摘要
提出了应用Kohonen神经网络解决电力负荷动态特性的聚类问题:首先对每组负荷扰动数据建模,进而将各负荷模型对相同电压激励的响应与相应的负荷有功运行水平合并形成特征向量,最后引入Kohonen神经网络进行聚类。通过对河北沧州地区1996年、1997年和1998年电力负荷特性数据的聚类与综合处理发现:Kohonen神经网络是一种学习速度快、分类精度高、抗噪声能力强、并且适用于电力负荷动态特性聚类的神经网络模型。同时还发现电力负荷特性具有可重复性,这也证明了总体测辨法的可行性。若将这些典型负荷模型实用化,将有利于提高电力系统仿真准确度。
In this paper, a new method based on Kohonen self-organization neural network is presented for the characteristics clustering of dynamic loads. At first, the model of every group of load disturbance data is established, then the responses of the load models to the same voltage excitation and the pre-disturbance active power of the loads are incorporated into the feature vectors. At last, Kohonen neural network is introduced to cluster. The advantages of this method include: self-learning function, rapid computation and strong type recognition. Many sets of load data measured from North China Power System in three years(1996-1998) have been dealt with using the method. The results show load characteristics have rule though they are random and time-varying. The feasibility of the Measurement-Based Modeling approach is also proved.The use of typical load models will improve the power system simulation veracity.
出处
《中国电机工程学报》
EI
CSCD
北大核心
2003年第5期1-5,43,共6页
Proceedings of the CSEE
