摘要
提出一种交替梯度算法,对径向基函数(RBF)神经网络的训练进行改进.改进的算法与传统梯度下降算法相比,具有更快的收敛速度和更高的预测精度.采用该改进算法应用于电力系统短期负荷预测模型,综合考虑了气象、日类型等影响负荷变化的因素,预测结果表明该算法具有一定实用性.
One kind of alternant gradient algorithm for (RBF) improving the training of Radial Basis Function neural network is proposed. Compared to the traditional gradient drop algorithm, the improvement algorithm has quicker convergence rate and higher forecasting precision. Many influencing factors are considered in this forecasting model such as weather, date-type, and so on. It is showed that the forecasting model has certain usability by means of forecasting results.
出处
《东华大学学报(自然科学版)》
CAS
CSCD
北大核心
2008年第2期204-207,共4页
Journal of Donghua University(Natural Science)
关键词
短期负荷预测
交替梯度算法
径向基函数(RBF)神经网络
电力系统
short-term load forecasting
alternant gradient algorithm
Radial Basis Function (RBF) neural network
electric power system