摘要
论文提出了一种基于自组织映射(SOM)和支持向量机(SVM)自适应混合算法分两阶段预测短期电力负荷。在第一阶段,用SOM网络以无人监督的方式将输入数据集聚类成若干子集,然后用第二天的负荷曲线的24个SVM的组以监督方式来拟合第二阶段中的每个子集的训练数。所提出的架构对不同数据类型来说具有鲁棒性,并且可以很好地处理负荷序列的非平稳性。该方法能够在常规日和异常日同时自动适应不同的模型。通过训练有素的自适应混合算法,可以直接预测第二天的每小时电力负荷。为了确认其有效性,论文对来自贵阳市国家电网有限公司的历史电量负荷数据进行了训练和测试。
This paper aims to develop a load forecasting method for short-term load forecasting,based on an adaptive two-stage hybrid network with self-organized map(SOM)and support vector machine(SVM).In the first stage,a SOM network is applied to cluster the input data set into several subsets in an unsupervised manner.Then,groups of 24 SVMs for the next day's load profile are used to fit the training data of each subset in the second stage in a supervised way.The proposed structure is robust with different data types and can deal well with the nonstationarity of load series.In particular,the method has the ability to adapt to dif⁃ferent models automatically for the regular days and anomalous days at the same time.With the trained network,it can straightfor⁃wardly predict the next-day hourly electricity load.To confirm the effectiveness,the proposed model has been trained and tested on the data of the historical energy load from Guiyang State Grid Corporation of China.
作者
杨婧
安江
YANG Jing;AN Jiang(Guizhou Power Grid Co.,Ltd.,Guiyang 550000)
出处
《计算机与数字工程》
2020年第11期2569-2577,共9页
Computer & Digital Engineering
关键词
自适应性
负荷预测
非平稳性
自组织映射
支持向量机
adaptiveness
load forecast
nonstationarity
robustness
SOM
support vector machine(SVM)
