rDFD: reactive distributed fault detection in wireless sensor networks

Abstract

Generally, fault detection approaches pursue high detection accuracy, but neglect energy consumption due to the high volume of messages exchanged. Therefore, in this work we propose a reactive distributed scheme for detecting faulty nodes. The scheme is able to detect transient and permanent faulty nodes accurately by exchanging fewer messages. In existing fault detection schemes, nodes exchange too many messages after every specific interval to detect suspicious node. However, in the proposed scheme comparatively much less messages are exchanged within a limited geographical area around the suspicious node only and that too when the node suspects its own readings. In the proposed scheme, each node exploits the temporal correlation in its own readings to detect any suspicious behavior. In order to confirm its status, the suspicious node communicates with its immediate neighbors who may be locally good or possible faulty with a certain level of confidence. Thus, the scheme utilizes the strength of both spatial and temporal correlation to find faulty nodes. Also, a confidence level is assigned to each correlated neighbor of suspicious node in order to enhance the detection accuracy. The ns-2 based simulation results show that our scheme performs better by reducing communication overhead and by detecting faulty nodes with high accuracy as compared to existing approaches.