Loading…

Transformers-Based Encoder Model for Forecasting Hourly Power Output of Transparent Photovoltaic Module Systems

Solar power generation is usually affected by different meteorological factors, such as solar radiation, cloud cover, rainfall, and temperature. This variability has shown a negative impact on the large-scale integration of solar energy into energy supply systems. For successful integration of solar...

Full description

Saved in:
Bibliographic Details
Published in:Energies (Basel) 2023-01, Vol.16 (3), p.1353
Main Authors: Sherozbek, Jumaboev, Park, Jaewoo, Akhtar, Mohammad Shaheer, Yang, O-Bong
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c400t-33facf0a44e8227e949c3f2b31476e1acdaa5f1c7a388d557c751adc256d66223
cites cdi_FETCH-LOGICAL-c400t-33facf0a44e8227e949c3f2b31476e1acdaa5f1c7a388d557c751adc256d66223
container_end_page
container_issue 3
container_start_page 1353
container_title Energies (Basel)
container_volume 16
creator Sherozbek, Jumaboev
Park, Jaewoo
Akhtar, Mohammad Shaheer
Yang, O-Bong
description Solar power generation is usually affected by different meteorological factors, such as solar radiation, cloud cover, rainfall, and temperature. This variability has shown a negative impact on the large-scale integration of solar energy into energy supply systems. For successful integration of solar energy into the electrical grid, it is necessary to predict the accurate power generation by solar panels. In this work, solar power generation forecasting for two types of solar system (non-transparent and transparent panels) was configured by the smart artificial intelligence (AI) modelling. For deep learning models, the dataset obtained from the target value of electricity generation in kWh and other features, such as weather conditions, solar radiance, and insolation. In PV power generation values from non-transparent and transparent solar panels were collected from 1 January to 31 December 2021 with an hourly interval. To prove the efficiency of the proposed model, several deep learning approaches RNN models, such as LSTM, GRU, and transformers models, were implemented. Transformers model for forecasting power generation expressed the best model for non-transparent and transparent solar panels with lower error rates for MAE 0.05 and 0.04, and RMSE 0.24 and 0.21, respectively. The proposed model showed efficient performance and proved effective in forecasting time-series data.
doi_str_mv 10.3390/en16031353
format article
fullrecord <record><control><sourceid>gale_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_d13ca2caf121448493807eb96a18f610</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A743141343</galeid><doaj_id>oai_doaj_org_article_d13ca2caf121448493807eb96a18f610</doaj_id><sourcerecordid>A743141343</sourcerecordid><originalsourceid>FETCH-LOGICAL-c400t-33facf0a44e8227e949c3f2b31476e1acdaa5f1c7a388d557c751adc256d66223</originalsourceid><addsrcrecordid>eNpNkVFLHDEQx5dSoaK-9BME-lZYm2SSze6jFa2CoqA-hzGZXPfY21yTbOW-faNXWhPIDDP_-TGZaZrPgp8CDPwbzaLjIEDDh-ZQDEPXCm7g4zv_U3OS85rXA1UHcNjEx4RzDjFtKOX2O2by7GJ20VNit_WdWM2xy5jIYS7jvGJXcUnTjt3Hlyq5W8p2KSwG9sbZYqK5sPufscTfcSo4ulfKMhF72OVCm3zcHAScMp38tUfN0-XF4_lVe3P34_r87KZ1ivPSAgR0gaNS1EtpaFCDgyCfQSjTkUDnEXUQziD0vdfaOKMFeid157tOSjhqrvdcH3Ftt2ncYNrZiKN9C8S0spjK6CayXoBD6TAIKZTq1QA9N_Q8dCj60AleWV_2rG2KvxbKxa7rDObavpXGqH6QWuuqOt2rVlih4xxiSejq9bQZXZwpjDV-ZlT9gwAFteDrvsClmHOi8K9Nwe3rQu3_hcIfG-OSnA</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2774892555</pqid></control><display><type>article</type><title>Transformers-Based Encoder Model for Forecasting Hourly Power Output of Transparent Photovoltaic Module Systems</title><source>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</source><creator>Sherozbek, Jumaboev ; Park, Jaewoo ; Akhtar, Mohammad Shaheer ; Yang, O-Bong</creator><creatorcontrib>Sherozbek, Jumaboev ; Park, Jaewoo ; Akhtar, Mohammad Shaheer ; Yang, O-Bong</creatorcontrib><description>Solar power