An adaptive modular artificial neural network hourly load forecaster and its implementation at electric utilities
This paper describes a modular artificial neural network (ANN) based hourly load forecaster which has already been implemented at 20 electric utilities across the US and is being used on-line by several of them. The behavior or the load and its correlation with parameters affecting it (e.g. weather...
Gespeichert in:
| Veröffentlicht in: | IEEE Transactions on Power Systems 1995-08, Vol.10 (3), p.1716-1722 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1722 |
|---|---|
| container_issue | 3 |
| container_start_page | 1716 |
| container_title | IEEE Transactions on Power Systems |
| container_volume | 10 |
| creator | Khotanzad, A. Rey-Chue Hwang Abaye, A. Maratukulam, D. |
| description | This paper describes a modular artificial neural network (ANN) based hourly load forecaster which has already been implemented at 20 electric utilities across the US and is being used on-line by several of them. The behavior or the load and its correlation with parameters affecting it (e.g. weather variables) are decomposed into three distinct trends of weekly, daily, and hourly. Each trend is modeled by a separate module containing several multi-layer feed-forward ANNs trained by the back-propagation learning rule. The forecasts produced by each module are then combined by adaptive filters to arrive at the final forecast. During the forecasting phase, the parameters of the ANNs within each module are adaptively changed in response to the system's latest forecast accuracy. The performance of the forecaster has been tested on data from these 20 utilities with excellent results. The on-line performance of the system has also been quite satisfactory and superior to other forecasting packages used by the utilities. Moreover, the forecaster is robust, easy to use, and produces accurate results in the case of rapid weather changes.< > |
| doi_str_mv | 10.1109/59.466468 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_miscellaneous_28435235</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>466468</ieee_id><sourcerecordid>28435235</sourcerecordid><originalsourceid>FETCH-LOGICAL-c394t-7a9e9be44a30c9a2850c87be0b82031326dde142ce44ffda2e34b0996f9c3313</originalsourceid><addsrcrecordid>eNqNkU1v1DAQhi1EJZbCgSsnI6FKHNI68UfsY1VRQKrEpXdr1pmoA068tR1Q_z1ZsuoVTnN4n3lmpJexd624bFvhrrS7VMYoY1-wXau1bYTp3Uu2E9bqxjotXrHXpfwQQpg12LHH65nDAIdKv5BPaVgiZA650kiBIPIZl_x31N8p_-QPacnxiccEAx9TxgCl4rowD5xq4TQdIk44V6iUVnHlGDHUTIEvlSJVwvKGnY0QC749zXN2f_v5_uZrc_f9y7eb67smSKdq04NDt0elQIrgoLNaBNvvUextJ2QrOzMM2KourMg4DtChVHvhnBldkGt-zj5s2lQq-RKoYngIaZ7Xf3xrpOjtylxszCGnxwVL9ROVgDHCjGkpvrNOWeu6_wCV1J3U_wZ7qfpeHo2fNjDkVErG0R8yTZCffCv8sUmvnd-aXNmPJymUAHHMMAcqzwvSKCfc8fb7DSNEfE5Pjj952qbf</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>27347732</pqid></control><display><type>article</type><title>An adaptive modular artificial neural network hourly load forecaster and its implementation at electric utilities</title><source>IEEE Electronic Library (IEL)</source><creator>Khotanzad, A. ; Rey-Chue Hwang ; Abaye, A. ; Maratukulam, D.</creator><creatorcontrib>Khotanzad, A. ; Rey-Chue Hwang ; Abaye, A. ; Maratukulam, D.</creatorcontrib><description>This paper describes a modular artificial neural network (ANN) based hourly load forecaster which has already been implemented at 20 electric utilities across the US and is being used on-line by several of them. The behavior or the load and its correlation with parameters affecting it (e.g. weather variables) are decomposed into three distinct trends of weekly, daily, and hourly. Each trend is modeled by a separate module containing several multi-layer feed-forward ANNs trained by the back-propagation learning rule. The forecasts produced by each module are then combined by adaptive filters to arrive at the final forecast. During the forecasting phase, the parameters of the ANNs within each module are adaptively changed in response to the system's latest forecast accuracy. The performance of the forecaster has been tested on data from these 20 utilities with excellent results. The on-line performance of the system has also been quite satisfactory and superior to other forecasting packages used by the utilities. Moreover, the forecaster is robust, easy to use, and produces accurate results in the case of rapid weather changes.