Harnessing Generative Pre-Trained Transformer for Datacenter Packet Trace Generation

TL;DR

This paper introduces DTG-GPT, a generative transformer model that synthesizes realistic datacenter traffic traces, enabling better research and optimization by accurately mimicking complex traffic patterns across different network scales.

Contribution

The paper presents a novel GPT-based model for datacenter traffic generation that effectively reproduces intricate traffic patterns from limited data, a significant step beyond traditional mathematical models.

Findings

DTG-GPT can generate traffic traces that closely mimic real traffic patterns.

The model maintains fidelity across different network scales.

It demonstrates potential for future data sharing via trained models.

Abstract

Today, the rapid growth of applications reliant on datacenters calls for new advancements to meet the increasing traffic and computational demands. Traffic traces from datacenters are essential for further development and optimization of future datacenters. However, traces are rarely released to the public. Researchers often use simplified mathematical models that lack the depth needed to recreate intricate traffic patterns and, thus, miss optimization opportunities found in realistic traffic. In this preliminary work, we introduce DTG-GPT, a packet-level Datacenter Traffic Generator (DTG), based on the generative pre-trained transformer (GPT) architecture used by many state-of-the-art large language models. We train our model on a small set of available traffic traces from different domains and offer a simple methodology to evaluate the fidelity of the generated traces to their original counterparts. We show that DTG-GPT can synthesize novel traces that mimic the spatiotemporal patterns found in real traffic traces. We further demonstrate that DTG-GPT can generate traces for networks of different scales while maintaining fidelity. Our findings indicate the potential that, in the future, similar models to DTG-GPT will allow datacenter operators to release traffic information to the research community via trained GPT models.