[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118198-en":3,"doc-seo-118198-105":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},118198,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Bayesian optimization for cloud resource management through machine learning","Optimal cloud configuration for recurring big data analytic jobs is a challenging industrial problem. Bayesian Optimization offers an efficient way to reach optimal or near-optimal configurations in cloud settings, while Machine Learning can exploit prior knowledge from application behavior. This paper presents a hybrid approach combining Bayesian Optimization with Machine Learning to handle time-constrained optimization and avoid infeasible configurations. Experiments show a substantial reduction in unfeasible executions versus a pure constrained BO baseline.","Bayesian optimization for cloud resource management through machine learning  \nBruno Guindani, Danilo Ardagna and Alessandra Guglielmi  \nAbstract Optimal cloud configuration of recurring big data analytic jobs is a relevant and challenging task in the industry. To this end, Bayesian Optimization is a promising method for efficiently finding optimal or near-optimal configurations for such applications, which are often executed in the cloud. On the other hand, Machine Learning methods can provide useful knowledge about the application at hand thanks to the quality of their estimations. In this paper, we propose a hybrid algorithm that is based on Bayesian Optimization and integrates elements from Machine Learning techniques to tackle time-constrained optimization problems in a cloud computing setting. We consider a recurring job scenario, where unfeasible points are to be avoided by all means, as they are a waste of resources. In such a context, Machine Learning helps to convey valuable information about the violation of constraints. Experiments on big data applications have shown that our algorithm significantly reduces the amount of unfeasible executions with respect to a pure constrained BO approach.  \nKey words: acquisition function, cloud computing, Gaussian Process  \n1 Introduction  \nBig data analytics are employed in several industrial fields to allow organizations and companies to make better decisions. The most suitable execution environment of big data analytic applications is a cluster of virtual machines (VMs) which allows the adjustment of the allocated resources (CPU, memory, disk, network) to match the application current needs. Choosing the right cloud configuration to minimize  \nBruno Guindani, e-mail: [bruno.guindani@polimi.it](bruno.guindani@polimi.it) · Danilo Ardagna, e-mail: danilo. [ardagna@polimi.it](ardagna@polimi.it) · Alessandra Guglielmi, e-mail: [alessandra.guglielmi@polimi.it](alessandra.guglielmi@polimi.it)[ ](alessandra.guglielmi@polimi.it)Politecnico di Milano, Piazza Leonardo da Vinci 32, 20133 Milano (Italy)  \n2 Bruno Guindani, Danilo Ardagna and Alessandra Guglielmi  \nexecution times and reduce costs is essential to service quality and business competitiveness. This is especially crucial for recurring cloud jobs, i.e., applications that need to be executed multiple times, which constitute a significant part of the total amount of analytic jobs running in the cloud [2, 20] . However, variability in the progress and resource requirements of analytic jobs imply that choosing the best configuration for a broad spectrum of applications is a challenging process [2] .  \nBayesian Optimization (BO) has recently gained notoriety as a powerful tool to solve global optimization problems in which expensive black-box functions are involved; see the recent paper [15] or the popular tutorial paper [5] . BO is a sequential design strategy that requires few steps to get sufficiently close to the true optimum, while requiring no derivative information on the optimized function. Most commonly, it is initialized by choosing and evaluating a small handful of starting points, then fitting a Gaussian process (GP) on these points. This approach can be interpreted as assuming a prior distribution for the unknown infinite-dimensional parameter 􀀵 , i.e., the function to be optimized. The posterior distribution of the fitted GP provides an estimate of both the function value at each point and the uncertainty around the estimate. BO then iteratively chooses new points at which to evaluate the function in a such a way to balance exploration (high uncertainty) and exploitation (best estimated function value); see, for instance,[11] . The topic of constrained BO has also received attention in the literature [8, 11] .  \nThe goal of this work is to integrate Bayesian Optimization algorithms with Machine Learning (ML) techniques in the context of cloud computing optimization for recurring jobs. The former techniques have proven ","cbCaim1bM7cLKR5n","https://ap.wps.com/l/cbCaim1bM7cLKR5n","pdf",1616546,1,13,"English","en",105,"# 1 Introduction\n# 2 Background and mathematical formulation\n## Bayesian Optimization overview\n## Constrained BO and motivation\n# 3 Proposed hybrid BO algorithm\n# 4 Experimental results\n# 5 Conclusion","[{\"question\":\"What problem does the paper address in cloud resource management?\",\"answer\":\"It targets selecting optimal cloud configurations for recurring big data analytic jobs while reducing execution time and cost. The approach also aims to avoid infeasible configurations that waste resources.\"},{\"question\":\"How does Bayesian Optimization work in this context?\",\"answer\":\"The method uses a sequential strategy that builds a Gaussian Process model from evaluated configurations. It then selects new points by balancing exploration and exploitation without requiring derivative information.\"},{\"question\":\"What is the key contribution of the proposed hybrid algorithm?\",\"answer\":\"The paper integrates Machine Learning elements into Bayesian Optimization to handle time-constrained optimization. Machine Learning is used to convey information about constraint violations, improving feasibility compared with pure constrained BO.\"}]","Bayesian optimization for cloud resource management through machine learning | PDF",1785682128,33,{"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},"bayesian-optimization-for-cloud-resource-management-through-machine-learning","",{"@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/bayesian-optimization-for-cloud-resource-management-through-machine-learning/118198/",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","2026-08-02",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 in cloud resource management?","Question",{"text":75,"@type":76},"It targets selecting optimal cloud configurations for recurring big data analytic jobs while reducing execution time and cost. The approach also aims to avoid infeasible configurations that waste resources.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does Bayesian Optimization work in this context?",{"text":80,"@type":76},"The method uses a sequential strategy that builds a Gaussian Process model from evaluated configurations. It then selects new points by balancing exploration and exploitation without requiring derivative information.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the key contribution of the proposed hybrid algorithm?",{"text":84,"@type":76},"The paper integrates Machine Learning elements into Bayesian Optimization to handle time-constrained optimization. Machine Learning is used to convey information about constraint violations, improving feasibility compared with pure constrained BO.","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"]