Loading…

Reliable Solar Irradiance Forecasting Approach Based on Choquet Integral and Deep LSTMs

The intermittent nature associated with photovoltaic (PV) generation is a challenging problem for the optimal planning and efficient management in smart grids. A reliable forecasting model of solar irradiance can play an essential role in allowing high PV penetrations without degrading the grid perf...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on industrial informatics 2021-03, Vol.17 (3), p.1873-1881
Main Authors: Abdel-Nasser, Mohamed, Mahmoud, Karar, Lehtonen, Matti
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-c399t-40273131998ceeddb539dfae06d1772ca7061378ab8e80836a4cfa880b72fada3
cites cdi_FETCH-LOGICAL-c399t-40273131998ceeddb539dfae06d1772ca7061378ab8e80836a4cfa880b72fada3
container_end_page 1881
container_issue 3
container_start_page 1873
container_title IEEE transactions on industrial informatics
container_volume 17
creator Abdel-Nasser, Mohamed
Mahmoud, Karar
Lehtonen, Matti
description The intermittent nature associated with photovoltaic (PV) generation is a challenging problem for the optimal planning and efficient management in smart grids. A reliable forecasting model of solar irradiance can play an essential role in allowing high PV penetrations without degrading the grid performance. For this purpose, most related works either use individual forecasting models or ensemble approaches (e.g., weighted average), ignoring the interaction between the values to be aggregated and thus may worsen the forecasting reliability. Differently, in this article, we propose a reliable solar irradiance forecasting method based on long short-term memory (LSTM) models and an aggregation function based on Choquet integral. This novel combination has the following features: 1) LSTM models can achieve accurate predictions because they model the temporal changes in solar irradiance, thanks to their recurrent architecture and memory units, and 2) the Choquet integral can model the interaction between the inputs to be aggregated through a fuzzy measure. This aggregation technique can determine the largest consistency among the conflicting forecasting results, taking advantage of each individual model. To demonstrate the effectiveness of the proposed approach, we compare it with several forecasting methods using six realistic datasets collected from different sites in Finland in which solar irradiance is intermittent. The comparison reveals the high reliability of the proposed forecasting model with different sites and solar profiles.
doi_str_mv 10.1109/TII.2020.2996235
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TII_2020_2996235</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9097938</ieee_id><sourcerecordid>2468767503</sourcerecordid><originalsourceid>FETCH-LOGICAL-c399t-40273131998ceeddb539dfae06d1772ca7061378ab8e80836a4cfa880b72fada3</originalsourceid><addsrcrecordid>eNo9kDFPwzAQRiMEEqWwI7FYYk4520lsj6VQiFSERIsYrYtzaVOFpNjpwL8nVSumu-F9d59eFN1ymHAO5mGV5xMBAibCmEzI9CwacZPwGCCF82FPUx5LAfIyugphCyAVSDOKvj6oqbFoiC27Bj3LvceyxtYRm3eeHIa-btdsutv5Dt2GPWKgknUtm226nz31LG97WntsGLYleyLascVy9Rauo4sKm0A3pzmOPufPq9lrvHh_yWfTReykMX2cgFCSS26MdkRlWaTSlBUSZCVXSjhUkHGpNBaaNGiZYeIq1BoKJSosUY6j--Pdod_QJ_R22-19O7y0Ism0ylQKcqDgSDnfheCpsjtff6P_tRzsQZ8d9NmDPnvSN0TujpGaiP5xA0YZqeUfm5hqfg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2468767503</pqid></control><display><type>article</type><title>Reliable Solar Irradiance Forecasting Approach Based on Choquet Integral and Deep LSTMs</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Abdel-Nasser, Mohamed ; Mahmoud, Karar ; Lehtonen, Matti</creator><creatorcontrib>Abdel-Nasser, Mohamed ; Mahmoud, Karar ; Lehtonen, Matti</creatorcontrib><description>The intermittent nature associated with photovoltaic (PV) generation is a challenging problem for the optimal planning and efficient management in smart grids. A reliable forecasting model of solar irradiance can play an essential role in allowing high PV penetrations without degrading the grid performance. For this purpose, most related works either use individual forecasting models or ensemble approaches (e.g., weighted average), ignoring the interaction between the values to be aggregated and thus may worsen the forecasting reliability. Differently, in this article, we propose a reliable solar irradiance forecasting method based on long short-term memory (LSTM) models and an aggregation function based on Choquet integral. This novel combination has the following features: 1) LSTM models can achieve accurate predictions because they model the temporal changes in solar irradiance, thanks to their recurrent architecture and memory units, and 2) the Choquet integral can model the interaction between the inputs to be aggregated through a fuzzy measure. This aggregation technique can determine the largest consistency among the conflicting forecasting results, taking advantage of each individual model. To demonstrate the effectiveness of the proposed approach, we compare it with several forecasting methods using six realistic datasets collected from different sites in Finland in which solar irradiance is intermittent. The comparison reveals the high reliability of the proposed forecasting model with different sites and solar profiles.