< ></description><identifier>ISSN: 0885-8950</identifier><identifier>EISSN: 1558-0679</identifier><identifier>DOI: 10.1109/59.466468</identifier><identifier>CODEN: ITPSEG</identifier><language>eng</language><publisher>New York, NY: IEEE</publisher><subject>Applied sciences ; Artificial neural networks ; COMPUTER CALCULATIONS ; Costs ; Economic forecasting ; Electrical engineering. Electrical power engineering ; Electrical power engineering ; ENERGY MANAGEMENT SYSTEMS ; ENERGY PLANNING AND POLICY ; Exact sciences and technology ; FORECASTING ; Load forecasting ; Maintenance ; NEURAL NETWORKS ; Operation. Load control. Reliability ; POWER DEMAND ; Power industry ; Power networks and lines ; Power system security ; POWER TRANSMISSION AND DISTRIBUTION ; Robustness ; Student members ; Weather forecasting</subject><ispartof>IEEE Transactions on Power Systems, 1995-08, Vol.10 (3), p.1716-1722</ispartof><rights>1995 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c394t-7a9e9be44a30c9a2850c87be0b82031326dde142ce44ffda2e34b0996f9c3313</citedby><cites>FETCH-LOGICAL-c394t-7a9e9be44a30c9a2850c87be0b82031326dde142ce44ffda2e34b0996f9c3313</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/466468$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,881,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/466468$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=3649095$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.osti.gov/biblio/163078$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>Khotanzad, A.</creatorcontrib><creatorcontrib>Rey-Chue Hwang</creatorcontrib><creatorcontrib>Abaye, A.</creatorcontrib><creatorcontrib>Maratukulam, D.</creatorcontrib><title>An adaptive modular artificial neural network hourly load forecaster and its implementation at electric utilities</title><title>IEEE Transactions on Power Systems</title><addtitle>TPWRS</addtitle><description>This paper describes a modular artificial neural network (ANN) based hourly load forecaster which has already been implemented at 20 electric utilities across the US and is being used on-line by several of them. The behavior or the load and its correlation with parameters affecting it (e.g. weather variables) are decomposed into three distinct trends of weekly, daily, and hourly. Each trend is modeled by a separate module containing several multi-layer feed-forward ANNs trained by the back-propagation learning rule. The forecasts produced by each module are then combined by adaptive filters to arrive at the final forecast. During the forecasting phase, the parameters of the ANNs within each module are adaptively changed in response to the system's latest forecast accuracy. The performance of the forecaster has been tested on data from these 20 utilities with excellent results. The on-line performance of the system has also been quite satisfactory and superior to other forecasting packages used by the utilities. Moreover, the forecaster is robust, easy to use, and produces accurate results in the case of rapid weather changes.< ></description><subject>Applied sciences</subject><subject>Artificial neural networks</subject><subject>COMPUTER CALCULATIONS</subject><subject>Costs</subject><subject>Economic forecasting</subject><subject>Electrical engineering. Electrical power engineering</subject><subject>Electrical power engineering</subject><subject>ENERGY MANAGEMENT SYSTEMS</subject><subject>ENERGY PLANNING AND POLICY</subject><subject>Exact sciences and technology</subject><subject>FORECASTING</subject><subject>Load forecasting</subject><subject>Maintenance</subject><subject>NEURAL NETWORKS</subject><subject>Operation. Load control. Reliability</subject><subject>POWER DEMAND</subject><subject>Power industry</subject><subject>Power networks and lines</subject><subject>Power system security</subject><subject>POWER TRANSMISSION AND DISTRIBUTION</subject><subject>Robustness</subject><subject>Student members</subject><subject>Weather forecasting</subject><issn>0885-8950</issn><issn>1558-0679</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1995</creationdate><recordtype>article</recordtype><recordid>eNqNkU1v1DAQhi1EJZbCgSsnI6FKHNI68UfsY1VRQKrEpXdr1pmoA068tR1Q_z1ZsuoVTnN4n3lmpJexd624bFvhrrS7VMYoY1-wXau1bYTp3Uu2E9bqxjotXrHXpfwQQpg12LHH65nDAIdKv5BPaVgiZA650kiBIPIZl_x31N8p_-QPacnxiccEAx9TxgCl4rowD5xq4TQdIk44V6iUVnHlGDHUTIEvlSJVwvKGnY0QC749zXN2f_v5_uZrc_f9y7eb67smSKdq04NDt0elQIrgoLNaBNvvUextJ2QrOzMM2KourMg4DtChVHvhnBldkGt-zj5s2lQq-RKoYngIaZ7Xf3xrpOjtylxszCGnxwVL9ROVgDHCjGkpvrNOWeu6_wCV1J3U_wZ7qfpeHo2fNjDkVErG0R8yTZCffCv8sUmvnd-aXNmPJymUAHHMMAcqzwvSKCfc8fb7DSNEfE5Pjj952qbf</recordid><startdate>19950801</startdate><enddate>19950801</enddate><creator>Khotanzad, A.</creator><creator>Rey-Chue Hwang</creator><creator>Abaye, A.</creator><creator>Maratukulam, D.</creator><general>IEEE</general><general>Institute of Electrical and Electronics Engineers</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7SP</scope><scope>H8D</scope><scope>OTOTI</scope></search><sort><creationdate>19950801</creationdate><title>An adaptive modular artificial neural network hourly load forecaster and its implementation at electric utilities</title><author>Khotanzad, A. ; Rey-Chue Hwang ; Abaye, A. ; Maratukulam, D.