Distributed context-aware Affinity Propagation clustering in Wireless Sensor Networks

Mahmoud ElGammal; Mohamed ElToweissy

6th International ICST Conference on Collaborative Computing: Networking, Applications, Worksharing

Research Article

Distributed context-aware Affinity Propagation clustering in Wireless Sensor Networks

Download545 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.4108/icst.collaboratecom.2010.54,
    author={Mahmoud ElGammal and Mohamed ElToweissy},
    title={Distributed context-aware Affinity Propagation clustering in Wireless Sensor Networks},
    proceedings={6th International ICST Conference on Collaborative Computing: Networking, Applications, Worksharing},
    publisher={IEEE},
    proceedings_a={COLLABORATECOM},
    year={2011},
    month={5},
    keywords={affinity propagation context awareness distributed clustering potential fields wireless sensor networks},
    doi={10.4108/icst.collaboratecom.2010.54}
}

Mahmoud ElGammal
Mohamed ElToweissy
Year: 2011
Distributed context-aware Affinity Propagation clustering in Wireless Sensor Networks
COLLABORATECOM
ICST
DOI: 10.4108/icst.collaboratecom.2010.54

Mahmoud ElGammal¹^,*, Mohamed ElToweissy²^,a^,*

1: Bradley Department of Electrical and Computer Engineering, Virginia Tech
2: Cyber Security Research, Pacific Northwest National Laboratory
a: This work was done in part while ElToweissy was affiliated with the Bradley Department of Electrical and Computer Engineering at Virginia Tech

*Contact email: gammal@vt.edu, mohamed.eltoweissy@pnl.gov

Abstract

We foresee the need for dynamically clustering nodes in Wireless Sensor Networks (WSNs) according to a multitude of disparate co-existing contexts. To this end, we propose a distributed, low-overhead context-aware clustering protocol for WSNs. We employ Affinity Propagation (AP) for clustering nodes based on multiple criteria including location, residual energy, and contextual data sensed from the environment. We propose a novel approach for context representation based on potential fields. We discuss the integration of our context representation model with AP and demonstrate using simulation the effectiveness and proficiency of the proposed protocol in satisfying its intended objectives.

Keywords: affinity propagation context awareness distributed clustering potential fields wireless sensor networks

Published: 2011-05-12
Publisher: IEEE

: http://dx.doi.org/10.4108/icst.collaboratecom.2010.54