Constrained K-means++ for multi-controller placement load balance

• Published in: 2024 International Conference on Circuit, Systems and Communication (ICCSC) pp. 1 - 4
• Main Authors: Chentouf, Aymen, Miyara, Mounia, Chiba, Zouhair
• Format: Conference Proceeding
• Language: English
• Published: IEEE 28.06.2024
• Subjects: clustering; Communication networks; Computer architecture; Control systems; Controller Placement Problem; Integrated circuit modeling; k-means; multi-controller; Partitioning algorithms; SDN; Software defined networking; software-defined network; Surges
• DOI: 10.1109/ICCSC62074.2024.10616998

The surge in interest surrounding Software Defined Networking (SDN) reflects its status as a groundbreaking and transformative network approach. In large-scale SDN networks, a sole centralized controller cannot fulfill the requirement; there arises the necessity for multiple controllers. With performance heavily correlated with the placement of controllers, the controller placement problem became the most important challenge in multi-controller SDN networks. In this paper, we introduce an algorithm that incorporates constrained k-means++ and subsequent modifications to mitigate some k-means-based network partition limitations. The experimental result shows that incorporating constraints on the amount of switches pertaining to controllers efficiently balances the load on controllers and considerably reduces the load difference degree compared to k means and k-means++.