[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82095-en":3,"doc-seo-82095-105":29,"detail-sidebar-cat-0-en-105":95},{"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":13,"seo_description":14,"update_tm":27,"read_time":28},82095,1374391975076,"Riley","https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051",8,"Research & Report","A Machine Learning Surrogate for Component Criticality Ranking in Interdependent Power-Communication Networks","Cyber-physical power systems face cascading failures driven by tight interdependencies between power and communication infrastructures. Full resilience evaluation across large 10−5 contingency sets using a high-fidelity simulator is computationally prohibitive. Leveraging MIIM as the ground-truth cascade simulator, the work trains a leakage-free machine-learning surrogate to predict per-contingency severity and produce a component-criticality ranking. On the IEEE 118-bus system, Gradient Boosting reaches Spearman correlations of 0.849 and 0.853, remains stable across three datasets, and outperforms topology baselines via inter-layer dependency features.","A Machine-Learning Surrogate for Component Criticality Ranking in Interdependent Power– Communication Networks  \nSohini Roy  \nDepartment of Computer Science University of Nevada, Las Vegas Las Vegas, USA [sohini.roy@unlv.edu](sohini.roy@unlv.edu)  \nXheni Hylviu  \nDepartment of Computer Science University of Nevada, Las Vegas Las Vegas, USA [hylvix1@unlv.nevada.edu](hylvix1@unlv.nevada.edu)  \nAbstract—Cyber-physical power systems are vulnerable to cascading failures caused by tight interdependencies between power and communication infrastructures. Evaluating these failures over large 􀡺 − 􀢑 contingency sets with a high-fidelity simulator is computationally prohibitive for resilience planning. Using the previously published Modified Implicative Interdependency Model (MIIM) as the ground-truth cascade simulator, this paper develops a machine-learning surrogate that predicts contingency severity from leakage-free structural features and derives a component-criticality ranking for prioritized hardening analysis. On the IEEE 118-bus system, the Gradient Boosting surrogate achieves Spearman correlations of 0.849 for per-contingency severity prediction and 0.853 for percomponent criticality ranking, while remaining stable across three independently sampled datasets. MIIM-derived component criticality itself reproduces only to a Spearman of approximately 0.85 under the present sampling pipeline, and the surrogate operates at this empirical ceiling to within sampling variation. Topological centrality measures on the full interdependent network provide meaningful baselines (Spearman 0.60–0.69), and feature ablation shows that the surrogate’s advantage is driven primarily by inter-layer dependency information. These results support a two-stage workflow in which the surrogate rapidly ranks candidate components and MIIM is reserved for selective verification.  \nKeywords—Cyber-physical power systems, cascading failures, interdependent networks, contingency screening, component criticality, power system resilience.  \nI. INTRODUCTION  \nCyber-physical power systems (CPPS) rely on tight coordination between the physical power grid and the communication infrastructure that supports monitoring, control, and data exchange. While this coupling improves situational awareness and operational efficiency, it also creates new pathways for cascading failures: disruption in the power layer can disable communication entities, while communication failures can in turn degrade grid observability and control. Resilience analysis in such systems must therefore account for interdependent failure propagation rather than treating the two layers in isolation.  \nA central challenge in CPPS is the analysis of 􀜰 −􀝇 contingencies, in which multiple components fail simultaneously and trigger cascading effects across layers. Although a high-fidelity interdependency simulator can  \nevaluate the severity of a candidate contingency, exhaustive evaluation becomes computationally prohibitive as network size and contingency order grow. For resilience planning, moreover, the key question is not only which contingencies are severe, but which components should be prioritized for hardening analysis to reduce cascade risk.  \nThis paper addresses that need by building on the previously published Modified Implicative Interdependency Model (MIIM), which is used here as the ground-truth simulation engine rather than as a new contribution. MIIM provides a logic-based representation of intra- and interdependencies in joint power–communication systems and supports cascade-state evaluation under failures. Using MIIM-generated severities as labels, we train a machinelearning surrogate that predicts cascade severity from leakagefree structural features and use it to derive a componentcriticality ranking for hardening analysis.  \nTwo findings shape the contribution. First, component criticality is sample-dependent: when computed on independently generated contingency datasets, the MIIMderived r","cbCaibJY7dgZoT4p","https://ap.wps.com/l/cbCaibJY7dgZoT4p","pdf",817828,1,6,"English","en",105,"# Introduction\n## Problem motivation and challenge\n## Approach based on MIIM\n## Key findings and workflow\n# Background and Related Work","[{\"question\":\"为什么需要用机器学习替代高保真仿真进行韧性分析？\",\"answer\":\"高保真互依赖仿真在大规模、多重失效（高阶）候选集合上的评估成本随网络规模与阶数增长而变得计算不可承受。论文据此提出用快速代理模型进行筛查。\"},{\"question\":\"论文如何生成训练标签并定义代理模型的预测任务？\",\"answer\":\"论文使用先前提出的 Modified Implicative Interdependency Model（MIIM）作为级联仿真引擎，利用 MIIM 生成的严重度作为标签。代理模型基于无泄漏的结构特征预测级联严重度，并进一步得到组件关键度排名。\"},{\"question\":\"在 IEEE 118-bus 系统上，代理模型的性能与稳定性如何？\",\"answer\":\"Gradient Boosting 在每个候选失效的严重度预测上达到 Spearman 相关系数 0.849，并在每个组件关键度排名上达到 0.853。结果在三个独立采样数据集上保持稳定。\"},{\"question\":\"代理模型的优势主要来自哪些信息？\",\"answer\":\"拓扑中心性在全互依赖网络上能提供有意义的基线（Spearman 0.60–0.69），而特征消融表明代理模型相对基线的优势主要由跨层（inter-layer）依赖信息驱动。\"}]",1784178181,15,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":90,"head_meta":92,"extra_data":94,"updated_unix":27},"a-machine-learning-surrogate-for-component-criticality-ranking-in-interdependent-power-communication-networks","",{"@graph":35,"@context":89},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/a-machine-learning-surrogate-for-component-criticality-ranking-in-interdependent-power-communication-networks/82095/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"为什么需要用机器学习替代高保真仿真进行韧性分析？","Question",{"text":75,"@type":76},"高保真互依赖仿真在大规模、多重失效（高阶）候选集合上的评估成本随网络规模与阶数增长而变得计算不可承受。论文据此提出用快速代理模型进行筛查。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"论文如何生成训练标签并定义代理模型的预测任务？",{"text":80,"@type":76},"论文使用先前提出的 Modified Implicative Interdependency Model（MIIM）作为级联仿真引擎，利用 MIIM 生成的严重度作为标签。代理模型基于无泄漏的结构特征预测级联严重度，并进一步得到组件关键度排名。",{"name":82,"@type":73,"acceptedAnswer":83},"在 IEEE 118-bus 系统上，代理模型的性能与稳定性如何？",{"text":84,"@type":76},"Gradient Boosting 在每个候选失效的严重度预测上达到 Spearman 相关系数 0.849，并在每个组件关键度排名上达到 0.853。结果在三个独立采样数据集上保持稳定。",{"name":86,"@type":73,"acceptedAnswer":87},"代理模型的优势主要来自哪些信息？",{"text":88,"@type":76},"拓扑中心性在全互依赖网络上能提供有意义的基线（Spearman 0.60–0.69），而特征消融表明代理模型相对基线的优势主要由跨层（inter-layer）依赖信息驱动。","https://schema.org",{"og:url":51,"og:type":91,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":93,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,118,123,126,131,134,138],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},"Technology",50,"technology",{"id":119,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":121,"slug":122},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":124,"slug":125},30,"research-report",{"id":127,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":129,"slug":130},9,"Religion & Spirituality",20,"religion-spirituality",{"id":129,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":129,"slug":133},"World Cup","world-cup",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":135,"slug":137},10,"Lifestyle","lifestyle",{"id":139,"doc_module":4,"doc_module_name":45,"category_name":140,"show_sort_weight":110,"slug":141},19,"General","general"]