自组织映射神经网络用于动态电压稳定分析的新方法

介绍了一种利用人工神经网络(ANN)进行动态电压稳定分析的新方法。这种多层自组织网络(SHNN)综合利用了自组织映射网络(文中使用Kohonen网络)和多层感知机网络（MLP）。Kohonen网络把输入样本按运行条件的相似性进行聚类，从而使MLP网络的性能得到提高。使用2个SHNN模型，一个用于判定电力系统是否处于动态稳定，另一个预测动态稳定系统的PQ节点的电压幅值。通过动态模拟得到训练样本。最后对WSCC 9节点系统和New England 39节点系统进行数字仿真，证明了该方法的有效性。

HYBRID NEURAL NETWORK APPROACH TO DYNAMIC VOLTAGE STABILITY ANALYSIS

An innovative application of artificial neural network (ANN) approach to dynamic voltage stability analysis ispresented. The approach developed is based on a self--organizing hierarchical neural network (SHNN), with hybrid of selforganizing input feature and the multilayer perceptron (MLP) neural network. Two SHNN models are 'utilized in theproposed approach. The first one is used to classify the power system, to determine whether it is dynamically stable orunstable. The second one is used for the dynamically stable system to predict the voltage magnitudes at all Po buses. Thetraining set patterns are generated by carrying out dynamic simulations. using induction motor and constant P--Q load models.The proposed method is demonstrated in dynamic voltage stability determination and bus voltage magnitude estimation atdifferent loading conditions for two test systems: WSCC 9-bus system and New England 39--bus system. The performance ofthe SHNN is tested and found to be effective in application.