Loading…

Short-term PV power prediction based on meteorological similarity days and SSA-BiLSTM

Accurate short-term photovoltaic (PV) power forecasting can reduce the un- certainty of PV power generation, which is crucial for grid operation as well as energy dispatch. Considering the influence of seasonal and meteorological factors on short-term PV power prediction, a short-term PV power predi...

Full description

Saved in:
Bibliographic Details
Published in:Systems and soft computing 2024-12, Vol.6, p.200084, Article 200084
Main Authors: Li, Yikang, Huang, Wei, Lou, Keying, Zhang, Xizheng, Wan, Qin
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c361t-85f111bc13d793b06a534a0ea4ab4428fa0066dc7f66f328e03f232fd225e023
container_end_page
container_issue
container_start_page 200084
container_title Systems and soft computing
container_volume 6
creator Li, Yikang
Huang, Wei
Lou, Keying
Zhang, Xizheng
Wan, Qin
description Accurate short-term photovoltaic (PV) power forecasting can reduce the un- certainty of PV power generation, which is crucial for grid operation as well as energy dispatch. Considering the influence of seasonal and meteorological factors on short-term PV power prediction, a short-term PV power predic- tion method based on meteorological similarity day and sparrow search algo- rithm and bi-directional long and short-term memory network combination (SSA-BiLSTM) is proposed. Firstly, the correlation between meteorological factors and PV power generation is calculated by using Pearson coefficients, getting the strongly correlated meteorological factors affecting PV power generation; afterwards,the historical data of the strongly correlated meteorological factors are clustered by fuzzy C-means clustering to achieve meteorological similar day clustering; then, the best similar day is selected from the meteorological similar day according to the test day seasonal features and meteorological data, and Forming a training set with historical data, and training the original BiLSTM network. the SSA algorithm was used to find the optimal BiLSTM network parameters. Finally, Using the optimal parameters construct BiLSTM network to achieve short-term PV power prediction. The experiments were conducted with historical data from a PV power plant in Xinjiang, and also compared with existing prediction algorithms.The results show that the accuracy of PV power prediction in different weather conditions is 33.1 %, 31.9 % and 24.1 % higher than that under the same intelligent optimization algorithm and different neural networks, the accuracy of PV power prediction in different weather conditions is 27.9 %, 24.7 % and 18.0 % higher than that under the different intelligent algorithms and same neural network. Therefore, the algorithm in this paper has better accuracy in short-term PV power prediction under different seasons and different weather conditions.
doi_str_mv 10.1016/j.sasc.2024.200084
format article
fullrecord <record><control><sourceid>elsevier_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_553699ed053447869da1f26c057135ce</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S2772941924000139</els_id><doaj_id>oai_doaj_org_article_553699ed053447869da1f26c057135ce</doaj_id><sourcerecordid>S2772941924000139</sourcerecordid><originalsourceid>FETCH-LOGICAL-c361t-85f111bc13d793b06a534a0ea4ab4428fa0066dc7f66f328e03f232fd225e023</originalsourceid><addsrcrecordid>eNp9kNtKAzEQhhdRsGhfwKu8wNYcdrO74E0tHgoVhVZvw2wyqSnbpiSL0rc3dUW88mZmGOb_Z-bLsitGJ4wyeb2ZRIh6wikvUqC0Lk6yEa8qnjcFa07_1OfZOMZNGuF1xRsmRtnr8t2HPu8xbMnLG9n7TwxkH9A43Tu_Iy1ENCQVW-zRB9_5tdPQkei2roPg-gMxcIgEdoYsl9P81i2Wq6fL7MxCF3H8ky-y1f3davaYL54f5rPpItdCsj6vS8sYazUTpmpESyWUogCKUEBbFLy2QKmURldWSit4jVRYLrg1nJdIubjI5oOt8bBR--C2EA7Kg1PfDR_WCkLvdIeqLIVsGjQ0bSiqWjYGmOVS07JiotSYvPjgpYOPMaD99WNUHTGrjTpiVkfMasCcRDeDCNOTHw6DitrhTid8AXWfznD_yb8AQXiEQA</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Short-term PV power prediction based on meteorological similarity days and SSA-BiLSTM</title><source>Elsevier ScienceDirect Journals</source><creator>Li, Yikang ; Huang, Wei ; Lou, Keying ; Zhang, Xizheng ; Wan, Qin</creator><creatorcontrib>Li, Yikang ; Huang, Wei ; Lou, Keying ; Zhang, Xizheng ; Wan, Qin</creatorcontrib><description>Accurate short-term photovoltaic (PV) power forecasting can reduce the un- certainty of PV power generation, which is crucial for grid operation as well as energy dispatch. Considering the influence of seasonal and meteorological factors on short-term PV power prediction, a short-term PV power predic- tion method based on meteorological similarity day and sparrow search algo- rithm and bi-directional long and short-term memory network combination (SSA-BiLSTM) is proposed. Firstly, the correlation between meteorological factors and PV power generation is calculated by using Pearson coefficients, getting the strongly correlated meteorological factors affecting PV power generation; afterwards,the historical data of the strongly correlated meteorological factors are clustered by fuzzy C-means clustering to achieve meteorological similar day clustering; then, the best similar day is selected from the meteorological similar day according to the test day seasonal features and meteorological data, and Forming a training set with historical data, and training the original BiLSTM network. the SSA algorithm was used to find the optimal BiLSTM network parameters. Finally, Using the optimal parameters construct BiLSTM network to achieve short-term PV power prediction. The experiments were conducted with historical data from a PV power plant in Xinjiang, and also compared with existing prediction algorithms.The results show that the accuracy of PV power prediction in different weather conditions is 33.1 %, 31.9 % and 24.1 % higher than that under the same intelligent optimization algorithm and different neural networks, the accuracy of PV power prediction in different weather conditions is 27.9 %, 24.7 % and 18.0 % higher than that under the different intelligent algorithms and same neural network. Therefore, the algorithm in this paper has better accuracy in short-term PV power prediction under different seasons and different weather conditions.</description><identifier>ISSN: 2772-9419</identifier><identifier>EISSN: 2772-9419</identifier><identifier>DOI: 10.1016/j.sasc.2024.200084</identifier><language>eng</language><publisher>Elsevier B.V</publisher><subject>Fuzzy C-means clustering ; Seasonal features ; Short-term PV power forecasting ; SSA-BiLSTM</subject><ispartof>Systems and soft computing, 2024-12, Vol.6, p.200084, Article 200084</ispartof><rights>2024</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c361t-85f111bc13d793b06a534a0ea4ab4428fa0066dc7f66f328e03f232fd225e023</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S2772941924000139$$EHTML$$P50$$Gelsevier$$Hfree_for_read</linktohtml><link.rule.ids>314,777,781,3536,27905,27906,45761</link.rule.ids></links><search><creatorcontrib>Li, Yikang</creatorcontrib><creatorcontrib>Huang, Wei</creatorcontrib><creatorcontrib>Lou, Keying</creatorcontrib><creatorcontrib>Zhang, Xizheng</creatorcontrib><creatorcontrib>Wan, Qin</creatorcontrib><title>Short-term PV power prediction based on meteorological similarity days and SSA-BiLSTM</title><title>Systems and soft computing</title><description>Accurate short-term photovoltaic (PV) power forecasting can reduce the un- certainty of PV power generation, which is crucial for grid operation as well as energy dispatch. Considering the influence of seasonal and meteorological factors on short-term PV power prediction, a short-term PV power predic- tion method based on meteorological similarity day and sparrow search algo- rithm and bi-directional long and short-term memory network combination (SSA-BiLSTM) is proposed. Firstly, the correlation between meteorological factors and PV power generation is calculated by using Pearson coefficients, getting the strongly correlated meteorological factors affecting PV power generation; afterwards,the historical data of the strongly correlated meteorological factors are clustered by fuzzy C-means clustering to achieve meteorological similar day clustering; then, the best similar day is selected from the meteorological similar day according to the test day seasonal features and meteorological data, and Forming a training set with historical data, and training the original BiLSTM network. the SSA algorithm was used to find the optimal BiLSTM network parameters. Finally, Using the optimal parameters construct BiLSTM network to achieve short-term PV power prediction. The experiments were conducted with historical data from a PV power plant in Xinjiang, and also compared with existing prediction algorithms.The results show that the accuracy of PV power prediction in different weather conditions is 33.1 %, 31.9 % and 24.1 % higher than that under the same intelligent optimization algorithm and different neural networks, the accuracy of PV power prediction in different weather conditions is 27.9 %, 24.7 % and 18.0 % higher than that under the different intelligent algorithms and same neural network. Therefore, the algorithm in this paper has better accuracy in short-term PV power prediction under different seasons and different weather conditions.</description><subject>Fuzzy C-means clustering</subject><subject>Seasonal features</subject><subject>Short-term PV power forecasting</subject><subject>SSA-BiLSTM</subject><issn>2772-9419</issn><issn>2772-9419</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNp9kNtKAzEQhhdRsGhfwKu8wNYcdrO74E0tHgoVhVZvw2wyqSnbpiSL0rc3dUW88mZmGOb_Z-bLsitGJ4wyeb2ZRIh6wikvUqC0Lk6yEa8qnjcFa07_1OfZOMZNGuF1xRsmRtnr8t2HPu8xbMnLG9n7TwxkH9A43Tu_Iy1ENCQVW-zRB9_5tdPQkei2roPg-gMxcIgEdoYsl9P81i2Wq6fL7MxCF3H8ky-y1f3davaYL54f5rPpItdCsj6vS8sYazUTpmpESyWUogCKUEBbFLy2QKmURldWSit4jVRYLrg1nJdIubjI5oOt8bBR--C2EA7Kg1PfDR_WCkLvdIeqLIVsGjQ0bSiqWjYGmOVS07JiotSYvPjgpYOPMaD99WNUHTGrjTpiVkfMasCcRDeDCNOTHw6DitrhTid8AXWfznD_yb8AQXiEQA</recordid><startdate>202412</startdate><enddate>202412</enddate><creator>Li, Yikang</creator><creator>Huang, Wei</creator><creator>Lou, Keying</creator><creator>Zhang, Xizheng</creator><creator>Wan, Qin</creator><general>Elsevier B.V</general><general>Elsevier</general><scope>6I.