High-Fidelity Cellular Network Control-Plane Traffic Generation without Domain Knowledge

TL;DR

This paper introduces CPT-GPT, a transformer-based model that generates high-fidelity mobile core network control-plane traffic without domain knowledge, outperforming GAN-based methods in fidelity and efficiency.

Contribution

The paper presents CPT-GPT, a novel transformer-based traffic generator that captures complex dependencies in control-plane data without relying on domain knowledge, addressing limitations of GAN-based approaches.

Findings

CPT-GPT achieves comparable fidelity to domain-knowledge-based methods.

It reduces stateful semantics violations by two orders of magnitude.

It accelerates transfer learning for new hourly models by 3.36 times.

Abstract

With rapid evolution of mobile core network (MCN) architectures, large-scale control-plane traffic (CPT) traces are critical to studying MCN design and performance optimization by the R&D community. The prior-art control-plane traffic generator SMM heavily relies on domain knowledge which requires re-design as the domain evolves. In this work, we study the feasibility of developing a high-fidelity MCN control plane traffic generator by leveraging generative ML models. We identify key challenges in synthesizing high-fidelity CPT including generic (to data-plane) requirements such as multimodality feature relationships and unique requirements such as stateful semantics and long-term (time-of-day) data variations. We show state-of-the-art, generative adversarial network (GAN)-based approaches shown to work well for data-plane traffic cannot meet these fidelity requirements of CPT, and develop a transformer-based model, CPT-GPT, that accurately captures complex dependencies among the samples in each traffic stream (control events by the same UE) without the need for GAN. Our evaluation of CPT-GPT on a large-scale control-plane traffic trace shows that (1) it does not rely on domain knowledge yet synthesizes control-plane traffic with comparable fidelity as SMM; (2) compared to the prior-art GAN-based approach, it reduces the fraction of streams that violate stateful semantics by two orders of magnitude, the max y-distance of sojourn time distributions of streams by 16.0%, and the transfer learning time in deriving new hourly models by 3.36x.