generation is usually affected by different meteorological factors, such as solar radiation, cloud cover, rainfall, and temperature. This variability has shown a negative impact on the large-scale integration of solar energy into energy supply systems. For successful integration of solar energy into the electrical grid, it is necessary to predict the accurate power generation by solar panels. In this work, solar power generation forecasting for two types of solar system (non-transparent and transparent panels) was configured by the smart artificial intelligence (AI) modelling. For deep learning models, the dataset obtained from the target value of electricity generation in kWh and other features, such as weather conditions, solar radiance, and insolation. In PV power generation values from non-transparent and transparent solar panels were collected from 1 January to 31 December 2021 with an hourly interval. To prove the efficiency of the proposed model, several deep learning approaches RNN models, such as LSTM, GRU, and transformers models, were implemented. Transformers model for forecasting power generation expressed the best model for non-transparent and transparent solar panels with lower error rates for MAE 0.05 and 0.04, and RMSE 0.24 and 0.21, respectively. The proposed model showed efficient performance and proved effective in forecasting time-series data.</description><identifier>ISSN: 1996-1073</identifier><identifier>EISSN: 1996-1073</identifier><identifier>DOI: 10.3390/en16031353</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Algorithms ; Alternative energy sources ; Artificial intelligence ; Cloud cover ; Deep learning ; Electric power grids ; Energy efficiency ; energy forecasting ; Energy resources ; Forecasting ; GRU ; Humidity ; LSTM ; Machine learning ; Neural networks ; Photovoltaic cells ; Photovoltaic power generation ; Photovoltaics ; Power ; Radiation ; Rainfall ; Renewable resources ; Root-mean-square errors ; Solar energy ; Solar panels ; Solar power ; Solar radiation ; Statistical methods ; Systems stability ; Time series ; transformers ; Weather</subject><ispartof>Energies (Basel), 2023-01, Vol.16 (3), p.1353</ispartof><rights>COPYRIGHT 2023 MDPI AG</rights><rights>2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c400t-33facf0a44e8227e949c3f2b31476e1acdaa5f1c7a388d557c751adc256d66223</citedby><cites>FETCH-LOGICAL-c400t-33facf0a44e8227e949c3f2b31476e1acdaa5f1c7a388d557c751adc256d66223</cites><orcidid>0000-0001-6008-0434 ; 0000-0001-7698-2619</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/2774892555/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/2774892555?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>314,776,780,25732,27903,27904,36991,44569,74873</link.rule.ids></links><search><creatorcontrib>Sherozbek, Jumaboev</creatorcontrib><creatorcontrib>Park, Jaewoo</creatorcontrib><creatorcontrib>Akhtar, Mohammad Shaheer</creatorcontrib><creatorcontrib>Yang, O-Bong</creatorcontrib><title>Transformers-Based Encoder Model for Forecasting Hourly Power Output of Transparent Photovoltaic Module Systems</title><title>Energies (Basel)</title><description>Solar power generation is usually affected by different meteorological factors, such as solar radiation, cloud cover, rainfall, and temperature. This variability has shown a negative impact on the large-scale integration of solar energy into energy supply systems. For successful integration of solar energy into the electrical grid, it is necessary to predict the accurate power generation by solar panels. In this work, solar power generation forecasting for two types of solar system (non-transparent and transparent panels) was configured by the smart artificial intelligence (AI) modelling. For deep learning models, the dataset obtained from the target value of electricity generation in kWh and other features, such as weather conditions, solar radiance, and insolation. In PV power generation values from non-transparent and transparent solar panels were collected from 1 January to 31 December 2021 with an hourly interval. To prove the efficiency of the proposed model, several deep learning approaches RNN models, such as LSTM, GRU, and transformers models, were implemented. Transformers model for forecasting power generation expressed the best model for non-transparent and transparent solar panels with lower error rates for MAE 0.05 and 0.04, and RMSE 0.24 and 0.21, respectively. The proposed model showed efficient performance and proved effective in forecasting time-series data.