###
Journal of ShangHai University of Electric Power :2015,31(6):511-513,524
View/Add Comment     Archive    Advanced search     HTML
←Previous   |   Next
基于支持向量机的光伏发电功率预测
(上海电力学院电气工程学院)
Photovoltaic Power Prediction Based on Support Vector Machine
(School of Electrical Engineering, Shanghai University of Electric Power, Shanghai 200090, China)
Abstract
Image-text
References
Similar literature
本文已被:浏览 1556次   下载 1128
Received:October 15, 2014    
中文摘要: 分析了光伏系统的发电特性以及影响光伏发电的因素,建立了基于支持向量机的光伏系统发电功率预测模型.该模型以结构风险最小化原则取代了传统机器学习方法中的经验风险最小化原则,在小样本的机器学习中有着优异的性能.用某一天的数据作为训练样本集,首先对数据进行去噪和归一化,然后用支持向量机方法对样本集进行训练和发电功率预测.仿真结果表明,基于支持向量机的预测模型具有较高的精度,可用于光伏发电系统的预测.
中文关键词: 光伏发电  功率预测  支持向量机
Abstract:The prediction method is put forward based on Support Vector Machine (SVM). SVM is a novel machine learning approach, based on the principle of structural risk minimization, which is unlike other traditional machine learning approach based on empirical risk minimization principle. SVM can perform well in Machine Learning with small sample. A kind of SVM for the prediction and simulation of the voltage of the maximum power output is presented, which takes the data of a certain day as the training sample set to be trained by SVM and the trained model will subsequently be used for prediction of power. Simulation results show that the SVM method can well predict the power point, which therefore can serve for prediction of photovoltaic power generation systems.
文章编号:20150602     中图分类号:    文献标志码:
基金项目:上海绿色能源并网工程技术研究中心资助项目(13DZ2251900).
Reference text:


###
DOI:
Journal of ShangHai University of Electric Power :2015,(6):-
View/Comment     Archive    Advanced search     HTML
←Previous   |   Next→
Abstract
Image-text
References
Similar literature
本文已被:浏览次   下载
    
中文摘要:
中文关键词:
Abstract:
keywords:
文章编号:20150602     中图分类号:    文献标志码:
基金项目:
Reference text: