| 基于KPCA和BP神经网络的短期负荷预测 |
| |
| 引用本文： | 刘 畅,刘天琪,陈振寰,王福军,何 川,关铁英. 基于KPCA和BP神经网络的短期负荷预测[J]. 电测与仪表, 2016, 53(10): 57-61. DOI: 10.3969/j.issn.1001-1390.2016.10.010 |
| |
| 作者姓名： | 刘 畅 刘天琪 陈振寰 王福军 何 川 关铁英 |
| |
| 作者单位： | 1. 四川大学电气信息学院,成都,610065;2. 国网甘肃省电力公司,兰州,730030 |
| |
| 基金项目： | 多源互补源网协调优化调度理论及方法的研究(5227201350PM) |
| |
| 摘 要： | 为了提高电力系统短期负荷预测的精度,文中提出了一种基于核主成分分析(KPCA)和BP神经网络的负荷预测方法。影响负荷的因素作为神经网络的输入变量,太多输入变量会加大神经网络的训练负担,运用核主成分分析的方法对初始神经网络输入变量进行非线性降维,将降维后的数据作为神经网络新的输入变量,并对神经网络的训练算法进行改进,以加快收敛速度,最后在每一个时刻点上建立模型进行预测。采用文中提出的方法对甘肃某地区2014年的负荷进行预测,并与已有的BP神经网络方法和PCA-BP神经网络方法进行对比,结果表明该方法可提高负荷预测的精度。
|
| 关 键 词： | 电力系统 负荷预测 核主成分分析 神经网络 |
| 收稿时间： | 2015-02-02 |
| 修稿时间： | 2015-04-27 |
Short-Term Power Load Forecasting Based on Kernel Principal Component Analysis and BP Neural Network |
| |
| Liu Chang,Liu Tianqi,Chen Zhenhuan,Wang Fujun,He Chuan and Guan Tieying. Short-Term Power Load Forecasting Based on Kernel Principal Component Analysis and BP Neural Network[J]. Electrical Measurement & Instrumentation, 2016, 53(10): 57-61. DOI: 10.3969/j.issn.1001-1390.2016.10.010 |
| |
| Authors: | Liu Chang Liu Tianqi Chen Zhenhuan Wang Fujun He Chuan Guan Tieying |
| |
| Affiliation: | School of Electrical Engineering and Information,Sichuan University,School of Electrical Engineering and Information,Sichuan University,Gansu Electric Power Corporation,Gansu Electric Power Corporation,School of Electrical Engineering and Information,Sichuan University,Gansu Electric Power Corporation |
| |
| Abstract: | A method for short-term load forecasting based on kernel principal component analysis and BP neural network is proposed .Firstly, original input variables of neural network were got fully considering the load factors. Then, the dimension of original input variables was reduced by Kernel Principal Component Analysis method to get input variables of neural network. Finally, improved training algorithm of neural network was established to predict the load for every moment. Load of a region in Gansu Province in 2014 was forecasted by using the proposed method in the paper. Comparison with other two methods shows that the method in the paper can improve the accuracy of load forecasting. |
| |
| Keywords: | power system load forecasting kernel principal component analysis (KPCA) neural network |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《电测与仪表》浏览原始摘要信息 |
|
点击此处可从《电测与仪表》下载免费的PDF全文 |
|
