Data fusion of heterogeneous network based on BP neural network and improved SEP

Abstract

This paper proposes a data fusion method for Heterogeneous Wireless Sensor Networks (WSN). On the basis of the classic heterogeneous network clustering algorithm Stable Election Protocol(SEP), the intermediate nodes are added to optimize the information transfer within the cluster, and the Back Propagation(BP) neural network is used to fuse the data received from the cluster head into the cluster. The simulation results show that the method can greatly improve the energy consumption of nodes and the lifetime of wireless sensor networks.