Artificial neural network model based on interrelationship of direct, diffuse and global solar radiations

•We present an innovative ANN model to estimate solar radiation components.•The model is based on interrelationship of direct, diffuse and global radiations.•Simulation and test results exhibit excellent compatibility with observations.•The model estimates exhibit good compatibility with NASA-SSE da...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Solar energy 2014-05, Vol.103, p.327-342
Hauptverfasser: Kaushika, N.D., Tomar, R.K., Kaushik, S.C.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 342
container_issue
container_start_page 327
container_title Solar energy
container_volume 103
creator Kaushika, N.D.
Tomar, R.K.
Kaushik, S.C.
description •We present an innovative ANN model to estimate solar radiation components.•The model is based on interrelationship of direct, diffuse and global radiations.•Simulation and test results exhibit excellent compatibility with observations.•The model estimates exhibit good compatibility with NASA-SSE data sets.•The isotropic/anisotropic irradiative sky conditions are also investigated. This paper presents a neural network model based on explicit approach using the interrelationship characteristics of direct, diffuse and global solar radiations. The computational algorithm includes the estimation of global, diffuse and direct components through clear sky conditions. The deviations of these estimates from measurements are considered to be due to random weather phenomena characterized by clearness indices. The clearness indices corresponding to direct, diffuse and global components of solar radiation are then mapped with long term monthly mean hourly data of weather-related parameters such as mean duration of sunshine per hour, relative humidity and total rainfall in the artificial neural network (ANN) analysis. The estimates of ANN model exhibit excellent compatibility with observations with overall root mean square error RMSE (%) and mean biased error MBE (%) for the global radiation as 5.19 and −0.194 respectively. The RMSE values for wet months (July, August, September, October) are relatively higher than those of the dry months (January, February, March, April) due to intensive monsoon in Indian region. Contour maps of ANN model calculations of global radiation as a function of latitude, time of the day and month of the year are presented. The model offers promise of being useable for the prediction of direct, diffuse and global components of solar radiation at an arbitrary location. A comparative study of the estimates of present ANN model with NASA surface meteorology and solar-energy data sets exhibits good compatibility. The global solar radiation on tilted planes has also been investigated using isotropic and anisotropic sky conditions. The results seem to be favouring an isotropic model during the year-round cycle at New Delhi (28.58°N).
doi_str_mv 10.1016/j.solener.2014.02.015
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1547848689</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0038092X14000930</els_id><sourcerecordid>1547848689</sourcerecordid><originalsourceid>FETCH-LOGICAL-c400t-3a8a3b780a535b2c12efcfefce43ff2146023aff5a0367386c62d53ed85e9da83</originalsourceid><addsrcrecordid>eNqFkU-LFDEQxYMoOK5-BCEggge7zd9O-iTLorvCghcFbyGTVDRjJhmT7hW_vVl78ODFQ_Euv_eqqIfQc0pGSuj05jC2kiBDHRmhYiRsJFQ-QDsqFB0ok-oh2hHC9UBm9uUxetLagRCqqFY7FC_rEkN00SacYa1_ZPlZ6nd8LB4S3tsGHpeMY16gVkh2iSW3b_GES8A-VnDL664hrA2wzR5_TWXfY_pNtuJqfdwcT9GjYFODZ2e9QJ_fv_t0dTPcfrz-cHV5OzhByDJwqy3fK02s5HLPHGUQXOgDgofAqJgI4zYEaQmfFNeTm5iXHLyWMHur-QV6teWeavmxQlvMMTYHKdkMZW2GSqG00JOeO_riH_RQ1pr7dZ2i8zzTWapOyY1ytbRWIZhTjUdbfxlKzH0B5mDOBZj7AgxhphfQfS_P6bY5m0K12cX218y0EFQp0bm3Gwf9K3expzQXITvYnmt8if_Z9Bv7Ap_8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1519991957</pqid></control><display><type>article</type><title>Artificial neural network model based on interrelationship of direct, diffuse and global solar radiations</title><source>Elsevier ScienceDirect Journals</source><creator>Kaushika, N.D. ; Tomar, R.K. ; Kaushik, S.C.</creator><creatorcontrib>Kaushika, N.D. ; Tomar, R.K. ; Kaushik, S.C.</creatorcontrib><description>•We present an innovative ANN model to estimate solar radiation components.•The model is based on interrelationship of direct, diffuse and global radiations.