pr\u00e9sentent<\/p>\n\n\n\n
Autoris\u00e9e \u00e0 pr\u00e9senter ses travaux en vue de l\u2019obtention du Doctorat de l’Institut Polytechnique de Paris, pr\u00e9par\u00e9 \u00e0 l’Institut Polytechnique de Paris T\u00e9l\u00e9com SudParis en :<\/p>\n\n\n\n
le LUNDI 9 NOVEMBRE 2026 \u00e0 14h00<\/p>\n\n\n\n
\u00e0<\/p>\n\n\n\n
Amphith\u00e9\u00e2tre C06
9 Rue Charles Fourier, 91000 \u00c9vry-Courcouronnes<\/p>\n\n\n\n
Membres du jury :<\/strong><\/p>\n\n\n\n M. Noel CRESPI<\/strong>, Full professor, Institut Polytechnique de Paris T\u00e9l\u00e9com SudParis, FRANCE – Directeur de these R\u00e9sum\u00e9 :<\/strong><\/p>\n\n\n\n L\u2019int\u00e9gration de technologies de jumeaux num\u00e9riques (Digital Twins) dans le cadre des villes intelligentes devient de plus en plus essentielle \u00e0 l\u2019\u00e8re du num\u00e9rique. \u00c0 mesure que les environnements urbains \u00e9voluent vers des \u00e9cosyst\u00e8mes interconnect\u00e9s, fond\u00e9s sur des donn\u00e9es en temps r\u00e9el et des syst\u00e8mes de gestion intelligents, les jumeaux num\u00e9riques offrent une approche puissante et dynamique pour la planification et la gestion urbaines. Cependant, de nombreux jumeaux num\u00e9riques existants restent principalement limit\u00e9s \u00e0 la visualisation et \u00e0 la surveillance. Par ailleurs, des difficult\u00e9s li\u00e9es \u00e0 la fiabilit\u00e9 de l\u2019acquisition des donn\u00e9es, \u00e0 la fragmentation des architectures, \u00e0 l\u2019interop\u00e9rabilit\u00e9 et au passage vers une prise de d\u00e9cision autonome continuent de limiter leur mise en \u0153uvre pratique. Cette th\u00e8se d\u00e9veloppe une cha\u00eene compl\u00e8te allant de l\u2019acquisition des donn\u00e9es \u00e0 la prise de d\u00e9cision. Dans un premier temps, une classification fond\u00e9e sur le niveau de maturit\u00e9 est \u00e9tablie afin de caract\u00e9riser les jumeaux num\u00e9riques urbains comme passifs, pr\u00e9dictifs, prescriptifs ou autonomes, selon leurs capacit\u00e9s. Afin de renforcer la couche sous-jacente d\u2019acquisition des donn\u00e9es, un m\u00e9canisme de contr\u00f4le d\u2019acc\u00e8s pr\u00e9dictif et sensible au contexte, appel\u00e9 Context-Aware Predictive Access Class Barring (CAP-ACB), est propos\u00e9 pour les d\u00e9ploiements massifs de l\u2019Internet des objets (IoT). En combinant la pr\u00e9diction des arriv\u00e9es, les retours d\u2019information du r\u00e9seau, les informations contextuelles et des m\u00e9canismes de r\u00e9solution des collisions, le CAP-ACB am\u00e9liore le d\u00e9bit, le d\u00e9lai d\u2019acc\u00e8s et l\u2019utilisation des ressources par rapport aux approches de contr\u00f4le d\u2019acc\u00e8s fixes, tout en atteignant des performances proches de celles des m\u00e9thodes th\u00e9oriquement optimales. Sur la base de cette couche de donn\u00e9es fiable, une architecture de r\u00e9f\u00e9rence inter-domaines est propos\u00e9e pour des jumeaux num\u00e9riques pr\u00e9dictifs et prescriptifs int\u00e9grant l\u2019humain dans la boucle de d\u00e9cision (human-in-the-loop). Cette architecture associe la gestion de donn\u00e9es h\u00e9t\u00e9rog\u00e8nes, la communication edge-cloud, la pr\u00e9vision, la simulation bas\u00e9e sur des sc\u00e9narios, les interfaces applicatives, la visualisation et l\u2019aide \u00e0 la d\u00e9cision. La transf\u00e9rabilit\u00e9 de cette architecture est d\u00e9montr\u00e9e \u00e0 travers deux applications r\u00e9elles utilisant des donn\u00e9es op\u00e9rationnelles provenant d\u2019Issy-les-Moulineaux, pour la gestion du trafic urbain, et de Cascais, au Portugal, pour la planification durable de la collecte des d\u00e9chets. Le jumeau num\u00e9rique d\u00e9di\u00e9 au trafic combine la pr\u00e9diction, la surveillance en temps r\u00e9el, la simulation de fermetures de routes ainsi que l\u2019\u00e9valuation des \u00e9missions en \u00e9quivalent CO\u2082. Le jumeau num\u00e9rique consacr\u00e9 \u00e0 la gestion des d\u00e9chets int\u00e8gre des pr\u00e9visions \u00e0 court et \u00e0 long terme, une planification des collectes fond\u00e9e sur des seuils, l\u2019optimisation des itin\u00e9raires, l\u2019\u00e9valuation de la flotte de v\u00e9hicules et l\u2019estimation des \u00e9missions. Enfin, cette th\u00e8se propose un cadre de recherche visant \u00e0 faire \u00e9voluer les jumeaux num\u00e9riques int\u00e9grant l\u2019humain dans la boucle vers des syst\u00e8mes capables de prendre en compte les comportements et de fonctionner de mani\u00e8re autonome, gr\u00e2ce \u00e0 l\u2019apprentissage par renforcement, \u00e0 l\u2019intelligence artificielle g\u00e9n\u00e9rative et \u00e0 l\u2019intelligence artificielle explicable. Dans l\u2019ensemble, ce travail montre que la mise en \u0153uvre efficace de jumeaux num\u00e9riques urbains n\u00e9cessite des avanc\u00e9es coordonn\u00e9es en mati\u00e8re de connectivit\u00e9 fiable, de gestion interop\u00e9rable des donn\u00e9es, de pr\u00e9diction, de simulation et d\u2019aide \u00e0 la d\u00e9cision centr\u00e9e sur l\u2019humain. Il fournit ainsi une base pratique pour une gestion des villes intelligentes plus performante, plus intelligente et davantage autonome.