(2024). Traffic Matrix Estimation Using Invertible Neural Networks. In 2024 International Conference on Software, Telecommunications and Computer Networks (SoftCOM) (pp. 1–7). IEEE. https://doi.org/10.23919/softcom62040.2024.10721829
Περίληψη
Ill-posed inverse problems appear in many fields and involve determining the causal factors behind a set of observations. Within the context of network tomography (NT), an interesting instance of such a linear inverse problem is traffic matrix estimation (TME) from link load measurements. In this paper, we investigate and experimentally assess the application of invertible neural networks (INNs) to address the TME problem. Specifically, we develop a custom INN architecture integrated with autoencoder (AE)-based dimensionality reduction and propose two operational modes, one of which is also capable of traffic matrix synthesis. A reference implementation of the proposed approach is published under a permissive open-source license, and performance evaluation is conducted using a comprehensive set of metrics on a dataset collected from a backbone network.
- DOI
- 10.23919/softcom62040.2024.10721829
- Τύπος
- Άρθρο σε Πρακτικά Συνεδρίου
- Έτος
- 2024
Σύνδεσμοι
BibTeX
@inproceedings{kakkavas2024traffic,
title = {Traffic Matrix Estimation Using Invertible Neural Networks},
author = {Grigorios Kakkavas and Petros Maratos and Vasileios Karyotis and Symeon Papavassiliou},
url = {https://doi.org/10.23919/softcom62040.2024.10721829},
doi = {10.23919/softcom62040.2024.10721829},
year = {2024},
date = {2024-01-01},
booktitle = {2024 International Conference on Software, Telecommunications and Computer Networks (SoftCOM)},
pages = {1–7},
publisher = {IEEE},
abstract = {Ill-posed inverse problems appear in many fields and involve determining the causal factors behind a set of observations. Within the context of network tomography (NT), an interesting instance of such a linear inverse problem is traffic matrix estimation (TME) from link load measurements. In this paper, we investigate and experimentally assess the application of invertible neural networks (INNs) to address the TME problem. Specifically, we develop a custom INN architecture integrated with autoencoder (AE)-based dimensionality reduction and propose two operational modes, one of which is also capable of traffic matrix synthesis. A reference implementation of the proposed approach is published under a permissive open-source license, and performance evaluation is conducted using a comprehensive set of metrics on a dataset collected from a backbone network.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}