•Simulation and test results exhibit excellent compatibility with observations.•The model estimates exhibit good compatibility with NASA-SSE data sets.•The isotropic/anisotropic irradiative sky conditions are also investigated. This paper presents a neural network model based on explicit approach using the interrelationship characteristics of direct, diffuse and global solar radiations. The computational algorithm includes the estimation of global, diffuse and direct components through clear sky conditions. The deviations of these estimates from measurements are considered to be due to random weather phenomena characterized by clearness indices. The clearness indices corresponding to direct, diffuse and global components of solar radiation are then mapped with long term monthly mean hourly data of weather-related parameters such as mean duration of sunshine per hour, relative humidity and total rainfall in the artificial neural network (ANN) analysis. The estimates of ANN model exhibit excellent compatibility with observations with overall root mean square error RMSE (%) and mean biased error MBE (%) for the global radiation as 5.19 and −0.194 respectively. The RMSE values for wet months (July, August, September, October) are relatively higher than those of the dry months (January, February, March, April) due to intensive monsoon in Indian region. Contour maps of ANN model calculations of global radiation as a function of latitude, time of the day and month of the year are presented. The model offers promise of being useable for the prediction of direct, diffuse and global components of solar radiation at an arbitrary location. A comparative study of the estimates of present ANN model with NASA surface meteorology and solar-energy data sets exhibits good compatibility. The global solar radiation on tilted planes has also been investigated using isotropic and anisotropic sky conditions. The results seem to be favouring an isotropic model during the year-round cycle at New Delhi (28.58°N).</description><identifier>ISSN: 0038-092X</identifier><identifier>EISSN: 1471-1257</identifier><identifier>DOI: 10.1016/j.solener.2014.02.015</identifier><identifier>CODEN: SRENA4</identifier><language>eng</language><publisher>Kidlington: Elsevier Ltd</publisher><subject>Algorithms ; Applied sciences ; Artificial intelligence ; Artificial neural network ; Computational model ; Energy ; Exact sciences and technology ; Humidity ; Meteorology ; Natural energy ; Neural networks ; Rain ; Solar energy ; Solar radiation ; Solar radiation estimates ; Solar radiation on tilted surfaces ; Ultraviolet radiation</subject><ispartof>Solar energy, 2014-05, Vol.103, p.327-342</ispartof><rights>2014 Elsevier Ltd</rights><rights>2015 INIST-CNRS</rights><rights>Copyright Pergamon Press Inc. May 2014</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c400t-3a8a3b780a535b2c12efcfefce43ff2146023aff5a0367386c62d53ed85e9da83</citedby><cites>FETCH-LOGICAL-c400t-3a8a3b780a535b2c12efcfefce43ff2146023aff5a0367386c62d53ed85e9da83</cites><orcidid>0000-0001-8759-4099</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.solener.2014.02.015$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3536,27903,27904,45974</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&amp;idt=28441774$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Kaushika, N.D.</creatorcontrib><creatorcontrib>Tomar, R.K.</creatorcontrib><creatorcontrib>Kaushik, S.C.</creatorcontrib><title>Artificial neural network model based on interrelationship of direct, diffuse and global solar radiations</title><title>Solar energy</title><description>•We present an innovative ANN model to estimate solar radiation components.•The model is based on interrelationship of direct, diffuse and global radiations.•Simulation and test results exhibit excellent compatibility with observations.•The model estimates exhibit good compatibility with NASA-SSE data sets.