Collaborative Filtering Based DNN Partitioning and Offloading on Heterogeneous Edge Computing Systems

Κακολύρης, Ανδρέας-Κοσμάς; Kakolyris, Andreas Kosmas

dc.contributor.author	Κακολύρης, Ανδρέας-Κοσμάς	el
dc.contributor.author	Kakolyris, Andreas Kosmas	en
dc.date.accessioned	2023-01-25T08:55:02Z
dc.date.available	2023-01-25T08:55:02Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/56896
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.24594
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/gr/	*
dc.subject	Cloud	en
dc.subject	Edge Computing	en
dc.subject	Collaborative Filtering	en
dc.subject	Neural Networks	en
dc.subject	Resource Management	en
dc.subject	Υπολογιστικό Νέφος	el
dc.subject	Ετερογένεια	el
dc.subject	Νευρωνικά Δίκτυα	el
dc.subject	Διαχείριση Πόρων	el
dc.subject	Τμηματοποίηση και Εκφόρτωση	el
dc.title	Collaborative Filtering Based DNN Partitioning and Offloading on Heterogeneous Edge Computing Systems	en
dc.contributor.department	Τομέας Τεχνολογίας Πληροφορικής και Υπολογιστών	el
heal.type	bachelorThesis
heal.classification	Computer engineering	en
heal.language	el
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2022-10-31
heal.abstract	Deep Neural Networks (DNNs) are an increasingly important part of many contemporary applications that reside at the edge of the Network. While DNNs are particularly effective at their respective tasks, they can be computationally intensive, often prohibitively so, when the resource and energy constraints of the edge computing environment are taken into account. In order to overcome these obstacles, the idea of partitioning and offloading part of the DNN computations to more powerful servers is often being proposed as a possible solution. While previous approaches have suggested resource management schemes to address this issue, the high dynamicity present in such environments is usually overlooked, both in regards to the variability of the DNN models and to the heterogeneous nature of the underlying hardware. In this thesis, we present a framework for DNN partitioning and offloading for edge computing systems. Our DNN partitioning and offloading framework utilizes a Collaborative Filtering mechanism based on knowledge gathered previously during profiling, in order to make quick and accurate estimates for the performance (latency) and energy consumption of the Neural Network layers over a diverse set of heterogeneous edge devices. Via the aggregation of this information and the utilization of an intelligent partitioning algorithm, our framework generates a set of Pareto optimal Neural Network splittings that trade-off between latency and energy consumption. Our framework is evaluated by using a variety of prominent DNN architectures to show that our approach outperforms current state-of-the-art methodologies by achieving a 9.58× speedup on average and up to 88.73% less energy consumption, simultaneously offering high estimation accuracy by limiting the prediction error down to 3.19% when it comes to latency and 0.18% when energy is concerned, while being lightweight and performing in a dynamic manner.	en
heal.advisorName	Soudris, Dimitrios
heal.committeeMemberName	Xydis, Sotirios
heal.committeeMemberName	Tsanakas, Panayiotis
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών. Τομέας Τεχνολογίας Πληροφορικής και Υπολογιστών	el
heal.academicPublisherID	ntua
heal.numberOfPages	72 σ	el
heal.fullTextAvailability	false