https:\/\/teams.microsoft.com\/meet\/3175321922718?p=Eb8g7Hnjbq5biLogLb<\/a><\/p>\n\n\n\nMembres du jury :<\/strong><\/p>\n\n\n\nM. Noel CRESPI<\/strong>, Professeur, T\u00e9l\u00e9com SudParis, FRANCE – Directeur de these
M. Antonio MANZALINI<\/strong>, Project Manager, Telecom Italia, ITALIE – Examinateur
M. Roberto MINERVA<\/strong>, Ma\u00eetre de conf\u00e9rences, Telecom SudParis , FRANCE – CoDirecteur de these
M. Pedro BRACONNOT VELLOSO<\/strong>, Associate Professor, Conservatoire National des Arts et M\u00e9tiers (CNAM), FRANCE – Rapporteur
Mme Barbara MARTINI<\/strong>, Professeur, Universitas Mercatorum, ITALIE – Examinateur
M. Paolo BELLAVISTA<\/strong>, Professor, University of Bologna, ITALIE – Rapporteur<\/p>\n\n\n\n\u00ab Jumelage num\u00e9rique en r\u00e9seau pour le continuum Edge-Cloud : R\u00f4les et exigences \u00bb<\/h2>\n\n\n\npr\u00e9sent\u00e9 par Monsieur Syed Mohsan RAZA<\/h2>\n\n\n\n
R\u00e9sum\u00e9 :<\/strong><\/p>\n\n\n\nUn Network Digital Twin collecte des donn\u00e9es provenant de composants physiques, virtuels et logiciels et prend en charge l’analyse en temps r\u00e9el des performances du r\u00e9seau, l’\u00e9mulation et le contr\u00f4le intelligent du r\u00e9seau physique. Il r\u00e9pond principalement aux exigences et aux objectifs business des op\u00e9rateurs et des fournisseurs de services. Cependant, les sp\u00e9cifications actuelles des Network Digital Twins de l’IETF, de l’ITU et des propositions acad\u00e9mqiue n\u00e9gligent les exigences d’autres parties prenantes dans le continuum Edge-Cloud, notamment celles des fournisseurs de services. Il est n\u00e9cessaire d’exploiter la flexibilit\u00e9 de l’architecture Network Digital Twin et d’int\u00e9grer de nouveaux mod\u00e8les de donn\u00e9es afin de contextualiser 1) les ressources dans les diff\u00e9rents segments du continuum Edge-Cloud, \u00e0 savoir Edge, Core et Cloud ; 2) les applications d\u00e9ploy\u00e9es dans les ressources ; et 3) le rendu des vues d’informations pour les utilisateurs ou les parties prenantes concern\u00e9s. R\u00e9cemment, la composantisation des applications utilisateur, r\u00e9seau et cloud a \u00e9t\u00e9 largement adopt\u00e9e \u00e0 l’aide d’une architecture de microservices. En g\u00e9n\u00e9ral, les programmeurs d’applications se concentrent sur les fonctionnalit\u00e9s plut\u00f4t que sur le temps de r\u00e9ponse potentiel et l’impact du placement des microservices sur les ressources informatiques sous-jacentes. Chaque microservice consomme diverses ressources, a un impact sur les n\u0153uds de calcul et doit \u00eatre d\u00e9ploy\u00e9 sur des n\u0153uds qui r\u00e9pondent \u00e0 ses exigences. Par ailleurs, le continuum Edge-Cloud comprend des n\u0153uds dont les performances sont dynamiques et qui pr\u00e9sentent des limites en termes de prise en charge de la qualit\u00e9 de service requise. De plus, leur propri\u00e9t\u00e9 entrave souvent une collaboration fluide. Les requ\u00eates des utilisateurs peuvent conna\u00eetre des temps de r\u00e9ponse plus longs si la passerelle d’interface de programmation d’application et les microservices associ\u00e9s sont \u00e9loign\u00e9s de l’origine de l’utilisateur, ou si la cha\u00eene de microservices est tr\u00e8s distribu\u00e9e \u00e0 travers le continuum. Cela remet en question l’hypoth\u00e8se courante selon laquelle les ressources Edge sont toujours le meilleur choix pour minimiser le temps de r\u00e9ponse. Il devient donc important de comprendre l’architecture de l’application, les interactions entre les microservices, de mesurer l’impact sur les ressources et d’organiser les microservices afin d’optimiser le temps de r\u00e9ponse global. Pour relever ces d\u00e9fis, cette th\u00e8se contribue tout d’abord \u00e0 utiliser les capacit\u00e9s de simulation du Network Digital Twin et \u00e0 d\u00e9velopper un mod\u00e8le pour un placement efficace des microservices dans le sc\u00e9nario Edge-Cloud Continuum. Ce mod\u00e8le permet au fournisseur de services de saisir les param\u00e8tres souhait\u00e9s li\u00e9s \u00e0 la distribution des ressources et au d\u00e9ploiement des microservices. Il permet au fournisseur de localiser la passerelle API dans un segment particulier, d’encha\u00eener les microservices dans un certain ordre et d’\u00e9valuer le temps de r\u00e9ponse afin d’agr\u00e9ger et d’organiser les microservices