R&I group

Software Networks

The Software Networks (SN) research group focuses on advancing the capabilities of next-generation networks through automation, intelligence, federation and integration. With the increasing shift from centralized to distributed infrastructures, the research group addresses resource management challenges. It focuses on combining AI, automation, and integration to simplify the management of complex networks, ensuring scalability, reliability, and efficiency for next-generation applications and services.

Research lines

  • Intent-Based Networking (IBN): This research line focuses on the intelligent orchestration of network resources through high-level business intent abstraction. IBN complements Network Function Virtualization (NFV) by abstracting the complexities of infrastructure configuration, much like NFV decouples services from physical hardware. At its core, IBN aims to translate business-level goals into network control policies via advanced generative AI (GenAI)  and machine reasoning tools, which are learned and executed by low-level agentic systems, leveraging the Emergent Communication (EC) paradigm. This enables networks to adapt dynamically, respond to changing requirements, and self-optimize with minimal human intervention.
  • Cognitive Cloud Continuum: This research line is focused on the investigation and prototyping of cloud-native solutions for providing extended capabilities and intelligence across the edge-to-cloud continuum to improve latency, scalability, resource utilization, and context-awareness.Specific research topics include the integration and interoperation of NFV and MEC orchestrators, AI/ML-based analytics services for workload placement and re-allocation, federation of inter-operator edge platforms, and integration with a vertical-oriented service exposure layer.

Innovation lines

  • Connected Collaborative Computing (3C) Networks
  • Resource Exposure, GSMA Operator Platform, CAMARA, Federation and Open Gateway

Technologies

  • Intelligent Application/Service Orchestration for Cognitive Cloud Continuum [incl. extension to NTN]
  • Telco capabilities exposure (CAMARA, GSMA Open Gateway, Operator Platform) and network federation
  • Intent-based Networking
  • Intelligent slice management
  • Distributed and secure Marketplace for 5G/6G resources
  • Agentic Networking and Multi-agent communications protocols
  • Testbed & telco -focused virtualisation stacks

Group leader

Pouria Sayyad Khodashenas

Software Networks

Publications

AI-Native Orchestration in the 6G Continuum: Evolving Operator Platforms with Agentic AI

C. Carballo González, H. Chergui, S. Giménez-Antón, M. Mosahebfard, J. S. Camargo, P. Sayyad Khodashenas, V. Theodorou, and C. Verikoukis, “AI-Native Orchestration in the 6G Continuum: Evolving Operator Platforms with Agentic AI,” IEEE Network, Jan. 2027 (to appear).

Topological Forwarding for LEO Constellations: A Scope-Specific Routing Policy in a Recursive User-Plane Architecture

Sergio Giménez-Antón, Eduard Grasa, Jordi Perelló, Maryan Rizinski, Mohammadreza Mosahebfard, John Day, Lubomir Chitkushev, Topological forwarding for LEO constellations: A scope-specific routing policy in a recursive user-plane architecture, Computer Networks, 2026, 112923, ISSN 1389-1286, https://doi.org/10.1016/j.comnet.2026.112923. (https://www.sciencedirect.com/science/article/pii/S1389128626009357) Abstract: A Low Earth Orbit (LEO) mega-constellation never stops moving, yet Internet Protocol (IP)-based routing ties each satellite’s forwarding state to constellation size and recomputes routes as the shell turns. We treat routing instead as a policy of one layer of the 6G Recursive User Plane Architecture (6G-RUPA), in which a satellite’s address states its position in the shell, so that forwarding becomes arithmetic: a distance policy prices the remaining path in kilometers from seven shell constants and the clock, a progress guard keeps every walk loop-free, and exception entries repair what failures break. We test the scheme in LEOPath, an open-source simulator, on four constellations and eleven shells from published filings, with Ring, +Grid, open-seam and three-laser brick-wall wirings and fifteen failure conditions, against link-state and explicit-path routing and a hop-only ablation. Per-satellite forwarding state, a proxy for router memory, falls from 351-1584 routes to the node degree, and where a full link-state table rewrites 12 to 65 routes per satellite and minute as a failure-free shell moves, a topological satellite rewrites none. Under the same addresses, forwarding matches the mean path length and delay of link-state without failures and, with northbound addresses, its delivery under failures, on paths up to 13% longer. At realistic failure rates the busiest satellite holds 25 to 474 exact exception entries, which group into 3 to 8 address regions. The price moves to the edge, as station renumbering and 7-22 ms of extra delay for attachment addressing, which a second address per station roughly halves. Whether smaller tables save lookup energy remains untested. Keywords: Routing; LEO satellites; 6G-RUPA; Satellite networks; Topological routing; Network scalability; Network architecture

Towards Seamless Integration of Terrestrial and Non-Terrestrial 6G Networks: An NFV-SDN Framework for Infrastructure Mobility Management

M. Mosahebfard, A. Cárdenas and L. Tomaszewski, “Towards Seamless Integration of terrestrial and Non-Terrestrial 6G Networks: An NFV-SDN Framework for Infrastructure Mobility Management,” in IEEE Open Journal of the Communications Society, vol. 7, Jun. 2026. doi: 10.1109/OJCOMS.2026.3705345

Dynamic Joint Scheduling of Movement and Data Processing Tasks using Extreme-Edge Computing in Multi-AGV Scenarios

M. Masoumi, E. Carmona-Cejudo, I. de Miguel, C. Torres-Pérez, R.J. Durán Barroso, “Dynamic Joint Scheduling of Movement and Data Processing Tasks using Extreme-Edge Computing in Multi-AGV Scenarios,” in IEEE Open Journal of the Industrial Electronics Society, in press.

Service Placement in dynamic multi-AGV environments for minimized energy consumption

C. Torres-Pérez, E. Carmona-Cejudo, C. Cervelló-Pastor, M. Masoumi, E. Coronado and M. S. Siddiqui, “Service Placement in Dynamic Multi-AGV Environments for Minimized Energy Consumption,” in IEEE Robotics and Automation Letters, vol. 11, no. 1, pp. 714-721, Jan. 2026, doi: 10.1109/LRA.2025.3636026

Journal of Network and Systems Management: Hardware-accelerated Edge AI Orchestration on the Multi-Tier Edge-Cloud Continuum

@article{palomares2025hardware, author = {Palomares, Javier and Coronado, Estefanía and Tzenetopoulos, Achilleas and Lentaris, George and Cervelló-Pastor, Cristina and Siddiqui, Muhammad Shuaib}, title = {Hardware-Accelerated Edge AI Orchestration on the Multi-Tier Edge-to-Cloud Continuum}, journal = {Journal of Network and Systems Management}, year = {2025}, doi = {10.1007/s10922-025-09959-4}, publisher = {Springer Nature} }

View all

Software Networks

Latest news