Clustering in mobile ad hoc network based on neural network

Abstract

An on-demand distributed clustering algorithm based on neural network was proposed. The system parameters and the combined weight for each node were computed, and cluster-heads were chosen using the weighted clustering algorithm, then a training set was created and a neural network was trained. In this algorithm, several system parameters were taken into account, such as the ideal node-degree, the transmission power, the mobility and the battery power of the nodes. The algorithm can be used directly to test whether a node is a cluster-head or not. Moreover, the clusters recreation can be speeded up.

Keywords

ad hoc network / clustering / neural network

References

[1] FrodighM., JohanssonP., LarssonP.. Wireless ad hoc networking: The art of networking without a network[J]. Ericsson Review, 2000, 77(4): 248-263

[2] Basagni S, Chlamtac I, Farago A. A generalized clustering algorithm for peer-to-peer networks[C] // Proceedings of Workshop on Algorithmic Aspects of Communication. Bologna: 1997: 1–14

[3] ChlamtacI., FaragoA.. A new approach to the design and analysis of peer-to-peer mobile networks[J]. Wireless Networks, 1999, 5(3): 149-156

[4] ChatterjeeM., SasS. K., TurgutD.. An on-demand weighted clustering algorithm (WCA) for ad hoc networks[C]. Proc 43rd IEEE Global Telecommunications Conference. San Francisco, 2000, 3: 1697-1701

[5] ChatterjeeM., DasS. K., TurgutD.. WCA: A weighted clustering. algorithm for obile ad hoc networks[J]. Journal of Clustering Computing: Special Issue on Mobile Ad Hoc Networks, 2002, 5(2): 193-204

[6] GerlaM., TsaiJ. T. X.. Multicluster, mobile, multimedia radio network[J]. Wireless Networks, 1995, 1(3): 255-265

[7] Parekh A K. Selecting routers in ad-hoc wireless networks[C]// Proceedings of the SBT/IEEE International Telecommunications symposium. JTC: de Rio Janeiro, 1994: 420–424.

[8] Baker D J, Ephremides A. A distributed algorithm for organizing mobile radio telecommunication networks[C]// Proceedings of the 2nd International Conference on Distributed Computer Systems. Paris: 1981: 476–483.

[9] BakerD. J., EphremidesA.. The architectural organization of a mobile radio network via a distributed algorithm[J]. IEEE Transactions on Communications COM, 1981, 29(11): 1694-1701

[10] EphremidesA., WieselthierJ. E., BakerD. J.. A design concept for reliable mobile radio networks with frequency hopping signaling[J]. Proceedings of IEEE, 1987, 75(1): 56-73

[11] Basagni S. Distributed clustering for ad hoc networks[C] // Proceedings of International Symposium on Parallel Architectures. Algorithms and Networks (I-SPAN’99). 1999: 310–315.

[12] Basagni S. Distributed and mobility-adaptive clustering for multimedia support in multi-hop wireless networks[J]. Proceedings of Vehicular Technology Conference. VTC, 1999: 889–893.

[13] AlmeidaJ. S.. Predictive non-linear modeling of complex data by artificial neural networks[J]. Current Opinion in Biotechnology, 2002, 13(1): 72-76

[14] KononenkoI.. Machine learning for medical diagnosis: history, state of the art and perspective[J]. Artif Intell Med, 2001, 23(1): 89-109

[15] CaiZ.-x., XuG.-you.Artificial intelligence: Principles and applications[M], 2003, Beijing, Tsinghua University Press: 191-197