Loading…
Cost Effective Dynamic Multi-Microgrid Formulation Method Using Deep Reinforcement Learning
This paper proposes an online Dynamic Multi-Microgrid Formulation (DMMF) method using Deep Reinforcement Learning. It aims to reconfigure the microgrid into several self-supplied islands and minimize total operation cost at the same time. Spanning Tree Algorithm is used to reduce the total number of...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 5 |
| container_issue | |
| container_start_page | 1 |
| container_title | |
| container_volume | |
| creator | Jung, YoonGun Chang, Minhyeok Kang, Sungwoo Jang, Gilsoo Lee, Hojun Yoon, Minhan Song, Sungyoon Han, Changhee |
| description | This paper proposes an online Dynamic Multi-Microgrid Formulation (DMMF) method using Deep Reinforcement Learning. It aims to reconfigure the microgrid into several self-supplied islands and minimize total operation cost at the same time. Spanning Tree Algorithm is used to reduce the total number of microgrid formulation. Proximal-Policy optimization is implemented to train the agent which determines the status of sectionalizing switches in microgrid in real-time. To show the effectiveness of the proposed DMMF method, a case study was conducted in the modified cigre-14 bus test network. The results demonstrated that the proposed DMMF method reduced the total operation cost compared to the operation cost derive from original Cigre 14 bus formulation. |
| doi_str_mv | 10.1109/PESGM52003.2023.10253225 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_10253225</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10253225</ieee_id><sourcerecordid>10253225</sourcerecordid><originalsourceid>FETCH-LOGICAL-i204t-e1b007d6364ab1fe5b39f9d0b130619999133932c973c2bcba1a80325c115d43</originalsourceid><addsrcrecordid>eNo1kM1KAzEURqMgWGvfwEVeYOq9uUlqltJfoYOideWiZDJ3aqQzUzJToW9vQT2bb3HgWxwhJMIYEdz9y_xtmRsFQGMFisYIypBS5kLcoLVGW60RLsUAndaZc0TXYtR1X3DG6Im1aiA-pm3Xy3lVcejjN8vZqfF1DDI_7vuY5TGkdpdiKRdtqo9738e2kTn3n20p37vY7OSM-SBfOTZVmwLX3PRyzT41Z3crriq_73j0t0OxWcw301W2fl4-TR_XWVSg-4yxAJiUlqz2BVZsCnKVK6FAAovuDBI5UsFNKKgiFB79A5AyAdGUmobi7vc2MvP2kGLt02n734J-AP5fU_A</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Cost Effective Dynamic Multi-Microgrid Formulation Method Using Deep Reinforcement Learning</title><source>IEEE Xplore All Conference Series</source><creator>Jung, YoonGun ; Chang, Minhyeok ; Kang, Sungwoo ; Jang, Gilsoo ; Lee, Hojun ; Yoon, Minhan ; Song, Sungyoon ; Han, Changhee</creator><creatorcontrib>Jung, YoonGun ; Chang, Minhyeok ; Kang, Sungwoo ; Jang, Gilsoo ; Lee, Hojun ; Yoon, Minhan ; Song, Sungyoon ; Han, Changhee</creatorcontrib><description>This paper proposes an online Dynamic Multi-Microgrid Formulation (DMMF) method using Deep Reinforcement Learning. It aims to reconfigure the microgrid into several self-supplied islands and minimize total operation cost at the same time. Spanning Tree Algorithm is used to reduce the total number of microgrid formulation. Proximal-Policy optimization is implemented to train the agent which determines the status of sectionalizing switches in microgrid in real-time. To show the effectiveness of the proposed DMMF method, a case study was conducted in the modified cigre-14 bus test network. The results demonstrated that the proposed DMMF method reduced the total operation cost compared to the operation cost derive from original Cigre 14 bus formulation.