摘要
提出了一种免疫聚类径向基函数神经网络(ICRBFNN)模型来预测电力系统短期负荷。在ICRBFNN的设计中,根据共生进化和免疫规划原理,提出了共生进化免疫规划聚类算法,该算法可以自动确定RBF网络隐层中心的数量和位置,并采用递推最小二乘法确定网络输出层的权值。对华东某市进行的电力系统短期负荷预测表明,与传统的径向基函数神经网络(RBFNN)预测方法相比,ICRBFNN方法具有更高的预测精度和更短的训练时间。
The paper presents an immune clustering RBF neural network（ICRBFNN） model for short-term load forecasting. In the design of the ICRBFNN, a novel clustering method based on the symbiotic evolutionary and the immune programming algorithm（SEIPCM） is proposed. The SEIPCM automatically adjust the number and positions of hidden layer RBF centers. The weights of output layer are decided by the recursive least squares algorithm. The proposed ICRBFNN model has been implemented based on the actual data collected from the East China Power Company and compared with the traditional RBF neural network（RBFNN） method. The test results reveal that the ICRBFNN method possesses far superior forecast precision and require less constructing time than the RB FNN method,
出处
《中国电机工程学报》
EI
CSCD
北大核心
2005年第16期53-56,共4页
Proceedings of the CSEE
关键词
电力系统
短期负荷预测
RBF神经网络
免疫算法
聚类分析
Power system
Short-term load forecasting
RBF neural network
Immune method
Clustering analyse
