Distributed Intermittent Fault Diagnosis in Wireless Sensor Network Using Likelihood Ratio Test

Abstract

In current days, sensor nodes are deployed in hostile environments for various military and commercial applications. Sensor nodes are becoming faulty and having adverse effects in the network if they are not diagnosed and inform the fault status to other nodes. Fault diagnosis is difficult when the nodes behave faulty some times and provide good data at other times. The intermittent disturbances may be random or kind of spikes either in regular or irregular intervals. In literature, the fault diagnosis algorithms are based on statistical methods using repeated testing or machine learning. To avoid more complex and time consuming repeated test processes and computationally complex machine learning methods, we proposed a one shot likelihood ratio test (LRT) here to determine the fault status of the sensor node. The proposed method measures the statistics of the received data over a certain period of time and then compares the likelihood ratio with the threshold value associated with a certain tolerance limit. The simulation results using a real time data set shows that the new method provides better detection accuracy (DA) with minimum false positive rate (FPR) and false alarm rate (FAR) over the modified three sigma test. LRT based hybrid fault diagnosis method detecting the fault status of a sensor node in wireless sensor network (WSN) for real time measured data with 100% DA, 0% FAR and 0% FPR if the probability of the data from faulty node exceeds 25%.INDEX TERMS Wireless sensor network, intermittent fault, likelihood ratio test, fault diagnosis, distributed algorithm.

An energy‐aware software fault detection system based on hierarchical rule approach for enhancing quality of service in internet of things‐enabled wireless sensor network

“…The efficiency of the proposed energy aware HRSFD framework is examined and compared with the existing software fault detection models: DBN, 19 LRT, 18 and CFDDR 21 . In order to confirm whether the comparisons were adequate, all the above models utilized a similar disseminated methodology for recognizing the fault detection of nodes.…”

“…The various fault classification models of the IWSN have been established in recent decades. A detailed review of these models is as follows: In Reference 18, a Likelihood Ratio Test (LRT) model was introduced to classify software faults in IWSN. It estimates the statistics of the sensed information over a period and then compares the attained value with the threshold value.…”

Self-Configuration Management towards Fix-Distributed Byzantine Sensors for Clustering Schemes in Wireless Sensor Networks

“…Where it is noticed that the transfer energy climbs just slightly in the proposed method, energy efficiency reaches 50% of the network's total energy. In contrast, it increased greatly when compared to other algorithms LRT [10] and PAR [11], as shown in Figure 4b. This means that, in the simulated experiment, the proposed technique can maintain a higher node survival rate.…”

“…The suggested approach entails computing the mean and variance of the received data over time and then comparing the probability ratio with a threshold value linked with a specific tolerance limit. As a result, they were able to detect intermittent problems in the nodes with high accuracy, without the need for repetitive testing or computationally intensive machine-learning algorithms [10].…”

“…The research revealed that as the number of participating nodes increased, the amount of messages exchanged in DSFD decreased. When compared to the PAR and LRT approaches, the overall time required to execute the DSFD algorithm decreased with increasing node count, with an average reduction of 0.24 µs [10,11]. By expanding the number of sensors in the network, LRT and PAR increased exchange time/delay.…”