You are here




Holistic and foundational resource allocation framework for optimized and impactful edge computing services

About LeadingEdge


The LeadingEdge project will deliver a novel and holistic framework to efficiently cope with unresolved challenges in edge computing ecosystems, regarding dynamic resource provisioning to multiple coexisting services amidst unknown service- and system-level dynamics. The project approach is three-faceted; it will optimize intra-service resource provisioning, inter-service resource coordination, and user perceived quality of experience (QoE).

Aim of the project

  • First, at service level, we will develop a framework, grounded on first principles, for opportunistic use of edge and cloud computation, bandwidth and cache resources according to instantaneous resource availability, mobility, connectivity, service resource requirements and service demand. Our approach will rely on solid online-learning theories such as online convex optimization (OCO), and transfer learning and it will eliminate our inherent inability to predict demand, mobility, and other dynamic processes that affect resource allocation. It will also use extreme-value theory and stochastic optimization towards a full-fledged study of the latency-reliability trade-off that is fundamental for mission-critical services.
  • At a second level, we will develop a system-level AI-empowered service orchestrator based on reinforcement learning and context awareness for service orchestration in terms of network slicing and service chain placement, such that instantaneous service-level requirements are fulfilled. The (OAI) and software platforms will be used as real-time experimentation environments with full 4G/5G functionalities for service orchestration to place services, direct traffic from users to servers, and measure latency and other QoE metrics.
  • Finally, at user level, we will leverage the community-network infrastructure of as an edge network to deploy services at scale in a controlled manner and to directly measure their impact on user QoE. The outcome of these latter user-level studies will be continually fed back to and guide the service- and the system-level optimization.

Fact sheet


The objectives of LeadingEdge are as follows:

  • Optimally utilize edge and cloud resources at a service level, through intelligent task offloading to the cloud, and dynamic allocation of computation among edge nodes. Stochastic optimization, transfer learning and novel usage of caching resources will guide the effort towards this objective.
  • Derive fundamental performance limits and devise dynamic algorithms for maximization of computation rate of data analytics, while maintaining low latency and high reliability. These goals will be achieved through stochastic optimization and extreme-value theories.
  • Overcome the unpredictability of service demand, user mobility and edge network topology through online convex optimization (OCO) algorithms for effective learning of dynamic processes that affect intra-service resource allocation decisions.
  • Provide service-level proof-of-concept (PoC) validation through (i) a real-time image recognition tool that optimally utilizes cache, bandwidth and computation resources, (ii) two video quality assessment solutions, each with different complexity and accuracy and different configuration of edge/cloud and cloud/backend resources.
  • Design an AI-based system-level service orchestrator with dynamic service placement, network slicing and dynamic resource provisioning capabilities across services by using reinforcement learning and context-awareness.
  • Provide system-level proof-of-concept validation on (OAI) and software platforms that will be used as real-time experimentation environment with full 4G/5G functionalities for service orchestration.
  • Leverage the community-network infrastructure to deploy services at scale and measure perceived user-level QoE. The outcome of user-level measurements will be continually fed back to and guide the service- and the system-level optimization.



