[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127269-en":3,"doc-seo-127269-105":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},127269,2336475104736,"Quinn","https://ap-avatar.wpscdn.com/avatar/22000c4c5e0e5b17e70?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786591360781797222",8,"Research & Report","Explainable Machine Learning - A SHAP value-based approach to locational frequency stability","Modern power systems face rising instability risks as converter interfaced generation (CIG) integration reduces the usefulness of conventional global frequency assumptions and obscures local frequency dynamics. This work proposes a machine learning framework using an artificial neural network to model local frequency characteristics and SHapley Additive exPlanations (SHAP) to interpret feature contributions to frequency behavior. Insights then support secure generation dispatch optimization models. Time-domain validation on an IEEE 39-bus variant shows accurate identification of key variables shaping local and global stability boundaries and enables simple rules for improved security.","Electrical Power and Energy Systems 170 (2025) 110885  \n| Explainable Machine Learning: A SHAP value-based approach to locational frequency stability\u003Cbr>Alinane B. Kilembe a, Robert I. Hamilton a, Panagiotis N. Papadopoulos b ,∗\u003Cbr>a University of Strathclyde, Department of Electronic and Electrical Engineering, 99 George Street, Glasgow, G1 1RD, United Kingdom b University of Manchester, Department of Electrical and Electronic Engineering, Oxford Road, Manchester, M13 9PL, United Kingdom |  |  |\n| --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |\n| Keywords:\u003Cbr>Centre of inertia\u003Cbr>Converter Interfaced Generation Explainability\u003Cbr>Local frequency Machine Learning Power system dynamics SHAP |  | The increasing complexity of modern power systems due to the high integration of Converter Interfaced Generation (CIG) challenges the effectiveness of current analytical frequency approaches, leading to instability risksand a diminished understanding of local frequency dynamics. To address this, we propose a Machine Learning (ML)-based technique, through Artificial Neural Network (ANN) to capture the frequency characteristics of the system at a local level and SHapley Additive exPlanations (SHAP), an additive feature attribution method, to enhance the understanding of the frequency dynamics. The proposed method further leverages these insights to inform system optimisation models for secure generation dispatch. Validation results from time-domain simulations conducted on a modified version of the IEEE 39-bus network indicate that the proposed method can accurately identify important system variables shaping the local and global frequency stability boundaries, and simple rules can be derived to guide the system optimisation for enhanced system security. |\n\n1. Introduction  \nThe modern power system is undergoing an unprecedented transformation due to the increased integration of Converter Interfaced Generation (CIG). As Synchronous Generation (SG), which provides essential inertia to mitigate against disturbances through the kinetic energy stored in the rotating mass of the rotor, is displaced by CIGs, new challenges arise because CIGs do not directly provide inertia. Specifically, systems with high CIG integration experience increasingly localised frequency dynamics compared to SG-dominated systems. Asa result, the conventional Centre of Inertia (COI) approach, which assumes frequency as a global phenomenon, becomes less reliable [1–4]. For example, the Electric Reliability Council of Texas (ERCOT) used the COI method to determine the inertia floor of at least 100 GW-s for its network, while Great Britain and Ireland, using the same method, calculated inertia floors of 135 GW-s and 23 GW-s, respectively [2].  \nThe authors [5,6] attempt to address this analytically by proposing the frequency divider (FD) method, which uses an augmented system admittance matrix for estimating local bus frequency, including in systems with high CIG integration. Given a steady-state model where the SGs frequencies determine the boundary conditions, the FD operates on the principle that the frequency at a particular bus is affected by power flows (by defining the quota of active power that contributes to frequency variations of buses) and the dynamics of SGs connected to it, weighted by electrical distances. The prediction of the location  \nfrequency response using the numerical derivative of the voltage phase angle is proposed by [2]. In a study on the Texas7000 model, locational frequency variations due to high CIG penetration were studied, and the possibilities of local frequency violations undetectable to the COI were showcased. Validation simulation results demonstrate that the proposed method can effectively capture these locational variations analytically. However, while analytical methods demonstrate some potential, application in modern large-scale interconnected power systems can be computationally intensive, due to the solving of Di","cbCairYFPmQERQvg","https://ap.wps.com/l/cbCairYFPmQERQvg","pdf",2271867,1,12,"English","en",105,"# Introduction\n## Background and limitations of centre of inertia\n## Analytical methods for locational frequency response\n## Data-driven approaches using machine learning","[{\"question\":\"Why does increasing CIG integration challenge conventional frequency analysis methods?\",\"answer\":\"Because CIGs do not provide inertia in the same way as synchronous generation, localised frequency dynamics become more prominent and the centre of inertia (COI) assumption of global frequency becomes less reliable.\"},{\"question\":\"How does the proposed approach use machine learning and SHAP?\",\"answer\":\"An artificial neural network models system frequency characteristics at a local level, while SHAP provides additive feature attributions to clarify how variables influence local and global frequency stability behavior.\"},{\"question\":\"What do the validation results on the modified IEEE 39-bus network show?\",\"answer\":\"Time-domain simulations indicate the method accurately identifies important system variables defining local and global frequency stability boundaries, and the study derives simple rules to support system optimization for enhanced security.\"}]","Explainable Machine Learning - A SHAP value-based approach to locational frequency stability | PDF",1785937917,30,{"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},"explainable-machine-learning-a-shap-value-based-approach-to-locational-frequency-stability","",{"@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/explainable-machine-learning-a-shap-value-based-approach-to-locational-frequency-stability/127269/",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","2026-08-05",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},"Why does increasing CIG integration challenge conventional frequency analysis methods?","Question",{"text":75,"@type":76},"Because CIGs do not provide inertia in the same way as synchronous generation, localised frequency dynamics become more prominent and the centre of inertia (COI) assumption of global frequency becomes less reliable.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed approach use machine learning and SHAP?",{"text":80,"@type":76},"An artificial neural network models system frequency characteristics at a local level, while SHAP provides additive feature attributions to clarify how variables influence local and global frequency stability behavior.",{"name":82,"@type":73,"acceptedAnswer":83},"What do the validation results on the modified IEEE 39-bus network show?",{"text":84,"@type":76},"Time-domain simulations indicate the method accurately identifies important system variables defining local and global frequency stability boundaries, and the study derives simple rules to support system optimization for enhanced security.","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},[93,97,101,105,110,115,120,122,127,130,134],{"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":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":29,"slug":121},"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"]