An improved genetic algorithm for network nodes clustering

Authors:
Yong Li;Zhenwei Yu
Affiliations:
College of Mechanical and Electronic Engineering, China University of Mining and Technology (Beijing), Beijing, China;College of Mechanical and Electronic Engineering, China University of Mining and Technology (Beijing), Beijing, China
Venue:
ICICA'11 Proceedings of the Second international conference on Information Computing and Applications
Year:
2011

Citing 5
Cited 0

On network-aware clustering of Web clients

Proceedings of the conference on Applications, Technologies, Architectures, and Protocols for Computer Communication
Clustering Hosts in P2P and Global Computing Platforms

CCGRID '03 Proceedings of the 3st International Symposium on Cluster Computing and the Grid
Vivaldi: a decentralized network coordinate system

Proceedings of the 2004 conference on Applications, technologies, architectures, and protocols for computer communications
P2PKMM: A Hybrid Clustering Algorithm over P2P Network

IITSI '10 Proceedings of the 2010 Third International Symposium on Intelligent Information Technology and Security Informatics
A construction of locality-aware overlay network: mOverlay and its performance

IEEE Journal on Selected Areas in Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Nodes clustering is a useful way to construct an effective network infrastructure for large-scale distributed network applications. In this paper, network nodes are clustered by the K-medoids clustering algorithm according to their coordinates. The coordinates of network nodes are gained by Vivaldi which is a simple and lightweight network coordinates system. But K-medoids algorithm is sensitive to the initial cluster centers and easy to get stuck at the local optimal solutions. In order to improve the performance of K-medoids algorithm, KCIGA(K-medoids clustering based on improved genetic algorithm) is presented in this paper. The improved genetic algorithm that uses self-adaptive genetic operator, dynamically adjusting the crossover rate and mutation rate, can avoid premature and slow convergence phenomenon in SGA(standard genetic algorithm). Experimental results show KCIGA has good reliability and expansibility, and it is effective for clustering network nodes.