[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124520-en":3,"doc-seo-124520-105":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},124520,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","A Machine Learning-Based Early Warning System For Electricity Outage Due to Extreme Weather - Jurnal E-Komtek Vol 9 No 2","Electricity is a critical resource that supports various sectors in Indonesia, especially during extreme weather. Outages create serious operational risks when extreme meteorological conditions disrupt infrastructure and equipment performance. This study proposes a machine learning-based early warning system that predicts electricity outages by integrating historical weather and outage records through spatial alignment. Geospatial feature enrichment is performed using HDBSCAN, Yeo-Johnson transformation, robust scaling, and class resampling with SMOTE, ADASYN, and SMOTE-ENN, followed by ensemble classification to support proactive mitigation.","Jurnal E-Komtek  \nVol 9, No. 2 (2025) pp. 360-376  \n[https://jurnal.politeknik-kebumen.ac.id/index.php/E-KOMTEK](https://jurnal.politeknik-kebumen.ac.id/index.php/E-KOMTEK)  \np-ISSN : 2580-3719 e-ISSN : 2622-3066  \n| A Machine Learning-Based Early Warning System For Electricity Outage Due to Extreme Weather\u003Cbr>Helmy Satria Martha Putra1,2 , Alit Kesatria Mendala1,2, Intan Jelita Saragih1,2, Neng Ayu Herawati1,3, Ayu Purwarianti1,3, Nugraha Priya Utama1,3\u003Cbr>1 Department of Electrical Engineering and Informatics, Institut Teknologi Bandung, Indonesia, 40116\u003Cbr>2 PT PLN (Persero), Indonesia\u003Cbr>3 Center of Excellence for AI: Computer Vision, NLP, and Big Data Analytics, Institut Teknologi Bandung, Indonesia, 40116\u003Cbr> [23524018@std.stei.itb.ac.id](23524018@std.stei.itb.ac.id)\u003Cbr> [https://doi.org/10.37339/e-komtek.v9i1.2484](https://doi.org/10.37339/e-komtek.v9i1.2484) |  |  |\n| --- | --- | --- |\n| Published by Politeknik Piksi Ganesha Indonesia |  |  |\n| Artikel Info\u003Cbr>Submitted:\u003Cbr>09-06-2025\u003Cbr>Revised:\u003Cbr>08-06-2025\u003Cbr>Accepted: 08-07-2025\u003Cbr>Online first :\u003Cbr>31-12-2025 |  Abstract\u003Cbr>\u003Cbr>Electricity is a critical resource that supports various sectors in Indonesia, especially during extreme weather. Outages have become serious for operational risks during extreme weather. This study proposes a machine learning-based early warning system to predict electricity outages caused by extreme weather. Historical weather and outage data were combined using spatial alignment. Key innovation of this study involved geospatial feature enrichment via HDBSCAN, Yeo-Johnson transformation, robust scaling, and class resampling using SMOTE, ADASYN, and SMOTE-ENN. Four ensemble classification models (Random Forest, XGBoost, AdaBoost, and LightGBM) were evaluated. LightGBM with SMOTE yielded the highest recall (0.99) and the fewest false negatives. These findings suggest a solution for a proactive early warning system risk mitigation in electricity under extreme weather conditions.\u003Cbr>Keywords: Classification, Early Warning System, Electricity Outage, Extreme Weather\u003Cbr>\u003Cbr>Abstrak\u003Cbr>Listrik merupakan sumber daya krusial yang menunjang berbagai sektor di Indonesia, terutama saat menghadapi cuaca ekstrem. Gangguan listrik telah menjadi risiko operasional serius selama periodecuaca ekstrem. Penelitian ini mengusulkan sistem peringatan dini berbasis machine learning untuk memprediksi gangguan listrik akibat cuaca ekstrem. Inovasi utama dalam studi ini terletak padapengayaan fitur geospasial menggunakan HDBSCAN, transformasi Yeo-Johnson, penskalaan robust, serta penyeimbangan kelas menggunakan SMOTE, ADASYN, dan SMOTE-ENN. Empat model klasifikasi ensemble dievaluasi. Model LightGBM dengan metode SMOTE menghasilkan nilai recall tertinggi (0,99) dan jumlah false negatif paling sedikit. Temuan ini menawarkan solusi sistemperingatan dini yang proaktif untuk mitigasi risiko gangguan listrik akibat kondisi cuaca ekstrem.\u003Cbr>Kata-kata kunci: Cuaca Ekstrem, Gangguan Kelistrikan, Klasifikasi, Sistem Peringatan Dini |  |\n|  |  | This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |\n\n© Helmy Satria Martha Putra1,2, Alit Kesatria Mendala1,2, Intan Jelita Saragih1,2,  \nNeng Ayu Herawati1,3, Ayu Purwarianti1,3, Nugraha Priya Utama1,3  \n1. Introduction  \nThe demand for electricity due to economic development is increasing. As the foundation of energy for society, the electric power system is an important need [1] . The lives of the population, the majority of Indonesians use electricity to support their daily lives. The electricity supply must be maintained and safe. There are two factors that cause power outages. These include internal factors such as operational errors and external factors such as extreme weather [2] .  \nPower outages due to extreme weather conditions are external factors that are becoming very problematic. Electrical equipment exposed to prolonged extreme weather may deteriorate in condition, p","cbCaiikEGVGjQlTN","https://ap.wps.com/l/cbCaiikEGVGjQlTN","pdf",512978,1,17,"English","en",105,"# Introduction\n## Problem of reactive monitoring and outage risk\n## Role of machine learning for early warning\n## Geospatial enrichment with HDBSCAN\n# Method overview (feature engineering and classification)","[{\"question\":\"What problem does the paper address?\",\"answer\":\"The paper addresses the lack of a proactive system for detecting electricity outages caused by extreme weather, noting that existing approaches are largely reactive and do not integrate weather data with grid data.\"},{\"question\":\"How does the proposed system prepare and enrich data?\",\"answer\":\"It combines historical weather and outage data using spatial alignment, enriches geospatial features with HDBSCAN, applies Yeo-Johnson transformation and robust scaling, and balances classes using SMOTE, ADASYN, and SMOTE-ENN.\"},{\"question\":\"Which model performs best and what metric is highlighted?\",\"answer\":\"LightGBM with SMOTE achieves the highest recall (0.99) and the fewest false negatives, supporting more reliable early warnings.\"}]","A Machine Learning-Based Early Warning System For Electricity Outage Due to Extreme Weather - Jurnal E-Komtek Vol 9 No 2 | PDF",1785822872,43,{"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},"a-machine-learning-based-early-warning-system-for-electricity-outage-due-to-extreme-weather-jurnal-e-komtek-vol-9-no-2","",{"@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/a-machine-learning-based-early-warning-system-for-electricity-outage-due-to-extreme-weather-jurnal-e-komtek-vol-9-no-2/124520/",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 problem does the paper address?","Question",{"text":75,"@type":76},"The paper addresses the lack of a proactive system for detecting electricity outages caused by extreme weather, noting that existing approaches are largely reactive and do not integrate weather data with grid data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed system prepare and enrich data?",{"text":80,"@type":76},"It combines historical weather and outage data using spatial alignment, enriches geospatial features with HDBSCAN, applies Yeo-Johnson transformation and robust scaling, and balances classes using SMOTE, ADASYN, and SMOTE-ENN.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model performs best and what metric is highlighted?",{"text":84,"@type":76},"LightGBM with SMOTE achieves the highest recall (0.99) and the fewest false negatives, supporting more reliable early warnings.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]