Sparse Wide-Area Control of Power Systems using Data-driven Reinforcement Learning

In this paper we present an online wide-area oscillation damping control (WAC) design for uncertain models of power systems using ideas from reinforcement learning. We assume that the exact small-signal model of the power system at the onset of a contingency is not known to the operator and use the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dizche, Amirhassan Fallah, Chakrabortty, Aranya, Duel-Hallen, Alexandra
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Dizche, Amirhassan Fallah
Chakrabortty, Aranya
Duel-Hallen, Alexandra
description In this paper we present an online wide-area oscillation damping control (WAC) design for uncertain models of power systems using ideas from reinforcement learning. We assume that the exact small-signal model of the power system at the onset of a contingency is not known to the operator and use the nominal model and online measurements of the generator states and control inputs to rapidly converge to a state-feedback controller that minimizes a given quadratic energy cost. However, unlike conventional linear quadratic regulators (LQR), we intend our controller to be sparse, so its implementation reduces the communication costs. We, therefore, employ the gradient support pursuit (GraSP) optimization algorithm to impose sparsity constraints on the control gain matrix during learning. The sparse controller is thereafter implemented using distributed communication. Using the IEEE 39-bus power system model with 1149 unknown parameters, it is demonstrated that the proposed learning method provides reliable LQR performance while the controller matched to the nominal model becomes unstable for severely uncertain systems.
doi_str_mv 10.48550/arxiv.1804.09827
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1804_09827</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1804_09827</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-b4449e64210b6f39cf94741fce9bc6a0627bb6d5c7469dcd59fe6d2bb872e4d03</originalsourceid><addsrcrecordid>eNotz71OwzAYhWEvHVDLBTDhG3BwHMeOxyr8SpGK2kqMkX8-I0uNXdmh0LsHCtNZXh3pQeimphXv2pbe6fwVTlXdUV5R1TF5hba7o84F8FtwQNYZNO5TnHM64OTxa_qEjHfnMsNU8EcJ8R3f61kTl8MJIt5CiD5lCxPEGQ-gc_xJVmjh9aHA9f8u0f7xYd8_k2Hz9NKvB6KFlMRwzhUIzmpqhG-U9YpLXnsLylihqWDSGOFaK7lQzrpWeRCOGdNJBtzRZolu_24vqPGYw6TzefzFjRdc8w3gZ0qv</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Sparse Wide-Area Control of Power Systems using Data-driven Reinforcement Learning</title><source>arXiv.org</source><creator>Dizche, Amirhassan Fallah ; Chakrabortty, Aranya ; Duel-Hallen, Alexandra</creator><creatorcontrib>Dizche, Amirhassan Fallah ; Chakrabortty, Aranya ; Duel-Hallen, Alexandra</creatorcontrib><description>In this paper we present an online wide-area oscillation damping control (WAC) design for uncertain models of power systems using ideas from reinforcement learning. We assume that the exact small-signal model of the power system at the onset of a contingency is not known to the operator and use the nominal model and online measurements of the generator states and control inputs to rapidly converge to a state-feedback controller that minimizes a given quadratic energy cost. However, unlike conventional linear quadratic regulators (LQR), we intend our controller to be sparse, so its implementation reduces the communication costs. We, therefore, employ the gradient support pursuit (GraSP) optimization algorithm to impose sparsity constraints on the control gain matrix during learning. The sparse controller is thereafter implemented using distributed communication. Using the IEEE 39-bus power system model with 1149 unknown parameters, it is demonstrated that the proposed learning method provides reliable LQR performance while the controller matched to the nominal model becomes unstable for severely uncertain systems.