BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Eastern BEGIN:DAYLIGHT DTSTART:20220313T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20211107T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20220223T192224Z UID:DAA08B02-1D83-4B30-9D8D-D6159A0AEDA6 DTSTART;TZID=US/Eastern:20220223T120000 DTEND;TZID=US/Eastern:20220223T130000 DESCRIPTION:5G and edge computing will serve various emerging use cases tha t have diverse requirements for multiple resources\, e.g.\, radio\, transp ortation\, and computing. Network slicing is a promising technology for cr eating virtual networks that can be customized according to the requiremen ts of different use cases. Provisioning network slices requires end-to-end resource orchestration which is challenging. This talk will discuss the c hallenges of end-to-end network slicing in wireless edge computing systems and present machine learning assisted network slicing solutions. First\, the design of a new decentralized cross-domain resource orchestration solu tion will be presented. This solution optimizes the cross-domain resource orchestration while providing the performance and functional isolations am ong network slices. Second\, a decentralized deep reinforcement learning a lgorithm will be designed to dynamically orchestrate resources for end-to- end network slicing. The system implementation and testbed design of the e nd-to-end network slicing system will also be discussed. Finally\, future research directions in designing end-to-end network slicing solutions with machine learning will be shared.\n\nCo-sponsored by: North Jersey Section \, Signal Processing Chapter\,\n\nSpeaker(s): Dr. Tao Han\, \n\nAgenda: \n 5G and edge computing will serve various emerging use cases that have dive rse requirements for multiple resources\, e.g.\, radio\, transportation\, and computing. Network slicing is a promising technology for creating virt ual networks that can be customized according to the requirements of diffe rent use cases. Provisioning network slices requires end-to-end resource o rchestration which is challenging. This talk will discuss the challenges o f end-to-end network slicing in wireless edge computing systems and presen t machine learning assisted network slicing solutions. First\, the design of a new decentralized cross-domain resource orchestration solution will b e presented. This solution optimizes the cross-domain resource orchestrati on while providing the performance and functional isolations among network slices. Second\, a decentralized deep reinforcement learning algorithm wi ll be designed to dynamically orchestrate resources for end-to-end network slicing. The system implementation and testbed design of the end-to-end n etwork slicing system will also be discussed. Finally\, future research di rections in designing end-to-end network slicing solutions with machine le arning will be shared.\n\nRoom: M105\, Bldg: Muscarelle Center\, M105\, \ , 1000 River Road \, Teaneck \, New Jersey\, United States\, 07666\, Virtu al: https://events.vtools.ieee.org/m/301143 LOCATION:Room: M105\, Bldg: Muscarelle Center\, M105\, \, 1000 River Road \, Teaneck \, New Jersey\, United States\, 07666\, Virtual: https://events .vtools.ieee.org/m/301143 ORGANIZER:zhao@fdu.edu SEQUENCE:1 SUMMARY:Machine Learning Assisted Network Slicing for Wireless Edge Computi ng System URL;VALUE=URI:https://events.vtools.ieee.org/m/301143 X-ALT-DESC:Description: <br /><p>5G and edge computing will serve various e merging use cases that have diverse requirements for multiple resources\, e.g.\, radio\, transportation\, and computing. Network slicing is a promis ing technology for creating virtual networks that can be customized accord ing to the requirements of different use cases. Provisioning network slice s requires end-to-end resource orchestration which is challenging. This ta lk will discuss the challenges of end-to-end network slicing in wireless e dge computing systems and present machine learning assisted network slicin g solutions. First\, the design of a new decentralized cross-domain resour ce orchestration solution will be presented. This solution optimizes the c ross-domain resource orchestration while providing the performance and fun ctional isolations among network slices. Second\, a decentralized deep rei nforcement learning algorithm will be designed to dynamically orchestrate resources for end-to-end network slicing. The system implementation and te stbed design of the end-to-end network slicing system will also be discuss ed. Finally\, future research directions in designing end-to-end network s licing solutions with machine learning will be shared.</p><br /><br />Agen da: <br /><p>5G and edge computing will serve various emerging use cases t hat have diverse requirements for multiple resources\, e.g.\, radio\, tran sportation\, and computing. Network slicing is a promising technology for creating virtual networks that can be customized according to the requirem ents of different use cases. Provisioning network slices requires end-to-e nd resource orchestration which is challenging. This talk will discuss the challenges of end-to-end network slicing in wireless edge computing syste ms and present machine learning assisted network slicing solutions. First\ , the design of a new decentralized cross-domain resource orchestration so lution will be presented. This solution optimizes the cross-domain resourc e orchestration while providing the performance and functional isolations among network slices. Second\, a decentralized deep reinforcement learning algorithm will be designed to dynamically orchestrate resources for end-t o-end network slicing. The system implementation and testbed design of the end-to-end network slicing system will also be discussed. Finally\, futur e research directions in designing end-to-end network slicing solutions wi th machine learning will be shared.</p> END:VEVENT END:VCALENDAR