改进的TSK型动态模糊神经网络在短期负荷预测中的应用(英文)

将改进的TSK型模糊神经网络(fuzzy neural network,FNN)应用于短期负荷预测。该FNN由椭圆基函数构成神经元的中心和宽度参数,并且具有以下特征:网络结构和参数可自动并同时进行调整,不需提前分割输入空间,也不需提前选择网络初始参数;模糊规则在学习过程中可动态增删,不需采用迭代算法即可快速生成。这种模糊规则可动态增删的模糊神经网络(growing and pruning fuzzy neural network,GPFNN)简单有效,可以降低网络的复杂性,加快网络的学习速度。使用EUNITE竞赛数据作测试数据对上述GPFNN方法进行测试,结果表明采用该方法进行短期负荷预测时可获得较高的准确率。

An Improved TSK-Type Dynamic Fuzzy Neural Network Approach for Short-Term Load Forecasting

In this paper,an improved TSK-Type fuzzy neural network (FNN) is proposed for short-term load forecasting. The FNN is based on ellipsoidal basis function neurons consisting of a center vector and a width vector,and has the following features:structure identification and parameters estimation are performed automatically and simultaneously without partitioning the input space and selecting initial parameters in advance; fuzzy rules can be recruited or deleted dynamically during the learning process,and can be...