</description><identifier>DOI: 10.48550/arxiv.1804.09827</identifier><language>eng</language><subject>Computer Science - Systems and Control</subject><creationdate>2018-04</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1804.09827$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1804.09827$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Dizche, Amirhassan Fallah</creatorcontrib><creatorcontrib>Chakrabortty, Aranya</creatorcontrib><creatorcontrib>Duel-Hallen, Alexandra</creatorcontrib><title>Sparse Wide-Area Control of Power Systems using Data-driven Reinforcement Learning</title><description>In this paper we present an online wide-area oscillation damping control (WAC) design for uncertain models of power systems using ideas from reinforcement learning. We assume that the exact small-signal model of the power system at the onset of a contingency is not known to the operator and use the nominal model and online measurements of the generator states and control inputs to rapidly converge to a state-feedback controller that minimizes a given quadratic energy cost. However, unlike conventional linear quadratic regulators (LQR), we intend our controller to be sparse, so its implementation reduces the communication costs. We, therefore, employ the gradient support pursuit (GraSP) optimization algorithm to impose sparsity constraints on the control gain matrix during learning. The sparse controller is thereafter implemented using distributed communication. Using the IEEE 39-bus power system model with 1149 unknown parameters, it is demonstrated that the proposed learning method provides reliable LQR performance while the controller matched to the nominal model becomes unstable for severely uncertain systems.</description><subject>Computer Science - Systems and Control</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz71OwzAYhWEvHVDLBTDhG3BwHMeOxyr8SpGK2kqMkX8-I0uNXdmh0LsHCtNZXh3pQeimphXv2pbe6fwVTlXdUV5R1TF5hba7o84F8FtwQNYZNO5TnHM64OTxa_qEjHfnMsNU8EcJ8R3f61kTl8MJIt5CiD5lCxPEGQ-gc_xJVmjh9aHA9f8u0f7xYd8_k2Hz9NKvB6KFlMRwzhUIzmpqhG-U9YpLXnsLylihqWDSGOFaK7lQzrpWeRCOGdNJBtzRZolu_24vqPGYw6TzefzFjRdc8w3gZ0qv</recordid><startdate>20180425</startdate><enddate>20180425</enddate><creator>Dizche, Amirhassan Fallah</creator><creator>Chakrabortty, Aranya</creator><creator>Duel-Hallen, Alexandra</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20180425</creationdate><title>Sparse Wide-Area Control of Power Systems using Data-driven Reinforcement Learning</title><author>Dizche, Amirhassan Fallah ; Chakrabortty, Aranya ; Duel-Hallen, Alexandra</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-b4449e64210b6f39cf94741fce9bc6a0627bb6d5c7469dcd59fe6d2bb872e4d03</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Computer Science - Systems and Control</topic><toplevel>online_resources</toplevel><creatorcontrib>Dizche, Amirhassan Fallah</creatorcontrib><creatorcontrib>Chakrabortty, Aranya</creatorcontrib><creatorcontrib>Duel-Hallen, Alexandra</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Dizche, Amirhassan Fallah</au><au>Chakrabortty, Aranya</au><au>Duel-Hallen, Alexandra</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Sparse Wide-Area Control of Power Systems using Data-driven Reinforcement Learning</atitle><date>2018-04-25</date><risdate>2018</risdate><abstract>In this paper we present an online wide-area oscillation damping control (WAC) design for uncertain models of power systems using ideas from reinforcement learning. We assume that the exact small-signal model of the power system at the onset of a contingency is not known to the operator and use the nominal model and online measurements of the generator states and control inputs to rapidly converge to a state-feedback controller that minimizes a given quadratic energy cost. However, unlike conventional linear quadratic regulators (LQR), we intend our controller to be sparse, so its implementation reduces the communication costs. We, therefore, employ the gradient support pursuit (GraSP) optimization algorithm to impose sparsity constraints on the control gain matrix during learning. The sparse controller is thereafter implemented using distributed communication. Using the IEEE 39-bus power system model with 1149 unknown parameters, it is demonstrated that the proposed learning method provides reliable LQR performance while the controller matched to the nominal model becomes unstable for severely uncertain systems.</abstract><doi>10.48550/arxiv.1804.09827</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1804.09827
ispartof
issn
language eng
recordid cdi_arxiv_primary_1804_09827
source arXiv.org
subjects Computer Science - Systems and Control
title Sparse Wide-Area Control of Power Systems using Data-driven Reinforcement Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T20%3A30%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Sparse%20Wide-Area%20Control%20of%20Power%20Systems%20using%20Data-driven%20Reinforcement%20Learning&rft.au=Dizche,%20Amirhassan%20Fallah&rft.date=2018-04-25&rft_id=info:doi/10.48550/arxiv.1804.09827&rft_dat=%3Carxiv_GOX%3E1804_09827%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true