pr\u00e9sentent<\/p>\n\n\n\n
Autoris\u00e9 \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 JEUDI 16 JUILLET 2026 \u00e0 14h00<\/p>\n\n\n\n
\u00e0<\/p>\n\n\n\n
Amphith\u00e9\u00e2tre 11
T\u00e9l\u00e9com SudParis 9 Rue Charles Fourier, 91000 \u00c9vry-Courcouronnes<\/p>\n\n\n\n
Membres du jury :<\/strong><\/p>\n\n\n\n M. Denis CONAN<\/strong>, Ma\u00eetre de conf\u00e9rences, Institut Polytechnique de Paris, T\u00e9l\u00e9com SudParis, FRANCE – Directeur de th\u00e8se Invit\u00e9 :<\/strong><\/p>\n\n\n\n M. Roberto YUS<\/strong>, Ma\u00eetre de conf\u00e9rences,University of Maryland, ETATS-UNIS <\/p>\n\n\n\n R\u00e9sum\u00e9 :<\/strong><\/p>\n\n\n\n Les syst\u00e8mes cyber-physiques modernes op\u00e8rent souvent dans des environnements o\u00f9 les processus physiques, le comportement humain et le contr\u00f4le logiciel sont \u00e9troitement coupl\u00e9s. Les b\u00e2timents intelligents en sont un exemple typique : des capteurs surveillent en continu les conditions int\u00e9rieures, des syst\u00e8mes de contr\u00f4le r\u00e9gulent l\u2019environnement, et les occupants r\u00e9agissent \u00e0 leur tour \u00e0 ces conditions et les influencent. Ces interactions deviennent particuli\u00e8rement complexes dans les espaces partag\u00e9s, o\u00f9 plusieurs occupants partagent des zones communes mais ont des besoins de confort vari\u00e9s, souvent contradictoires. Par cons\u00e9quent, l\u2019\u00e9quilibre entre confort individuel et consommation d\u2019\u00e9nergie reste un d\u00e9fi majeur. Ce d\u00e9fi est aggrav\u00e9 par la nature multimodale des besoins de confort des occupants, qui d\u00e9pendent de facteurs comme la temp\u00e9rature, le niveau de bruit, la qualit\u00e9 de l\u2019air et l\u2019affluence. Ces facteurs sont interd\u00e9pendants, et l\u2019am\u00e9lioration d\u2019un aspect de l\u2019environnement int\u00e9rieur peut d\u00e9grader involontairement un autre. Par exemple, augmenter la ventilation pour am\u00e9liorer la qualit\u00e9 de l\u2019air peut modifier la temp\u00e9rature int\u00e9rieure et r\u00e9duire le confort thermique de certains occupants. En outre, les conditions environnementales comme les pr\u00e9f\u00e9rences de confort des occupants \u00e9voluent au fil du temps, si bien que des r\u00e9glages adapt\u00e9s \u00e0 un moment donn\u00e9 peuvent devenir inadapt\u00e9s ensuite. Les syst\u00e8mes actuels de fourniture du confort dans les espaces partag\u00e9s se r\u00e9partissent principalement en deux cat\u00e9gories : le contr\u00f4le de l\u2019environnement et l\u2019allocation de l\u2019espace. Le premier r\u00e9gule les conditions int\u00e9rieures partag\u00e9es, tandis que la seconde oriente les occupants vers des emplacements adapt\u00e9s. Cependant, les \u00e9tudes existantes dans ces deux cat\u00e9gories ne r\u00e9pondent pas pleinement aux d\u00e9fis expos\u00e9s ci-dessus. Cette th\u00e8se soutient que l\u2019\u00e9quilibre entre le confort individuel multimodal et l\u2019efficacit\u00e9 \u00e9nerg\u00e9tique dans les espaces partag\u00e9s n\u00e9cessite une approche hybride combinant le contr\u00f4le de l\u2019environnement et l\u2019allocation de l\u2019espace. \u00c0 cette fin, nous proposons un syst\u00e8me hybride de fourniture du confort qui s\u2019appuie sur des jumeaux num\u00e9riques (DT), c\u2019est-\u00e0-dire des r\u00e9pliques num\u00e9riques d\u2019entit\u00e9s et d\u2019environnements r\u00e9els. La premi\u00e8re contribution est un mod\u00e8le de repr\u00e9sentation \u00e0 base de graphes de propri\u00e9t\u00e9s des b\u00e2timents, des occupants et de leurs interactions. Ce mod\u00e8le capture \u00e0 la fois des informations statiques et dynamiques, et permet des simulations de haute fid\u00e9lit\u00e9 ainsi que la synchronisation avec des donn\u00e9es r\u00e9elles. La deuxi\u00e8me contribution est une couche extensible d\u2019orchestration des DT qui instancie et coordonne des jumeaux de b\u00e2timent et d\u2019occupant, ainsi que des jumeaux suppl\u00e9mentaires sp\u00e9cifiques au domaine ou des composants de simulation (p. ex., des mod\u00e8les d\u2019autres facteurs environnementaux ou dispositifs), via un middleware de co-simulation. Cette conception permet au syst\u00e8me d\u2019int\u00e9grer, selon les besoins, de nouveaux facteurs li\u00e9s au confort et des mod\u00e8les sp\u00e9cifiques aux sc\u00e9narios, tout en permettant la configuration dynamique des sc\u00e9narios, l\u2019analyse what-if et l\u2019\u00e9valuation contextuelle. La troisi\u00e8me contribution est une approche d\u2019optimisation hybride en ligne qui calcule conjointement les actions de guidage des occupants et de contr\u00f4le de l\u2019environnement. S\u2019appuyant sur l\u2019infrastructure DT, cette approche pr\u00e9dit les effets de diff\u00e9rentes actions sur les conditions int\u00e9rieures futures, le confort des occupants et la consommation d\u2019\u00e9nergie, puis identifie des solutions appropri\u00e9es au moyen d\u2019une optimisation multi-objectifs. Les contributions de la th\u00e8se sont instanci\u00e9es et \u00e9valu\u00e9es dans deux contextes r\u00e9els \u00e0 grande \u00e9chelle, dont un espace de co-working et le terminal d\u2019un a\u00e9roport international. Les r\u00e9sultats montrent que le syst\u00e8me hybride pilot\u00e9 par les DT peut am\u00e9liorer le confort individuel multimodal et l\u2019efficacit\u00e9 \u00e9nerg\u00e9tique.