  1. N. Llisterri Giménez, M. Monfort Grau, R. Pueyo Centelles, and F. Freitag, "On-Device Training of Machine Learning Models on Microcontrollers with Federated Learning,", in electronics, Volume: 11, Issue: 4, 2022, doi: 10.3390/electronics11040573.
  2. A. M. Girgis, H. Seo, J. Park, M. Bennis and J. Choi, "Predictive Closed-Loop Remote Control Over Wireless Two-Way Split Koopman Autoencoder,", in IEEE Internet of Things Journal, Volume: 9, Issue: 23, pp. 23285-23301, 1 Dec. 2022, doi: 10.1109/JIOT.2022.3206415.
  3. M. M. Wadu, S. Samarakoon and M. Bennis "Joint Client Scheduling and Resource Allocation Under Channel Uncertainty in Federated Learning,", in IEEE Transactions on Communications, vol. 69, no. 9, pp. 5962-5974, Sept. 2021, doi: 10.1109/TCOMM.2021.3088528
  4. RP Centelles, F Freitag, R Meseguer, L Navarro " Beyond the star of stars: An introduction to multihop and mesh for LoRa and LoRaWAN ", in IEEE Pervasive Computing, Volume: 20, Issue: 2, April-June 1 2021.
  5. S. Samarakoon, M. Bennis, W. Saad and M. Debbah, "Predictive Ultra-Reliable Communication: A Survival Analysis Perspective,", in IEEE Communications Letters, vol. 25, no. 4, pp. 1221-1225, April 2021, doi: 10.1109/LCOMM.2020.3047446.
  6. Bouziane Brik and Adlen Ksentini "Towards an Optimal MEC Resources Dimensioning for Vehicle Collision Avoidance System: A Deep Learning Approach", in IEEE Network Magazine, Special Issue on AI-Empowered Mobile Edge Computing in the Internet of Vehicles, May-June 2021.
  7. Roger Pueyo Centelles, Roc Meseguer, Felix Freitag, Leandro Navarro, Sergio F. Ochoa, Rodrigo M. Santos "LoRaMoto: A Communication System to Provide Safety Awareness AmongCivilians After an Earthquake", in Future Generation Computer Systems, 2021.
  8. H. Seo, J. Park, M. Bennis and W. Choi, "Communication and Consensus Co-Design for Distributed, Low-Latency and Reliable Wireless Systems,", in IEEE Internet of Things Journal, Jan, 2021, doi: 10.1109/JIOT.2020.2997596.
  9. George Koutitas, Shashwat Vyas, Chaitanya Vyas, Shivesh Singh Jadon, Iordanis Koutsopoulos "Practical Methods for Efficient Resource Utilization in Augmented Reality Services", in IEEE Access, Dec, 2020.
  10. Sumudu Prasad Samarakoon, Mehdi Bennis, Walid Saad, and Mérouane Debbah "Predictive Ultra-Reliable Communication: A Survival Analysis Perspective", in IEEE Communications Letters, Dec, 2020.
  11. D. Wen, M. Bennis, K. Huang, “Joint Parameter-and-Bandwidth Allocation for Improving the Efficiency of Partitioned Edge Learning,”, in IEEE Trans. Wireless Commun. 2020.
  12. H. Shiri, J. Park and M. Bennis, "Communication-Efficient Massive UAV Online Path Control: Federated Learning Meets Mean-Field Game Theory,", in IEEE Transactions on Communications 2020, Volume 68, Issue 11, doi: 10.1109/TCOMM.2020.3017281.
  13. S. Oh, J. Park, E. Jeong, H. Kim, M. Bennis and S. Kim, "Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup,", in IEEE Communications Letters, Volume: 24, Issue: 10, Oct. 2020, doi: 10.1109/LCOMM.2020.3003693.


