BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VEVENT DTSTAMP:20260124T045032Z UID:AC27220B-27CC-4260-8A34-13C0D81D9D3C DTSTART;TZID=Etc/UTC:20250918T120000 DTEND;TZID=Etc/UTC:20250918T130000 DESCRIPTION:[ALLSTaR: Automated LLM-Driven Scheduler Generation and Testing for Intent-Based RAN]\n\nSpecial Presentation by Dr. Maxime Elkael (North eastern U.\, USA)\n\nHosted by the Future Networks Artificial Intelligence & Machine Learning (AIML) Working Group\n\nDate/Time: Thursday\, 18 Septe mber 2025 @ 12:00 UTC (12 PM GMT)\n\nPDH Certificate: while basic attendan ce is free\, this course also offers one (1) Professional Development Hour (PDH) for a nominal fee\; please choose the appropriate "Registration Fee " when registering\; actual\, verified real-time attendance required for P DH\; additional terms and conditions apply.\n\nTopic:\n\nALLSTaR - Automat ed LLM-Driven Scheduler Generation and Testing for Intent-Based RAN\n\nAbs tract:\n\nThe evolution toward open\, programmable O-RAN and AI-RAN 6G net works creates unprecedented opportunities for Intent-Based Networking (IBN ) to dynamically optimize RAN operations based on dynamic operators requir ements. However\, applying IBN effectively to the RANscheduler - a critica l component determining resource allocation and system performance - remai ns a significant challenge. Current approaches predominantly rely on coars e-grained network slicing\, lacking the granularity for dynamic adaptation to individual user conditions and traffic patterns. Despite the existence of a vast body of scheduling algorithms that could potentially translate high-level intents into executable policies\, their practical utilization is hindered by implementation heterogeneity\, insufficient systematic eval uation in production environments\, and the complexity of developing high- performance scheduler implementations. This necessitates a more granular\, flexible\, and verifiable approach to align scheduler behavior with opera tor-defined intents.\n\nTo address these limitations\, we propose ALLSTaR\ , a novel framework leveraging LLMs for automated\, intent-driven schedule r design\, implementation\, and evaluation. ALLSTaR interprets natural lan guage intents\, automatically generates functional scheduler code from the research literature using Optical Character Recognition (OCR) and LLMs\, and intelligently matches operator intents to the most suitable scheduler( s). Our implementation deploys these schedulers as O-RAN dApps\, enabling on-the-fly deployment and comprehensive testing on a production-grade\, mu lti-vendor 5G-compliant testbed. This approach has enabled the largest-sca le OTA experimental comparison of 18 scheduling algorithms automatically s ynthesized from the academic literature. The resulting performance profile s serve as the input for our Intent-Based Scheduling framework\, which dyn amically selects and deploys appropriate schedulers that optimally satisfy operator intents. We validate our approach through multiple use cases una ttainable with current slicing-based optimization techniques\, demonstrati ng fine-grained control based on buffer status\, physical layer conditions \, and heterogeneous traffic types.\n\nSpeaker:\n\n[]\nMaxime Elkael is a Postodoctoral Researcher at the Institute for the Wireless Internet of Thi ngs at Northeastern University. He received his Ph.D in Computer Science f rom Institut Polytechnique De Paris/Telecom SudParis in 2023. His research interest lies at the intersection of optimization theory\, artificial int elligence and graph theory applied to next generation wireless networks\, especially Open RAN networks.\n\nCo-sponsored by: Future Networks Artifici al Intelligence & Machine Learning (AIML) Working Group\n\nVirtual: https: //events.vtools.ieee.org/m/489656 LOCATION:Virtual: https://events.vtools.ieee.org/m/489656 ORGANIZER:baw@ieee.org SEQUENCE:54 SUMMARY:ALLSTaR - Automated LLM-Driven Scheduler Generation and Testing for Intent-Based RAN URL;VALUE=URI:https://events.vtools.ieee.org/m/489656 X-ALT-DESC:Description: <br /><p class="MsoNormal" style="margin-top: .25in \;"><img src="https://events.vtools.ieee.org/vtools_ui/media/display/5cf28 5e3-f8c0-4623-ad01-e194a6e65e7a" alt="ALLSTaR: Automated LLM-Driven Schedu ler Generation and Testing for Intent-Based RAN" width="750" height="197"> </p>\n<p class="MsoNormal" style="margin-top: 12.0pt\;">Special Presentati on by<strong> Dr. Maxime Elkael (Northeastern U.\, USA)</strong></p>\n<p c lass="MsoNormal" style="margin-top: 12.0pt\;">Hosted by the Future Network s<strong> Artificial Intelligence &amp\; Machine Learning (AIML) Working G roup</strong></p>\n<p class="MsoNormal" style="margin-top: 12.0pt\;"><stro ng><span style="font-size: 14.0pt\; font-family: Copperplate\; mso-fareast -font-family: PMingLiU\; mso-fareast-theme-font: minor-fareast\; mso-bidi- font-family: Arial\; mso-bidi-theme-font: minor-bidi\; mso-ansi-language: EN-US\; mso-fareast-language: ZH-TW\; mso-bidi-language: AR-SA\;">Date/Tim e</span></strong><span style="font-size: 12.0pt\; font-family: 'Calibri'\, sans-serif\; mso-ascii-theme-font: minor-latin\; mso-fareast-font-family: PMingLiU\; mso-fareast-theme-font: minor-fareast\; mso-hansi-theme-font: m inor-latin\; mso-bidi-font-family: