基于遗传RBF神经网络的无线传感器网络流量预测方法

Network Flow Prediction Method of Wireless Sensor Based on Genetic-RBF Neural Network

提出了基于遗传RBF神经网络的无线传感器网络流量预测方法.在这里,RBF神经网络有6个输入节点,8个隐藏节点和1个输出节点.RBF神经网络的训练参数对RBF神经网络的预测能力有一定的影响,应该选择一个优化的方法来选择合适的参数.实验结果表明,无线传感器网络流量的预测结果优于RBF神经网络和BP神经网络.

Network flow prediction method of wireless sensor based on genetic - RBF neural network is proposed in this paper. Here, RBF neural network with 6 input nodes, 8 hidden nodes and 1 output node is used. The training parameters of RBF neural network have a certain influence on the prediction ability of RBF neural network, an optimization method to select the appropriate parameter of RBF neural network are selected. Genetic algorithm is a robust and efficient optimization technique. As genetic algorithm has the higher global optimal ability than the traditional optimization methods, genetic algorithm is applied to select the appropriate parameter of RBF neural network. The experimental results show that network flow prediction results of wireless sensor are better than RBF neural network and BP neural network.