Project PID2020-112675RB-C41 ONOFRE-3
On-Demand Provisioning of Network and Computing Resources from the Cloud to the Edge: Optimal Planning and Coordinates Access (ONOFRE-3-UPCT
Funder: AGENCIA ESTATAL DE INVESTIGACIÓN
Call: Convocatoria de tramitación anticipada para el año 2020 del procedimiento de concesión de ayudas a «Proyectos de I+D+i», en el marco del Programa Estatal de Generación de Conocimiento y Fortalecimiento Científico y Tecnológico del Sistema de I+D+i y del Programa Estatal de I+D+i Orientada a los Retos de la Sociedad, del Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 (AGENCIA ESTATAL DE INVESTIGACIÓN)
Of National scope. With a Public character. It has been granted under a regime of Competitive.
5G, and especially future networks (6G), introduce as defining features new massive latency-constrained service classes, cell-less architectures with multiaccess coordination and ML-based network intelligence, all of it supported by Multiaccess Edge Computing (MEC). Convergent networks work as their backhaul and meet their stringent requirements with Network Function Virtualization (NFV) techniques, MEC and Management and Orchestration (MANO), Software-Defined Networking (SDN), framing a solution able to manage and orchestrate the complete lifecycle of future services. Computation services can be instantiated in such virtualized infrastructures, enabling the possibility of offloading tasks from mobile nodes but requiring the design of frameworks to control and manage networks interconnecting cloud and MEC servers. The cell-less architecture is implemented by the coordinated use of multiple RAT with support from the MEC servers. To realize this architecture, it is necessary to overcome the heterogeneity of the edge, fog, and cloud processing layers and proper management of dynamic QoS application requirements running on mobile nodes. To overcome this complexity, AI and Machine Learning techniques for contextual information prediction and network management is the trend. AI/ML can also support both offline planning methods and multiaccess coordination and control and be deployed at end devices. In this scenario, security is also mandatory from the start, with advanc
In collaboration with other entities. Role: Coordinator
Researchers
Former participants (3)
- Ramos Sorroche, Emilio 20222022
- Ramos Sorroche, Emilio 20222022
- Rubio Aparicio, Jesús 20223000
Publications related to the project
Show by type2025
-
Exploiting Personalized Observation Frequency for Proportional Integral Derivative-Based Diabetes Management
Electronics (Switzerland)
-
Adjacent Channel Interference and Congestion Control for Multi-Channel Operation in Vehicular Networks
IEEE Transactions on Intelligent Transportation Systems
2024
2023
-
A 3D simulation framework with ray-tracing propagation for LoRaWAN communication
Internet of Things
-
Evaluation of Offline Reinforcement Learning for Blood Glucose Level Control in Type 1 Diabetes
IEEE Access
-
ORIENTATE: automated machine learning classifiers for oral health prediction and research
BMC Oral Health
2022
-
Towards Outdoor Electromagnetic Field Exposure Mapping Generation Using Conditional GANs
Sensors
-
Approximate reinforcement learning to control beaconing congestion in distributed networks
Scientific Reports
-
Optimal Joint Power and Rate Adaptation for Awareness and Congestion Control in Vehicular Networks
IEEE Transactions on Intelligent Transportation Systems