In-situ Model Downloading to Realize Versatile Edge AI in 6G Mobile Networks

TL;DR

This paper introduces in-situ model downloading for 6G edge AI, enabling real-time, adaptive AI model updates on devices by leveraging a virtualized network architecture and dynamic compression techniques.

Contribution

It proposes a novel in-situ model downloading technology with adaptive compression and a 6G network architecture for efficient edge AI deployment.

Findings

Quantifies 6G connectivity needs for in-situ model downloading

Demonstrates adaptive compression supports real-time model updates

Discusses research opportunities in 6G edge AI deployment

Abstract

The sixth-generation (6G) mobile networks are expected to feature the ubiquitous deployment of machine learning and AI algorithms at the network edge. With rapid advancements in edge AI, the time has come to realize intelligence downloading onto edge devices (e.g., smartphones and sensors). To materialize this version, we propose a novel technology in this article, called in-situ model downloading, that aims to achieve transparent and real-time replacement of on-device AI models by downloading from an AI library in the network. Its distinctive feature is the adaptation of downloading to time-varying situations (e.g., application, location, and time), devices' heterogeneous storage-and-computing capacities, and channel states. A key component of the presented framework is a set of techniques that dynamically compress a downloaded model at the depth-level, parameter-level, or bit-level to support adaptive model downloading. We further propose a virtualized 6G network architecture customized for deploying in-situ model downloading with the key feature of a three-tier (edge, local, and central) AI library. Furthermore, experiments are conducted to quantify 6G connectivity requirements and research opportunities pertaining to the proposed technology are discussed.