Unsupervised machine learning techniques applied to composite reliability assessment of power systems
Summary Composite generation and transmission system reliability evaluation allows the assessment of the risks of system operation failure, taking into account the uncertainties associated with the availability of equipment. One of the great challenges faced in the use of techniques based on probabi...
Gespeichert in:
| Veröffentlicht in: | International transactions on electrical energy systems 2021-11, Vol.31 (11), p.n/a |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | n/a |
|---|---|
| container_issue | 11 |
| container_start_page | |
| container_title | International transactions on electrical energy systems |
| container_volume | 31 |
| creator | Assis, Fernando A. Coelho, Alex J. C. Rezende, Lucas D. Leite da Silva, Armando M. Resende, Leonidas C. |
| description | Summary
Composite generation and transmission system reliability evaluation allows the assessment of the risks of system operation failure, taking into account the uncertainties associated with the availability of equipment. One of the great challenges faced in the use of techniques based on probabilistic assessment during the planning stages is related to the required computational costs. Depending on the reliability levels of the system under study and on the grid size, a large number of operation performance analyzes are necessary. In this sense, this article proposes a new and simple method to efficiently evaluate the composite reliability of electrical power networks. The nonsequential Monte Carlo simulation (MCS) method is combined with unsupervised machine learning (UML) techniques to reduce the computational effort involved in the process of estimating composite reliability indices. The proposed approach allows different unsupervised techniques to be employed, in order to obtain significant reductions in CPU times, without losing the accuracy of the estimated indices. The IEEE‐RTS system, considering the original load and generation and its modified version with the transmission network stressed, in addition to a real large system, is used for evaluating the performance of the proposed method. The results obtained with the use of three different classification techniques (Kohonen self‐organizing map, K‐means, and K‐medoids) are presented and analyzed.
A new and simple method to efficiently evaluate the composite (generation and transmission) reliability of electrical power networks is proposed. The nonsequential Monte Carlo simulation method is combined with unsupervised machine learning techniques to reduce the computational effort involved in the estimation process. Different unsupervised techniques are investigated with significant reductions in CPU times, without loss of accuracy in estimating reliability indices. |
| doi_str_mv | 10.1002/2050-7038.13109 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2591900547</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2591900547</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3579-d2565091b665cdbba3f9981017ef869785c145052906a5b06a9ec538c46ddead3</originalsourceid><addsrcrecordid>eNqFkEFPwzAMhSMEEtPYmWskzt2StmmbI5oGTJoEh-0cpanLMrVNiTum_ntaihA3fLAt63u29Qi552zJGQtXIRMsSFmULXnEmbwis9_J9Z_-liwQT2wIGXOeZjMChwbPLfhPi1DQWpujbYBWoH1jm3fagTk29uMMSHXbVnZgOkeNq1uHtgPqobI6t5XteqoRAbGGpqOupK27gKfYYwc13pGbUlcIi586J4enzX79Euxen7frx11gIpHKoAhFIpjkeZIIU-S5jkopM854CmWWyDQThseCiVCyRIt8SBKMiDITJ0UBuojm5GHa23o3Pt2pkzv7ZjipQiG5ZEzE6UCtJsp4h-ihVK23tfa94kyNdqrRMDUapr7tHBTJpLjYCvr_cLXZb94m4RdA1nhO</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2591900547</pqid></control><display><type>article</type><title>Unsupervised machine learning techniques applied to composite reliability assessment of power systems</title><source>Wiley Journals</source><creator>Assis, Fernando A. ; Coelho, Alex J. C. ; Rezende, Lucas D. ; Leite da Silva, Armando M. ; Resende, Leonidas C.</creator><creatorcontrib>Assis, Fernando A. ; Coelho, Alex J. C. ; Rezende, Lucas D. ; Leite da Silva, Armando M. ; Resende, Leonidas C.</creatorcontrib><description>Summary
Composite generation and transmission system reliability evaluation allows the assessment of the risks of system operation failure, taking into account the uncertainties associated with the availability of equipment. One of the great challenges faced in the use of techniques based on probabilistic assessment during the planning stages is related to the required computational costs. Depending on the reliability levels of the system under study and on the grid size, a large number of operation performance analyzes are necessary. In this sense, this article proposes a new and simple method to efficiently evaluate the composite reliability of electrical power networks. The nonsequential Monte Carlo simulation (MCS) method is combined with unsupervised machine learning (UML) techniques to reduce the computational effort involved in the process of estimating composite reliability indices. The proposed approach allows different unsupervised techniques to be employed, in order to obtain significant reductions in CPU times, without losing the accuracy of the estimated indices. The IEEE‐RTS system, considering the original load and generation and its modified version with the transmission network stressed, in addition to a real large system, is used for evaluating the performance of the proposed method. The results obtained with the use of three different classification techniques (Kohonen self‐organizing map, K‐means, and K‐medoids) are presented and analyzed.
