Nour Yellas, Ph.D. student in the ROC Team, will defend her Ph.D. thesis on December 18, 2023, at 9:30 a.m., in the Amphitheatre Georges Friedmann, CNAM, 2 rue Conté, 75003 Paris, France.
Thesis Title: Multi-criteria optimization for resource allocation in multi-access edge computing
Thesis Title (French): Optimisation multi-critères de l’allocation des ressources de calcul à la bordure du réseau
Abstract:
Mobile cloud computing was a promising paradigm to achieve gigabit access in the new-generation wireless networks by offloading the computation tasks of mobile devices to a central cloud data center. However, bandwidth congestion at the core network is an inherent limitation in terms of communication delays and energy consumption. Multi-access edge computing (MEC) was initially proposed to overcome the limitation of mobile cloud computing. It moves the cloud computing data center down into the access network to better meet the requirements of pervasive applications as the set of constraints in terms of quality of service can go beyond basic low-latency, high bandwidth and real-time access to radio-network information. However, colocating application servers, cellular core network and radio-access network sub-components at MEC hosts makes the resource assignment task a very important challenge to tackle as it has direct impact on network operations cost and end-to-end infrastructure reliability.
This thesis investigates a set of robust resource scheduling solutions in the context of MEC. More precisely, we address different techniques to assign the available resources on a MEC host to a given task. We focus on the optimization of the resource orchestration decisions at both the infrastructure and the application levels. First, we address the base station to MEC hosts assignment orchestration decision while taking into account a data-driven assignment objective against traffic fluctuation. Then, we go beyond MEC infrastructure management by proposing an In-network control scheme for efficiently placing MEC applications under stringent time constraints where a federated learning-based anomaly detection is considered.
Nour’s publications:
Journal articles
- Nour-El-Houda Yellas, Bernardetta Addis, Selma Boumerdassi, Roberto Riggio, Stefano Secci. Function Placement for In-network Federated Learning. Computer Networks, 2024, 256, pp.110900. ⟨10.1016/j.comnet.2024.110900⟩. ⟨hal-04766732⟩
- Nour-El-Houda Yellas, Selma Boumerdassi, Alberto Ceselli, Bilal Maaz, Stefano Secci. Robust Access Point Clustering in Edge Computing Resource Optimization. IEEE Transactions on Network and Service Management, 2022, 19 (3), pp.2738 - 2750. ⟨10.1109/TNSM.2022.3186856⟩. ⟨hal-03719676⟩
Conference papers
- Elif Ebru Ohri, Qi Liao, Anastasios Giovanidis, Francesca Fossati, Nour-El-Houda Yellas. MetaLore: learning to orchestrate communication and computation for metaverse synchronization. IEEE Global Communications Conference (GLOBECOM), Dec 2025, Taipei, Taiwan. ⟨hal-05317622⟩
- Nour-El-Houda Yellas, Yann Dujardin, Nancy Perrot. Optimizing edge resource allocation for sustainable and latency-aware applications. 11th International Conference on Control, Decision and Information Technologies(CODIT), Jul 2025, Split - Croatia, Croatia. ⟨hal-05139835⟩
- Patient Ntumba, Nour-El-Houda Yellas, Salah Bin Ruba, Fehmi Ben Abdesslem, Stefano Secci. Data Pipeline System Designs for In-network Learning. 20th International Conference on Network and Service Management Prague, Czech Republic // 28 - 31 October 2024, Oct 2024, Prague, Czech Republic. ⟨hal-04681121⟩
- Nour-El-Houda Yellas, Éric Renault, Selma Boumerdassi. Grubbs Test Based Algorithms to Improve the Efficiency of Blockchain Oracles. 2024 International Wireless Communications and Mobile Computing (IWCMC), May 2024, Ayia Napa, Cyprus. pp.1478-1482, ⟨10.1109/IWCMC61514.2024.10592444⟩. ⟨hal-04680646⟩
- Nour-El-Houda Yellas, Jeongku Choi, Prosper Chemouil, Stefano Secci, Deep Medhi. Network Slice Robustness with Function Sets. IEEE/IFIP Network Operations and Management Symposium (NOMS 2024), IEEE, May 2024, Séoul, South Korea. pp.1-9, ⟨10.1109/NOMS59830.2024.10575871⟩. ⟨hal-04429291⟩
- Nour-El-Houda Yellas, Bernardetta Addis, Roberto Riggio, Stefano Secci. Function Placement and Acceleration for In-Network Federated Learning Services. 2022 18th International Conference on Network and Service Management (CNSM), Oct 2022, Thessaloniki, Greece. pp.212-218, ⟨10.23919/CNSM55787.2022.9964625⟩. ⟨hal-03883727⟩
- Dung Chi Phung, Nour-El-Houda Yellas, Salah Bin Ruba, Stefano Secci. An Open Dataset for Beyond-5G Data-driven Network Automation Experiments. 2022 1st International Conference on 6G Networking (6GNet), Jul 2022, Paris, France. ⟨10.1109/6GNet54646.2022.9830292⟩. ⟨hal-03698732v2⟩
- Salah Bin Ruba, Nour-El-Houda Yellas, Stefano Secci. Anomaly Detection for 5G Softwarized Infrastructures with Federated Learning. 2022 1st International Conference on 6G Networking (6GNet), Jul 2022, Paris, France. ⟨10.1109/6GNet54646.2022.9830390⟩. ⟨hal-03712114⟩
- Nour-El-Houda Yellas, Selma Boumerdassi, Alberto Ceselli, Stefano Secci. Complexity-Performance Trade-offs in Robust Access Point Clustering for Edge Computing. 17th International Conference on the Design of Reliable Communication Networks (DRCN 2021), Apr 2021, Milan, Italy. ⟨10.1109/DRCN51631.2021.9477332⟩. ⟨hal-03285731⟩
Theses
- Nour-El-Houda Yellas. Multi-criteria Optimization for Resource Allocation in Multi-access Edge Computing. Networking and Internet Architecture [cs.NI]. Hesam Université; Cnam Paris, 2023. English. ⟨NNT : ⟩. ⟨tel-04766847⟩
Powered by HAL 
Access Thesis: https://theses.fr/2023HESAC063
