Fault Prediction Method for Wireless Sensor Network Based on Evidential Reasoning and Belief-Rule-Base

Wei He, Chuan-Qiang Yu, Guo-Hui Zhou, Zhi-Jie Zhou, Guan-Yu Hu
2019 IEEE Access  
Wireless sensor network (WSN) is a distributed intelligent network, which can independently achieve the information collection task of monitoring targets. However, the WSN is susceptible to faults due to various factors, such as sensor resources, network bandwidth, and work environment. The WSN fault prediction technology can estimate the fault trend of the WSN, which can provide the basis for the formulation and implementation of emergency strategies. In this paper, a new WSN fault prediction
more » ... ethod is proposed based on evidential reasoning (ER) and belief rule base (BRB). First, the process of the WSN fault prediction is described, which mainly includes the fault assessment of the current WSN and the fault prediction of future WSN. Second, the WSN fault prediction model is constructed, including the ER-based fault assessment model and BRB-based fault prediction model. The projection covariance matrix adaptation evolutionary strategies (P-CMA-ESs) are used to optimize model parameters. Finally, a case study is constructed to verify the validity of the WSN fault prediction model. The experimental results show that the model can adequately estimate the fault state of the current WSN and then predict the fault status of future WSN. INDEX TERMS Fault prediction, belief rule base (BRB), fault assessment, evidential reasoning (ER) wireless sensor network (WSN). 78930 2169-3536
doi:10.1109/access.2019.2922677 fatcat:4p6ugdjjmbfhbf6wap5cgbqd2i