},"It develops a two-factor Taylor series approximation that integrates LCC-HVDC reactive power consumption into standard AC OPF formulations.",{"name":82,"@type":73,"acceptedAnswer":83},"How is machine learning used, and what benefit does it provide?",{"text":84,"@type":76},"Pre-trained ML models predict bus voltages from nodal injections and transmission-line power flows, achieving reliability comparable to conventional OPF while enabling more complex and scalable optimization.","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},[93,97,101,105,110,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"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"]