Point of contact
- Abdel Lisser, L2S, abdel.lisser@centralesupelec.fr
- Aline Carneiro Viana, INRIA Saclay, aline.viana@inria.fr
- Hind Castel , Samovar, hind.castel@telecom-sudparis.fr
Summary
Address resource management to guarantee the balance between QoS constraints and energy efficiency in 5G/6G networks.
Explore distributionally robust optimization (DRO) to capture the randomness of the harvest energy and in 5G networks while privacy conscious. Build real world ambiguity sets in order to model the uncertainty with the objective to minimize the expected total energy cost of mobile network operators.
Consider artificial intelligence (neuronal networks, reinforcement learning,…) together with DRO in order to developp efficient algorithms handling the explosion of state space.
Analyse realistic scenarios : dynamic configuration/reconfiguration of slices, end-to-end slicing including radio interface, Scheduling and multiplexing of heterogeneous services on 5G and beyond networks, mobile edge computing and fog computing for IoT services
Keywords
resource allocation, optimization, artificial intelligence
Researchers involved or interested
- Marco Di Renzo , L2S, marco.direnzo@centralesupelec.fr
- Hind Castel , Samovar, hind.castel@telecom-sudparis.fr
- Sheng Yang, L2S, Sheng.Yang@centralesupelec.fr
A few references
- M.Yan, G.Feng, J.Zhou, Y.Sun, Y-C Liang, Intelligent Resource Scheduling for 5G Radio Access Network Slicing, IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, VOL. 68, NO. 8, AUGUST 2019
- P. Du, B. Li, Q. Zeng, D. Zhai, D. Zhou and L. Ran, “Distributionally Robust Two-Stage Energy Management for Hybrid Energy Powered Cellular Networks,” in IEEE Transactions on Vehicular Technology, vol. 69, no. 10, pp. 12162-12174, Oct. 2020, doi: 10.1109/TVT.2020.3013877