Communication Dans Un Congrès Année : 2025

Data-driven Energy Optimization in Mobile Networks with User Experience Guarantees

Résumé

In this paper, we model carrier shutdown in multicarrier mobile networks as a deep reinforcement learning problem. Our model takes energy-saving actions by turning off carriers and reallocating their users while in addition to maintaining connectivity guarantees a novel user experience metric. Leveraging real and recent datasets, we train and evaluate our model over realistic network scenarios. Our results show more than 15% energy saving with the fulfillment of the user experience constraints, outperforming currently deployed solutions and researched approaches in the literature by almost 50%. More interestingly our approach exhibits generalization properties, a very promising characteristic for its adoption in real mobile networks deployment.

Fichier principal
Vignette du fichier
IEEE_INFOCOM_2025.pdf (912.25 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05040259 , version 1 (18-04-2025)

Licence

Identifiants

Citer

Anh-Khoa Dang, Hicham Khalifé, Mathias Sintorn, Stephane Rovedakis, Stefano Secci. Data-driven Energy Optimization in Mobile Networks with User Experience Guarantees. IEEE INFOCOM 2025 - IEEE Conference on Computer Communications, May 2025, London, United Kingdom. ⟨10.1109/INFOCOM55648.2025.11044545⟩. ⟨hal-05040259⟩
458 Consultations
89 Téléchargements

Altmetric

Partager

  • More