Intelligent Synchronization and Controller Placement in Software-Defined Networks

As software-defined networks (SDNs) continue to evolve, new challenges emerge in maintaining efficient, reliable, and scalable control across increasingly dynamic and distributed environments. Our research focuses on building intelligent SDN control architectures that can adapt to changing network conditions while minimizing communication overhead and ensuring high network performance. We study how synchronization between controllers and their placement within the network affect overall system behavior, and we develop optimization frameworks to manage these processes effectively. By advancing synchronization strategies and placement algorithms, our goal is to design SDN systems that are more flexible, resilient, and capable of meeting the demands of future wireless and mobile networks.

Selected Publications

Panitsas, I., Mudvari, A., & Tassiulas, L. D2Q Synchronizer: Distributed SDN Synchronization for Time-Sensitive Applications. IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN), 2025.

Mudvari, A., & Tassiulas, L. Joint SDN Synchronization and Controller Placement in Wireless Networks Using Deep Reinforcement Learning. IEEE Network Operations and Management Symposium (NOMS), 2024.

Mudvari, A., Poularakis, K., & Tassiulas, L. Robust SDN Synchronization in Mobile Networks Using Deep Reinforcement and Transfer Learning. IEEE International Conference on Communications (ICC), 2023.

Poularakis, K., Qin, Q., Ma, L., Kompella, S., Leung, K. K., & Tassiulas, L. Learning the Optimal Synchronization Rates in Distributed SDN Control Architectures. IEEE Conference on Computer Communications (INFOCOM), 2019.