</scope><scope>AAFTH</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>DOA</scope></search><sort><creationdate>202412</creationdate><title>Short-term PV power prediction based on meteorological similarity days and SSA-BiLSTM</title><author>Li, Yikang ; Huang, Wei ; Lou, Keying ; Zhang, Xizheng ; Wan, Qin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c361t-85f111bc13d793b06a534a0ea4ab4428fa0066dc7f66f328e03f232fd225e023</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Fuzzy C-means clustering</topic><topic>Seasonal features</topic><topic>Short-term PV power forecasting</topic><topic>SSA-BiLSTM</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Yikang</creatorcontrib><creatorcontrib>Huang, Wei</creatorcontrib><creatorcontrib>Lou, Keying</creatorcontrib><creatorcontrib>Zhang, Xizheng</creatorcontrib><creatorcontrib>Wan, Qin</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><collection>CrossRef</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Systems and soft computing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Yikang</au><au>Huang, Wei</au><au>Lou, Keying</au><au>Zhang, Xizheng</au><au>Wan, Qin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Short-term PV power prediction based on meteorological similarity days and SSA-BiLSTM</atitle><jtitle>Systems and soft computing</jtitle><date>2024-12</date><risdate>2024</risdate><volume>6</volume><spage>200084</spage><pages>200084-</pages><artnum>200084</artnum><issn>2772-9419</issn><eissn>2772-9419</eissn><abstract>Accurate short-term photovoltaic (PV) power forecasting can reduce the un- certainty of PV power generation, which is crucial for grid operation as well as energy dispatch. Considering the influence of seasonal and meteorological factors on short-term PV power prediction, a short-term PV power predic- tion method based on meteorological similarity day and sparrow search algo- rithm and bi-directional long and short-term memory network combination (SSA-BiLSTM) is proposed. Firstly, the correlation between meteorological factors and PV power generation is calculated by using Pearson coefficients, getting the strongly correlated meteorological factors affecting PV power generation; afterwards,the historical data of the strongly correlated meteorological factors are clustered by fuzzy C-means clustering to achieve meteorological similar day clustering; then, the best similar day is selected from the meteorological similar day according to the test day seasonal features and meteorological data, and Forming a training set with historical data, and training the original BiLSTM network. the SSA algorithm was used to find the optimal BiLSTM network parameters. Finally, Using the optimal parameters construct BiLSTM network to achieve short-term PV power prediction. The experiments were conducted with historical data from a PV power plant in Xinjiang, and also compared with existing prediction algorithms.The results show that the accuracy of PV power prediction in different weather conditions is 33.1 %, 31.9 % and 24.1 % higher than that under the same intelligent optimization algorithm and different neural networks, the accuracy of PV power prediction in different weather conditions is 27.9 %, 24.7 % and 18.0 % higher than that under the different intelligent algorithms and same neural network. Therefore, the algorithm in this paper has better accuracy in short-term PV power prediction under different seasons and different weather conditions.</abstract><pub>Elsevier B.V</pub><doi>10.1016/j.sasc.2024.200084</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2772-9419
ispartof Systems and soft computing, 2024-12, Vol.6, p.200084, Article 200084
issn 2772-9419
2772-9419
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_553699ed053447869da1f26c057135ce
source Elsevier ScienceDirect Journals
subjects Fuzzy C-means clustering
Seasonal features
Short-term PV power forecasting
SSA-BiLSTM
title Short-term PV power prediction based on meteorological similarity days and SSA-BiLSTM
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T11%3A19%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-elsevier_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Short-term%20PV%20power%20prediction%20based%20on%20meteorological%20similarity%20days%20and%20SSA-BiLSTM&rft.jtitle=Systems%20and%20soft%20computing&rft.au=Li,%20Yikang&rft.date=2024-12&rft.volume=6&rft.spage=200084&rft.pages=200084-&rft.artnum=200084&rft.issn=2772-9419&rft.eissn=2772-9419&rft_id=info:doi/10.1016/j.sasc.2024.200084&rft_dat=%3Celsevier_doaj_%3ES2772941924000139%3C/elsevier_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c361t-85f111bc13d793b06a534a0ea4ab4428fa0066dc7f66f328e03f232fd225e023%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true