2026-04-14T08:53:50Zhttps://recercat.cat/oai/request

oai:recercat.cat:10256/235272025-02-04T05:53:03Zcom_2072_452955com_2072_2054col_2072_453069

Improving Network Delay Predictions Using GNNs Farreras Casamort, Miquel Soto, Paola Camelo Botero, Miguel Hernando Fàbrega i Soler, Lluís Vilà Talleda, Pere European Commission Xarxes neuronals (Informàtica) Neural networks (Computer science) Autonomous network management is crucial for Fifth Generation (5G) and Beyond 5G (B5G) networks, where a constantly changing environment is expected and network configuration must adapt accordingly. Modeling tools are required to predict the impact on performance (packet and delay loss) when new traffic demands arrives and when changes in routing paths are applied in the network. Mathematical analysis and network simulators are techniques for modeling networks but both have limitations, as the former provides low accuracy and the latter requires high execution times. To overcome these limitations, machine learning (ML) algorithms, and more specifically, graph neural networks (GNNs), are proposed for network modeling due to their ability to capture complex relationships from graph-like data while predicting network properties with high accuracy and low computational requirements. However, one of the main issues when using GNNs is their lack of generalization capability to larger networks, i.e., when trained in small networks (in number of nodes, paths length, links capacity), the accuracy of predictions on larger networks is poor. This paper addresses the GNN generalization problem by the use of fundamental networking concepts. Our solution is built from a baseline GNN model called RouteNet (developed by Barcelona Neural Networking Center-Universitat Politècnica de Catalunya (BNN-UPC)) that predicts the average delay in network paths, and through a number of simple additions significantly improves the prediction accuracy in larger networks. The improvement ratio compared to the baseline model is 101, from a 187.28% to a 1.828%, measured by the Mean Average Percentage Error (MAPE). In addition, we propose a closed-loop control context where the resulting GNN model could be potentially used in different use cases This project has received funding from the Generalitat de Catalunya through the Consolidated Research Group 2017-SGR-1318 and 2017-SGR-1552, the Secretaria d’Universitats i Recerca del Departament d’Empresa i Coneixement de la Generalitat de Catalunya for the FI-SDUR fellowship funding 2020 FISDU00590 assigned to Miquel Farreras, the Scientific Research Flanders (FWO) under grant agreement no. G055619N, and the European Union’s Horizon 2020 research and innovation program under grant agreement no. 101017109 ’DAEMON’. Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature 2023-07-20 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion peer-reviewed http://hdl.handle.net/10256/23527 eng info:eu-repo/semantics/altIdentifier/doi/10.1007/s10922-023-09758-9 info:eu-repo/semantics/altIdentifier/issn/1064-7570 info:eu-repo/semantics/altIdentifier/eissn/1573-7705 info:eu-repo/grantAgreement/EC/H2020/101017109/EU/Network intelligence for aDAptive and sElf-Learning MObile Networks/DAEMON Attribution 4.0 International http://creativecommons.org/licenses/by/4.0/ info:eu-repo/semantics/openAccess application/pdf Springer Journal of Network and Systems Management, 2023, vol. 31, p. 65 Articles publicats (D-IMA)