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c394t-7a9e9be44a30c9a2850c87be0b82031326dde142ce44ffda2e34b0996f9c3313</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1995</creationdate><topic>Applied sciences</topic><topic>Artificial neural networks</topic><topic>COMPUTER CALCULATIONS</topic><topic>Costs</topic><topic>Economic forecasting</topic><topic>Electrical engineering. Electrical power engineering</topic><topic>Electrical power engineering</topic><topic>ENERGY MANAGEMENT SYSTEMS</topic><topic>ENERGY PLANNING AND POLICY</topic><topic>Exact sciences and technology</topic><topic>FORECASTING</topic><topic>Load forecasting</topic><topic>Maintenance</topic><topic>NEURAL NETWORKS</topic><topic>Operation. Load control. Reliability</topic><topic>POWER DEMAND</topic><topic>Power industry</topic><topic>Power networks and lines</topic><topic>Power system security</topic><topic>POWER TRANSMISSION AND DISTRIBUTION</topic><topic>Robustness</topic><topic>Student members</topic><topic>Weather forecasting</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Khotanzad, A.</creatorcontrib><creatorcontrib>Rey-Chue Hwang</creatorcontrib><creatorcontrib>Abaye, A.</creatorcontrib><creatorcontrib>Maratukulam, D.</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Computer and Information Systems 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><collection>Electronics & Communications Abstracts</collection><collection>Aerospace Database</collection><collection>OSTI.GOV</collection><jtitle>IEEE Transactions on Power Systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Khotanzad, A.</au><au>Rey-Chue Hwang</au><au>Abaye, A.</au><au>Maratukulam, D.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An adaptive modular artificial neural network hourly load forecaster and its implementation at electric utilities</atitle><jtitle>IEEE Transactions on Power Systems</jtitle><stitle>TPWRS</stitle><date>1995-08-01</date><risdate>1995</risdate><volume>10</volume><issue>3</issue><spage>1716</spage><epage>1722</epage><pages>1716-1722</pages><issn>0885-8950</issn><eissn>1558-0679</eissn><coden>ITPSEG</coden><abstract>This paper describes a modular artificial neural network (ANN) based hourly load forecaster which has already been implemented at 20 electric utilities across the US and is being used on-line by several of them. The behavior or the load and its correlation with parameters affecting it (e.g. weather variables) are decomposed into three distinct trends of weekly, daily, and hourly. Each trend is modeled by a separate module containing several multi-layer feed-forward ANNs trained by the back-propagation learning rule. The forecasts produced by each module are then combined by adaptive filters to arrive at the final forecast. During the forecasting phase, the parameters of the ANNs within each module are adaptively changed in response to the system's latest forecast accuracy. The performance of the forecaster has been tested on data from these 20 utilities with excellent results. The on-line performance of the system has also been quite satisfactory and superior to other forecasting packages used by the utilities. Moreover, the forecaster is robust, easy to use, and produces accurate results in the case of rapid weather changes.< ></abstract><cop>New York, NY</cop><pub>IEEE</pub><doi>10.1109/59.466468</doi><tpages>7</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0885-8950 |
| ispartof | IEEE Transactions on Power Systems, 1995-08, Vol.10 (3), p.1716-1722 |
| issn | 0885-8950 1558-0679 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_28435235 |
| source | IEEE Electronic Library (IEL) |
| subjects | Applied sciences Artificial neural networks COMPUTER CALCULATIONS Costs Economic forecasting Electrical engineering. Electrical power engineering Electrical power engineering ENERGY MANAGEMENT SYSTEMS ENERGY PLANNING AND POLICY Exact sciences and technology FORECASTING Load forecasting Maintenance NEURAL NETWORKS Operation. Load control. Reliability POWER DEMAND Power industry Power networks and lines Power system security POWER TRANSMISSION AND DISTRIBUTION Robustness Student members Weather forecasting |
| title | An adaptive modular artificial neural network hourly load forecaster and its implementation at electric utilities |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-15T23%3A24%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=An%20adaptive%20modular%20artificial%20neural%20network%20hourly%20load%20forecaster%20and%20its%20implementation%20at%20electric%20utilities&rft.jtitle=IEEE%20Transactions%20on%20Power%20Systems&rft.au=Khotanzad,%20A.&rft.date=1995-08-01&rft.volume=10&rft.issue=3&rft.spage=1716&rft.epage=1722&rft.pages=1716-1722&rft.issn=0885-8950&rft.eissn=1558-0679&rft.coden=ITPSEG&rft_id=info:doi/10.1109/59.466468&rft_dat=%3Cproquest_RIE%3E28435235%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=27347732&rft_id=info:pmid/&rft_ieee_id=466468&rfr_iscdi=true |