Data-driven faulty node detection scheme for Wireless Sensor Networks

In this paper, a faulty node detection scheme with a hybrid algorithm using a Markov chain model that performs collective monitoring of wireless sensor networks is proposed. Mostly wireless sensor networks are large-scale systems, heavily noised, and the system workload is unfairly distributed among the master node and slave nodes. Hence, the master node may not easily detect a faulty slave node. In this paper, a more accurate faulty node detection scheme using a Markov chain model is investigated. Each slave node's condition can be divided into three states by probability calculation: Good-,Warning-, and Bad-state. Using this information, the master node can predicts the area in which an error frequently occurs. Simulation results show that the proposed method can improve the reliability of faulty node detection and the miss detection rate for a Wireless Sensor Networks.