pertinents. Deuxi\u00e8mement, cette th\u00e8se apporte une analyse par couches des segments dans le continuum Edge-Cloud. Elle propose ensuite un nouveau mod\u00e8le de donn\u00e9es qui conceptualise principalement les caract\u00e9ristiques des n\u0153uds et des microservices d\u00e9ploy\u00e9s, dans le but de rendre le Network Digital Twin sensible au contexte. Elle adopte une repr\u00e9sentation ontologique pour les composants du cluster dans un segment et met en \u0153uvre un mod\u00e8le de donn\u00e9es utilisable qui caract\u00e9rise les donn\u00e9es de performance et de consommation des n\u0153uds. En r\u00e9sum\u00e9, les contributions de la th\u00e8se sont doubles : le placement des microservices dans le continuum Edge-Cloud et la promotion d’une mod\u00e9lisation pr\u00e9cise pour \u00e9tendre les capacit\u00e9s du Network Digital Twin.<\/p>\n\n\n\n
Abstract :<\/strong><\/p>\n\n\n\nNetwork Digital Twin collects data from physical, virtual, and software components and supports real-time network performance analysis, emulation, and intelligent physical network control. Primarily, it supports the requirements and business objectives of network operators and communication service providers. However, the current Network Digital Twin specifications from the Internet Research Task Force, the International Telecommunication Union, and academic proposals overlook the requirements of other stakeholders in the Edge-Cloud Continuum, such as service providers. It necessitates exploiting the flexibility of Network Digital Twin architecture and integrating new data models to contextualize 1) the resources across segments of the Edge-Cloud Continuum, namely Edge, Core, and Cloud; 2) applications deployed in resources; and 3) rendering the information views for the relevant users or stakeholders. Recently, componentization of user, network, and cloud applications has been widely adopted using a microservices architecture. Typically, application programmers focus on functionality rather than the potential response time and the impact of microservice placement on the underlying computing resources. Each microservice consumes various resources, impacts computational nodes, and must be deployed on nodes that meet its requirements. Meanwhile, the Edge-Cloud Continuum includes nodes with dynamic performance characteristics and limitations in supporting the required service quality, and their ownership often hinders seamless collaboration. User requests can experience larger response times if the application programming interface gateway and related microservices are far from the user’s origin, or the microservice chain is highly distributed across the continuum. This challenges the common assumption that Edge resources are always the best choice for minimizing response time. Thus, it becomes important to understand the application architecture, interactions among microservices, measuring the impact on resources, and arranging microservices to optimize overall response time. To address the aforementioned challenges, this thesis first contributes by utilizing the simulation capabilities of Network Digital Twin and developing a model for efficient microservices placement in the Edge-Cloud Continuum scenario. This model allows the service provider to input the desired parameters related to resource distribution and microservices deployment. It enables the provider to locate the API Gateway in a particular segment, enchain the microservices in a certain order, and evaluate the response time to aggregate and arrange the relevant microservices. Secondly, this thesis contributes a layer-wise analysis of the segments in Edge-Cloud Continuum. Next, it proposes a novel data model that primarily conceptualizes the characteristics of nodes and deployed microservices, aiming to make the Network Digital Twin context-aware. It adopts an ontological representation for the cluster components in a segment and implements a usable data model that characterizes the performance and node consumption data. In summary, the thesis contributions are twofold: microservices placement in the Edge-Cloud Continuum and promoting precise modeling to extend the Network Digital Twin capabilities.<\/p>\n","protected":false},"excerpt":{"rendered":"
L’Ecole doctorale : Ecole Doctorale de l’Institut Polytechnique de Paris et le Laboratoire de recherche SAMOVAR – Services r\u00e9partis, Architectures, Mod\u00e9lisation, Validation, Administration des R\u00e9seaux pr\u00e9sentent l\u2019AVIS DE SOUTENANCE de Monsieur Syed Mohsan RAZA Autoris\u00e9 \u00e0 pr\u00e9senter ses travaux en vue de l\u2019obtention du Doctorat de l’Institut Polytechnique de Paris, pr\u00e9par\u00e9 \u00e0 T\u00e9l\u00e9com SudParis en […]<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ocean_post_layout":"","ocean_both_sidebars_style":"","ocean_both_sidebars_content_width":0,"ocean_both_sidebars_sidebars_width":0,"ocean_sidebar":"","ocean_second_sidebar":"","ocean_disable_margins":"enable","ocean_add_body_class":"","ocean_shortcode_before_top_bar":"","ocean_shortcode_after_top_bar":"","ocean_shortcode_before_header":"","ocean_shortcode_after_header":"","ocean_has_shortcode":"","ocean_shortcode_after_title":"","ocean_shortcode_before_footer_widgets":"","ocean_shortcode_after_footer_widgets":"","ocean_shortcode_before_footer_bottom":"","ocean_shortcode_after_footer_bottom":"","ocean_display_top_bar":"default","ocean_display_header":"default","ocean_header_style":"","ocean_center_header_left_menu":"","ocean_custom_header_template":"","ocean_custom_logo":0,"ocean_custom_retina_logo":0,"ocean_custom_logo_max_width":0,"ocean_custom_logo_tablet_max_width":0,"ocean_custom_logo_mobile_max_width":0,"ocean_custom_logo_max_height":0,"ocean_custom_logo_tablet_max_height":0,"ocean_custom_logo_mobile_max_height":0,"ocean_header_custom_menu":"","ocean_menu_typo_font_family":"","ocean_menu_typo_font_subset":"","ocean_menu_typo_font_size":0,"ocean_menu_typo_font_size_tablet":0,"ocean_menu_typo_font_size_mobile":0,"ocean_menu_typo_font_size_unit":"px","ocean_menu_typo_font_weight":"","ocean_menu_typo_font_weight_tablet":"","ocean_menu_typo_font_weight_mobile":"","ocean_menu_typo_transform":"","ocean_menu_typo_transform_tablet":"","ocean_menu_typo_transform_mobile":"","ocean_menu_typo_line_height":0,"ocean_menu_typo_line_height_tablet":0,"ocean_menu_typo_line_height_mobile":0,"ocean_menu_typo_line_height_unit":"","ocean_menu_typo_spacing":0,"ocean_menu_typo_spacing_tablet":0,"ocean_menu_typo_spacing_mobile":0,"ocean_menu_typo_spacing_unit":"","ocean_menu_link_color":"","ocean_menu_link_color_hover":"","ocean_menu_link_color_active":"","ocean_menu_link_background":"","ocean_menu_link_hover_background":"","ocean_menu_link_active_background":"","ocean_menu_social_links_bg":"","ocean_menu_social_hover_links_bg":"","ocean_menu_social_links_color":"","ocean_menu_social_hover_links_color":"","ocean_disable_title":"default","ocean_disable_heading":"default","ocean_post_title":"","ocean_post_subheading":"","ocean_post_title_style":"","ocean_post_title_background_color":"","ocean_post_title_background":0,"ocean_post_title_bg_image_position":"","ocean_post_title_bg_image_attachment":"","ocean_post_title_bg_image_repeat":"","ocean_post_title_bg_image_size":"","ocean_post_title_height":0,"ocean_post_title_bg_overlay":0.5,"ocean_post_title_bg_overlay_color":"","ocean_disable_breadcrumbs":"default","ocean_breadcrumbs_color":"","ocean_breadcrumbs_separator_color":"","ocean_breadcrumbs_links_color":"","ocean_breadcrumbs_links_hover_color":"","ocean_display_footer_widgets":"default","ocean_display_footer_bottom":"default","ocean_custom_footer_template":"","ocean_post_oembed":"","ocean_post_self_hosted_media":"","ocean_post_video_embed":"","ocean_link_format":"","ocean_link_format_target":"self","ocean_quote_format":"","ocean_quote_format_link":"post","ocean_gallery_link_images":"on","ocean_gallery_id":[],"footnotes":""},"categories":[286,402],"tags":[],"class_list":["post-6891","post","type-post","status-publish","format-standard","hentry","category-fractualites-ennews-fr","category-seminaires-ness-2013-fr","entry"],"_links":{"self":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6891","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/comments?post=6891"}],"version-history":[{"count":1,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6891\/revisions"}],"predecessor-version":[{"id":6892,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6891\/revisions\/6892"}],"wp:attachment":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/media?parent=6891"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/categories?post=6891"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/tags?post=6891"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}