NEOL: Multiscale Adaptation of Large Language Models for Network Energy Optimization
Virtual: https://events.vtools.ieee.org/m/519915Special Presentation by Dr. Dilip Krishnaswamy (C-DOT, India) Hosted by the Future Networks Artificial Intelligence & Machine Learning (AIML) Working Group Date/Time: Thursday, 15 January 2025 @ 12:00 UTC (12 PM GMT) Topic: NEOL: Multiscale Adaptation of Large Language Models for Network Energy Optimization Abstract: Focusing on energy conservation and sustainable system development in wireless mobile networks, in this talk we explore energy-saving approaches in the telecommunications sector through a proactive methodology that predicts network usage patterns. Edge cloud resources can be leveraged for AI model learning based on observed network key performance indicators. Dynamic network edge processing is utilized to enable dynamic network resource management with digital twin model processing to provide the dynamic input context window to an AI inferencing engine. Furthermore, the study finds that Large Language Models (LLMs) that have the ability to process data across different timescales could be leveraged to create a future predicted network resource utilization context window. Our results indicate that such a predicted context window combined with dual threshold monitoring of network utilization can be used to enable dynamic network resource optimization. Speaker: [] Dilip Krishnaswamy has led the architecture, design, and development of engineering platforms & products at Intel Corp, Qualcomm Research, IBM Research, and Jio Platforms. He received his PhD degree in Electrical Engineering from the University of Illinois at Urbana-Champaign. He is an inventor on 80+ granted patents and has authored 80+ research publications. He is presently serving as Executive Vice-President at C-DOT (Centre for Development of Telematics), Bangalore, India, where he is leading Advanced-5G Engineering and 6G Innovation efforts. Brochure (PDF): (https://drive.google.com/file/d/1bzse7ocgUEqir1XCyBsM8o5lyPtKe_26/view) Co-sponsored by: Future Networks Artificial Intelligence & Machine Learning (AIML) Working Group Virtual: https://events.vtools.ieee.org/m/519915