在电力通信预警中优化的BP神经网络模型研究

阐述了当前电力通信预警中存在的问题和常用算法,针对在电力通信预警中,BP神经网络模型存在易陷入最小值、收敛速度慢的问题,提出了一种应用遗传算法对BP神经网络模型的初始权值和阈值进行优化的方法。选取52节点典型电力通信预警模型,分别对传统BP神经网络模型和遗传算法优化网络模型进行仿真试验。经过遗传算法优化的BP神经网络模型收敛速度快、拟合精度高,能够有效提高电力通信预警的反应速度和响应准确度。

Research on Optimized BP Neural Network Model on Power-System Communication Waring

It illustrates the current algorithms and problems of power communication warning.Aiming at the problem of BP neural network easily getting stuck in a local minimum and having a slow convergence rate on power communication warning,it proposes a method using genetic algorithm to optimize the initial weights and threshold values of the BP neural network.It selects a typical power communication warning model to experiment.It simulates and trains the traditional BP neural network and GA-BP neural network respectively.The GA-BP neural network has a faster convergence speed and a higher precision,which can efficiently improve the reaction speed and can respond the evaluation of the power communication warning system.