<\/p>\n\n\n\n Abstract :<\/strong><\/p>\n\n\n\n Modern cyber-physical systems often operate in environments where physical processes, human behaviour, and software control are tightly coupled. Smart buildings are a typical example, where sensors continuously monitor indoor conditions, control systems regulate the environment, and occupants in turn react to and influence these conditions. These interactions become especially complex in shared spaces, where multiple occupants share common zones but have diverse, and often conflicting, comfort needs. As a result, balancing individual comfort and energy consumption remains a major challenge. This challenge is further compounded by the multi-modal nature of occupant comfort needs, which depends on factors such as temperature, noise level, air quality, and crowdedness. These factors are interrelated, and improving one aspect of the indoor environment may unintentionally degrade another. For example, increasing ventilation to improve air quality can alter indoor temperature and reduce thermal comfort for some occupants. In addition, both environmental conditions and occupants’ comfort preferences change over time, so settings that are suitable at one moment may become unsuitable later. Current comfort provision systems in shared spaces mainly fall into two categories: environmental control and space allocation. The former regulates shared indoor conditions, while the latter guides occupants to suitable locations. However, existing studies in both categories do not fully address the challenges outlined above. This PhD thesis argues that balancing multi-modal individual comfort and energy efficiency in shared spaces requires a hybrid approach that combines both environmental control and space allocation. To this end, we propose a hybrid comfort provision system that leverages Digital Twins (DTs), which are digital replicas of real-world entities and environments. The first contribution is a property-graph-based representation model for buildings, occupants, and their interactions. This model captures both static and dynamic information and supports high-fidelity simulation as well as synchronisation with real-world data. The second contribution is an extensible DT orchestration layer that instantiates and coordinates building and occupant twins, together with additional domain-specific twins or simulation components (e.g., models for additional environmental factors or devices), through a co-simulation middleware. This design supports the system to incorporate new comfort-related factors and scenario-specific models as needed, while supporting dynamic scenario configuration, what-if analysis, and context-aware evaluation. The third contribution is an online hybrid optimisation approach that jointly computes occupant guidance and environmental control actions. Building on the DT infrastructure, the approach predicts the effects of alternative actions on future indoor conditions, occupant comfort, and energy consumption, and identifies suitable solutions through multi-objective optimisation. The thesis contributions are instantiated and evaluated in two large-scale real-world settings, including a co-working space and an international airport terminal. The results show that the DT-driven hybrid multi-modal individual comfort provisioning system can improve both multi-modal individual comfort and energy efficiency.<\/p>\n","protected":false},"excerpt":{"rendered":" L\u2019\u00c9cole doctorale : \u00c9cole 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 Jun MA Autoris\u00e9 \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_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":[286,549],"tags":[],"class_list":["post-7667","post","type-post","status-publish","format-standard","hentry","category-fractualites-ennews-fr","category-seminaire-acmes","entry"],"_links":{"self":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/7667","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=7667"}],"version-history":[{"count":1,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/7667\/revisions"}],"predecessor-version":[{"id":7668,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/7667\/revisions\/7668"}],"wp:attachment":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/media?parent=7667"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/categories?post=7667"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/tags?post=7667"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
M. Guillaume PIERRE<\/strong>, Professeur des universit\u00e9s, Universit\u00e9 de Rennes, FRANCE – Rapporteur
M. Fr\u00e9d\u00e9ric LE MOU\u00cbL<\/strong>, Professeur des universit\u00e9s, INSA Lyon, FRANCE – Rapporteur
M. Khalil DRIRA<\/strong>, Directeur de recherche, LAAS-CNRS, Universit\u00e9 de Toulouse, FRANCE – Examinateur
Mme Ella PELTONEN<\/strong>, Associate Professor, University of Oulu, FINLANDE – Examinateur
M. John Paul GIBSON<\/strong>, Professeur, Institut Polytechnique de Paris, T\u00e9l\u00e9com SudParis, FRANCE – Examinateur
M. Georgios BOULOUKAKIS<\/strong>, Ma\u00eetre de conf\u00e9rences, Institut Polytechnique de Paris, T\u00e9l\u00e9com SudParis et University of Patras , FRANCE – Co-encadrant de th\u00e8se<\/p>\n\n\n\n\u00ab Une Approche \u00e0 base de Jumeaux Num\u00e9riques pour l\u2019Optimisation du Confort Individuel Multimodal et de l\u2019Efficacit\u00e9 \u00c9nerg\u00e9tique dans des Environnements Multi-Occupants \u00bb<\/h2>\n\n\n\n
pr\u00e9sent\u00e9 par Monsieur Jun MA<\/h2>\n\n\n\n