NeuralEmu: in situ Measurement-Driven, ML-based, High-Fidelity 5G Network Emulation

TL;DR

NeuralEmu is a high-fidelity, machine learning-based 5G network emulator that accurately predicts resource allocation and contention, enabling realistic testing of network applications under dynamic conditions.

Contribution

NeuralEmu introduces a novel ML-driven framework that learns complex 5G scheduler behaviors from high-resolution telemetry, handling multiple clients and realistic traffic patterns.

Findings

Reduces emulation error by up to 57% for various applications.

Handles multiple clients and complex scheduling behaviors.

Provides a high-performance, realistic testing environment for 5G networks.

Abstract

Current and future applications demand ultra-low latency and consistent throughput, yet frequently traverse 5G cellular networks, so cope with volatile packet dynamics, as 5G base station schedulers dynamically react to user workloads and wireless channel conditions. The task of evaluating network algorithms in these environments is hamstrung by current tools: record-and-replay emulators sever the feedback interaction that exists between application end points and a commercial operator's proprietary 5G scheduler, while full-stack simulators rely on overly simplistic scheduling logic. To bridge this reality gap, we present NeuralEmu, a high-fidelity, machine learning-based emulation framework that learns complex 5G scheduler resource allocation behaviors directly from extremely high-resolution network telemetry tools. The first emulator to handle multiple clients, NeuralEmu utilizes machine learning to dynamically predict resource block allocations and modulation schemes based on instantaneous user buffer occupancy and channel states. To capture realistic cross-user contention, a traffic reconstruction model inverts cellular network scheduling results to recover the underlying traffic patterns of uncontrolled background users. Implemented as an high-performance Linux middlebox emulator, NeuralEmu reduces emulation error relative to the state of the art for various network applications including but not limited to 55% for web-page load time, 57% for WebRTC encoder bit rate, and 51% for cloud gaming packet one-way delay, providing an accurate, standardized testing ground for tomorrow's real-time interactive network protocols and applications.