Increasing sensor reliability through confidence attribution

Roberto M. Scheffel,Antônio A. Fröhlich

doi:10.1186/s13173-019-0094-6

Abstract

The reliability of wireless sensor networks (WSN) is getting increasing importance as this kind of networks are becoming the communication base for many cyber-physical systems (CPS). Such systems rely on sensor data correctness to make decisions; therefore, faulty data can lead such systems to take wrong actions. Errors can be originated by sensor’s hardware failures or software bugs and also from the intentional interference of intruders. The gateways that connect such WSN to the Internet are natural intruders’ targets as they usually run conventional operating systems and communication protocols. This work proposes a confidence attribution scheme, based on lightweight predictors running on the sensors. The solution also proposes a parameterizable formula, in order to stamp every value sent by a sensor with a confidence level, calculated upon the values of a subset of correlated sensors. This work also presents an algorithm that can identify a defective sensor into its subset. The use of predictors and confidence attribution are proposed as the basis of a mechanism that increases the WSN resilience against sensor failure or bad data injection by intruders. Several simulations were performed to evaluate the detection efficiency against different types of sensor errors. This work also analyses mechanisms to deal with concept drifts in the WSN lifetime.

Highlights

The advances in the embedded systems technology brought the use of wireless sensor networks (WSN) to a variety of application fields
The results show that for some sensors the error detection rate (EDR) is significantly lower than the compared technique
Models comparing readings variations of each sensor and comparing them to the variations in other sensors must be built, mixing statistical analysis and predictions results. These ensembles can use some voting mechanism, for example, to decide if a concept drift has occurred. Another solution is use the outputs of all the different detection mechanisms and build and train a classifier to verify if the data streams should be considered errors or concept drifts

Summary

Introduction

The advances in the embedded systems technology brought the use of WSN to a variety of application fields. The objective of the local confidence determination of the sensor read value proposed in this work has as objective to avoid extra messages exchange between the neighbor nodes to verify faults and identify their origin. Each sensor listens to the data transmitted by other nodes and uses the model to predict its value.

Results

Conclusion