BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20261101T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260326T190917Z UID:70516F4A-4D96-489F-B7AD-0EE7747CA057 DTSTART;TZID=America/New_York:20260326T140000 DTEND;TZID=America/New_York:20260326T150000 DESCRIPTION:Due to the rapid emergence of smart\, autonomous\, and connecte d vehicles\, Vehicular networks in 6G and beyond are entering an era where reactive radio resource control is no longer sufficient. Traditional radi o resource management (RRM) suffers from outdated channel measurements\, s ignificant overhead and latency in channel state acquisition\, and lack of situational awareness. Thus\, addressing the extreme dynamics of mobility \, blockage\, and interference demands a paradigm shift toward predictive\ , context-aware\, and proactive RRM schemes.\nIn this talk\, we present th at digital twin (DT) technology is a key enabler to realize this transform ation. By maintaining a synchronized\, high-fidelity\, geo-spatial replica of the physical network\, DT allows networks to “see the future” — anticipating channel evolution\, traffic demand\, and environmental change s before they occur. This capability enables predictive optimization\, con text-aware decision-making\, and real-time what-if analysis under rapidly changing vehicular scenarios.\nThis talk presents our vision toward DT-in- the-loop proactive RRM\, where real-time network data continuously updates the twin\, and AI-driven optimization leverages this predictive insight t o make proactive control decisions. We will first discuss the design of a geospatially aware\, propagation-centric\, high-fidelity DT capable of acc urately modeling dynamic wireless channels. We will then introduce several DT-in-the-loop optimization frameworks that integrate real-time data from physical networks with predictive modeling to enable proactive and adapti ve resource management. These approaches effectively mitigate the impact o f outdated channel information\, enhance interference management\, and imp rove connectivity reliability. Furthermore\, we will demonstrate a DT-base d framework for real-time\, high-resolution radio environment mapping in d ynamic vehicular environments while accounting for time-varying blockages. We will also outline several future research directions toward scalable a nd practical DT-enabled RRM for 6G and beyond.\n\nSpeaker(s): Zoheb Hassan \, \n\nVirtual: https://events.vtools.ieee.org/m/550554 LOCATION:Virtual: https://events.vtools.ieee.org/m/550554 ORGANIZER:ajmery.sultana@algomau.ca SEQUENCE:24 SUMMARY:Digital Twin and AI-Empowered Proactive Radio Resource Management f or Vehicular Networks in 6G and Beyond. URL;VALUE=URI:https://events.vtools.ieee.org/m/550554 X-ALT-DESC:Description: <br /><div style="text-align: justify\; line-height : 1.38\; margin: 0in 0in 8pt\; font-family: Verdana\,Geneva\,sans-serif\; font-size: 12pt\; color: rgb(0\,0\,0)\;">Due to the rapid emergence of sma rt\, autonomous\, and connected vehicles\, Vehicular networks in 6G and be yond are entering an era where reactive radio resource control is no longe r sufficient. Traditional radio resource management (RRM)&nbsp\;suffers fr om outdated channel measurements\, significant overhead and latency in cha nnel state acquisition\, and lack of situational awareness. Thus\, address ing the extreme dynamics of mobility\, blockage\, and interference demands a paradigm shift toward predictive\, context-aware\, and proactive RRM sc hemes.</div>\n<div style="text-align: justify\; line-height: 1.38\; margin : 0in 0in 8pt\; font-family: Verdana\,Geneva\,sans-serif\; font-size: 12pt \; color: rgb(0\,0\,0)\;">&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\ ;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\; In this talk\, we prese nt that digital twin (DT) technology is a key enabler to realize this tran sformation. By maintaining a synchronized\, high-fidelity\, geo-spatial re plica of the physical network\, DT allows networks to &ldquo\;see the futu re&rdquo\; &mdash\; anticipating channel evolution\, traffic demand\, and environmental changes before they occur. This capability enables predictiv e optimization\, context-aware decision-making\, and real-time <em>what-if </em>&nbsp\;analysis under rapidly changing vehicular scenarios.</div>\n<d iv style="text-align: justify\; line-height: 1.38\; margin: 0in 0in 8pt\; font-family: Verdana\,Geneva\,sans-serif\; font-size: 12pt\; color: rgb(0\ ,0\,0)\;">&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;& nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\; This talk presents our vision toward DT -in-the-loop proactive RRM\, where real-time network data continuously upd ates the twin\, and AI-driven optimization leverages this predictive insig ht to make proactive control decisions. We will first discuss the design o f a geospatially aware\, propagation-centric\, high-fidelity DT capable of accurately modeling dynamic wireless channels. We will then introduce sev eral DT-in-the-loop optimization frameworks that integrate real-time data from physical networks with predictive modeling to enable proactive and ad aptive resource management. These approaches effectively mitigate the impa ct of outdated channel information\, enhance interference management\, and improve connectivity reliability. Furthermore\, we will demonstrate a DT- based framework for real-time\, high-resolution radio environment mapping in dynamic vehicular environments while accounting for time-varying blocka ges. We will also outline several future research directions toward scalab le and practical DT-enabled RRM for 6G and beyond.</div>\n<div style="text -align: justify\; line-height: 1.38\; margin: 0in 0in 8pt\; font-family: V erdana\,Geneva\,sans-serif\; font-size: 12pt\; color: rgb(0\,0\,0)\;">&nbs p\;</div> END:VEVENT END:VCALENDAR