摘要
提出了一种基于自组织特征映射(SOFM)的聚类分析和支持向量机(SVM)的电力系统短期负荷预测方法。该方法首先利用自组织特征映射网络,通过无监督学习策略对训练样本集进行聚类分析,将其分为若干相似子类,再针对每一子类构造一个支持向量机回归模型;使用基于SVM的回归估计算法建立了回归估计函数表达式,给出了基于SOFM和SVM的网络结构;采用河北省某市的实际负荷数据选择样本进行预测。算例表明该方法能够缩短训练时间,提高预测精度。
The load forecasting method based on self-organizing feature map （SOFM） and support vector machine （SVM） was put forward. The proposed method is first based on SOFM that can discover the similar input data and cluster them into several subsets in an unsupervised strategy. Then, several SVR models were constructed in corresponding to the subsets. In this paper, the expression of regression estimation function was established by SVM based regression estimation algorithm and the structure of SVM and SOFM network is given. Adopting the actual data from a certain city in he-bei province, the forecasted results were shown that the presented forecasting method is more accurate.
出处
《电力科学与工程》
2009年第8期27-29,44,共4页
Electric Power Science and Engineering
关键词
自组织特征映射
聚类分析
支持向量机
短期负荷预测
核函数
self-organizing feature map （SOFM）
cluster
support vector machine （SVM）
short-term load forecasting
kernel function
