2021
Kakkavas, G.; Kalntis, M.; Karyotis, V.; Papavassiliou, S.
Future Network Traffic Matrix Synthesis and Estimation Based on Deep Generative Models Conference
vol. 2021-July, Institute of Electrical and Electronics Engineers Inc., 2021, ISSN: 10952055, (cited By 9; Conference of 30th International Conference on Computer Communications and Networks, ICCCN 2021 ; Conference Date: 19 July 2021 Through 22 July 2021; Conference Code:171515).
Abstract | Links | BibTeX | Tags: Anomaly detection; Decoding; Information management; Inverse problems; Matrix algebra, Computational costs; ILL-posed inverse problem; Incremental optimization; Link load measurement; Minimization problems; Traffic Engineering; Traffic matrix estimation; Traffic measurements, Computer networks
@conference{Kakkavas2021,
title = {Future Network Traffic Matrix Synthesis and Estimation Based on Deep Generative Models},
author = {G. Kakkavas and M. Kalntis and V. Karyotis and S. Papavassiliou},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85114962425&doi=10.1109%2fICCCN52240.2021.9522222&partnerID=40&md5=b55537afb9ced698d9c0012a1d046d67},
doi = {10.1109/ICCCN52240.2021.9522222},
issn = {10952055},
year = {2021},
date = {2021-01-01},
journal = {Proceedings - International Conference on Computer Communications and Networks, ICCCN},
volume = {2021-July},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Traffic matrices (TMs) contain information that is essential for network management, traffic engineering, and anomaly detection. However, constructing a TM through direct traffic measurements has a high administrative and computational cost. A more feasible approach is to estimate the TM from the easily obtainable link load measurements. In this paper, we address the issue of traffic matrix estimation (TME) from link loads using a deep generative model - namely, a variational autoencoder (VAE) - to solve the respective ill-posed inverse problem. In particular, we train the VAE with historical data (previously observed TMs) and we leverage the trained decoder to transform TME into a minimization problem in the latent space, which in turn can be solved by employing a gradient-based optimizer. Furthermore, the trained decoder can be used for traffic matrix synthesis, i.e., for generating synthetic TM examples that have 'similar' properties to the samples of the training set. Finally, we explore the incremental optimization of the sequence of objectives constructed from the sequence of decoders that we obtain at different stages of the VAE training. The performance of the proposed methods is evaluated using a publicly available dataset of actual traffic matrices recorded in a real backbone network. © 2021 IEEE.},
note = {cited By 9; Conference of 30th International Conference on Computer Communications and Networks, ICCCN 2021 ; Conference Date: 19 July 2021 Through 22 July 2021; Conference Code:171515},
keywords = {Anomaly detection; Decoding; Information management; Inverse problems; Matrix algebra, Computational costs; ILL-posed inverse problem; Incremental optimization; Link load measurement; Minimization problems; Traffic Engineering; Traffic matrix estimation; Traffic measurements, Computer networks},
pubstate = {published},
tppubtype = {conference}
}
Traffic matrices (TMs) contain information that is essential for network management, traffic engineering, and anomaly detection. However, constructing a TM through direct traffic measurements has a high administrative and computational cost. A more feasible approach is to estimate the TM from the easily obtainable link load measurements. In this paper, we address the issue of traffic matrix estimation (TME) from link loads using a deep generative model - namely, a variational autoencoder (VAE) - to solve the respective ill-posed inverse problem. In particular, we train the VAE with historical data (previously observed TMs) and we leverage the trained decoder to transform TME into a minimization problem in the latent space, which in turn can be solved by employing a gradient-based optimizer. Furthermore, the trained decoder can be used for traffic matrix synthesis, i.e., for generating synthetic TM examples that have 'similar' properties to the samples of the training set. Finally, we explore the incremental optimization of the sequence of objectives constructed from the sequence of decoders that we obtain at different stages of the VAE training. The performance of the proposed methods is evaluated using a publicly available dataset of actual traffic matrices recorded in a real backbone network. © 2021 IEEE.