•The isotropic/anisotropic irradiative sky conditions are also investigated. This paper presents a neural network model based on explicit approach using the interrelationship characteristics of direct, diffuse and global solar radiations. The computational algorithm includes the estimation of global, diffuse and direct components through clear sky conditions. The deviations of these estimates from measurements are considered to be due to random weather phenomena characterized by clearness indices. The clearness indices corresponding to direct, diffuse and global components of solar radiation are then mapped with long term monthly mean hourly data of weather-related parameters such as mean duration of sunshine per hour, relative humidity and total rainfall in the artificial neural network (ANN) analysis. The estimates of ANN model exhibit excellent compatibility with observations with overall root mean square error RMSE (%) and mean biased error MBE (%) for the global radiation as 5.19 and −0.194 respectively. The RMSE values for wet months (July, August, September, October) are relatively higher than those of the dry months (January, February, March, April) due to intensive monsoon in Indian region. Contour maps of ANN model calculations of global radiation as a function of latitude, time of the day and month of the year are presented. The model offers promise of being useable for the prediction of direct, diffuse and global components of solar radiation at an arbitrary location. A comparative study of the estimates of present ANN model with NASA surface meteorology and solar-energy data sets exhibits good compatibility. The global solar radiation on tilted planes has also been investigated using isotropic and anisotropic sky conditions. The results seem to be favouring an isotropic model during the year-round cycle at New Delhi (28.58°N).</description><subject>Algorithms</subject><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Artificial neural network</subject><subject>Computational model</subject><subject>Energy</subject><subject>Exact sciences and technology</subject><subject>Humidity</subject><subject>Meteorology</subject><subject>Natural energy</subject><subject>Neural networks</subject><subject>Rain</subject><subject>Solar energy</subject><subject>Solar radiation</subject><subject>Solar radiation estimates</subject><subject>Solar radiation on tilted surfaces</subject><subject>Ultraviolet radiation</subject><issn>0038-092X</issn><issn>1471-1257</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><recordid>eNqFkU-LFDEQxYMoOK5-BCEggge7zd9O-iTLorvCghcFbyGTVDRjJhmT7hW_vVl78ODFQ_Euv_eqqIfQc0pGSuj05jC2kiBDHRmhYiRsJFQ-QDsqFB0ok-oh2hHC9UBm9uUxetLagRCqqFY7FC_rEkN00SacYa1_ZPlZ6nd8LB4S3tsGHpeMY16gVkh2iSW3b_GES8A-VnDL664hrA2wzR5_TWXfY_pNtuJqfdwcT9GjYFODZ2e9QJ_fv_t0dTPcfrz-cHV5OzhByDJwqy3fK02s5HLPHGUQXOgDgofAqJgI4zYEaQmfFNeTm5iXHLyWMHur-QV6teWeavmxQlvMMTYHKdkMZW2GSqG00JOeO_riH_RQ1pr7dZ2i8zzTWapOyY1ytbRWIZhTjUdbfxlKzH0B5mDOBZj7AgxhphfQfS_P6bY5m0K12cX218y0EFQp0bm3Gwf9K3expzQXITvYnmt8if_Z9Bv7Ap_8</recordid><startdate>20140501</startdate><enddate>20140501</enddate><creator>Kaushika, N.D.</creator><creator>Tomar, R.K.</creator><creator>Kaushik, S.C.</creator><general>Elsevier Ltd</general><general>Elsevier</general><general>Pergamon Press Inc</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7ST</scope><scope>8FD</scope><scope>C1K</scope><scope>FR3</scope><scope>KR7</scope><scope>L7M</scope><scope>SOI</scope><scope>7TG</scope><scope>KL.</scope><orcidid>https://orcid.org/0000-0001-8759-4099</orcidid></search><sort><creationdate>20140501</creationdate><title>Artificial neural network model based on interrelationship of direct, diffuse and global solar radiations</title><author>Kaushika, N.D. ; Tomar, R.K. ; Kaushik, S.C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c400t-3a8a3b780a535b2c12efcfefce43ff2146023aff5a0367386c62d53ed85e9da83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Algorithms</topic><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Artificial neural network</topic><topic>Computational model</topic><topic>Energy</topic><topic>Exact sciences and technology</topic><topic>Humidity</topic><topic>Meteorology</topic><topic>Natural energy</topic><topic>Neural networks</topic><topic>Rain</topic><topic>Solar energy</topic><topic>Solar radiation</topic><topic>Solar radiation estimates</topic><topic>Solar radiation on tilted surfaces</topic><topic>Ultraviolet radiation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kaushika, N.D.</creatorcontrib><creatorcontrib>Tomar, R.K.</creatorcontrib><creatorcontrib>Kaushik, S.C.