Arial\; mso-bidi-theme-font: minor-bidi \; mso-ansi-language: EN-US\; mso-fareast-language: ZH-TW\; mso-bidi-langu age: AR-SA\;">: <strong>Thursday\, 18 September 2025</strong><strong> @ 12 :00 UTC (12 PM GMT)</strong></span></p>\n<p class="MsoNormal" style="margi n-top: 12.0pt\;"><span style="font-size: 12.0pt\; font-family: 'Calibri'\, sans-serif\; mso-ascii-theme-font: minor-latin\; mso-fareast-font-family: PMingLiU\; mso-fareast-theme-font: minor-fareast\; mso-hansi-theme-font: m inor-latin\; mso-bidi-font-family: Arial\; mso-bidi-theme-font: minor-bidi \; mso-ansi-language: EN-US\; mso-fareast-language: ZH-TW\; mso-bidi-langu age: AR-SA\;"><strong><em><span style="font-size: 14.0pt\; font-family: Co pperplate\; mso-fareast-font-family: PMingLiU\; mso-fareast-theme-font: mi nor-fareast\; mso-bidi-font-family: Arial\; mso-bidi-theme-font: minor-bid i\; mso-ansi-language: EN-US\; mso-fareast-language: ZH-TW\; mso-bidi-lang uage: AR-SA\;">PDH Certificate</span>: </em></strong><em>while basic atten dance is free\, this course also offers one (1) Professional Development H our (PDH) for a nominal fee\; please choose the appropriate "Registration Fee" when registering\; actual\, verified real-time attendance required fo r PDH\; additional terms and conditions apply.</em></span></p>\n<p class=" MsoNormal" style="margin-top: .25in\;"><strong><u><span style="font-size: 16.0pt\; font-family: Copperplate\;">Topic</span></u></strong><strong><spa n style="font-size: 16.0pt\; font-family: Copperplate\;">:</span></strong> </p>\n<p class="MsoNormal"><strong><span style="font-size: 16pt\;">ALLSTaR - Automated LLM-Driven Scheduler Generation and Testing for Intent-Based RAN&nbsp\;</span></strong></p>\n<p class="MsoNormal" style="margin-top: .2 5in\;"><strong><u><span style="font-size: 16.0pt\; font-family: Copperplat e\;">Abstract</span></u></strong><strong><span style="font-size: 16.0pt\; font-family: Copperplate\;">:</span></strong></p>\n<p class="MsoNormal">Th e evolution toward open\, programmable O-RAN and AI-RAN 6G networks create s unprecedented opportunities for Intent-Based Networking (IBN) to dynamic ally optimize RAN operations based on dynamic operators requirements. Howe ver\, applying IBN effectively to the RANscheduler - a critical component determining resource allocation and system performance - remains a signifi cant challenge. Current approaches predominantly rely on coarse-grained ne twork slicing\, lacking the granularity for dynamic adaptation to individu al user conditions and traffic patterns. Despite the existence of a vast b ody of scheduling algorithms that could potentially translate high-level i ntents into executable policies\, their practical utilization is hindered by implementation heterogeneity\, insufficient systematic evaluation in pr oduction environments\, and the complexity of developing high-performance scheduler implementations. This necessitates a more granular\, flexible\, and verifiable approach to align scheduler behavior with operator-defined intents.</p>\n<p class="MsoNormal">To address these limitations\, we propo se ALLSTaR\, a novel framework leveraging LLMs for automated\, intent-driv en scheduler design\, implementation\, and evaluation. ALLSTaR interprets natural language intents\, automatically generates functional scheduler co de from the research literature using Optical Character Recognition (OCR) and LLMs\, and intelligently matches operator intents to the most suitable scheduler(s). Our implementation deploys these schedulers as O-RAN dApps\ , enabling on-the-fly deployment and comprehensive testing on a production -grade\, multi-vendor 5G-compliant testbed. This approach has enabled the largest-scale OTA experimental comparison of 18 scheduling algorithms auto matically synthesized from the academic literature. The resulting performa nce profiles serve as the input for our Intent-Based Scheduling framework\ , which &nbsp\;dynamically selects and deploys appropriate schedulers that optimally satisfy operator intents. We validate our approach through mult iple use cases unattainable with current slicing-based optimization techni ques\, demonstrating fine-grained control based on buffer status\, physica l layer conditions\, and heterogeneous traffic types.</p>\n<p><strong><spa n style="font-size: 16.0pt\; font-family: Copperplate\;"><u>Speaker</u>:</ span></strong></p>\n<table style="border-collapse: collapse\; width: 100%\ ;" border="1"><colgroup><col style="width: 17.466411%\;"><col style="width : 82.43762%\;"></colgroup>\n<tbody>\n<tr>\n<td><img src="https://events.vt ools.ieee.org/vtools_ui/media/display/10b2a63e-a038-40b4-86f3-dafcaaf0d7eb " alt="" width="150" height="174"></td>\n<td>\n<p class="MsoNormal" style= "margin-top: 6.0pt\;"><strong>Maxime Elkael</strong> is a Postodoctoral Re searcher at the Institute for the Wireless Internet of Things at Northeast ern University. He received his Ph.D in Computer Science from Institut Pol ytechnique De Paris/Telecom SudParis in 2023. His research interest lies a t the intersection of optimization theory\, artificial intelligence and gr aph theory applied to next generation wireless networks\, especially Open RAN networks.</p>\n</td>\n</tr>\n</tbody>\n</table> END:VEVENT END:VCALENDAR