Servicenavigation

Project Details

Back

Projekt Print View

Adversarial Design Framework for Self-Driving Networks (ADVISE)

Applicant Professor Dr.-Ing. Wolfgang Kellerer, since 4/2022
Subject Area Security and Dependability, Operating-, Communication- and Distributed Systems
Term from 2020 to 2024
Project identifier Deutsche Forschungsgemeinschaft (DFG) - Project number 438892507
 
Final Report Year 2024

Final Report Abstract

Communication networks have become a critical infrastructure of our digital society. As most network outages today are due to human errors, the networking community is currently engaged in designing more automated and “self-driving” communication networks that overcome today’s manually managed networks. These networks exploit the flexibilities introduced by emerging software-defined and virtualized communication technologies, to implement more demand-aware networks which meet the stringent requirements of new applications. The ADVISE project contributes toward our fundamental understanding of such self-driving networks, as well as first tools to realize them. To this end, we develop and apply both methods from artificial intelligence and formal approaches (and games) providing formal correctness and performance guarantees. In particular, ADVISE empirically studies the temporal and spatial structure of traffic workloads, and develop models accordingly, which can be used to design and evaluate self-driving networks. We then develop the algorithmic foundations for self-driving networks, leveraging and integrating predictions (as they may come from machine learning (ML) models) with formal frameworks such as competitive analysis and games. For example, this results in online algorithms which not only provide the classic worst-case guarantees, but which also profit from an infused advice which improves their performance in practice where traffic may be more stochastic and predictable then in the worst case. We study and apply our approaches in different use case, in particular, in the context of reconfigurable datacenter networks (RDCNs) and in software-defined radio access networks (SD-RANs).

Publications

 
 

Additional Information

© 2026 DFG Disclaimer / Copyright / Privacy Policy

Textvergrößerung und Kontrastanpassung