</description><subject>Algorithms</subject><subject>Alternative energy sources</subject><subject>Artificial intelligence</subject><subject>Cloud cover</subject><subject>Deep learning</subject><subject>Electric power grids</subject><subject>Energy efficiency</subject><subject>energy forecasting</subject><subject>Energy resources</subject><subject>Forecasting</subject><subject>GRU</subject><subject>Humidity</subject><subject>LSTM</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Photovoltaic cells</subject><subject>Photovoltaic power generation</subject><subject>Photovoltaics</subject><subject>Power</subject><subject>Radiation</subject><subject>Rainfall</subject><subject>Renewable resources</subject><subject>Root-mean-square errors</subject><subject>Solar energy</subject><subject>Solar panels</subject><subject>Solar power</subject><subject>Solar radiation</subject><subject>Statistical methods</subject><subject>Systems stability</subject><subject>Time series</subject><subject>transformers</subject><subject>Weather</subject><issn>1996-1073</issn><issn>1996-1073</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><sourceid>DOA</sourceid><recordid>eNpNkVFLHDEQx5dSoaK-9BME-lZYm2SSze6jFa2CoqA-hzGZXPfY21yTbOW-faNXWhPIDDP_-TGZaZrPgp8CDPwbzaLjIEDDh-ZQDEPXCm7g4zv_U3OS85rXA1UHcNjEx4RzDjFtKOX2O2by7GJ20VNit_WdWM2xy5jIYS7jvGJXcUnTjt3Hlyq5W8p2KSwG9sbZYqK5sPufscTfcSo4ulfKMhF72OVCm3zcHAScMp38tUfN0-XF4_lVe3P34_r87KZ1ivPSAgR0gaNS1EtpaFCDgyCfQSjTkUDnEXUQziD0vdfaOKMFeid157tOSjhqrvdcH3Ftt2ncYNrZiKN9C8S0spjK6CayXoBD6TAIKZTq1QA9N_Q8dCj60AleWV_2rG2KvxbKxa7rDObavpXGqH6QWuuqOt2rVlih4xxiSejq9bQZXZwpjDV-ZlT9gwAFteDrvsClmHOi8K9Nwe3rQu3_hcIfG-OSnA</recordid><startdate>20230101</startdate><enddate>20230101</enddate><creator>Sherozbek, Jumaboev</creator><creator>Park, Jaewoo</creator><creator>Akhtar, Mohammad Shaheer</creator><creator>Yang, O-Bong</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0001-6008-0434</orcidid><orcidid>https://orcid.org/0000-0001-7698-2619</orcidid></search><sort><creationdate>20230101</creationdate><title>Transformers-Based Encoder Model for Forecasting Hourly Power Output of Transparent Photovoltaic Module Systems</title><author>Sherozbek, Jumaboev ; Park, Jaewoo ; Akhtar, Mohammad Shaheer ; Yang, O-Bong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c400t-33facf0a44e8227e949c3f2b31476e1acdaa5f1c7a388d557c751adc256d66223</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Alternative energy sources</topic><topic>Artificial intelligence</topic><topic>Cloud cover</topic><topic>Deep learning</topic><topic>Electric power grids</topic><topic>Energy efficiency</topic><topic>energy forecasting</topic><topic>Energy resources</topic><topic>Forecasting</topic><topic>GRU</topic><topic>Humidity</topic><topic>LSTM</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Photovoltaic cells</topic><topic>Photovoltaic power generation</topic><topic>Photovoltaics</topic><topic>Power</topic><topic>Radiation</topic><topic>Rainfall</topic><topic>Renewable resources</topic><topic>Root-mean-square errors</topic><topic>Solar energy</topic><topic>Solar panels</topic><topic>Solar power</topic><topic>Solar radiation</topic><topic>Statistical methods</topic><topic>Systems stability</topic><topic>Time series</topic><topic>transformers</topic><topic>Weather</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Sherozbek, Jumaboev</creatorcontrib><creatorcontrib>Park, Jaewoo</creatorcontrib><creatorcontrib>Akhtar, Mohammad