无线传感器网络中基于神经网络的数据融合模型

Neural-network Based Aggregation Framework for Wireless Sensor Networks

数据融合技术通过减少传感器节点间的数据通信量,可以有效地节省传感器节点能耗,延长无线传感器网络的寿命。提出了独特的基于神经网络的数据融合模型(NNBA),该模型巧妙地将无线传感器网络的分簇层次结构与神经网络的层次结构相结合,将每个簇设计为一个三层感知器神经网络模型,通过神经网络方法从采集到的大量原始数据中提取特征数据,然后将特征数据发送给汇聚节点。以森林火灾实时监测网为应用实例,设计神经元模型及功能函数,并给出NNBA模型的仿真测试结果。

Data aggregation is an efficient way to save energy and to prolong lifetime of network in wireless sensor networks. Proposed NNBA, a data aggregation framework for clustered wireless sensor networks. NNBA poses a three-layer MLP for data aggregation in the clustered sensor network. And the input layer neuron and the first layer neuron are located in every cluster member, while the second layer neuron and the output layer neuron are located in every cluster head. In each neuron, various nonlinear functions can be applied according the requirements of the application. The re- sults of simulation showed that NNBA is useful and practicable for data aggregation in clustered sensor networks.