FDS: Fault Detection Scheme for Wireless Sensor Networks

Since more than one decade, Wireless Sensor Networks (WSN) have been emerged as a promising and interesting area which increasingly drawing researcher attention. So, the attraction to WSNs is due to their large applicability having growing tendency to fit almost all domains in our daily life. WSNs consist of a large number of heterogeneous/homogeneous sensor nodes communicating through wireless medium and working cooperatively to sense or monitor environment sizes related to physical phenomena. As a corner stone involved in WSN design, fault detection is indispensable to offer WSN applications robustness capability allowing them to meet mission success requirements. In order to ensure high quality of service, it is essential for a WSN to be able to detect its faulty sensor nodes before carrying out necessary recovery actions. In this paper, we propose a fault detection scheme (FDS) to identify faulty sensor nodes. FDS performs in two levels; the first level is conducted locally inside the sensor nodes, while the second level is carried out in a higher level (e.g., in a cluster head or gateway). The performance evaluation is tested through simulation to evaluate some factors such as: detection accuracy, false alarm rate, control overhead and memory overhead. We compared our results with referenced algorithm: Fault Detection in Wireless Sensor Networks (FDWSN), and found that FDS performance outperforms that of FDWSN.

[1]  Pat Langley,et al.  Estimating Continuous Distributions in Bayesian Classifiers , 1995, UAI.

[2]  Abid Sarwar,et al.  Intelligent Naïve Bayes Approach to Diagnose Diabetes Type-2 , 2012 .

[3]  Neelam Sharma,et al.  INTRUSION DETECTION USING NAIVE BAYES CLASSIFIER WITH FEATURE REDUCTION , 2012 .

[4]  Yoon-Hwa Choi,et al.  Fault detection of wireless sensor networks , 2008, Comput. Commun..

[5]  Luca Benini,et al.  A discrete-time battery model for high-level power estimation , 2000, DATE '00.

[6]  Arun Somani,et al.  Distributed fault detection of wireless sensor networks , 2006, DIWANS '06.

[7]  Houkuan Huang,et al.  Feature selection for text classification with Naïve Bayes , 2009, Expert Syst. Appl..

[8]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[9]  Rajashekhar C. Biradar,et al.  Fault tolerance in wireless sensor network using hand-off and dynamic power adjustment approach , 2013, J. Netw. Comput. Appl..

[10]  Susan T. Dumais,et al.  A Bayesian Approach to Filtering Junk E-Mail , 1998, AAAI 1998.

[11]  Peng Jiang,et al.  A New Method for Node Fault Detection in Wireless Sensor Networks , 2009, Sensors.

[12]  Mehran Sahami,et al.  Learning Limited Dependence Bayesian Classifiers , 1996, KDD.

[13]  Dimitrios Gunopulos,et al.  Online outlier detection in sensor data using non-parametric models , 2006, VLDB.

[14]  Wei Wei,et al.  Fault-tolerant monitor placement for out-of-band wireless sensor network monitoring , 2012, Ad Hoc Networks.

[15]  Loren Schwiebert,et al.  Distributed Event Detection in Sensor Networks , 2006, 2006 International Conference on Systems and Networks Communications (ICSNC'06).

[16]  Makhlouf Aliouat,et al.  Outlier Detection Approach Using Bayes Classifiers in Wireless Sensor Networks , 2015, Wireless Personal Communications.

[17]  Arunita Jaekel,et al.  Design of fault tolerant wireless sensor networks satisfying survivability and lifetime requirements , 2012, Comput. Commun..

[18]  David E. Culler,et al.  TOSSIM: accurate and scalable simulation of entire TinyOS applications , 2003, SenSys '03.

[19]  Gregory F. Cooper,et al.  A Bayesian Method for the Induction of Probabilistic Networks from Data , 1992 .