BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Stockholm BEGIN:DAYLIGHT DTSTART:20240331T030000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST END:DAYLIGHT BEGIN:STANDARD DTSTART:20231029T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20231128T154159Z UID:A574328D-4485-42D2-9B51-D0BE56471490 DTSTART;TZID=Europe/Stockholm:20231122T090000 DTEND;TZID=Europe/Stockholm:20231122T100000 DESCRIPTION:The evolution of future beyond 5G/6G networks is expected to re ly greatly on network slicing technology. Through network slicing\, commun ication service providers seek to meet all the requirements imposed by ver ticals by differentiating services and ensuring performance. Radio access network (RAN) slicing is a critical component of end-to-end network slicin g\, especially for ultra-reliable low-latency communication (URLLC) servic es. These services are a key enabler for applications requiring near-real- time responsiveness\, such as autonomous vehicles\, augmented reality\, an d precision and mission-critical robotics. However\, due to the stringent requirements of URLLC services and the dynamics of the RAN environment\, s licing the RAN is a challenge. The Open Radio Access Network (Open RAN) ar chitecture paves the way for flexible sharing of network resources by intr oducing more programmability into the RAN. In addition\, artificial intell igence (AI) and machine learning (ML) techniques\, such as deep reinforcem ent learning (DRL) algorithms\, are promising tools for efficient manageme nt of network resources with increased flexibility and agility.  In this talk\, we will provide an overview of the use of ML for RAN slicing in an Open RAN context\, as well as an overview of current challenges and open questions.\n\nCo-sponsored by: Luleå University of Technology\n\nSpeaker( s): Prof. Soumaya Cherkaoui\, \n\nRoom: Room B192\, LTU\, Campus Porsön\, Luleå\, Norrbottens lan\, Sweden\, 971 87\, Virtual: https://events.vtoo ls.ieee.org/m/384288 LOCATION:Room: Room B192\, LTU\, Campus Porsön\, Luleå\, Norrbottens lan\ , Sweden\, 971 87\, Virtual: https://events.vtools.ieee.org/m/384288 ORGANIZER:karl.andersson@ltu.se SEQUENCE:44 SUMMARY:IEEE ComSoc Distinguished Lecture: Prof. Soumaya Cherkaoui\, Polyte chnique Montréal\, Canada URL;VALUE=URI:https://events.vtools.ieee.org/m/384288 X-ALT-DESC:Description: <br /><p>The evolution of future beyond 5G/6G netwo rks is expected to rely greatly on network slicing technology. Through net work slicing\, communication service providers seek to meet all the requir ements imposed by verticals by differentiating services and ensuring perfo rmance. Radio access network (RAN) slicing is a critical component of end- to-end network slicing\, especially for ultra-reliable low-latency communi cation (URLLC) services.&nbsp\;&nbsp\; These services are a key enabler fo r applications requiring near-real-time responsiveness\, such as autonomou s vehicles\, augmented reality\, and precision and mission-critical roboti cs. However\, due to the stringent requirements of URLLC services and the dynamics of the RAN environment\, slicing the RAN is a challenge.&nbsp\; T he Open Radio Access Network (Open RAN) architecture paves the way for fle xible sharing of network resources by introducing more programmability int o the RAN. In addition\, artificial intelligence (AI) and machine learning (ML) techniques\, such as deep reinforcement learning (DRL) algorithms\, are promising tools for efficient management of network resources with inc reased flexibility and agility.  In this talk\, we will provide an overv iew of the use of ML for RAN slicing in an Open RAN context\, as well as a n overview of current challenges and open questions.</p> END:VEVENT END:VCALENDAR