A new and simple method to efficiently evaluate the composite (generation and transmission) reliability of electrical power networks is proposed. The nonsequential Monte Carlo simulation method is combined with unsupervised machine learning techniques to reduce the computational effort involved in the estimation process. Different unsupervised techniques are investigated with significant reductions in CPU times, without loss of accuracy in estimating reliability indices.</description><identifier>ISSN: 2050-7038</identifier><identifier>EISSN: 2050-7038</identifier><identifier>DOI: 10.1002/2050-7038.13109</identifier><language>eng</language><publisher>Hoboken: Hindawi Limited</publisher><subject>clustering algorithms ; composite reliability ; Computing costs ; Electric power ; electric power systems ; Machine learning ; Monte Carlo simulation ; Network reliability ; Performance evaluation ; Reliability analysis ; System reliability ; Unsupervised learning ; unsupervised machine learning</subject><ispartof>International transactions on electrical energy systems, 2021-11, Vol.31 (11), p.n/a</ispartof><rights>2021 John Wiley & Sons Ltd.</rights><rights>2021 John Wiley & Sons, Ltd.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3579-d2565091b665cdbba3f9981017ef869785c145052906a5b06a9ec538c46ddead3</citedby><cites>FETCH-LOGICAL-c3579-d2565091b665cdbba3f9981017ef869785c145052906a5b06a9ec538c46ddead3</cites><orcidid>0000-0002-4749-3303 ; 0000-0002-0283-6018 ; 0000-0001-6064-4666</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1002%2F2050-7038.13109$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2F2050-7038.13109$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,780,784,1417,27924,27925,45574,45575</link.rule.ids></links><search><creatorcontrib>Assis, Fernando A.</creatorcontrib><creatorcontrib>Coelho, Alex J. C.</creatorcontrib><creatorcontrib>Rezende, Lucas D.</creatorcontrib><creatorcontrib>Leite da Silva, Armando M.</creatorcontrib><creatorcontrib>Resende, Leonidas C.</creatorcontrib><title>Unsupervised machine learning techniques applied to composite reliability assessment of power systems</title><title>International transactions on electrical energy systems</title><description>Summary
Composite generation and transmission system reliability evaluation allows the assessment of the risks of system operation failure, taking into account the uncertainties associated with the availability of equipment. One of the great challenges faced in the use of techniques based on probabilistic assessment during the planning stages is related to the required computational costs. Depending on the reliability levels of the system under study and on the grid size, a large number of operation performance analyzes are necessary. In this sense, this article proposes a new and simple method to efficiently evaluate the composite reliability of electrical power networks. The nonsequential Monte Carlo simulation (MCS) method is combined with unsupervised machine learning (UML) techniques to reduce the computational effort involved in the process of estimating composite reliability indices. The proposed approach allows different unsupervised techniques to be employed, in order to obtain significant reductions in CPU times, without losing the accuracy of the estimated indices. The IEEE‐RTS system, considering the original load and generation and its modified version with the transmission network stressed, in addition to a real large system, is used for evaluating the performance of the proposed method. The results obtained with the use of three different classification techniques (Kohonen self‐organizing map, K‐means, and K‐medoids) are presented and analyzed.
A new and simple method to efficiently evaluate the composite (generation and transmission) reliability of electrical power networks is proposed. The nonsequential Monte Carlo simulation method is combined with unsupervised machine learning techniques to reduce the computational effort involved in the estimation process. Different unsupervised techniques are investigated with significant reductions in CPU times, without loss of accuracy in estimating reliability indices.</description><subject>clustering algorithms</subject><subject>composite reliability</subject><subject>Computing costs</subject><subject>Electric power</subject><subject>electric power systems</subject><subject>Machine learning</subject><subject>Monte Carlo simulation</subject><subject>Network reliability</subject><subject>Performance evaluation</subject><subject>Reliability analysis</subject><subject>System reliability</subject><subject>Unsupervised learning</subject><subject>unsupervised machine learning</subject><issn>2050-7038</issn><issn>2050-7038</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNqFkEFPwzAMhSMEEtPYmWskzt2StmmbI5oGTJoEh-0cpanLMrVNiTum_ntaihA3fLAt63u29Qi552zJGQtXIRMsSFmULXnEmbwis9_J9Z_-liwQT2wIGXOeZjMChwbPLfhPi1DQWpujbYBWoH1jm3fagTk29uMMSHXbVnZgOkeNq1uHtgPqobI6t5XteqoRAbGGpqOupK27gKfYYwc13pGbUlcIi586J4enzX79Euxen7frx11gIpHKoAhFIpjkeZIIU-S5jkopM854CmWWyDQThseCiVCyRIt8SBKMiDITJ0UBuojm5GHa23o3Pt2pkzv7ZjipQiG5ZEzE6UCtJsp4h-ihVK23tfa94kyNdqrRMDUapr7tHBTJpLjYCvr_cLXZb94m4RdA1nhO</recordid><startdate>202111</startdate><enddate>202111</enddate><creator>Assis, Fernando A.</creator><creator>Coelho, Alex J. C.</creator><creator>Rezende, Lucas D.</creator><creator>Leite da Silva, Armando M.</creator><creator>Resende, Leonidas C.