Traffic Matrix Estimation based on Denoising Diffusion Probabilistic Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Xinyu, Qiao, Yan, Zhao, Pei, Hu, Rongyao, Zhang, Benchu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909357407469568
author Yuan, Xinyu
Qiao, Yan
Zhao, Pei
Hu, Rongyao
Zhang, Benchu
author_facet Yuan, Xinyu
Qiao, Yan
Zhao, Pei
Hu, Rongyao
Zhang, Benchu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15716
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Traffic Matrix Estimation based on Denoising Diffusion Probabilistic Model
Yuan, Xinyu
Qiao, Yan
Zhao, Pei
Hu, Rongyao
Zhang, Benchu
Machine Learning
Networking and Internet Architecture
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.
title Traffic Matrix Estimation based on Denoising Diffusion Probabilistic Model
topic Machine Learning
Networking and Internet Architecture
url https://arxiv.org/abs/2410.15716