Deep reinforcement learning for tail latency regulation in co-located applications through cooperative core and cache allocation

Κιμωνίδης, Αλέξανδρος; Kimonidis, Alexandros

dc.contributor.author	Κιμωνίδης, Αλέξανδρος
dc.contributor.author	Kimonidis, Alexandros	en
dc.date.accessioned	2022-03-02T10:18:56Z
dc.date.available	2022-03-02T10:18:56Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/54900
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.22598
dc.rights	Default License
dc.subject	Cloud	en
dc.subject	Management	en
dc.subject	Resource	en
dc.subject	AI	en
dc.subject	Deep reinforcement learning	en
dc.subject	Νέφος	el
dc.subject	Διαχείριση πόρων	el
dc.subject	Τεχνητή νοημοσύνη	el
dc.subject	Βαθιά ενισχυμένη εκμάθηση	el
dc.subject	Τεχνητή μάθηση	el
dc.title	Deep reinforcement learning for tail latency regulation in co-located applications through cooperative core and cache allocation	en
heal.type	bachelorThesis
heal.classification	Resource Management	en
heal.classification	Cloud	el
heal.classification	Deep Reinforcement Learning	el
heal.language	el
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2021-10-25
heal.abstract	The amount of workloads ran on the Cloud is growing all the time. Data center operators and cloud providers have embraced workload co-location and multi- tenancy as first-class system design concerns to efficiently service and manage these massive computing needs. Current state-of-the-art resource managers place applications on the available pool of resources using standard metrics such as CPU or memory usage. As a result, current state-of-the-art resource managers fail to achieve adequate resource utilization. In this thesis, we design a resource manager that leverages deep reinforce- ment learning for its policy and uses performance monitoring counters which are a more complex metric that is able to determine a machine’s current state. We showcase the impact of applying stress on different server resources and the need for a better scheduler that considers the correct metrics. We integrate our solution with OpenAI Gym, one of the most widely used tool-kits for devel- oping and comparing reinforcement learning algorithms, and we show that we can achieve higher resource usage compared to the default scheduler as well as other state-of-the-art schedulers.	en
heal.advisorName	Σούντρης, Δημήτριος	el
heal.committeeMemberName	Σούντρης, Δημήτριος	el
heal.committeeMemberName	Τσανάκας, Παναγιώτης	el
heal.committeeMemberName	Γκούμας, Γεώργιος	el
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών	el
heal.academicPublisherID	ntua
heal.numberOfPages	97 σ.	el
heal.fullTextAvailability	false