{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-deep-learning-based-approach-to-vm-behavior","title":"A Deep Learning based approach to VM behavior identification in cloud systems","arxiv_id":"1903.01930","date":"2019-03-05","proceeding":null,"authors":["Matteo Stefanini","Riccardo Lancellotti","Lorenzo Baraldi","Simone Calderara"],"abstract":"Cloud computing data centers are growing in size and complexity to the point\nwhere monitoring and management of the infrastructure become a challenge due to\nscalability issues. A possible approach to cope with the size of such data\ncenters is to identify VMs exhibiting a similar behavior. Existing literature\ndemonstrated that clustering together VMs that show a similar behavior may\nimprove the scalability of both monitoring andmanagement of a data center.\nHowever, available techniques suffer from a trade-off between accuracy and time\nto achieve this result. Throughout this paper we propose a different approach\nwhere, instead of an unsupervised clustering, we rely on classifiers based on\ndeep learning techniques to assigna newly deployed VMs to a cluster of\nalready-known VMs. The two proposed classifiers, namely DeepConv and DeepFFT\nuse a convolution neural network and (in the latter model) exploits Fast\nFourier Transformation to classify the VMs. Our proposal is validated using a\nset of traces describing the behavior of VMs from a realcloud data center. The\nexperiments compare our proposal with state-of-the-art solutions available in\nliterature, demonstrating that our proposal achieve better performance.\nFurthermore, we show that our solution issignificantly faster than the\nalternatives as it can produce a perfect classification even with just a few\nsamples of data, making our proposal viable also toclassify on-demand VMs that\nare characterized by a short life span.","url_abs":"http://arxiv.org/abs/1903.01930v1","url_pdf":"http://arxiv.org/pdf/1903.01930v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-deep-learning-based-approach-to-vm-behavior","repo_url":"https://github.com/MatteoStefanini/DeepVM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cloud-computing","task_name":"Cloud Computing"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"management","task_name":"Management"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}