</description><identifier>EISSN: 1944-9933</identifier><identifier>EISBN: 1665464410</identifier><identifier>EISBN: 9781665464413</identifier><identifier>DOI: 10.1109/PESGM52003.2023.10253225</identifier><language>eng</language><publisher>IEEE</publisher><subject>Costs ; Deep learning ; Deep Reinforcement Learning (DRL) ; Distributed generation (DG) ; Dynamic Multi-Microgrid Formulation ; Force ; Heuristic algorithms ; Microgrid (MG) ; Microgrids ; Reconfiguration ; Reinforcement learning ; Spanning Tree Algorithm ; Switches</subject><ispartof>2023 IEEE Power & Energy Society General Meeting (PESGM), 2023, p.1-5</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10253225$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,23909,23910,25118,27902,54530,54907</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10253225$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Jung, YoonGun</creatorcontrib><creatorcontrib>Chang, Minhyeok</creatorcontrib><creatorcontrib>Kang, Sungwoo</creatorcontrib><creatorcontrib>Jang, Gilsoo</creatorcontrib><creatorcontrib>Lee, Hojun</creatorcontrib><creatorcontrib>Yoon, Minhan</creatorcontrib><creatorcontrib>Song, Sungyoon</creatorcontrib><creatorcontrib>Han, Changhee</creatorcontrib><title>Cost Effective Dynamic Multi-Microgrid Formulation Method Using Deep Reinforcement Learning</title><title>2023 IEEE Power & Energy Society General Meeting (PESGM)</title><addtitle>PESGM</addtitle><description>This paper proposes an online Dynamic Multi-Microgrid Formulation (DMMF) method using Deep Reinforcement Learning. It aims to reconfigure the microgrid into several self-supplied islands and minimize total operation cost at the same time. Spanning Tree Algorithm is used to reduce the total number of microgrid formulation. Proximal-Policy optimization is implemented to train the agent which determines the status of sectionalizing switches in microgrid in real-time. To show the effectiveness of the proposed DMMF method, a case study was conducted in the modified cigre-14 bus test network. The results demonstrated that the proposed DMMF method reduced the total operation cost compared to the operation cost derive from original Cigre 14 bus formulation.</description><subject>Costs</subject><subject>Deep learning</subject><subject>Deep Reinforcement Learning (DRL)</subject><subject>Distributed generation (DG)</subject><subject>Dynamic Multi-Microgrid Formulation</subject><subject>Force</subject><subject>Heuristic algorithms</subject><subject>Microgrid (MG)</subject><subject>Microgrids</subject><subject>Reconfiguration</subject><subject>Reinforcement learning</subject><subject>Spanning Tree Algorithm</subject><subject>Switches</subject><issn>1944-9933</issn><isbn>1665464410</isbn><isbn>9781665464413</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2023</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo1kM1KAzEURqMgWGvfwEVeYOq9uUlqltJfoYOideWiZDJ3aqQzUzJToW9vQT2bb3HgWxwhJMIYEdz9y_xtmRsFQGMFisYIypBS5kLcoLVGW60RLsUAndaZc0TXYtR1X3DG6Im1aiA-pm3Xy3lVcejjN8vZqfF1DDI_7vuY5TGkdpdiKRdtqo9738e2kTn3n20p37vY7OSM-SBfOTZVmwLX3PRyzT41Z3crriq_73j0t0OxWcw301W2fl4-TR_XWVSg-4yxAJiUlqz2BVZsCnKVK6FAAovuDBI5UsFNKKgiFB79A5AyAdGUmobi7vc2MvP2kGLt02n734J-AP5fU_A</recordid><startdate>20230716</startdate><enddate>20230716</enddate><creator>Jung, YoonGun</creator><creator>Chang, Minhyeok</creator><creator>Kang, Sungwoo</creator><creator>Jang, Gilsoo</creator><creator>Lee, Hojun</creator><creator>Yoon, Minhan</creator><creator>Song, Sungyoon</creator><creator>Han, Changhee</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>20230716</creationdate><title>Cost Effective Dynamic Multi-Microgrid Formulation Method Using Deep Reinforcement Learning</title><author>Jung, YoonGun ; Chang, Minhyeok ; Kang, Sungwoo ; Jang, Gilsoo ; Lee, Hojun ; Yoon, Minhan ; Song, Sungyoon ; Han, Changhee</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i204t-e1b007d6364ab1fe5b39f9d0b130619999133932c973c2bcba1a80325c115d43</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Costs</topic><topic>Deep