Short-term Power Prediction of Photovoltaic Power Generation Based on LSTM and Error Correction

In order to improve the stability of photovoltaic power grid connection and make full use of error information to correct the model prediction results, this paper proposes a short-term photovoltaic power prediction model based on long short-term memory (LSTM) and error correction. First, the data is...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHU Tao, LI Junwei, ZHU Yuanfu, YE Zhiming, TANG Yi
Format: Article
Language:zho
Published: Harbin University of Science and Technology Publications 2025-04-01
Series:Journal of Harbin University of Science and Technology
Subjects:
Online Access:https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2420
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849427063229906944
author ZHU Tao
LI Junwei
ZHU Yuanfu
YE Zhiming
TANG Yi
author_facet ZHU Tao
LI Junwei
ZHU Yuanfu
YE Zhiming
TANG Yi
author_sort ZHU Tao
collection DOAJ
description In order to improve the stability of photovoltaic power grid connection and make full use of error information to correct the model prediction results, this paper proposes a short-term photovoltaic power prediction model based on long short-term memory (LSTM) and error correction. First, the data is preliminarily predicted by LSTM to generate an error sequence, and then the error sequence is decomposed into submodels of different frequencies by empirical mode decomposition (EMD). Similarity measurement is conducted according to Hausdorff distance ( HD), and each modal component is assigned weights, and then LSTM optimized by Sparrow Search Algorithm ( SSA) is used to predict error modal components. The weighted prediction error is combined with the predicted value to achieve error correction. Through experiments, it has been proven that the model proposed in this article outperforms traditional LSTM models, BP models, and SVM models in evaluation indicators such as root mean square error (RMSE) and mean absolute percentage error (MAPE), verifying the effectiveness of the combined model.
format Article
id doaj-art-34aa3ee8e68946bab5ca4b8a6cff5f2b
institution Kabale University
issn 1007-2683
language zho
publishDate 2025-04-01
publisher Harbin University of Science and Technology Publications
record_format Article
series Journal of Harbin University of Science and Technology
spelling doaj-art-34aa3ee8e68946bab5ca4b8a6cff5f2b2025-08-20T03:29:09ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832025-04-01300212213010.15938/j.jhust.2025.02.013Short-term Power Prediction of Photovoltaic Power Generation Based on LSTM and Error CorrectionZHU Tao0LI Junwei1ZHU Yuanfu2YE Zhiming3TANG Yi4Kunming Power Supply Bureau of Yunnan Power Grid Co. , Ltd. , Kunming 650011, ChinaKunming Power Supply Bureau of Yunnan Power Grid Co. , Ltd. , Kunming 650011, ChinaKunming Power Supply Bureau of Yunnan Power Grid Co. , Ltd. , Kunming 650011, ChinaKunming Power Supply Bureau of Yunnan Power Grid Co. , Ltd. , Kunming 650011, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 210092, China; Nanjing Dongbo Smart Energy Research Institute Co. , Ltd. , Nanjing 210004, ChinaIn order to improve the stability of photovoltaic power grid connection and make full use of error information to correct the model prediction results, this paper proposes a short-term photovoltaic power prediction model based on long short-term memory (LSTM) and error correction. First, the data is preliminarily predicted by LSTM to generate an error sequence, and then the error sequence is decomposed into submodels of different frequencies by empirical mode decomposition (EMD). Similarity measurement is conducted according to Hausdorff distance ( HD), and each modal component is assigned weights, and then LSTM optimized by Sparrow Search Algorithm ( SSA) is used to predict error modal components. The weighted prediction error is combined with the predicted value to achieve error correction. Through experiments, it has been proven that the model proposed in this article outperforms traditional LSTM models, BP models, and SVM models in evaluation indicators such as root mean square error (RMSE) and mean absolute percentage error (MAPE), verifying the effectiveness of the combined model.https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2420photovoltaic power generationerror correctionoptimization algorithmempirical mode decompositionpower prediction
spellingShingle ZHU Tao
LI Junwei
ZHU Yuanfu
YE Zhiming
TANG Yi
Short-term Power Prediction of Photovoltaic Power Generation Based on LSTM and Error Correction
Journal of Harbin University of Science and Technology
photovoltaic power generation
error correction
optimization algorithm
empirical mode decomposition
power prediction
title Short-term Power Prediction of Photovoltaic Power Generation Based on LSTM and Error Correction
title_full Short-term Power Prediction of Photovoltaic Power Generation Based on LSTM and Error Correction
title_fullStr Short-term Power Prediction of Photovoltaic Power Generation Based on LSTM and Error Correction
title_full_unstemmed Short-term Power Prediction of Photovoltaic Power Generation Based on LSTM and Error Correction
title_short Short-term Power Prediction of Photovoltaic Power Generation Based on LSTM and Error Correction
title_sort short term power prediction of photovoltaic power generation based on lstm and error correction
topic photovoltaic power generation
error correction
optimization algorithm
empirical mode decomposition
power prediction
url https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2420
work_keys_str_mv AT zhutao shorttermpowerpredictionofphotovoltaicpowergenerationbasedonlstmanderrorcorrection
AT lijunwei shorttermpowerpredictionofphotovoltaicpowergenerationbasedonlstmanderrorcorrection
AT zhuyuanfu shorttermpowerpredictionofphotovoltaicpowergenerationbasedonlstmanderrorcorrection
AT yezhiming shorttermpowerpredictionofphotovoltaicpowergenerationbasedonlstmanderrorcorrection
AT tangyi shorttermpowerpredictionofphotovoltaicpowergenerationbasedonlstmanderrorcorrection