</creator><general>Hindawi Limited</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>H8D</scope><scope>KR7</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0002-4749-3303</orcidid><orcidid>https://orcid.org/0000-0002-0283-6018</orcidid><orcidid>https://orcid.org/0000-0001-6064-4666</orcidid></search><sort><creationdate>202111</creationdate><title>Unsupervised machine learning techniques applied to composite reliability assessment of power systems</title><author>Assis, Fernando A. ; Coelho, Alex J. C. ; Rezende, Lucas D. ; Leite da Silva, Armando M. ; Resende, Leonidas C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3579-d2565091b665cdbba3f9981017ef869785c145052906a5b06a9ec538c46ddead3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>clustering algorithms</topic><topic>composite reliability</topic><topic>Computing costs</topic><topic>Electric power</topic><topic>electric power systems</topic><topic>Machine learning</topic><topic>Monte Carlo simulation</topic><topic>Network reliability</topic><topic>Performance evaluation</topic><topic>Reliability analysis</topic><topic>System reliability</topic><topic>Unsupervised learning</topic><topic>unsupervised machine learning</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Assis, Fernando A.</creatorcontrib><creatorcontrib>Coelho, Alex J. C.</creatorcontrib><creatorcontrib>Rezende, Lucas D.</creatorcontrib><creatorcontrib>Leite da Silva, Armando M.</creatorcontrib><creatorcontrib>Resende, Leonidas C.</creatorcontrib><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>International transactions on electrical energy systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Assis, Fernando A.</au><au>Coelho, Alex J. C.</au><au>Rezende, Lucas D.</au><au>Leite da Silva, Armando M.</au><au>Resende, Leonidas C.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Unsupervised machine learning techniques applied to composite reliability assessment of power systems</atitle><jtitle>International transactions on electrical energy systems</jtitle><date>2021-11</date><risdate>2021</risdate><volume>31</volume><issue>11</issue><epage>n/a</epage><issn>2050-7038</issn><eissn>2050-7038</eissn><abstract>Summary
Composite generation and transmission system reliability evaluation allows the assessment of the risks of system operation failure, taking into account the uncertainties associated with the availability of equipment. One of the great challenges faced in the use of techniques based on probabilistic assessment during the planning stages is related to the required computational costs. Depending on the reliability levels of the system under study and on the grid size, a large number of operation performance analyzes are necessary. In this sense, this article proposes a new and simple method to efficiently evaluate the composite reliability of electrical power networks. The nonsequential Monte Carlo simulation (MCS) method is combined with unsupervised machine learning (UML) techniques to reduce the computational effort involved in the process of estimating composite reliability indices. The proposed approach allows different unsupervised techniques to be employed, in order to obtain significant reductions in CPU times, without losing the accuracy of the estimated indices. The IEEE‐RTS system, considering the original load and generation and its modified version with the transmission network stressed, in addition to a real large system, is used for evaluating the performance of the proposed method. The results obtained with the use of three different classification techniques (Kohonen self‐organizing map, K‐means, and K‐medoids) are presented and analyzed.
A new and simple method to efficiently evaluate the composite (generation and transmission) reliability of electrical power networks is proposed. The nonsequential Monte Carlo simulation method is combined with unsupervised machine learning techniques to reduce the computational effort involved in the estimation process. Different unsupervised techniques are investigated with significant reductions in CPU times, without loss of accuracy in estimating reliability indices.</abstract><cop>Hoboken</cop><pub>Hindawi Limited</pub><doi>10.1002/2050-7038.13109</doi><tpages>18</tpages><orcidid>https://orcid.org/0000-0002-4749-3303</orcidid><orcidid>https://orcid.org/0000-0002-0283-6018</orcidid><orcidid>https://orcid.org/0000-0001-6064-4666</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2050-7038 |
| ispartof | International transactions on electrical energy systems, 2021-11, Vol.31 (11), p.n/a |
| issn | 2050-7038 2050-7038 |
| language | eng |
| recordid | cdi_proquest_journals_2591900547 |
| source | Wiley Journals |
| subjects | clustering algorithms composite reliability Computing costs Electric power electric power systems Machine learning Monte Carlo simulation Network reliability Performance evaluation Reliability analysis System reliability Unsupervised learning unsupervised machine learning |
| title | Unsupervised machine learning techniques applied to composite reliability assessment of power systems |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T01%3A02%3A25IST&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=Unsupervised%20machine%20learning%20techniques%20applied%20to%20composite%20reliability%20assessment%20of%20power%20systems&rft.jtitle=International%20transactions%20on%20electrical%20energy%20systems&rft.au=Assis,%20Fernando%20A.&rft.date=2021-11&rft.volume=31&rft.issue=11&rft.epage=n/a&rft.issn=2050-7038&rft.eissn=2050-7038&rft_id=info:doi/10.1002/2050-7038.13109&rft_dat=%3Cproquest_cross%3E2591900547%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=2591900547&rft_id=info:pmid/&rfr_iscdi=true |