[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126841-en":3,"doc-seo-126841-105":30,"detail-sidebar-cat-0-en-105":92},{"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},126841,1099523882367,"Hazel","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",6,"Technology","Integrating Bayesian Optimization and Machine Learning for the Optimal Configuration of Cloud Systems","Bayesian Optimization (BO) is used to efficiently search for optimal cloud configurations, while Machine Learning (ML) contributes predictive knowledge about the application under study. The proposed method combines BO with ML components to optimize recurring jobs on public and private cloud platforms, including scenarios with black-box constraints such as execution time or accuracy. The approach is evaluated across edge computing, scientific computing, and Big Data use cases, showing improved results over state-of-the-art black-box techniques.","Integrating Bayesian Optimization and Machine Learning for the Optimal Configuration of Cloud Systems  \nBruno Guindani  , Graduate Student Member, IEEE, Danilo Ardagna, Senior Member, IEEE, Alessandra Guglielmi , Roberto Rocco  , Graduate Student Member, IEEE, and Gianluca Palermo , Senior Member, IEEE  \nAbstract—Bayesian Optimization (BO) is an efficient method for finding optimal cloud configurations for several types of applications. On the other hand, Machine Learning (ML) can provide helpful knowledge about the application at hand thanks to its predicting capabilities. This work proposes a general approach based on BO, which integrates elements from ML techniques in multiple ways, to find an optimal configuration of recurring jobs running in public and private cloud environments, possibly subject to blackbox constraints, e.g., application execution time or accuracy. We test our approach by considering several use cases, including edge computing, scientific computing, and Big Data applications. Results show that our solution outperforms other state-of-the-art black-box techniques, including classical autotuning and BO-and ML-based algorithms, reducing the number of unfeasible executions and corresponding costs up to 2–4 times.  \nIndex Terms—Acquisition function, Bayesian optimization, black-box optimization, machine learning.  \nI. INTRODUCTION  \nT ODAY, Information and Communication Technology  \n(ICT) systems often exploit increasingly complex applications. These applications can execute in a distributed fashion on computer networks or cloud systems and are often computing intensive. This complexity allows little insight into their inner workings, especially for system administrators who did not engineer them. Examples of these systems include Big Data analytic tools running on the cloud, scientific computing programs for simulations requiring massive computational power, electronic or mechanical devices operated by Artificial Intelligence, and  \nManuscript received 13 February 2023; revised 2 January 2024; accepted 28 January 2024 . Date of publication 1 February 2024; date of current version 8 March 2024 . The work of Alessandra Guglielmi was supported by MUR, Grant Dipartimento di Eccellenza 2023-2027 . This work was supported by the European Commission through the Horizon 2020 under Grant 956137 LIGATE: LIgand Generator and portable drug discovery platform AT Exascale, as part of the European High-Performance Computing (EuroHPC) Joint Undertaking Program. Recommended for acceptance by D. Wu. (Corresponding author: Bruno Guindani.)  \nBruno Guindani, Danilo Ardagna, Roberto Rocco, and Gianluca Palermo are with the Department of Electronics, Information, and Bioengineering, Politecnico di Milano, 20133 Milano, Italy (e-mail: bruno.guindani@polimi. it; [danilo.ardagna@polimi.it](danilo.ardagna@polimi.it); [roberto.rocco@polimi.it](roberto.rocco@polimi.it); gianluca.palermo@ [polimi.it](polimi.it)).  \nAlessandra Guglielmi is with the Department of Mathematics, Politecnico di Milano, 20133 Milano, Italy (e-mail: [alessandra.guglielmi@polimi.it](alessandra.guglielmi@polimi.it)).  \nDigital Object Identifier 10.1109/TCC.2024.3361070  \ncomputing continuum systems for efficient distributed computation. These systems require the configuration of software settings or the available hardware resources (CPU, memory, disk, network, etc.). However, a poor choice for such settings can lead to application under-performance or additional costs for the end users. The impact of incorrect configuration is potentially paramount [1], [2], [3], and proper optimization prevents such negative effects. For instance, running a big-data application in the cloud without the correct configuration multiplies the execution cost by a factor of three on average, up to ten in the worst case [3] . This is especially true for recurring jobs, i.e., applications that must execute multiple times, possibly with regular frequency. In this case, the additional cost of suboptimal","cbCainptl1Gj9mVk","https://ap.wps.com/l/cbCainptl1Gj9mVk","pdf",6296679,1,18,"English","en",105,"# Abstract\n# Introduction\n## Problem of configuration in cloud and recurring jobs\n## Limits of white-box modeling and need for black-box methods\n# Related work and black-box optimization context","[{\"question\":\"What is the main goal of integrating Bayesian optimization with machine learning in the paper?\",\"answer\":\"To find optimal cloud configurations by combining BO’s search efficiency with ML’s predictive guidance about the application.\"},{\"question\":\"What types of cloud jobs and constraints are targeted?\",\"answer\":\"Recurring jobs in public and private cloud environments, potentially subject to black-box constraints like execution time or accuracy.\"},{\"question\":\"Which application areas are used to test the proposed approach?\",\"answer\":\"Edge computing, scientific computing, and Big Data applications.\"}]","Integrating Bayesian Optimization and Machine Learning for the Optimal Configuration of Cloud Systems | PDF",1785935167,45,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"integrating-bayesian-optimization-and-machine-learning-for-the-optimal-configuration-of-cloud-systems","",{"@graph":36,"@context":86},[37,54,69],{"@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/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/integrating-bayesian-optimization-and-machine-learning-for-the-optimal-configuration-of-cloud-systems/126841/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is the main goal of integrating Bayesian optimization with machine learning in the paper?","Question",{"text":76,"@type":77},"To find optimal cloud configurations by combining BO’s search efficiency with ML’s predictive guidance about the application.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What types of cloud jobs and constraints are targeted?",{"text":81,"@type":77},"Recurring jobs in public and private cloud environments, potentially subject to black-box constraints like execution time or accuracy.",{"name":83,"@type":74,"acceptedAnswer":84},"Which application areas are used to test the proposed approach?",{"text":85,"@type":77},"Edge computing, scientific computing, and Big Data applications.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,114,119,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":112,"slug":113},50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},8,"Research & Report",30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]