Article (Scientific journals)
Network Traffic Modeling and Prediction Using Graph Gaussian Processes
MEHRIZI, Sajad; Chatzinotas, Symeon
2022In IEEE Access
Peer Reviewed verified by ORBi


Full Text
Publisher postprint (1.41 MB)

All documents in ORBilu are protected by a user license.

Send to


Abstract :
[en] Traffic modeling and prediction is a vital task for designing efficient resource allocation strategies in telecommunication networks. This is challenging because network traffic data exhibits complex nonlinear spatiotemporal interactions. Moreover, the data can have missing values when traffic statistic collection is unavailable in certain nodes. In this paper, we introduce a graph Gaussian Process (GP) model for this challenging problem. The GP is a Bayesian non-parametric model and highly flexible in capturing complex patterns in the data. Additionally, it provides uncertainty information which can be exploited for robust resource allocation problems. The developed graph GP model is almost free of hyper-parameter tuning, can accurately capture short-term and long-term temporal patterns and can infer missing values by learning spatiotemporal interactions among the nodes in the network. Subsequently, we approximate the intractable posterior distribution using Variational Bayes (VB) algorithm which can be efficiently implemented. Finally, we evaluate the accuracy of the proposed model for predicting the data traffic using two real-world network datasets. Our simulation results shows that the proposed model can achieve better prediction accuracy with respect to the state-of-the-art approaches
Disciplines :
Computer science
Author, co-author :
Chatzinotas, Symeon  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
External co-authors :
Language :
Title :
Network Traffic Modeling and Prediction Using Graph Gaussian Processes
Publication date :
Journal title :
IEEE Access
Publisher :
Institute of Electrical and Electronics Engineers, Piscataway, United States - New Jersey
Peer reviewed :
Peer Reviewed verified by ORBi
Focus Area :
Computational Sciences
Funders :
European Research Council (Grant Number: 742648)
10.13039/501100001866-Fonds National de la Recherche Luxembourg (Grant Number: 13718904)
Available on ORBilu :
since 21 December 2022


Number of views
18 (1 by Unilu)
Number of downloads
21 (0 by Unilu)

Scopus citations®
Scopus citations®
without self-citations
WoS citations


Similar publications

Contact ORBilu