learning</topic><topic>Deep Reinforcement Learning (DRL)</topic><topic>Distributed generation (DG)</topic><topic>Dynamic Multi-Microgrid Formulation</topic><topic>Force</topic><topic>Heuristic algorithms</topic><topic>Microgrid (MG)</topic><topic>Microgrids</topic><topic>Reconfiguration</topic><topic>Reinforcement learning</topic><topic>Spanning Tree Algorithm</topic><topic>Switches</topic><toplevel>online_resources</toplevel><creatorcontrib>Jung, YoonGun</creatorcontrib><creatorcontrib>Chang, Minhyeok</creatorcontrib><creatorcontrib>Kang, Sungwoo</creatorcontrib><creatorcontrib>Jang, Gilsoo</creatorcontrib><creatorcontrib>Lee, Hojun</creatorcontrib><creatorcontrib>Yoon, Minhan</creatorcontrib><creatorcontrib>Song, Sungyoon</creatorcontrib><creatorcontrib>Han, Changhee</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Jung, YoonGun</au><au>Chang, Minhyeok</au><au>Kang, Sungwoo</au><au>Jang, Gilsoo</au><au>Lee, Hojun</au><au>Yoon, Minhan</au><au>Song, Sungyoon</au><au>Han, Changhee</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Cost Effective Dynamic Multi-Microgrid Formulation Method Using Deep Reinforcement Learning</atitle><btitle>2023 IEEE Power & Energy Society General Meeting (PESGM)</btitle><stitle>PESGM</stitle><date>2023-07-16</date><risdate>2023</risdate><spage>1</spage><epage>5</epage><pages>1-5</pages><eissn>1944-9933</eissn><eisbn>1665464410</eisbn><eisbn>9781665464413</eisbn><abstract>This paper proposes an online Dynamic Multi-Microgrid Formulation (DMMF) method using Deep Reinforcement Learning. It aims to reconfigure the microgrid into several self-supplied islands and minimize total operation cost at the same time. Spanning Tree Algorithm is used to reduce the total number of microgrid formulation. Proximal-Policy optimization is implemented to train the agent which determines the status of sectionalizing switches in microgrid in real-time. To show the effectiveness of the proposed DMMF method, a case study was conducted in the modified cigre-14 bus test network. The results demonstrated that the proposed DMMF method reduced the total operation cost compared to the operation cost derive from original Cigre 14 bus formulation.</abstract><pub>IEEE</pub><doi>10.1109/PESGM52003.2023.10253225</doi><tpages>5</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | EISSN: 1944-9933 |
| ispartof | 2023 IEEE Power & Energy Society General Meeting (PESGM), 2023, p.1-5 |
| issn | 1944-9933 |
| language | eng |
| recordid | cdi_ieee_primary_10253225 |
| source | IEEE Xplore All Conference Series |
| subjects | Costs Deep learning Deep Reinforcement Learning (DRL) Distributed generation (DG) Dynamic Multi-Microgrid Formulation Force Heuristic algorithms Microgrid (MG) Microgrids Reconfiguration Reinforcement learning Spanning Tree Algorithm Switches |
| title | Cost Effective Dynamic Multi-Microgrid Formulation Method Using Deep Reinforcement Learning |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T08%3A04%3A51IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Cost%20Effective%20Dynamic%20Multi-Microgrid%20Formulation%20Method%20Using%20Deep%20Reinforcement%20Learning&rft.btitle=2023%20IEEE%20Power%20&%20Energy%20Society%20General%20Meeting%20(PESGM)&rft.au=Jung,%20YoonGun&rft.date=2023-07-16&rft.spage=1&rft.epage=5&rft.pages=1-5&rft.eissn=1944-9933&rft_id=info:doi/10.1109/PESGM52003.2023.10253225&rft.eisbn=1665464410&rft.eisbn_list=9781665464413&rft_dat=%3Cieee_CHZPO%3E10253225%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i204t-e1b007d6364ab1fe5b39f9d0b130619999133932c973c2bcba1a80325c115d43%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10253225&rfr_iscdi=true |