</description><identifier>ISSN: 1551-3203</identifier><identifier>EISSN: 1941-0050</identifier><identifier>DOI: 10.1109/TII.2020.2996235</identifier><identifier>CODEN: ITIICH</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Agglomeration ; Choquet integral ; deep long short-term memory (LSTM) ; Forecasting ; Fuzzy set theory ; Integrals ; Irradiance ; irradiance forecasting ; Long short term memory ; Mathematical models ; photovoltaic (PV) ; Photovoltaic cells ; Photovoltaic systems ; Power generation planning ; Power generation reliability ; Reliability ; Smart grid ; Solar power generation</subject><ispartof>IEEE transactions on industrial informatics, 2021-03, Vol.17 (3), p.1873-1881</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c399t-40273131998ceeddb539dfae06d1772ca7061378ab8e80836a4cfa880b72fada3</citedby><cites>FETCH-LOGICAL-c399t-40273131998ceeddb539dfae06d1772ca7061378ab8e80836a4cfa880b72fada3</cites><orcidid>0000-0002-9979-7333 ; 0000-0002-6729-6809 ; 0000-0002-1074-2441</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9097938$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,54796</link.rule.ids></links><search><creatorcontrib>Abdel-Nasser, Mohamed</creatorcontrib><creatorcontrib>Mahmoud, Karar</creatorcontrib><creatorcontrib>Lehtonen, Matti</creatorcontrib><title>Reliable Solar Irradiance Forecasting Approach Based on Choquet Integral and Deep LSTMs</title><title>IEEE transactions on industrial informatics</title><addtitle>TII</addtitle><description>The intermittent nature associated with photovoltaic (PV) generation is a challenging problem for the optimal planning and efficient management in smart grids. A reliable forecasting model of solar irradiance can play an essential role in allowing high PV penetrations without degrading the grid performance. For this purpose, most related works either use individual forecasting models or ensemble approaches (e.g., weighted average), ignoring the interaction between the values to be aggregated and thus may worsen the forecasting reliability. Differently, in this article, we propose a reliable solar irradiance forecasting method based on long short-term memory (LSTM) models and an aggregation function based on Choquet integral. This novel combination has the following features: 1) LSTM models can achieve accurate predictions because they model the temporal changes in solar irradiance, thanks to their recurrent architecture and memory units, and 2) the Choquet integral can model the interaction between the inputs to be aggregated through a fuzzy measure. This aggregation technique can determine the largest consistency among the conflicting forecasting results, taking advantage of each individual model. To demonstrate the effectiveness of the proposed approach, we compare it with several forecasting methods using six realistic datasets collected from different sites in Finland in which solar irradiance is intermittent. The comparison reveals the high reliability of the proposed forecasting model with different sites and solar profiles.</description><subject>Agglomeration</subject><subject>Choquet integral</subject><subject>deep long short-term memory (LSTM)</subject><subject>Forecasting</subject><subject>Fuzzy set theory</subject><subject>Integrals</subject><subject>Irradiance</subject><subject>irradiance forecasting</subject><subject>Long short term memory</subject><subject>Mathematical models</subject><subject>photovoltaic (PV)</subject><subject>Photovoltaic cells</subject><subject>Photovoltaic systems</subject><subject>Power generation planning</subject><subject>Power generation reliability</subject><subject>Reliability</subject><subject>Smart grid</subject><subject>Solar power generation</subject><issn>1551-3203</issn><issn>1941-0050</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNo9kDFPwzAQRiMEEqWwI7FYYk4520lsj6VQiFSERIsYrYtzaVOFpNjpwL8nVSumu-F9d59eFN1ymHAO5mGV5xMBAibCmEzI9CwacZPwGCCF82FPUx5LAfIyugphCyAVSDOKvj6oqbFoiC27Bj3LvceyxtYRm3eeHIa-btdsutv5Dt2GPWKgknUtm226nz31LG97WntsGLYleyLascVy9Rauo4sKm0A3pzmOPufPq9lrvHh_yWfTReykMX2cgFCSS26MdkRlWaTSlBUSZCVXSjhUkHGpNBaaNGiZYeIq1BoKJSosUY6j--Pdod_QJ_R22-19O7y0Ism0ylQKcqDgSDnfheCpsjtff6P_tRzsQZ8d9NmDPnvSN0TujpGaiP5xA0YZqeUfm5hqfg</recordid><startdate>20210301</startdate><enddate>20210301</enddate><creator>Abdel-Nasser, Mohamed</creator><creator>Mahmoud, Karar</creator><creator>Lehtonen, Matti</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-9979-7333</orcidid><orcidid>https://orcid.org/0000-0002-6729-6809</orcidid><orcidid>https://orcid.org/0000-0002-1074-2441</orcidid></search><sort><creationdate>20210301</creationdate><title>Reliable Solar Irradiance Forecasting Approach Based on Choquet Integral and Deep