Quantifying the Operational Benefits of Deep Learning based Dynamic Traffic Prediction using Real-World Dataset
A convolutional neural network is trained using real-world data, for dynamic prediction of the required transceivers supporting 6G X-haul, leading to 20% and 16% lower average transceiver utilization over static and semi-static cases, respectively.
Authors
- Josep M. Fàbrega (ORCID: https://orcid.org/0000-0001-9285-9768)
- Ivan De Francesca (ORCID: https://orcid.org/0009-0005-6507-0768)
- Dan M. Marom (ORCID: https://orcid.org/0000-0002-8740-5419)
- Dimitris Uzunidis (ORCID: https://orcid.org/0000-0002-9993-5230)
- Ioannis Tomkos (ORCID: https://orcid.org/0000-0001-9721-3405)
- David Larrabeiti (ORCID: https://orcid.org/0000-0003-4983-0243)
- C. Christofodis
- J. M. Rivas Moscoso
Institutions
- University of Patras (GR)
- Hebrew University of Jerusalem (IL)
- Centre Tecnologic de Telecomunicacions de Catalunya (ES)
- Telefónica (Spain) (ES)
- Universidad Carlos III de Madrid (ES)
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1364/ofc.2025.w2a.46
- Primary Topic
- Traffic Prediction and Management Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00