Shaheer</creatorcontrib><creatorcontrib>Yang, O-Bong</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Energies (Basel)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Sherozbek, Jumaboev</au><au>Park, Jaewoo</au><au>Akhtar, Mohammad Shaheer</au><au>Yang, O-Bong</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Transformers-Based Encoder Model for Forecasting Hourly Power Output of Transparent Photovoltaic Module Systems</atitle><jtitle>Energies (Basel)</jtitle><date>2023-01-01</date><risdate>2023</risdate><volume>16</volume><issue>3</issue><spage>1353</spage><pages>1353-</pages><issn>1996-1073</issn><eissn>1996-1073</eissn><abstract>Solar power generation is usually affected by different meteorological factors, such as solar radiation, cloud cover, rainfall, and temperature. This variability has shown a negative impact on the large-scale integration of solar energy into energy supply systems. For successful integration of solar energy into the electrical grid, it is necessary to predict the accurate power generation by solar panels. In this work, solar power generation forecasting for two types of solar system (non-transparent and transparent panels) was configured by the smart artificial intelligence (AI) modelling. For deep learning models, the dataset obtained from the target value of electricity generation in kWh and other features, such as weather conditions, solar radiance, and insolation. In PV power generation values from non-transparent and transparent solar panels were collected from 1 January to 31 December 2021 with an hourly interval. To prove the efficiency of the proposed model, several deep learning approaches RNN models, such as LSTM, GRU, and transformers models, were implemented. Transformers model for forecasting power generation expressed the best model for non-transparent and transparent solar panels with lower error rates for MAE 0.05 and 0.04, and RMSE 0.24 and 0.21, respectively. The proposed model showed efficient performance and proved effective in forecasting time-series data.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/en16031353</doi><orcidid>https://orcid.org/0000-0001-6008-0434</orcidid><orcidid>https://orcid.org/0000-0001-7698-2619</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1996-1073
ispartof Energies (Basel), 2023-01, Vol.16 (3), p.1353
issn 1996-1073
1996-1073
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_d13ca2caf121448493807eb96a18f610
source Publicly Available Content Database (Proquest) (PQ_SDU_P3)
subjects Algorithms
Alternative energy sources
Artificial intelligence
Cloud cover
Deep learning
Electric power grids
Energy efficiency
energy forecasting
Energy resources
Forecasting
GRU
Humidity
LSTM
Machine learning
Neural networks
Photovoltaic cells
Photovoltaic power generation
Photovoltaics
Power
Radiation
Rainfall
Renewable resources
Root-mean-square errors
Solar energy
Solar panels
Solar power
Solar radiation
Statistical methods
Systems stability
Time series
transformers
Weather
title Transformers-Based Encoder Model for Forecasting Hourly Power Output of Transparent Photovoltaic Module Systems
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T12%3A37%3A51IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Transformers-Based%20Encoder%20Model%20for%20Forecasting%20Hourly%20Power%20Output%20of%20Transparent%20Photovoltaic%20Module%20Systems&rft.jtitle=Energies%20(Basel)&rft.au=Sherozbek,%20Jumaboev&rft.date=2023-01-01&rft.volume=16&rft.issue=3&rft.spage=1353&rft.pages=1353-&rft.issn=1996-1073&rft.eissn=1996-1073&rft_id=info:doi/10.3390/en16031353&rft_dat=%3Cgale_doaj_%3EA743141343%3C/gale_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c400t-33facf0a44e8227e949c3f2b31476e1acdaa5f1c7a388d557c751adc256d66223%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2774892555&rft_id=info:pmid/&rft_galeid=A743141343&rfr_iscdi=true