LSTMs</title><author>Abdel-Nasser, Mohamed ; Mahmoud, Karar ; Lehtonen, Matti</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c399t-40273131998ceeddb539dfae06d1772ca7061378ab8e80836a4cfa880b72fada3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Agglomeration</topic><topic>Choquet integral</topic><topic>deep long short-term memory (LSTM)</topic><topic>Forecasting</topic><topic>Fuzzy set theory</topic><topic>Integrals</topic><topic>Irradiance</topic><topic>irradiance forecasting</topic><topic>Long short term memory</topic><topic>Mathematical models</topic><topic>photovoltaic (PV)</topic><topic>Photovoltaic cells</topic><topic>Photovoltaic systems</topic><topic>Power generation planning</topic><topic>Power generation reliability</topic><topic>Reliability</topic><topic>Smart grid</topic><topic>Solar power generation</topic><toplevel>online_resources</toplevel><creatorcontrib>Abdel-Nasser, Mohamed</creatorcontrib><creatorcontrib>Mahmoud, Karar</creatorcontrib><creatorcontrib>Lehtonen, Matti</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEL</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on industrial informatics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Abdel-Nasser, Mohamed</au><au>Mahmoud, Karar</au><au>Lehtonen, Matti</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Reliable Solar Irradiance Forecasting Approach Based on Choquet Integral and Deep LSTMs</atitle><jtitle>IEEE transactions on industrial informatics</jtitle><stitle>TII</stitle><date>2021-03-01</date><risdate>2021</risdate><volume>17</volume><issue>3</issue><spage>1873</spage><epage>1881</epage><pages>1873-1881</pages><issn>1551-3203</issn><eissn>1941-0050</eissn><coden>ITIICH</coden><abstract>The intermittent nature associated with photovoltaic (PV) generation is a challenging problem for the optimal planning and efficient management in smart grids. A reliable forecasting model of solar irradiance can play an essential role in allowing high PV penetrations without degrading the grid performance. For this purpose, most related works either use individual forecasting models or ensemble approaches (e.g., weighted average), ignoring the interaction between the values to be aggregated and thus may worsen the forecasting reliability. Differently, in this article, we propose a reliable solar irradiance forecasting method based on long short-term memory (LSTM) models and an aggregation function based on Choquet integral. This novel combination has the following features: 1) LSTM models can achieve accurate predictions because they model the temporal changes in solar irradiance, thanks to their recurrent architecture and memory units, and 2) the Choquet integral can model the interaction between the inputs to be aggregated through a fuzzy measure. This aggregation technique can determine the largest consistency among the conflicting forecasting results, taking advantage of each individual model. To demonstrate the effectiveness of the proposed approach, we compare it with several forecasting methods using six realistic datasets collected from different sites in Finland in which solar irradiance is intermittent. The comparison reveals the high reliability of the proposed forecasting model with different sites and solar profiles.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/TII.2020.2996235</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0002-9979-7333</orcidid><orcidid>https://orcid.org/0000-0002-6729-6809</orcidid><orcidid>https://orcid.org/0000-0002-1074-2441</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1551-3203
ispartof IEEE transactions on industrial informatics, 2021-03, Vol.17 (3), p.1873-1881
issn 1551-3203
1941-0050
language eng
recordid cdi_crossref_primary_10_1109_TII_2020_2996235
source IEEE Electronic Library (IEL) Journals
subjects Agglomeration
Choquet integral
deep long short-term memory (LSTM)
Forecasting
Fuzzy set theory
Integrals
Irradiance
irradiance forecasting
Long short term memory
Mathematical models
photovoltaic (PV)
Photovoltaic cells
Photovoltaic systems
Power generation planning
Power generation reliability
Reliability
Smart grid
Solar power generation
title Reliable Solar Irradiance Forecasting Approach Based on Choquet Integral and Deep LSTMs
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T10%3A57%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Reliable%20Solar%20Irradiance%20Forecasting%20Approach%20Based%20on%20Choquet%20Integral%20and%20Deep%20LSTMs&rft.jtitle=IEEE%20transactions%20on%20industrial%20informatics&rft.au=Abdel-Nasser,%20Mohamed&rft.date=2021-03-01&rft.volume=17&rft.issue=3&rft.spage=1873&rft.epage=1881&rft.pages=1873-1881&rft.issn=1551-3203&rft.eissn=1941-0050&rft.coden=ITIICH&rft_id=info:doi/10.1109/TII.2020.2996235&rft_dat=%3Cproquest_cross%3E2468767503%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c399t-40273131998ceeddb539dfae06d1772ca7061378ab8e80836a4cfa880b72fada3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2468767503&rft_id=info:pmid/&rft_ieee_id=9097938&rfr_iscdi=true