Usage of Network Simulators in Machine-Learning-Assisted 5G/6G Networks

TL;DR

This paper explores how network simulators can be integrated into ML-aware 5G/6G networks to improve training, testing, and validation of ML models, addressing trust and reliability concerns.

Contribution

It proposes an architectural framework for integrating network simulators into ML-driven communication systems and demonstrates a proof-of-concept implementation.

Findings

Successful integration of simulators in ML-based network testing

Identification of key challenges and potential solutions

Validation through a residential Wi-Fi network testbed

Abstract

Without any doubt, Machine Learning (ML) will be an important driver of future communications due to its foreseen performance when applied to complex problems. However, the application of ML to networking systems raises concerns among network operators and other stakeholders, especially regarding trustworthiness and reliability. In this paper, we devise the role of network simulators for bridging the gap between ML and communications systems. In particular, we present an architectural integration of simulators in ML-aware networks for training, testing, and validating ML models before being applied to the operative network. Moreover, we provide insights on the main challenges resulting from this integration, and then give hints discussing how they can be overcome. Finally, we illustrate the integration of network simulators into ML-assisted communications through a proof-of-concept testbed implementation of a residential Wi-Fi network.