神经网络在网络丢包预测中的应用

摘要

通过在网络控制系统中加入BP神经网络从而达到对网络丢包进行预测的目的,为进一步的丢包补偿做足准备.利用粒子群算法优化BP神经网络预测器.仿真结果表明：与BP神经网络相比,PSO-BP神经网络具有更好的网络丢包预测性能.%The purpose of the research is mainly to predict the packet loss through joining BP neural network on NCS, to prepare for the compensation of packet loss, and to use particle swarm algorithm to optimize the BP neural network predictor. The simulation results show that, compared with the BP neural network, PSO - BP neural network has better network packet loss prediction performance.