Expert Systems With Applications 45 (2016) 307–321
Contents lists available at ScienceDirect
Expert Systems With Applications
journal homepage: www.elsevier.com/locate/eswa
Fuzzy rule-based faulty node classification and management scheme for
large scale wireless sensor networks
Prasenjit Chanak
*
, Indrajit Banerjee
Department of Information Technology, Indian Institute of Engineering Science and Technology (IIEST), Shibpur, Howrah 711103, West Bengal, India
article info
Key words:
Wireless sensor networks (WSNs)
Fault detection
Fuzzy logic
Energy efficiency
Faulty nodes reusability
abstract
In a wireless sensor network (WSNs), probability of node failure rises with increase in number of sensor
nodes within the network. The, quality of service (QoS) of WSNs is highly affected by the faulty sensor nodes.
If faulty sensor nodes can be detected and reused for network operation, QoS of WSNs can be improved and
will be sustainable throughout the monitoring period. The faulty nodes in the deployed WSN are crucial to
detect due to its improvisational nature and invisibility of internal running status. Furthermore, most of the
traditional fault detection methods in WSNs do not consider the uncertainties that are inherited in the WSN
environment during the fault diagnosis period. Resulting traditional fault detection methods suffer from low
detection accuracy and poor performance. To address these issues, we propose a fuzzy rule-based faulty node
classification and management scheme for WSNs that can detect and reuse faulty sensor nodes according to
their fault status. In order to overcome uncertainties that are inherited in the WSN environment, a fuzzy
logic based method is utilized. Fuzzy interface engine categorizes different nodes according to the chosen
membership function and the defuzzifier generates a non-fuzzy control to retrieve the various types of nodes.
In addition, we employed a routing scheme that reuses the retrieved faulty nodes during the data routing
process. We performed extensive experiments on the proposed scheme using various network scenarios.
The experimental results are compared with the existing algorithms to demonstrate the effectiveness of the
proposed algorithm in terms of various important performance metrics.
© 2015 Elsevier Ltd. All rights reserved.
1. Introduction
Wireless sensor network (WSN) is a collection of thousands of
low-cost, low power electronically programmable devices, which are
deployed in a monitoring area in stochastic manner. Due to rapid
growth in Micro-Electro-Mechanical System (MEMS) and Very Large-
Scale Integrated (VLSI) circuit it is possible to fabricate the portable
smart sensor nodes at low cost with better accuracy that makes WSN
an attractive solution for a plethora of applications such as mili-
tary tracking, fire monitoring, clinical monitoring and many more
(Collotta, Bello, & Pau, 2015; Heinzelman, Chandrakasan, & Balakr-
ishnan, 2002; Kosar, Bojaxhiu, Onur, & Ersoy, 2011). Hence, in such
applications, a large number of sensor nodes are deployed in the tar-
get field to improve the Quality of Service (QoS) of the network (Attea,
& Khalil, 2012; Geeta, Nalini,& Biradar, 2013; Jain & Reddy, 2015). In
such WSNs, several deployed sensor nodes suffer from hardware and
software faults due to the environmental hazards like heavy rainfall,
*
Corresponding author. Tel.: +91 9874040413, +91 33 2668 4561 63; fax: +91 33
2668 9313.
E-mail addresses: prasenjit.chanak@gmail.com, pchanak.besu@gmail.com (P.
Chanak), ibanerjee@it.iiests.ac.in (I. Banerjee).
flood, heavy wind, fire, and so on (Chen, Kher, & Somani, 2006; Lee
& Choi, 2008). The probability of sensor node failure increases with
increase in number of deployed sensor nodes within the network.
Faulty nodes are unable to transmit data to the Base Station (BS) or
may transmit erroneous data. Hence, faulty sensor nodes can poten-
tially degrade the functionality of WSNs, it is desirable to detect and
locate these faulty nodes within the network. Existing fault detection
approaches suffer from high energy overhead and poor performance
that create an urgency to propose a fault detection and management
scheme for WSNs.
In WSNs, node faults are broadly classified into two groups, viz.
software fault and hardware fault. In software fault, the system
software of a node executes erroneously (Chessa, & Santi, 2001;
Jing, & Weo, 2011). However, in hardware fault, different hardware
components of a node are damaged and hence transmitted data
packet cannot be reached to the destination node or BS. Hardware
faulty nodes can be classified into five categories, viz. transmitter
circuit fault, receiver circuit fault, microcontroller fault, sensor cir-
cuit fault, and power/battery fault (Banerjee, Chanak, Rahaman, &
Samanta, 2014). Existing fault detection approaches are unable to
control the proliferation of faulty node with increase in network
lifetime (Ding, Chen, Xing, & Cheng, 2005). They only detect faulty
sensor nodes on the basis of hypothetical test results and exclude
http://dx.doi.org/10.1016/j.eswa.2015.09.040
0957-4174/© 2015 Elsevier Ltd. All rights reserved.