[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125802-en":3,"doc-seo-125802-105":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},125802,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","MASTER - Machine Learning-Based Cold Start Latency Prediction Framework in Serverless Edge Computing Environments for Industry 4.0","Serverless edge computing combined with the Industrial Internet of Things (IIoT) can improve industrial production efficiency, yet cold start latency remains a key obstacle that wastes resources. MASTER is a machine learning-based resource management framework that applies an extreme gradient boosting (XGBoost) model to predict cold start latency for Industry 4.0 applications. A new cold start dataset is built from an IIoT scenario focused on predictive maintenance, and real-platform experiments validate the approach.","36 IEEE JOURNAL OF SELECTED AREAS IN SENSORS, VOL. 1, 2024  \nMASTER: Machine Learning-Based Cold Start Latency Prediction Framework in Serverless Edge Computing Environments for Industry 4.0  \nMuhammed Golec , Sukhpal Singh Gill , Huaming Wu , Talat Cemre Can , Mustafa Golec  , Oktay Cetinkaya , Felix Cuadrado , Ajith Kumar Parlikad , and Steve Uhlig   \nAbstract—The integration of serverless edge computing and the Industrial Internet of Things (IIoT) has the potential to optimize industrial production. However, cold start latency is one of the main challenges in this area, resulting in resource waste. To address this issue, we propose a new machine learning-based resource management framework called MASTER which utilizes an extreme gradient boosting (XGBoost) model to predict the cold start latency for Industry 4.0 applications for performance optimization. Furthermore, we created a new cold start dataset using an IIoT scenario (i.e. predictive maintenance) to validate the proposed MASTER framework in serverless edge computing  \nManuscript received 16 January 2024; revised 25 February 2024; accepted 29 April 2024 . Date of publication 2 May 2024; date of current version 23 May 2024 . This work was supported in part by the National Natural Science Foundation of China under Grant 62071327 and in part by the Tianjin Science and Technology Planning Project under Grant 22ZYYYJC00020 . The work of Muhammed Golec was supported by the Ministry of Education of the Turkish Republic. The work of Felix Cuadrado was supported by HE ACES Project under Grant 101093126 . Recommended by Lead Guest Editor Yuemin Ding and Guest Editor Kan Yu. (Corresponding author: Huaming Wu.)  \nMuhammed Golec is with the School of Electronic Engineering and Computer Science, Queen Mary University of London, E1 4NS London, U.K., and also with Abdullah Gul University, Kayseri 38080, Türkiye (e[mail: m.golec@qmul.ac.uk](mail: m.golec@qmul.ac.uk)).  \nSukhpal Singh Gill and Steve Uhlig are with the School of Electronic Engineering and Computer Science, Queen Mary University of London, E1 4NS London, U.K. (e-mail: [s.s.gill@qmul.ac.uk](s.s.gill@qmul.ac.uk) ; [steve.uhlig@qmul.ac.uk](steve.uhlig@qmul.ac.uk)).  \nHuaming Wu is with the Center for Applied Mathematics, Tianjin University, Tianjin 300072, China ([e-mail: whming@tju.edu.cn](e-mail: whming@tju.edu.cn)).  \nTalat Cemre Can is with TFI TAB Food Investments, Istanbul 34349, Türkiye ([e-mail: talatcemrecan@gmail.com](e-mail: talatcemrecan@gmail.com)).  \nMustafa Golec is with the Faculty of Engineering Computer Engineering, Dumlupınar University, Kütahya 43100, Türkiye (e-mail: [mustafagolec36@gmail.com](mustafagolec36@gmail.com)).  \nOktay Cetinkaya is with the Oxford e-Research Centre (OeRC), Department of Engineering Science, University of Oxford, OX1 2JD Oxford, U.K. (e-mail: [oktay.cetinkaya@eng.ox.ac.uk](oktay.cetinkaya@eng.ox.ac.uk)).  \nFelix Cuadrado is with the School of Telecommunications Engineering, Technical University of Madrid (UPM), 43100 Madrid, Spain (e-mail: [felix.cuadrado@upm.es](felix.cuadrado@upm.es)).  \nAjith Kumar Parlikad is with the Institute for Manufacturing, Department of Engineering, University of Cambridge, CB2 1TN Cambridge, U.K. (e-mail: [aknp2@cam.ac.uk](aknp2@cam.ac.uk)).  \nData is available online at [https://github.com/MuhammedGolec/Cold](https://github.com/MuhammedGolec/Cold)Start-Dataset-V2 .  \nDigital Object Identifier 10.1109/JSAS.2024.3396440  \nenvironments. We have evaluated the performance of the MASTER framework using a real-world serverless platform, Google Cloud Platform for single-step prediction (SSP) and multiple-step prediction (MSP) operations and compared it with existing frameworks that used deep deterministic policy gradient (DDPG) and long short-term memory (LSTM) models. The experimental results show that the XGBoostbased resource management framework is the most successful model in predicting cold start with mean absolute percentage error (MAPE) values of 0","cbCaicOYmQCIpWOT","https://ap.wps.com/l/cbCaicOYmQCIpWOT","pdf",3574112,1,13,"English","en",105,"# Introduction\n## Cold Start Latency Challenge in IIoT\n## Predictive Maintenance in Industry 4.0\n# Proposed MASTER Framework\n## XGBoost-Based Latency Prediction\n## New Cold Start Dataset\n# Experimental Setup and Results\n## Single-Step and Multiple-Step Prediction\n## Comparison With DDPG and LSTM\n## Resource-Aware Evaluation (Energy and CO2)\n# Index Terms","[{\"question\":\"What problem does the MASTER framework address in serverless edge computing?\",\"answer\":\"MASTER targets cold start latency in serverless edge computing for Industry 4.0, which can waste resources. It provides predictions to support performance-optimized resource management.\"},{\"question\":\"How does MASTER predict cold start latency?\",\"answer\":\"MASTER uses an extreme gradient boosting (XGBoost) model to forecast cold start latency for Industry 4.0 applications. It is evaluated using both single-step and multiple-step prediction settings.\"},{\"question\":\"How are the MASTER predictions validated and what models are compared against?\",\"answer\":\"Validation uses a newly created cold start dataset based on an IIoT scenario for predictive maintenance. Experiments run on a real serverless platform (Google Cloud Platform) and compare MASTER against frameworks using DDPG and LSTM models, reporting lower prediction error for XGBoost.\"}]","MASTER - Machine Learning-Based Cold Start Latency Prediction Framework in Serverless Edge Computing Environments for Industry 4.0 | PDF",1785901290,33,{"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},"master-machine-learning-based-cold-start-latency-prediction-framework-in-serverless-edge-computing-environments-for-industry-40","",{"@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/master-machine-learning-based-cold-start-latency-prediction-framework-in-serverless-edge-computing-environments-for-industry-40/125802/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the MASTER framework address in serverless edge computing?","Question",{"text":75,"@type":76},"MASTER targets cold start latency in serverless edge computing for Industry 4.0, which can waste resources. It provides predictions to support performance-optimized resource management.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does MASTER predict cold start latency?",{"text":80,"@type":76},"MASTER uses an extreme gradient boosting (XGBoost) model to forecast cold start latency for Industry 4.0 applications. It is evaluated using both single-step and multiple-step prediction settings.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the MASTER predictions validated and what models are compared against?",{"text":84,"@type":76},"Validation uses a newly created cold start dataset based on an IIoT scenario for predictive maintenance. Experiments run on a real serverless platform (Google Cloud Platform) and compare MASTER against frameworks using DDPG and LSTM models, reporting lower prediction error for XGBoost.","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"]