基于PSO-BP的无线传感器网络数据融合算法研究

发布时间：2018-03-24 19:28

本文选题：数据融合　切入点：无线传感器网络　出处：《计算机测量与控制》2014年04期

【摘要】：为提高无线传感器网络(WSN)数据融合效率,减少网络的通信量以及降低传感网的能量消耗,提出一种基于粒子群优化BP神经网络的无线传感器网络数据融合算法;该算法将粒子群算法优化BP神经网络的权值和阈值后,与传感器网络分簇路由协议有机结合,将无线传感器网络中簇头和节点等同于BP神经网络里的神经元,利用优化后的BP神经网络有效地提取WSN数据融合原始数据之中的少量特征数据,之后把提取的特征数据发送到汇聚节点,进而提升数据融合效率,延长网络生存周期;仿真实验证明,与LEACH算法、BP神经网络和GABP算法相比,该算法可有效减少网络通信量,降低节点总能耗的15%,延长网络生存时间。
[Abstract]:In order to improve the data fusion efficiency of wireless sensor networks (WSNs), reduce the network traffic and reduce the energy consumption of wireless sensor networks, a data fusion algorithm based on particle swarm optimization BP neural network (PSO) for wireless sensor networks (WSN) is proposed. After optimizing the weight and threshold of BP neural network by particle swarm optimization, the algorithm combines with the clustering routing protocol of sensor network, and equates the cluster head and node in wireless sensor network with the neuron in BP neural network. The optimized BP neural network is used to effectively extract a small amount of feature data from the original data of WSN data fusion, and then send the extracted feature data to the convergence node to improve the efficiency of data fusion and prolong the lifetime of the network. The simulation results show that compared with LEACH algorithm and GABP algorithm, the proposed algorithm can effectively reduce the network traffic, reduce the total energy consumption of nodes and prolong the network lifetime.
【作者单位】：河南城建学院计算机科学与工程学院;
【基金】：河南省科技厅基金项目(102102210020)
【分类号】：TP212.9;TN929.5

【参考文献】