Sequence models improve layer 3 protocol message prediction for networks
Sequence Models for Layer-3 Protocol Emulation
Networking and Internet Architecture
Summary
The authors study how to represent complex network protocol messages as sequences that can be predicted efficiently by machine learning models. They create a combined system where a model suggests message parts while fixed rules keep secure or configured parts safe. Their smaller custom model does better than a much larger general one and runs fast enough for some real-time uses. This approach could help test, simulate, and potentially improve future network control systems, but challenges remain before practical use.
What this means in practice
- •For network testing teams: Enable more accurate and efficient emulation of Layer-3 protocol messages to improve network testing and simulation fidelity.
- •For telecommunications operators: Optimize Layer-3 protocol message handling within RAN deployments, potentially improving performance and enabling specialized network functions.
Authors
Alix Jeannerot, Petko Petkov, Alvaro Valcarce Rial
Abstract
This article investigates whether Layer-3 radio-protocol behavior can be represented by compact sequence models suitable for deployment inside the RAN. We introduce the RRC sequence engine (RSE), a hybrid architecture in which a sequence model predicts protocol-dependent message structure while deterministic components retain control over security-sensitive or configured fields and over transport containers. Using NR protocol traces, we show that protocol-aware tokenization, cross-stack context, and explicit placeholders matter more than general-sequence model scale. A purpose-built 11M-parameter Mamba engine achieves 0.90 exact match on the evaluated next-generation Node B (gNB)-side test set with a median generation latency of 115 ms, sufficient for some timers of Layer-3, outperforming a fine-tuned 0.6B-parameter model. We discuss applications in testing, simulation, deployment specialization, and future trainable 6G control planes, as well as the validation, latency, robustness, and security challenges that remain before operational use.