[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123102-en":3,"doc-seo-123102-105":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},123102,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Sensitivity Analysis of Machine Learning Algorithms for Outage Risk Prediction","Severe weather drives forced outages in electric distribution grids, motivating data-driven forecasting of outage State of Risk (SoR). This paper examines how sensitive multiple machine learning algorithms are to (1) adding weather parameters from adjacent geographic areas and (2) varying data availability. Models are trained and tested on real utility company data. Results show that larger training datasets improve performance measured by ROC, Average Precision, and F1, with experiments indicating at least two years of training data for satisfactory outcomes. Statistical checks assess the impact of broader-area weather inclusion.","Proceedings of the 57th Hawaii International Conference on System Sciences | 2024  \nSensitivity Analysis of Machine Learning Algorithms for Outage Risk  \nPrediction  \nRashid Baembitov, Mladen Kezunovic Texas A&M University [bae_rashid@tamu.edu](bae_rashid@tamu.edu), [kezunov@ece.tamu.edu](kezunov@ece.tamu.edu)  \nDaniel Saranovic, Zoran Obradovic Temple University [daniel.saranovic@temple.edu](daniel.saranovic@temple.edu), [zoran.obradovic@temple.edu](zoran.obradovic@temple.edu)  \nAbstract  \nSevere weather conditions are known for causing forced outages in the electric distribution grid. Recent research efforts were aimed at predicting outages using weather and historical outage data. This paper studies the sensitivity of different Machine Learning (ML) algorithms to the inclusion of weather parameters from adjacent geographic areas and data availability. We analyzed the ability of different ML algorithms to predict electric grid outage State of Risk (SoR). The selected algorithms are trained and tested on actual utility company data. The findings indicate that a bigger size of the training dataset improves the performance of all models, which is measured by the Receiver Operating Curve, Average Precision, and F1 Score. Conducted experiments suggest that at least two years of training data is required to achieve satisfactory performance. Also, we investigate a statistical significance in models’ performance with  \nthe inclusion of weather in adjacent geographic areas. Keywords: ML, State of Risk, Outage Prediction.  \n1. Introduction  \nThe occurrence of forced outages in power systems, resulting from short circuits caused by faults or equipment failure, can pose a considerable safety hazard and economic burden for utilities, their customers, and society as a whole. The rise in severe weather conditions due to climate change has become one of the major concerns since it causes more frequent impacts of inclement weather on overhead feeders and other exposed components of the electric grid (Panteli et al., 2015) . A new approach of predicting outages in the system allows a proactive mitigation approach to reducing or avoiding detrimental impact (M. Kezunovic et al., 2022),(Khoshjahan et al., 2021) .  \nSeveral data model aspects such as historical weather and forecasts, GIS representation of utilities’assets, machine learning (ML) methods, and digitalization of utility operations to assess the  \npotential risk to the power grid have been reported so far (Kezunovic et al., 2020), (Kezunovic et al., Nov., 2019) . The selection of the best ML algorithm is vital in accurately predicting the State of Risk (SoR) for outages in the network, which reflects the probability of an outage occurrence in each place and time. Different algorithms have various strengths and weaknesses, which can impact the accuracy of the predictions. For instance, the ensemble algorithms such as Random Forest (RF) and Gradient Boosting are known for their robustness and accuracy, but they are less interpretable than decision trees (Shi et al., 2018), (Leistner et al., 2009) .  \nIn the past, RF algorithm was used along with dimensionality reduction techniques to predict the probability of transmission line outage during severe weather storms (Taylor et al., 2023) . The Neural Network (NN) was utilized to predict the time of repair and restoration in distribution networks (Arif et al., 2018) . Logistic Regression (LR) was implemented to predict the likelihood of power grid elements failure from an approaching hurricane (Eskandarpour et al., 2017) . Support Vector Machine (SVM) that considers the deterioration level of the equipment was suggested in (Eskandarpour et al., 2018) to estimate theoperability of the grid's components during extreme weather events. Graph Convolutional NN were used to process weather parameters and anticipate outages in the system (Owerko et al., 2018) . Ensemble learning approaches were also utilized for outage prediction (Shashaani et al.,","cbCaivqd5lf174Vo","https://ap.wps.com/l/cbCaivqd5lf174Vo","pdf",1094428,1,10,"English","en",105,"# Introduction\n## Outage drivers and the need for proactive prediction\n## Prior ML approaches for outage modeling\n## Focus and contribution of this paper","[{\"question\":\"What does the paper analyze regarding machine learning for outage prediction?\",\"answer\":\"It studies the sensitivity of different machine learning algorithms to weather-feature inclusion from adjacent areas and to data availability when predicting outage State of Risk (SoR).\"},{\"question\":\"How is model performance evaluated?\",\"answer\":\"Performance is assessed using Receiver Operating Curve metrics, Average Precision, and F1 Score on trained and tested utility data.\"},{\"question\":\"What training-data duration is suggested for satisfactory performance?\",\"answer\":\"Experiments indicate that using at least two years of training data is required to reach satisfactory predictive performance.\"}]","Sensitivity Analysis of Machine Learning Algorithms for Outage Risk Prediction | PDF",1785814648,25,{"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},"sensitivity-analysis-of-machine-learning-algorithms-for-outage-risk-prediction","",{"@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/sensitivity-analysis-of-machine-learning-algorithms-for-outage-risk-prediction/123102/",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","2026-08-04",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 does the paper analyze regarding machine learning for outage prediction?","Question",{"text":75,"@type":76},"It studies the sensitivity of different machine learning algorithms to weather-feature inclusion from adjacent areas and to data availability when predicting outage State of Risk (SoR).","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is model performance evaluated?",{"text":80,"@type":76},"Performance is assessed using Receiver Operating Curve metrics, Average Precision, and F1 Score on trained and tested utility data.",{"name":82,"@type":73,"acceptedAnswer":83},"What training-data duration is suggested for satisfactory performance?",{"text":84,"@type":76},"Experiments indicate that using at least two years of training data is required to reach satisfactory predictive performance.","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},[93,97,101,105,110,115,120,123,128,131,134],{"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":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":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]