Data Aggregation of Wireless Sensor Network Based on Event-Driven and Neural Network
Xi Hou · Chuangan jishu xuebao · 2014
To reduce energy consumption and data redundancy of wireless sensor network( WSN) emergency monitoring,a data fusion algorithm EBPDF( Event-Driven Back-Propagation Data Fusion Algorithm) based on event-driven dynamic clustering scheme and BP neural network is proposed. Dynamic clusters as well as cluster head election process is based on the severity of the incident and the node residual energy. The life cycle and coverage of the cluster are adjusted dynamically according to the urgency of the event and the node residual energy. Meanwhile the hierarchy of the neural network is combined with the cluster structure of WSN in order to reduce the network traffic. The threelayer neural network model is applied in the dynamic cluster structure,so a few eigenvalues which is sent to the sink node can be extracted from the raw data collected by the neural network algorithm. The method prolongs the network life cycle,reduces the redundancy of data transmission. The simulation experiments show that,compared with LEACH algorithm,EBPDF can reduce network traffic and the number of node communication effectively.