An Overview and Solution for Democratizing AI Workflows at the Network Edge

TL;DR

This paper introduces NAOMI, a modular and scalable solution for democratizing AI/ML workflows at the network edge, addressing current challenges and leveraging open-source tools for improved deployment and execution efficiency.

Contribution

The paper presents NAOMI, a novel hardware architecture-independent framework that enhances democratization of AI workflows at the network edge through design guided by architecture analysis and open-source tools.

Findings

NAOMI achieves up to 40% faster deployment times.

NAOMI reduces workflow execution time by up to 73% for large datasets.

NAOMI performs inference and resource utilization comparable to existing solutions.

Abstract

With the process of democratization of the network edge, hardware and software for networks are becoming available to the public, overcoming the confines of traditional cloud providers and network operators. This trend, coupled with the increasing importance of AI in 6G and beyond cellular networks, presents opportunities for innovative AI applications and systems at the network edge. While AI models and services are well-managed in cloud systems, achieving similar maturity for serving network needs remains an open challenge. Existing open solutions are emerging and are yet to consider democratization requirements. In this work, we identify key requirements for democratization and propose NAOMI, a solution for democratizing AI/ML workflows at the network edge designed based on those requirements. Guided by the functionality and overlap analysis of the O-RAN AI/ML workflow architecture and MLOps systems, coupled with the survey of open-source AI/ML tools, we develop a modular, scalable, and distributed hardware architecture-independent solution. NAOMI leverages state-of-the-art open-source tools and can be deployed on distributed clusters of heterogeneous devices. The results show that NAOMI performs up to 40% better in deployment time and up to 73% faster in AI/ML workflow execution for larger datasets compared to AI/ML Framework, a representative open network access solution, while performing inference and utilizing resources on par with its counterpart.