Edge AI Meets Wireless Systems: Implications for Connectivity & RF Design

Abstract:

The rapid adoption of AI at the network edge, including recent advances in generative and reasoning-capable models, is reshaping the way distributed systems generate traffic, interact with networks, and consume wireless resources. Unlike traditional cloud-centric AI workloads, edge AI applications introduce new constraints and dynamics, such as tight latency budgets, intermittent connectivity, heterogeneous hardware capabilities, and energy-aware operation.

In this talk, I will discuss how emerging Edge AI workloads challenge long-standing assumptions in wireless and RF system design. I will highlight how inference pipelines, agent-based AI systems, and hybrid edge–cloud execution models affect traffic patterns, protocol behavior, and system-level performance. Through concrete examples drawn from edge computing, IoT, and networked AI systems, I will outline where current connectivity abstractions fall short and identify new design opportunities for future wireless, RF, and microwave technologies.

The goal of the talk is to provide a system- and architecture-level perspective on Edge AI, offering insights into how the evolution of AI workloads may influence the design of next-generation wireless networks and RF systems.

Speaker's Bio

Roberto Morabito is an Assistant Professor in the Networked Systems group of the Communication Systems Department at EURECOM, a Grande École, research center, and graduate school located in the French Riviera. He is also a Docent at the University of Helsinki, Finland. Before joining EURECOM, I was a Senior Researcher in the Department of Computer Science at the University of Helsinki. Earlier in my career (2014–2022), he spent eight years at Ericsson Research Finland, first with the Cloud and System Platforms team and later with the IoT Technologies & Cyber-Physical Systems team. He earned his PhD in Networking Technology from Aalto University (Finland) in 2019. From 2019 to 2021, he worked as a Postdoctoral Researcher at the EDGE Lab, School of Electrical and Computer Engineering, Princeton University (USA). Over the years, he has also held visiting research positions at INRIA Lille (France), the Technical University of Munich (Germany), and Yale University (USA). His research lies at the intersection of Networked Systems, Edge Computing, and Distributed AI, focusing on trade-offs in AI service provisioning, interoperability, and lifecycle management under computing- and networking-resource constraints.

Know what’s Happening Next — before everyone else does.

Get App

Host or Publisher IEEE Santa Clara - San Francisco Microwave Theory and Techniques Chapter