[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119853-en":3,"doc-seo-119853-105":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},119853,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","CloudProphet - A Machine Learning-Based Performance Prediction for Public Clouds - research report","CloudProphet presents a machine learning-driven approach to predict application performance in public clouds where virtual machines behave as black boxes. Consolidating multiple VMs on one server can cause severe resource contention and performance interference, yet most management techniques require accurate performance prediction that is difficult to obtain in public-cloud settings. The method first identifies the running application type inside each VM, then selects highly correlated runtime metrics to predict performance level. Experiments on cloud benchmarks show over 2x improvement in worst prediction error, and a performance degradation index addresses variable workloads across different server and VM configurations.","arXiv :2309 . 16333v1 [ cs .DC] 28 Sep 2023  \nCloudProphet: A Machine Learning-Based Performance Prediction for Public Clouds  \nDarong Huang, Luis Costero, Ali Pahlevan, Marina Zapater, Member, IEEE, David Atienza, Fellow, IEEE  \nAbstract—Computing servers have played a key role in developing and processing emerging compute-intensive applications in recent years. Consolidating multiple virtual machines (VMs) inside one server to run various applications introduces severe competence for limited resources among VMs. Many techniques such as VM scheduling and resource provisioning are proposed to maximize the cost-efficiency of the computing servers while alleviating the performance inference between VMs. However, these management techniques require accurate performance prediction of the application running inside the VM, which is challenging to get in the public cloud due to the black-box nature of the VMs. From this perspective, this paper proposes a novel machine learning-based performance prediction approach for applications running in the cloud. To achieve high accuracy predictions for black-box VMs, the proposed method first identifies the running application inside the virtual machine. It then selects highly-correlated runtime metrics as the input of the machine learning approach to accurately predict the performance level of the cloud application. Experimental results with  \nstate-of-the-art cloud benchmarks demonstrate that our proposed method outperforms the existing prediction methods by more than 2xin terms of worst prediction error. In addition, we successfully tackle the challenge in performance prediction for applications with variable workloads by introducing the performance degradation index, which other comparison methods fail to consider. The workflow versatility of the proposed approach has been verified with different modern servers and VM configurations.  \nIndex Terms—performance prediction, application type identification, machine learning, virtual machine, public clouds  \n~~ ~~ ✦ ~~ ~~  \n1 INTRODUCTION  \nCLOUD platforms have gained tremendous growth in the  \nlast decades because of their vast advantages in security, flexibility, and cost-efficiency [1] . Therefore, attracting end-users to transition their applications to the cloud. In the post-COVID future, cloud-computing investment increased by 37% in the first quarter of 2020 [2] . With this trend, worldwide end-user spending on cloud services is forecast to gain over 20% average growth in recent years and reach around 400 billion dollars in 2022 [3] .  \nThe demand for public clouds has increased drastically in the last decade, entailing an explosion in energy usage. Data centers consume roughly 200 terawatt-hours of energy each year, which contributes to 1% of global electricity demand [4] . The demand keeps ramping up, and estimations show that data centers will use around 6-10% of global electricity in 2030 [5] . This motivates cloud service providers, particularly Amazon, Microsoft, Google, and Huawei, among others, to optimize the efficiency and usage of cloud servers towards a more sustainable and economical way [1], [6] . Thanks to the virtualization technology sup-  \nDarong Huang, Ali Pahlevan, and David Atienza are with the Embedded Systems Laboratory (ESL), ´Ecole polytechnique f´ed´erale de Lausanne (EPFL), 1015 Lausanne, Switzerland. E-mail: {darong.huang, ali.pahlevan, [david.atienza](david.atienza}@epfl.ch)[}](david.atienza}@epfl.ch)[@epfl.ch](david.atienza}@epfl.ch).  \nLuis Costero was with the Embedded System Laboratory (ESL), ´Ecole Polytechnique F´ed´erale de Lausanne (EPFL), 1015 Lausanne, Switzerland. Now, he is with the Dpto. of Computer Architecture and Automatics, Complutense University of Madrid (UCM), Spain (email: [lcostero@ucm.es](lcostero@ucm.es)).  \nMarina Zapater was with the Embedded System Laboratory (ESL), ´Ecole Polytechnique F´ed´erale de Lausanne (EPFL), 1015 Lausanne, Switzerland. Now, she is with the School of Engine","cbCailkLWZZhvWwz","https://ap.wps.com/l/cbCailkLWZZhvWwz","pdf",1123562,1,15,"English","en",105,"# Introduction\n## Performance prediction challenges in public clouds\n## VM collocation and resource contention","[{\"question\":\"Why is performance prediction difficult in public clouds?\",\"answer\":\"Public-cloud VMs are black boxes due to privacy policies, limiting cloud providers from accessing VMs created by clients and reading detailed runtime metrics.\"},{\"question\":\"How does CloudProphet improve prediction accuracy for black-box VMs?\",\"answer\":\"It identifies the running application inside the VM, then uses highly correlated runtime metrics as inputs to a machine learning model to predict the performance level.\"},{\"question\":\"How does CloudProphet handle applications with variable workloads?\",\"answer\":\"It introduces a performance degradation index designed to capture performance drops under changing workloads, which other comparison methods fail to consider.\"}]","CloudProphet - A Machine Learning-Based Performance Prediction for Public Clouds - research report | PDF",1785726661,38,{"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},"cloudprophet-a-machine-learning-based-performance-prediction-for-public-clouds-research-report","",{"@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/cloudprophet-a-machine-learning-based-performance-prediction-for-public-clouds-research-report/119853/",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","2026-08-03",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},"Why is performance prediction difficult in public clouds?","Question",{"text":75,"@type":76},"Public-cloud VMs are black boxes due to privacy policies, limiting cloud providers from accessing VMs created by clients and reading detailed runtime metrics.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does CloudProphet improve prediction accuracy for black-box VMs?",{"text":80,"@type":76},"It identifies the running application inside the VM, then uses highly correlated runtime metrics as inputs to a machine learning model to predict the performance level.",{"name":82,"@type":73,"acceptedAnswer":83},"How does CloudProphet handle applications with variable workloads?",{"text":84,"@type":76},"It introduces a performance degradation index designed to capture performance drops under changing workloads, which other comparison methods fail to consider.","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"]