COM4AI

Abstract: Modern cloud and telecom networks increasingly run high-speed packet processing as software on commodity servers. While flexible, these systems often suffer unpredictable throughput and latency degradation under shared-resource contention, yet traditional monitoring based on packet inspection and in-band instrumentation is costly and operationally heavy. This talk presents a non-invasive performance intelligence approach that uses low-level hardware and system telemetry (e.g., CPU/cache counters and OS signals) to infer service-level KPIs without touching the dataplane. I will describe a two-layer architecture: an analytics layer with pluggable surrogate models for instantaneous KPI estimation and short-horizon forecasting, and an MLOps layer that automates drift detection, model selection, retraining, and safe rollout. The design is built to adapt across deployment environments, including settings where hardware counter access is limited, and to scale model lifecycle operations through distributed execution. The ultimate goal is to combine lightweight telemetry and tailored data-driven analytics to derive performance insights of high-speed network systems.

Speaker: Tianzhu Zhang is a research scientist at Nokia Bell Labs. He received his B.S. degree from Huazhong University of Science and Technology in China in 2012. He received his M.S. and Ph.D. degrees in 2014 and 2017 from Politecnico di Torino, Italy. From 2017 to 2019, he was a PostDoc researcher at Telecom ParisTech. His research interests center around applied AI/ML for network systems.

Abstract: As GPUs redefine the Data Center, infrastructure has become the critical foundation for AI success. Understanding the evolution of Networking is essential to navigating the shift from traditional High Performance Compute to the massive, high-throughput demands of modern AI.

In this session, we will use intuitive, real-world analogies to demystify complex architectural challenges. We’ll explore why traditional networks are hitting a wall, why Ethernet is receiving a necessary "booster”, Is that enough and what it truly takes to build an AI-ready fabric.

Key Takeaways:

1. The GPU Challenge: Understand why AI workloads demand a new class of network performance.
2. The Ethernet Evolution: Discover if current "boosters" are enough to sustain the future of AI.
3. Simplified Concepts: Master complex networking architecture through relatable, real-world stories.

Join us for an architectural deep dive that proves that in technology, history often repeats itself. As the famous saying goes:

“Every old idea will be proposed again with a different name and a different presentation, regardless of whether it works.”

Speaker: Sunil Pareek is a Senior Delivery Architect at Cisco working primarily on the customer transformation towards AI Ready Next Gen Networks. He is focused on design & deployment of large-scale Enterprise and Data Center Networks. Apart from working with customers, he do Blogging/ Trainings, Tech-Talks at various Industry forums. He has approved Patents, externally published white-papers and Dual CCIE since 2011.