SDN Multi Controller Deployment Strategy Based on Improved Spectral Clustering Algorithm
Authors:
- 15 April 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 117-120
Abstract
Multi controller deployment in Software-Defined Networking plays a pivotal role in maximizing network resource utilization. However, the existing deployment strategies cannot consider both latency and load, directly determine the optimal number of controllers to be deployed, and ignore the impact of edge nodes on controller deployment. This paper proposes a multi controller deployment strategy for Software-Defined Networking based on an improved spectral clustering algorithm to improve the network quality under Software-Defined Networking architecture. After comparison experiments, it is demonstrated that the proposed strategy not only can effectively deploy multiple controllers for Software-Defined Networking without the influence of edge nodes but also can optimize the latency while achieving load balancing.Keywords
This publication has 11 references indexed in Scilit:
- HPSOSA: A Hybrid Approach in Resilient Controller Placement in SDN2020
- Spectral Clustering of Large-scale Data by Directly Solving Normalized Cut2018
- An Effective Approach to Controller Placement in Software Defined Wide Area NetworksIEEE Transactions on Network and Service Management, 2017
- On the Capacitated Controller Placement Problem in Software Defined NetworksIEEE Communications Letters, 2014
- The controller placement problemACM SIGCOMM Computer Communication Review, 2012
- Incremental spectral clustering by efficiently updating the eigen-systemPattern Recognition, 2010
- Spectral clustering with eigenvector selectionPattern Recognition, 2008
- Robust path-based spectral clusteringPattern Recognition, 2008
- EthaneACM SIGCOMM Computer Communication Review, 2007
- Automatic Determination of the Number of Clusters Using Spectral Algorithms2006