[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125949-en":3,"doc-seo-125949-105":31,"detail-sidebar-cat-0-en-105":93},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},125949,137451207643,"Noah","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",6,"Technology","Self-Adaptive Service Selection for Machine Learning Continuous Delivery - Paper","Machine-learning applications on streaming data face continual change in models and inputs, making static model choice lead to degrading performance and added redeployment costs. This paper presents a self-adaptive system that autonomously selects interchangeable models for production and experimental processing, balancing predictive accuracy against redeployment frequency. Based on the MAPE-K reference model, it uses adaptive control loops, “what-if” environments for additional data, and two adaptation policies to plan upcoming module selection. A learning-based method reduces experimental needs, while a 16-year energy forecasting evaluation cuts errors by up to 34%.","University of Groningen  \nSelf-Adaptive Service Selection for Machine Learning Continuous Delivery  \nHadadian Nejad Yousefi, Mostafa; Degeler, Victoria; Lazovik, Alexander  \nPublished in:  \nIEEE International Conference on Web Services  \nDOI:  \n10.1109/ICWS62655.2024.00123  \nIMPORTANT NOTE: You are advised to consult the publisher's version (publisher's PDF) if you wish to cite from it. Please check the document version below.  \nDocument Version  \nPublisher's PDF, also known as Version of record  \nPublication date: 2024  \nLink to publication in University of Groningen/UMCG research database  \nCitation for published version (APA):  \nHadadian Nejad Yousefi, M. , Degeler, V. , & Lazovik, A. (2024) . Self-Adaptive Service Selection for Machine Learning Continuous Delivery. In IEEE International Conference on Web Services (pp. 1048- 1056) . IEEE. [https://doi.org/10.1109/ICWS62655.2024.00123](https://doi.org/10.1109/ICWS62655.2024.00123)  \nCopyright  \nOther than for strictly personal use, it is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license (like Creative Commons) .  \nThe publication may also be distributed here under the terms of Article 25fa of the Dutch Copyright Act, indicated by the “Taverne” license. More information can be found on the University of Groningen website: [https://www.rug.nl/library/open-access/self-archiving-pure/taverne](https://www.rug.nl/library/open-access/self-archiving-pure/taverne)amendment.  \nTake-down policy  \nIf you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.  \nDownloaded from the University of Groningen/U MCG research database (Pure): [http://www.rug. nl/research/portal. For technical reasons the](http://www.rug. nl/research/portal. For technical reasons the)[ ](http://www.rug. nl/research/portal. For technical reasons the)[number of authors shown on this cover page is limited to 10 maximum.](number of authors shown on this cover page is limited to 10 maximum.)  \nDownload date: 29-12-2025  \n2024 IEEE International Conference on Web Services (ICWS) | 979-8-3503-6855-0/24/$31.00 ©2024 IEEE | DOI: 10. 1 109/ICWS62655.2024.00123  \n2024 IEEE International Conference on Web Services (ICWS)  \nSelf-Adaptive Service Selection for Machine Learning Continuous Delivery  \nMostafa Hadadian Nejad Yousefi  \nBernoulli Institute University of Groningen Groningen, The Netherlands [m.hadadian@rug.nl](m.hadadian@rug.nl)  \nVictoria Degeler  \nInformatics Institute University of Amsterdam Amsterdam, The Netherlands [v.o.degeler@uva.nl](v.o.degeler@uva.nl)  \nAlexander Lazovik  \nBernoulli Institute University of Groningen Groningen, The Netherlands [a.lazovik@rug.nl](a.lazovik@rug.nl)  \nAbstract—In the dynamic landscape of machine learning applications on streaming data, the constant evolution of models and input data complicates optimal model deployment. The static selection of a model risks suboptimal performance as data patterns evolve, while frequent redeployments increase operational costs. This paper proposes a self-adaptive system that autonomously selects interchangeable models for processing streaming data while balancing the tradeoff of performance and redeployment frequency. Inspired by the MAPE-K reference model, our approach utilizes an adaptive model selection control loop to continuously monitor model performance on production and experimental data.“what-if” environments are introduced to collect additional experimental data, simulating production-like scenarios. A selection algorithm that employs two distinct adaptation policies is introduced that strategically plans the selection of the most suitable module for upcoming data. Leveraging a learning-based method, we improve the efficiency of our system by recognizing the patterns of selection eliminating the","cbCaikVskDlmtalz","https://ap.wps.com/l/cbCaikVskDlmtalz","pdf",1085273,11,1,10,"English","en",105,"# Abstract\n# Introduction\n# Problem Statement and Motivation\n# Proposed Self-Adaptive Selection Approach\n## Adaptive Control Loop Inspired by MAPE-K\n## What-If Environments for Data Collection\n## Two Adaptation Policies for Planning\n# Learning-Based Pattern Recognition\n# Empirical Evaluation and Results\n## Energy Forecasting Use Case (16 Years of Data)","[{\"question\":\"Why does static model selection become inefficient for continuous machine learning on streaming data?\",\"answer\":\"Static selection can become suboptimal as data patterns shift over time, while redeploying models frequently increases operational costs.\"},{\"question\":\"How does the proposed approach adapt model choice during ongoing development?\",\"answer\":\"It continuously monitors performance using an adaptive control loop inspired by the MAPE-K reference model and uses “what-if” environments plus two adaptation policies to plan which module to select next.\"},{\"question\":\"What evidence shows the framework improves performance compared with static selection?\",\"answer\":\"An energy forecasting evaluation over 16 years of data reports error reductions of up to 34% versus the best static selection, and it also indicates that experimental “what-if” analyses can often be discontinued with only 12% of historical data.\"}]","Self-Adaptive Service Selection for Machine Learning Continuous Delivery - Paper | PDF",1785902183,25,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"self-adaptive-service-selection-for-machine-learning-continuous-delivery-paper","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/technology/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/self-adaptive-service-selection-for-machine-learning-continuous-delivery-paper/125949/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"Why does static model selection become inefficient for continuous machine learning on streaming data?","Question",{"text":77,"@type":78},"Static selection can become suboptimal as data patterns shift over time, while redeploying models frequently increases operational costs.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How does the proposed approach adapt model choice during ongoing development?",{"text":82,"@type":78},"It continuously monitors performance using an adaptive control loop inspired by the MAPE-K reference model and uses “what-if” environments plus two adaptation policies to plan which module to select next.",{"name":84,"@type":75,"acceptedAnswer":85},"What evidence shows the framework improves performance compared with static selection?",{"text":86,"@type":78},"An energy forecasting evaluation over 16 years of data reports error reductions of up to 34% versus the best static selection, and it also indicates that experimental “what-if” analyses can often be discontinued with only 12% of historical data.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,115,120,125,130,133,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":113,"slug":114},50,"technology",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":121,"doc_module":4,"doc_module_name":47,"category_name":122,"show_sort_weight":123,"slug":124},8,"Research & Report",30,"research-report",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":127,"show_sort_weight":128,"slug":129},9,"Religion & Spirituality",20,"religion-spirituality",{"id":128,"doc_module":4,"doc_module_name":47,"category_name":131,"show_sort_weight":128,"slug":132},"World Cup","world-cup",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":22,"slug":135},"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":108,"slug":139},19,"General","general"]