Photovoltaic Short-Term Output Power Forecast Model Based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise–Kernel Principal Component Analysis–Long Short-Term Memory

To solve the problem of photovoltaic power prediction in areas with large climate changes, this article proposes a hybrid Long Short-Term Memory method to improve the prediction accuracy and noise resistance. It combines the improved complete ensemble empirical mode decomposition with adaptive noise...

Full description

Saved in:
Bibliographic Details
Main Authors: Lan Cao, Haoyu Yang, Chenggong Zhou, Shaochi Wang, Yingang Shen, Binxia Yuan
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/17/24/6365
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850050393269075968
author Lan Cao
Haoyu Yang
Chenggong Zhou
Shaochi Wang
Yingang Shen
Binxia Yuan
author_facet Lan Cao
Haoyu Yang
Chenggong Zhou
Shaochi Wang
Yingang Shen
Binxia Yuan
author_sort Lan Cao
collection DOAJ
description To solve the problem of photovoltaic power prediction in areas with large climate changes, this article proposes a hybrid Long Short-Term Memory method to improve the prediction accuracy and noise resistance. It combines the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and kernel principal component analysis (KPCA) algorithm. The ICEEMDAN algorithm reduces the instability of the environmental factor sequence. The KPCA algorithm reduces the input dimensions of the model. LSTM performs dynamic time modeling of the multivariate feature sequences to predict the output PV power. The adaptability of the ICEEMDAN-KPCA-LSTM model is assessed with datasets from a PV plant in west China and evaluated by root mean squared error (RMSE), mean absolute percentage error (MAPE), and R-squared metrics. Using 70% of the datasets for output PV power estimation, the results show a good performance, with an RMSE of 4.3715, MAPE of 8.9264%, and R-squared value of 89.973%. By comparing with other prediction models, the ICEEMDAN-KPCA-LSTM photovoltaic output power model outperforms other models.
format Article
id doaj-art-8b2ddbcbc0c5495d9d6c450a5a5ced10
institution DOAJ
issn 1996-1073
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-8b2ddbcbc0c5495d9d6c450a5a5ced102025-08-20T02:53:29ZengMDPI AGEnergies1996-10732024-12-011724636510.3390/en17246365Photovoltaic Short-Term Output Power Forecast Model Based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise–Kernel Principal Component Analysis–Long Short-Term MemoryLan Cao0Haoyu Yang1Chenggong Zhou2Shaochi Wang3Yingang Shen4Binxia Yuan5College of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 201306, ChinaCollege of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 201306, ChinaCollege of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 201306, ChinaCollege of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 201306, ChinaCollege of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 201306, ChinaCollege of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 201306, ChinaTo solve the problem of photovoltaic power prediction in areas with large climate changes, this article proposes a hybrid Long Short-Term Memory method to improve the prediction accuracy and noise resistance. It combines the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and kernel principal component analysis (KPCA) algorithm. The ICEEMDAN algorithm reduces the instability of the environmental factor sequence. The KPCA algorithm reduces the input dimensions of the model. LSTM performs dynamic time modeling of the multivariate feature sequences to predict the output PV power. The adaptability of the ICEEMDAN-KPCA-LSTM model is assessed with datasets from a PV plant in west China and evaluated by root mean squared error (RMSE), mean absolute percentage error (MAPE), and R-squared metrics. Using 70% of the datasets for output PV power estimation, the results show a good performance, with an RMSE of 4.3715, MAPE of 8.9264%, and R-squared value of 89.973%. By comparing with other prediction models, the ICEEMDAN-KPCA-LSTM photovoltaic output power model outperforms other models.https://www.mdpi.com/1996-1073/17/24/6365photovoltaic output power predictionshort-term forecastingICEEMDANKPCALSTM
spellingShingle Lan Cao
Haoyu Yang
Chenggong Zhou
Shaochi Wang
Yingang Shen
Binxia Yuan
Photovoltaic Short-Term Output Power Forecast Model Based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise–Kernel Principal Component Analysis–Long Short-Term Memory
Energies
photovoltaic output power prediction
short-term forecasting
ICEEMDAN
KPCA
LSTM
title Photovoltaic Short-Term Output Power Forecast Model Based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise–Kernel Principal Component Analysis–Long Short-Term Memory
title_full Photovoltaic Short-Term Output Power Forecast Model Based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise–Kernel Principal Component Analysis–Long Short-Term Memory
title_fullStr Photovoltaic Short-Term Output Power Forecast Model Based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise–Kernel Principal Component Analysis–Long Short-Term Memory
title_full_unstemmed Photovoltaic Short-Term Output Power Forecast Model Based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise–Kernel Principal Component Analysis–Long Short-Term Memory
title_short Photovoltaic Short-Term Output Power Forecast Model Based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise–Kernel Principal Component Analysis–Long Short-Term Memory
title_sort photovoltaic short term output power forecast model based on improved complete ensemble empirical mode decomposition with adaptive noise kernel principal component analysis long short term memory
topic photovoltaic output power prediction
short-term forecasting
ICEEMDAN
KPCA
LSTM
url https://www.mdpi.com/1996-1073/17/24/6365
work_keys_str_mv AT lancao photovoltaicshorttermoutputpowerforecastmodelbasedonimprovedcompleteensembleempiricalmodedecompositionwithadaptivenoisekernelprincipalcomponentanalysislongshorttermmemory
AT haoyuyang photovoltaicshorttermoutputpowerforecastmodelbasedonimprovedcompleteensembleempiricalmodedecompositionwithadaptivenoisekernelprincipalcomponentanalysislongshorttermmemory
AT chenggongzhou photovoltaicshorttermoutputpowerforecastmodelbasedonimprovedcompleteensembleempiricalmodedecompositionwithadaptivenoisekernelprincipalcomponentanalysislongshorttermmemory
AT shaochiwang photovoltaicshorttermoutputpowerforecastmodelbasedonimprovedcompleteensembleempiricalmodedecompositionwithadaptivenoisekernelprincipalcomponentanalysislongshorttermmemory
AT yingangshen photovoltaicshorttermoutputpowerforecastmodelbasedonimprovedcompleteensembleempiricalmodedecompositionwithadaptivenoisekernelprincipalcomponentanalysislongshorttermmemory
AT binxiayuan photovoltaicshorttermoutputpowerforecastmodelbasedonimprovedcompleteensembleempiricalmodedecompositionwithadaptivenoisekernelprincipalcomponentanalysislongshorttermmemory