Traffic Matrix Estimation based on Denoising Diffusion Probabilistic Model

TL;DR

This paper introduces a novel traffic matrix estimation method using denoising diffusion probabilistic models, achieving superior accuracy by combining distribution learning with a tailored preprocessing and optimization approach.

Contribution

First application of DDPMs to TME, with a new preprocessing module and noise parameterization to enhance estimation accuracy.

Findings

Outperforms state-of-the-art TME methods on real datasets.

Effective in both TM synthesis and estimation tasks.

Demonstrates the potential of diffusion models in network traffic analysis.

Abstract

The traffic matrix estimation (TME) problem has been widely researched for decades of years. Recent progresses in deep generative models offer new opportunities to tackle TME problems in a more advanced way. In this paper, we leverage the powerful ability of denoising diffusion probabilistic models (DDPMs) on distribution learning, and for the first time adopt DDPM to address the TME problem. To ensure a good performance of DDPM on learning the distributions of TMs, we design a preprocessing module to reduce the dimensions of TMs while keeping the data variety of each OD flow. To improve the estimation accuracy, we parameterize the noise factors in DDPM and transform the TME problem into a gradient-descent optimization problem. Finally, we compared our method with the state-of-the-art TME methods using two real-world TM datasets, the experimental results strongly demonstrate the superiority of our method on both TM synthesis and TM estimation.