Decentralized Kalman Filter in Wireless Sensor Networks – Case Studies

Application of data fusion techniques in new fields brings always up new sets of practical problems. This paper studies the decentralized Kalman filter (DKF) in out-of-sequence (OOSM) and clusterized topology problems, which rise in application to wireless sensor networks. The OOSM problem is closely related to the uncertainty of wireless links. Data may be randomly delayed or completely lost. The possible clusterized topology of large wireless sensor networks raises also problems for DKF. Namely, how much information should be kept in memory, if the sensor node moves from one network cluster to another. The above problems and solutions are discussed and examined in case simulations.

[1]  Xiaojiang Du,et al.  Improving routing in sensor networks with heterogeneous sensor nodes , 2005, 2005 IEEE 61st Vehicular Technology Conference.

[2]  Kay Römer,et al.  The design space of wireless sensor networks , 2004, IEEE Wireless Communications.

[3]  Edward J. Coyle,et al.  An energy efficient hierarchical clustering algorithm for wireless sensor networks , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[4]  Yaakov Bar-Shalom.  Update with out-of-sequence measurements in tracking: exact solution , 2002 .

[5]  Arthur Gelb,et al.  Applied Optimal Estimation , 1974 .

[6]  Hugh F. Durrant-Whyte,et al.  Delayed and asequent data in decentralized sensing networks , 2001, SPIE Optics East.

[7]  S. Grime,et al.  Data fusion in decentralized sensor networks , 1994 .

[8]  Melody Moh,et al.  On data aggregation quality and energy efficiency of wireless sensor network protocols - extended summary , 2004, First International Conference on Broadband Networks.