Short Term Photovoltaic Power Combination Prediction Method Based on Similar Day Selection and Data Reconstruction

A short-term photovoltaic power combination prediction method based on similar day selection and data reconstruction is proposed to address the strong randomness of photovoltaic power. Firstly, clustering analysis of photovoltaic power is performed using the kernel fuzzy C-means algorithm, and the m...

Full description

Saved in:
Bibliographic Details
Main Authors: Qingbin CHEN, Genghuang YANG, Liqing GENG, Juan SU, Jingsheng SUN
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2024-12-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202406005
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850070483064586240
author Qingbin CHEN
Genghuang YANG
Liqing GENG
Juan SU
Jingsheng SUN
author_facet Qingbin CHEN
Genghuang YANG
Liqing GENG
Juan SU
Jingsheng SUN
author_sort Qingbin CHEN
collection DOAJ
description A short-term photovoltaic power combination prediction method based on similar day selection and data reconstruction is proposed to address the strong randomness of photovoltaic power. Firstly, clustering analysis of photovoltaic power is performed using the kernel fuzzy C-means algorithm, and the main influencing features are extracted through the maximum information coefficient. Secondly, the cooperative game theory is used to calculate the comprehensive correlation coefficient between the predicted days and the historical days, and the historical days with strong correlation are selected to construct the training set. Then, the variational mode decomposition method is used to decompose the photovoltaic power into several subsequences, and the permutation entropy is calculated and reconstructed into trend, low-frequency, and high-frequency terms. Finally, the long short-term memory neural networks are used to predict the trend and low-frequency items, while the convolutional neural network-bidirectional long short-term memory-attention models are used to predict the high-frequency items. The final prediction result is obtained by overlaying the results. Through practical examples, it has been verified that under different weather conditions, the overall prediction error of the model is the smallest, which can effectively improve the prediction accuracy.
format Article
id doaj-art-2e42f894704c4e03978ecae2f722464d
institution DOAJ
issn 1004-9649
language zho
publishDate 2024-12-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-2e42f894704c4e03978ecae2f722464d2025-08-20T02:47:32ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492024-12-015712718110.11930/j.issn.1004-9649.202406005zgdl-57-12-chenqingbinShort Term Photovoltaic Power Combination Prediction Method Based on Similar Day Selection and Data ReconstructionQingbin CHEN0Genghuang YANG1Liqing GENG2Juan SU3Jingsheng SUN4School of Automation and Electrical Engineering, Tianjin University of Technology and Education, Tianjin 300222, ChinaSchool of Automation and Electrical Engineering, Tianjin University of Technology and Education, Tianjin 300222, ChinaSchool of Automation and Electrical Engineering, Tianjin University of Technology and Education, Tianjin 300222, ChinaCollege of Information and Electrical Engineering, China Agricultural University, Beijing 100083, ChinaState Grid Tianjin Electric Power Company Comprehensive Service Center, Tianjin 300010, ChinaA short-term photovoltaic power combination prediction method based on similar day selection and data reconstruction is proposed to address the strong randomness of photovoltaic power. Firstly, clustering analysis of photovoltaic power is performed using the kernel fuzzy C-means algorithm, and the main influencing features are extracted through the maximum information coefficient. Secondly, the cooperative game theory is used to calculate the comprehensive correlation coefficient between the predicted days and the historical days, and the historical days with strong correlation are selected to construct the training set. Then, the variational mode decomposition method is used to decompose the photovoltaic power into several subsequences, and the permutation entropy is calculated and reconstructed into trend, low-frequency, and high-frequency terms. Finally, the long short-term memory neural networks are used to predict the trend and low-frequency items, while the convolutional neural network-bidirectional long short-term memory-attention models are used to predict the high-frequency items. The final prediction result is obtained by overlaying the results. Through practical examples, it has been verified that under different weather conditions, the overall prediction error of the model is the smallest, which can effectively improve the prediction accuracy.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202406005photovoltaic powersimilar daysvariational mode decompositionbidirectional long short term memory neural networkcombination prediction
spellingShingle Qingbin CHEN
Genghuang YANG
Liqing GENG
Juan SU
Jingsheng SUN
Short Term Photovoltaic Power Combination Prediction Method Based on Similar Day Selection and Data Reconstruction
Zhongguo dianli
photovoltaic power
similar days
variational mode decomposition
bidirectional long short term memory neural network
combination prediction
title Short Term Photovoltaic Power Combination Prediction Method Based on Similar Day Selection and Data Reconstruction
title_full Short Term Photovoltaic Power Combination Prediction Method Based on Similar Day Selection and Data Reconstruction
title_fullStr Short Term Photovoltaic Power Combination Prediction Method Based on Similar Day Selection and Data Reconstruction
title_full_unstemmed Short Term Photovoltaic Power Combination Prediction Method Based on Similar Day Selection and Data Reconstruction
title_short Short Term Photovoltaic Power Combination Prediction Method Based on Similar Day Selection and Data Reconstruction
title_sort short term photovoltaic power combination prediction method based on similar day selection and data reconstruction
topic photovoltaic power
similar days
variational mode decomposition
bidirectional long short term memory neural network
combination prediction
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202406005
work_keys_str_mv AT qingbinchen shorttermphotovoltaicpowercombinationpredictionmethodbasedonsimilardayselectionanddatareconstruction
AT genghuangyang shorttermphotovoltaicpowercombinationpredictionmethodbasedonsimilardayselectionanddatareconstruction
AT liqinggeng shorttermphotovoltaicpowercombinationpredictionmethodbasedonsimilardayselectionanddatareconstruction
AT juansu shorttermphotovoltaicpowercombinationpredictionmethodbasedonsimilardayselectionanddatareconstruction
AT jingshengsun shorttermphotovoltaicpowercombinationpredictionmethodbasedonsimilardayselectionanddatareconstruction