[1]彭 飞,张健男,张晓华,等.基于初始化非负矩阵分解的光伏发电预测[J].计算机技术与发展,2021,31(02):185-190.[doi:10. 3969 / j. issn. 1673-629X. 2021. 02. 034]
　PENG Fei,ZHANG Jian-nan,ZHANG Xiao-hua,et al.Prediction of Photovoltaic Power Generation Based on Initialized Non-negative Matrix Factorization[J].,2021,31(02):185-190.[doi:10. 3969 / j. issn. 1673-629X. 2021. 02. 034]
点击复制

基于初始化非负矩阵分解的光伏发电预测()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年02期
页码:
185-190
栏目:
应用前沿与综合
出版日期:
2021-02-10

文章信息/Info

Title:
Prediction of Photovoltaic Power Generation Based on Initialized Non-negative Matrix Factorization
文章编号:
1673-629X(2021)02-0185-06
作者:
彭 飞1 ; 张健男1 ; 张晓华1 ; 王汉军2 ; 吴 奕2 ; 陈志奎3
1. 国家电网公司 东北分部,辽宁 沈阳 110180;?
2. 中国科学院 沈阳计算技术研究所有限公司,辽宁 沈阳 110180;?
3. 大连理工大学 软件学院,辽宁 大连 116620
Author(s):
PENG Fei 1 ; ZHANG Jian-nan 1 ; ZHANG Xiao-hua 1 ; WANG Han-jun 2 ; WU Yi 2 ; CHEN Zhi-kui3
1. Department of Northeast Branch of State Grid Corporation,Shenyang 110180,China;?
2. Shenyang Institute of Computing Technology,Chinese Academy of Sciences,Shenyang 110180,China;?
3. School of Software Technology,Dalian University of Technology,Dalian 116620,China)
关键词:
光伏发电; 精准预测; 初始化; 非负矩阵分解算法; 模糊 C 均值聚类算法
Keywords:
photovoltaic power generation; accurate prediction; initialization; NMF; FCM
分类号:
TP39
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 02. 034
文献标志码:
A
摘要:
光伏发电作为一种可再生能源发电技术,使用规模日益扩大,光伏发电的精准预测已成为数据挖掘的重要研究领 域,但是光伏发电本身的随机性和不确定性使得现有的预测功率难以达到理想的高度,对电网运行的稳定性造成了不利 的影响。 为了探索预测日的发电功率、历史日的发电功率以及气象数据等相关因素之间的关系,解决光伏发电难以准确 预测的问题,提出了基于初始化非负矩阵分解的光伏发电预测方法,将影响光伏发电的因素建立关联关系,根据模糊 C 均 值聚类算法为预测模型的构建提供较好的初值。 将此模型应用到真实数据集上,分别对两种天气情况进行了从早上 7 点 到晚上 6 点 15 分,46 个采样点的预测。 通过与基本的非负矩阵分解等算法进行对比实验,表明该模型能够有效提高光伏 发电预测精准度。
Abstract:
As a renewable energy power generation technology, photovoltaic power generation is increasingly used. The accurate prediction? of photovoltaic power generation has become an important research area for data mining. However, the randomness and uncert-ainty of photovoltaic power generation makes it difficult for the current predicted power to reach the desired height,which adversely affects the stability of grid operation. In order to explore the relationship between the forecasted generation power and historical generation power,meteorological data and other related factors and to solve the problem that photovoltaic power generation is difficult to accurately predict,a photovoltaic power generation prediction method based on non-negative matrix factorization (NMF) is proposed. This algorithm not only establishes the relationship between the factors affecting photovoltaic power generation,but also provides a better initial value for the construction of the prediction model based on the fuzzy C-means (FCM). Applying this model to a real data set,the two weather conditions were predicted from 7 am to 6:15 pm for 46 sample points. The comparison experiments with the basic NMF models show that the model can effectively improve the accuracy of photovoltaic power generation prediction.

相似文献/References:

[1]李香云,任 帅,张卫钢,等.基于高斯过程回归的公交到站预测方法[J].计算机技术与发展,2019,29(10):21.[doi:10. 3969 / j. issn. 1673-629X. 2019. 10. 005]
　LI Xiang-yun,REN Shuai,ZHANG Wei-gang,et al.A Bus-to-station Prediction Method Based on Gaussian Process Regression[J].,2019,29(02):21.[doi:10. 3969 / j. issn. 1673-629X. 2019. 10. 005]
[2]张 洁,郝倩男.基于烟花算法优化 BP 神经网络的光伏功率预测[J].计算机技术与发展,2021,31(10):146.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 025]
　ZHANG Jie,HAO Qian-nan.Forecast of Photovoltaic Power Generation Based on Firework Algorithm Optimized BP Neural Network[J].,2021,31(02):146.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 025]

更新日期/Last Update: 2020-02-10