<\/p>\n\n\n\n Abstract :<\/strong><\/p>\n\n\n\n The integration of Digital Twin technology into smart city frameworks is becoming increasingly vital in the digital era. As urban environments evolve into interconnected ecosystems driven by real-time data and intelligent management systems, digital twins offer a powerful, dynamic approach to urban planning and operations. However, many existing Digital twins remain limited to visualization and monitoring, while challenges related to reliable data acquisition, architectural fragmentation, interoperability, and the transition toward autonomous decision-making continue to restrict their practical application. This thesis develops the complete data-to-decision pipeline. Firstly, a maturity-oriented classification is established to characterize urban Digital Twins as passive, predictive, prescriptive, and autonomic according to their capabilities.To strengthen the underlying data acquisition layer, a Context-Aware Predictive Access Class Barring (CAP-ACB) mechanism is proposed for massive IoT deployments. By combining arrival prediction, network feedback, contextual information, and collision-resolution mechanisms, CAP-ACB improves throughput, access delay, and resource utilization compared with fixed access-control approaches while achieving performance close to theoretically optimal schemes. Building on this reliable data layer, a cross-domain reference architecture is proposed for predictive and prescriptive human-in-the-loop Digital Twins.The architecture integrates heterogeneous data management, edge-cloud communication, forecasting, scenario-based simulation, application interfaces, visualization, and decision support. Its transferability is demonstrated through two real-world applications using operational data from Issy-les-Moulineaux, France, for urban traffic management, and Cascais, Portugal, for sustainable waste-collection planning. The traffic Digital Twin combines prediction, real time monitoring, road closure simulation and Co2 equivalent emission assesment.The waste management Digital Twin integrate short and long term prediction with threshold based collection planning routing, fleet assesment and emission estimation.Finally, the thesis proposes a research framework for progressing from human-in-the-loop Digital Twins toward behavior-aware and autonomic systems through reinforcement learning, generative AI, and explainable AI. Overall, the work demonstrates that effective urban Digital Twins require coordinated advances in reliable connectivity, interoperable data management, prediction, simulation, and human-centered decision support, providing a practical foundation for more intelligent and autonomous smart city management.<\/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 Madame Maira ALVI Autoris\u00e9e \u00e0 pr\u00e9senter ses travaux en vue de l\u2019obtention du Doctorat de l’Institut Polytechnique de Paris, pr\u00e9par\u00e9 \u00e0 l’Institut Polytechnique de Paris […]<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ocean_front_end_style_editor":"no","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-7719","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\/7719","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=7719"}],"version-history":[{"count":1,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/7719\/revisions"}],"predecessor-version":[{"id":7720,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/7719\/revisions\/7720"}],"wp:attachment":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/media?parent=7719"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/categories?post=7719"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/tags?post=7719"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
Mme Tiziana MARGARIA<\/strong>, Full professor, University of Limerick; Lero \u2013 Research Ireland Centre for Software, IRLANDE – Rapporteur
Mme Maria PIA FANTI<\/strong>, Full professor, Department of Electrical and Information Engineering, Politecnico di Bari, Italy, ITALIE – Rapporteur
M. Soheil SABRI<\/strong>, Assistant professor, University of Central Florida, School of Modeling, Simulation and Training \/ Institute for Simulation & Training. , ETATS-UNIS – Examinateur
M. Thierry COUPAYE<\/strong>, VP Research Augmented Operations, Orange Innovation , FRANCE – Examinateur
M. Giancarlo FORTINO<\/strong>, Full professor, Department of Informatics, Modeling, Electronics and Systems, University of Calabria, Italy, ITALIE – Examinateur
M. Marcelo DIAS DE AMORIM<\/strong>, Directeur de recherche, Sorbonne Universit\u00e9 \u2014 LIP6 (Laboratoire d’Informatique de Paris 6), FRANCE – Examinateur
M. Roberto MINERVA<\/strong>, Professeur associ\u00e9, Telecom SudParis, FRANCE – Co-encadrant de these<\/p>\n\n\n\n\u00ab Digital Twin Approach for Smart City Development \u00bb<\/h2>\n\n\n\n
pr\u00e9sent\u00e9 par Madame Maira ALVI<\/h2>\n\n\n\n