基于BP神经网络的无线传感器网络路由协议的研究

Improved Routing Protocol of Wireless Sensor Network Based on the BP Neural Networks

无线传感器网络的资源有限,尤其是节点的能量受限,为了尽可能的减少信息收集与传输过程中的能耗,延长网络的寿命。提出一种基于BP神经网络的路由协议改进算法模型。该算法模型将BP神经网络的层次结构与无线传感器网络路由协议的分簇结构相结合,在每个簇结构中应用设计一个3层的BP神经网络模型,把采集到的大量原始数据通过设计好的神经网络模型,得到能够反映原始数据特征的的少量的数据信息。将融合得到的特征数据传送给汇聚节点可以减少数据信息的传送量,降低信息传送的通信能耗。仿真结果表明:改进后的BPDFA算法较LEACH协议在平衡节点能量和延长网络寿命方面具有更优越的性能。

Due to the limitation of the energy of the nodes and the resource of the wireless sensor network, a routing protocol improved algorithm model based on BP neural network is proposed for saving the energy and prolonging the network lifetime. The algorithm combines the hierarchical structure of BP neural network with the clustering structure of the network routing protocol. In each cluster a three-layer BP neural network model is designed, which processes a large number of raw data collected by the sensors and obtains a few data representing the data information features of raw data. So the transmission amount of data is reduced and the energy is saved. The simulation results show that compared with LEACH, the improved BPDFA algorithm has a better performance in balancing node energy and prolonging the lifetime of the network.