Title:

An Efficient Controller Placement Algorithm using Clustering in Software Defined Networks, Journal of Telecommunications and Information Technology, 2023, nr 4

Group publication title:

2023, nr 4, JTIT-artykuły

Creator:

Jacob, Joshua ; Shinde, Sumedha ; D.G., Narayan

Subject and Keywords:

clustering ; controller placement ; PAM ; K-means++ ; silhouette score ; SDN

Abstrakt:

Software-defined networking (SDN) is an emerging network paradigm that separates the control plane from data plane and provides programmable network management. The control plane within SDN is responsible for decision-making, while packet forwarding is handled by the data plane based on flow entries defined by the control plane. The placement of controllers is an important research issue that significantly impacts performance of SDN. In this work, we utilize clustering algorithms to group networks into multiple clusters and propose an algorithm for optimal controller placement within each cluster. Initially, using the silhouette score, we determine the optimal number of controllers for various topologies. Additionally, to enhance network performance, we employ the meeting point algorithm to calculate the optimal location for placing the controller within each cluster. We implement the proposed work in the Mininet emulator with POX as the SDN controller. Furthermore, we compare our proposed approach to existing work in terms of throughput, delay, and jitter using six topologies from the Internet Zoo dataset.

Number:

4

Publisher:

Instytut Łączności - Państwowy Instytut Badawczy

Date:

2023

Resource Type:

artykuł

DOI:

doi.org/10.26636/jtit.2023.4.1371

ISSN:

1509-4553

eISSN:

1899-8852

Source:

Journal of Telecommunications and Information Technology

Language:

ang

License:

CC BY 4.0

rights owner:

Instytut Łączności - Państwowy Instytut Badawczy