ASWELL: AutonomouS NetWork Slicing for IntEgrated SateLlite-TerrestriaL Transport Networks

Funding Source: Luxembourg National Research Fund (FNR)
Partners: SES
Principal Investigator: Dr. Symeon Chatzinotas (UL)
Research Team: Dr. Lei Lei (UL), Dr. Thang X. Vu (UL), Dr. Konstantinos Liolis (SES), Prof. Björn Ottersten (UL)
Start Date: TBD
Duration: 36 months

About the Project

During the last decade, networks have largely increased in size and complexity due to the wide adoption of mobile devices and wireless access. In parallel, the prospection of new verticals in the context of 5G (Internet of Things, Vehicles, and Drones) has necessitated the support of multiple Service Level Agreements (SLAs) with heterogeneous guarantees (latency, reliability, rate, terminal number). In an attempt to streamline the network management, both research community and industry stakeholders have been progressively adopting network virtualization and softwarization technologies. However, this wave of virtualization has exponentially increased the degrees of freedom in the network management process. In addition, the combination of terrestrial and non-terrestrial links (e.g. satellite) in transport networks has introduced new dimensions of network heterogeneity and dynamicity. In this context, the main challenge of the project ASWELL is to devise network-slicing algorithms that can efficiently and autonomously configure the large number of parameters present in a virtualized dynamic graph representing an integrated satellite-terrestrial transport network. An illustrative framework of ASWELL is shown in Figure 1.

 

Figure 1. An illustrative framework of ASWELL: The common physical infrastructure is sliced into multiple virtual logical networks. Each network slice becomes an independent virtualized end-to-end network and can be configured based on the SLA of the targeted traffic, e.g., enhanced mobile broadband (eMBB), ultra-reliable low-latency communications (URLLC) and massive machine-type communications (mMTC).

ASWELL aims at devising efficient and scalable machine-learning or deep-learning (ML/DL) solutions for autonomous network slicing in integrated satellite-terrestrial transport networks. We will apply ML/DL to provide a viable alternative to conventional human-engineered heuristic or optimization-based algorithms, which cannot rise to the occasion of heterogeneous dynamic large-scale software-defined networks. To this end, the ML/DL-driven paradigm will be employed a) to accelerate the flow management algorithms for large-dimensional graphs, b) to autonomously manage the on-line network flows for graphs with temporal dynamics, c) to consider joint flow and node resource slicing for networks which include processing/storage functionalities. Addressing the aforementioned challenges will contribute towards self-managing, self-adapting, and self-optimizing slicing with the aim of supporting the operational monitoring and configuration of integrated transport networks.

The planed R&D tasks are organized in 5 Work Packages (WPs). WP1 focuses on literature review and scenario definition, while WP2-WP4 include the technical contributions in flow management and virtual network embedding for autonomous network slicing. Finally, WP5 is devoted to project management, dissemination and valorisation. The following paragraphs offer more details on the project plan and WPs.

Figure 2: Work packages interconnection and working flow

Project Partners

• SIGCOM, SnT, University of Luxembourg, Luxembourg (SnT, UL)
• SES (Luxembourg)

Funding Details

• Funding Source: National Research Fund (FNR), multi-annual thematic research programme (CORE), Luxembourg

Contact: Dr Symeon Chatzinotas