  1. E. Cruz Harillo and F. Freitag, "Exploring blockchain-based management for LoRa IoT nodes", in 19th International Conference on the Economics of Grids, Clouds, Systems and Services (GECON 2022).
  2. E. Cruz Harillo and F. Freitag, "LoRaCoin: Towards a blockchain-based platform for managing LoRa devices", in IEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), 2022, pp. 1-2.
  3. M. Karaliopoulos and I. Koutsopoulos, "Empowering synergies of communities with service providers for the bottom-up Deployment of Network Infrastructures", in Proceedings of ACM International Conference on Modeling, analysis and simulation of wireless and mobile systems 2022, Montreal, Canada.
  4. S. Nikoloutsopoulos, I. Koutsopoulos and M. Titsias, "Online continual learning from imbalanced data with Kullback-Leibler-loss based replay buffer updates", in Proceedings of Human in the Loop (HiLL) workshop, in Conference on Neural Information Processing Systems (NeurIPS) 2022, New Orleans.
  5. L. E. Chatzieleftheriou, C.-F. Liu, I. Koutsopoulos, M. Bennis and M. Debbah, "Online learning for Industrial IoT: The Online Convex Optimization perspective", in Proceedings of Workshop on Intelligence Distribution of Computing in Cloud Continuum (ID3C), in IEEE International Mediterranean Conference on Communications and Networking (MeditCom), 2022, pp. 7-12, doi: 10.1109/MeditCom55741.2022.9928703, Athens, Greece.
  6. Y. -L. Hsu, C. -F. Liu, H. -Y. Wei and M. Bennis, "Optimized Data Sampling and Energy Consumption in IIoT: A Federated Learning Approach", in IEEE Transactions on Communications, 2022, doi: 10.1109/TCOMM.2022.3216353.
  7. K. Ntougias, C. Psomas, E. Demarchou, I. Krikidis and I. Koutsopoulos, "Joint dynamic wireless edge caching and user association: A Stochastic optimization approach", in Proceedings of International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2022, Oulu, Finland.
  8. G. Darzanos, I. Koutsopoulos, K. Papakonstantinopoulou and G.D. Stamoulis, "Economics of Multi-Operator Network Slicing", in Proceedings of International Symposium on Modelling and Optimization in Mobile, Ad hoc and wireless networks (WiOpt) 2022, Turin, Italy.
  9. A.Chouayakh and A. Destounis, " Towards no regret with no service outages in online resource allocation for edge computing ", in IEEE ICC 2022 (to appear).
  10. F. Freitag, P. Vilchez, Ch. Liu, L. Wei, M. Selimi. " Performance Evaluation of Federated Learning over Wireless Mesh Networks with Low-Capacity Devices. ", in International Conference on Information Technology & Systems (ICITS 2022), Feb 2022.
  11. F. Freitag, P. Vilchez, L. Wei, C.H Liu, M. Selimi, I. Koutsopoulos. " Demo: An Experimental Environment Based On Mini-PCs For Federated Learning Research.", in 2022 IEEE 19th Annual Consumer Communications & Networking Conference (CCNC), Jan 2022.
  12. C.-F. Liu and M. Bennis " Federated learning with correlated data: Taming the tail for age-optimal industrial IoT ", in Proc. 19th Int. Symp. Modeling Optim. Mobile, Ad Hoc, Wireless Netw., Oct. 2021, pp. 1-6.
  13. Y.-L. Hsu, C.-F. Liu, S. Samarakoon, H.-Y. Wei, and M. Bennis, " Age-optimal power allocation in industrial IoT: A risk-sensitive federated learning approach ", in Proc. IEEE 32nd Annu. Int. Symp. Pers., Indoor, Mobile Radio Commun., Sep. 2021, pp. 1-6.
  14. Georgios Cheirmpos, Merkouris Karaliopoulos, Iordanis Koutsopoulos "Optimizing shared data plans for mobile data access", in ITC 33 - Networked Systems and Services Aug. 31st - Sep. 3rd 2021, Avignon, France.
  15. L Navarro, M Roura, D Franquesa " eReuse poster: the circular economy of digital devices ", in COMPASS 2021: ACM SIGCAS Conference on Computing and Sustainable Societies, June 2021.
  16. Iordanis Koutsopoulos, Maria Halkidi "Optimization of Multi-stakeholder Recommender Systems for Diversity and Coverage", in 17th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2021, Hersonissos, Crete, Greece. pp.703-714.
  17. Livia Elena Chatzieleftheriou, Apostolos Destounis, Georgios Paschos, Iordanis Koutsopoulos "Blind Optimal User Association in Small-Cell Networks", in IEEE International Conference on Communications (INFOCOM), May, 2021.
  18. Iordanis Koutsopoulos "The Impact of Baseband Functional Splits on Resource Allocation in 5G Radio Access Networks", in IEEE International Conference on Communications (INFOCOM), May, 2021.
  19. Mennan Selimi, Leandro Navarro, Bart Braem, Felix Freitag, Adisorn Lertsinsrubtavee "Towards Information-Centric Edge Platform for Mesh Networks: The Case of CityLab Testbed ", in IEEE International Conference on Fog Computing (ICFC), April, 2020 .
  20. Javier Panadero, Laura Calvet, Christopher BaylissJoan, Manuel Marques, Mennan Selimi, Felix Freitag "A SIMHEURISTIC ALGORITHM FOR SERVICE PLACEMENT IN COMMUNITY NETWORKS", in 2020 Winter Simulation Conference, Dec, 2020.
  21. Roger Pueyo Centelles, Mennan Selimi, Felix Freitag, Leandro Navarro "REDEMON: Resilient Decentralized MonitoringSystem for Edge Infrastructures", in 20th IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGRID), May, 2020.
  22. Mohamed K. Abdel-Aziz, Sumudu Samarakoon, Cristina Perfecto, and Mehdi Bennis "Cooperative perception in Vehicular Networks using Multi-Agent Reinforcement Learning", in 54th Asilomar Conference on Signals, Systems, and Computers, Nov., 2020.
  23. M. Karaliopoulos and I. Koutsopoulos, "Collective subscriptions: a novel funding tool for crowdsourced network infrastructures", in IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (IEEE WoWMoM 2020).

Grant PCI2019-111851-2 funded by MCIN/AEI/ 10.13039/501100011033