Wavelet-enhanced graph neural networks: towards non-parametric network traffic modeling

Abstract

Network modeling is crucial for the design, management, and optimization of modern telecommunications and data networks. Recent advancements in Machine Learning (ML), specifically Graph Neural Networks (GNNs), offer promising solutions but rely on parameterized traffic representations, necessitating retraining for new traffic patterns. This paper explores integrating the Discrete Wavelet Transform (DWT) with GNNs to enhance network traffic modeling. By leveraging wavelets, which decompose signals into both time and frequency components, we aim to encode traffic patterns without assuming specific distributions, improving model adaptability and accuracy. We modify the state-of-the-art RouteNet-Fermi model to incorporate wavelet-based traffic encoding and evaluate its performance across different synthetic and real traffic scenarios. Our findings show that wavelet-based encoding handles unseen traffic distributions with minimal impact on performance, unlike traditional parameter-based approaches. This work represents a step forward in bridging the gap between non-parametric traffic representation and advanced network modeling, offering a promising solution for dynamic and complex network environments.

This publication is part of the Spanish I+D+i project TRAINER-A (ref.PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA). Carlos Güemes is funded by the Joan Oró predoctoral program, from the Secretariat for Universities and Research, part of the Ministry of Research and Universities of the Government of Catalonia, and the European Social Fund Plus (ref. BDNS 657443). Jordi Paillisse is funded by NextGen EU, Ministry of Universities and Recovery, Transformation and Resilience Plan, through a call from UPC (Grant Ref. 2022 UPC-MSC-93871).

Peer Reviewed

Postprint (author's final draft)