</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Environment Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>Engineering Research Database</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Environment Abstracts</collection><collection>Meteorological &amp; Geoastrophysical Abstracts</collection><collection>Meteorological &amp; Geoastrophysical Abstracts - Academic</collection><jtitle>Solar energy</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kaushika, N.D.</au><au>Tomar, R.K.</au><au>Kaushik, S.C.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Artificial neural network model based on interrelationship of direct, diffuse and global solar radiations</atitle><jtitle>Solar energy</jtitle><date>2014-05-01</date><risdate>2014</risdate><volume>103</volume><spage>327</spage><epage>342</epage><pages>327-342</pages><issn>0038-092X</issn><eissn>1471-1257</eissn><coden>SRENA4</coden><abstract>•We present an innovative ANN model to estimate solar radiation components.•The model is based on interrelationship of direct, diffuse and global radiations.•Simulation and test results exhibit excellent compatibility with observations.•The model estimates exhibit good compatibility with NASA-SSE data sets.•The isotropic/anisotropic irradiative sky conditions are also investigated. This paper presents a neural network model based on explicit approach using the interrelationship characteristics of direct, diffuse and global solar radiations. The computational algorithm includes the estimation of global, diffuse and direct components through clear sky conditions. The deviations of these estimates from measurements are considered to be due to random weather phenomena characterized by clearness indices. The clearness indices corresponding to direct, diffuse and global components of solar radiation are then mapped with long term monthly mean hourly data of weather-related parameters such as mean duration of sunshine per hour, relative humidity and total rainfall in the artificial neural network (ANN) analysis. The estimates of ANN model exhibit excellent compatibility with observations with overall root mean square error RMSE (%) and mean biased error MBE (%) for the global radiation as 5.19 and −0.194 respectively. The RMSE values for wet months (July, August, September, October) are relatively higher than those of the dry months (January, February, March, April) due to intensive monsoon in Indian region. Contour maps of ANN model calculations of global radiation as a function of latitude, time of the day and month of the year are presented. The model offers promise of being useable for the prediction of direct, diffuse and global components of solar radiation at an arbitrary location. A comparative study of the estimates of present ANN model with NASA surface meteorology and solar-energy data sets exhibits good compatibility. The global solar radiation on tilted planes has also been investigated using isotropic and anisotropic sky conditions. The results seem to be favouring an isotropic model during the year-round cycle at New Delhi (28.58°N).</abstract><cop>Kidlington</cop><pub>Elsevier Ltd</pub><doi>10.1016/j.solener.2014.02.015</doi><tpages>16</tpages><orcidid>https://orcid.org/0000-0001-8759-4099</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0038-092X
ispartof Solar energy, 2014-05, Vol.103, p.327-342
issn 0038-092X
1471-1257
language eng
recordid cdi_proquest_miscellaneous_1547848689
source Elsevier ScienceDirect Journals
subjects Algorithms
Applied sciences
Artificial intelligence
Artificial neural network
Computational model
Energy
Exact sciences and technology
Humidity
Meteorology
Natural energy
Neural networks
Rain
Solar energy
Solar radiation
Solar radiation estimates
Solar radiation on tilted surfaces
Ultraviolet radiation
title Artificial neural network model based on interrelationship of direct, diffuse and global solar radiations
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T11%3A37%3A43IST&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=Artificial%20neural%20network%20model%20based%20on%20interrelationship%20of%20direct,%20diffuse%20and%20global%20solar%20radiations&rft.jtitle=Solar%20energy&rft.au=Kaushika,%20N.D.&rft.date=2014-05-01&rft.volume=103&rft.spage=327&rft.epage=342&rft.pages=327-342&rft.issn=0038-092X&rft.eissn=1471-1257&rft.coden=SRENA4&rft_id=info:doi/10.1016/j.solener.2014.02.015&rft_dat=%3Cproquest_cross%3E1547848689%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1519991957&rft_id=info:pmid/&rft_els_id=S0038092X14000930&rfr_iscdi=true