Functional Split of In-Network Deep Learning for 6G: A Feasibility Study

TL;DR

This paper explores the feasibility of integrating in-network deep learning into 6G mobile networks by decomposing neural networks for efficient inference, demonstrated through a BSS problem in a full-stack emulator.

Contribution

It proposes a functional split approach for in-network deep learning, enabling efficient inference in programmable network devices for future 6G systems.

Findings

Decomposition of DNNs improves inference efficiency in network devices.

Full-stack emulator validates the approach with real datasets.

Provides design guidelines for in-network intelligence in 6G.

Abstract

In existing mobile network systems, the data plane (DP) is mainly considered a pipeline consisting of network elements end-to-end forwarding user data traffics. With the rapid maturity of programmable network devices, however, mobile network infrastructure mutates towards a programmable computing platform. Therefore, such a programmable DP can provide in-network computing capability for many application services. In this paper, we target to enhance the data plane with in-network deep learning (DL) capability. However, in-network intelligence can be a significant load for network devices. Then, the paradigm of the functional split is applied so that the deep neural network (DNN) is decomposed into sub-elements of the data plane for making machine learning inference jobs more efficient. As a proof-of-concept, we take a Blind Source Separation (BSS) problem as an example to exhibit the benefits of such an approach. We implement the proposed enhancement in a full-stack emulator and we provide a quantitative evaluation with professional datasets. As an initial trial, our study provides insightful guidelines for the design of the future mobile network system, employing in-network intelligence (e.g., 6G).