Compressive System Identification of LTI and LTV ARX models

In this paper, we consider identifying Auto Regressive with eXternal input (ARX) models for both Linear Time-Invariant (LTI) and Linear Time-Variant (LTV) systems. We aim at doing the identification from the smallest possible number of observations. This is inspired by the field of Compressive Sensi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sanandaji, B. M., Vincent, T. L., Wakin, M. B., Toth, R., Poolla, K.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 798
container_issue
container_start_page 791
container_title
container_volume
creator Sanandaji, B. M.
Vincent, T. L.
Wakin, M. B.
Toth, R.
Poolla, K.
description In this paper, we consider identifying Auto Regressive with eXternal input (ARX) models for both Linear Time-Invariant (LTI) and Linear Time-Variant (LTV) systems. We aim at doing the identification from the smallest possible number of observations. This is inspired by the field of Compressive Sensing (CS), and for this reason, we call this problem Compressive System Identification (CSI). In the case of LTI ARX systems, a system with a large number of inputs and unknown input delays on each channel can require a model structure with a large number of parameters, unless input delay estimation is performed. Since the complexity of input delay estimation increases exponentially in the number of inputs, this can be difficult for high dimensional systems. We show that in cases where the LTI system has possibly many inputs with different unknown delays, simultaneous ARX identification and input delay estimation is possible from few observations, even though this leaves an apparently ill-conditioned identification problem. We discuss identification guarantees and support our proposed method with simulations. We also consider identifying LTV ARX models. In particular, we consider systems with parameters that change only at a few time instants in a piecewise-constant manner where neither the change moments nor the number of changes is known a priori. The main technical novelty of our approach is in casting the identification problem as recovery of a block-sparse signal from an underdetermined set of linear equations. We suggest a random sampling approach for LTV identification, address the issue of identifiability and again support our approach with illustrative simulations.
doi_str_mv 10.1109/CDC.2011.6160935
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6160935</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6160935</ieee_id><sourcerecordid>6160935</sourcerecordid><originalsourceid>FETCH-LOGICAL-i217t-4c077472e6cf6281ac74c7eeff03921270f970c0956ba45da1e6122f28c2235f3</originalsourceid><addsrcrecordid>eNotj01LAzEUACMq2NbeBS_5A7u-95JNNngq61ehIGgVbyVmXyDS7ZbNIvTfW7CnuQ0zQtwglIjg7pqHpiRALA0acKo6E1PUxirQlVXnYu5sjQap1jWAuRATQIcFEZorMc35BwBqMGYi7pu-2w-cc_pl-X7II3dy2fJuTDEFP6Z-J_soV-ul9Lv2yE-5ePuSXd_yNl-Ly-i3mecnzsTH0-O6eSlWr8_LZrEqEqEdCx3AWm2JTYiGavTB6mCZYwTlCMlCdBYCuMp8e121HvlYTpHqQKSqqGbi9t-bmHmzH1Lnh8PmNK7-AD5bR5E</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Compressive System Identification of LTI and LTV ARX models</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Sanandaji, B. M. ; Vincent, T. L. ; Wakin, M. B. ; Toth, R. ; Poolla, K.</creator><creatorcontrib>Sanandaji, B. M. ; Vincent, T. L. ; Wakin, M. B. ; Toth, R. ; Poolla, K.</creatorcontrib><description>In this paper, we consider identifying Auto Regressive with eXternal input (ARX) models for both Linear Time-Invariant (LTI) and Linear Time-Variant (LTV) systems. We aim at doing the identification from the smallest possible number of observations. This is inspired by the field of Compressive Sensing (CS), and for this reason, we call this problem Compressive System Identification (CSI). In the case of LTI ARX systems, a system with a large number of inputs and unknown input delays on each channel can require a model structure with a large number of parameters, unless input delay estimation is performed. Since the complexity of input delay estimation increases exponentially in the number of inputs, this can be difficult for high dimensional systems. We show that in cases where the LTI system has possibly many inputs with different unknown delays, simultaneous ARX identification and input delay estimation is possible from few observations, even though this leaves an apparently ill-conditioned identification problem. We discuss identification guarantees and support our proposed method with simulations. We also consider identifying LTV ARX models. In particular, we consider systems with parameters that change only at a few time instants in a piecewise-constant manner where neither the change moments nor the number of changes is known a priori. The main technical novelty of our approach is in casting the identification problem as recovery of a block-sparse signal from an underdetermined set of linear equations. We suggest a random sampling approach for LTV identification, address the issue of identifiability and again support our approach with illustrative simulations.</description><identifier>ISSN: 0191-2216</identifier><identifier>ISBN: 9781612848006</identifier><identifier>ISBN: 1612848001</identifier><identifier>EISBN: 1467304573</identifier><identifier>EISBN: 1612847994</identifier><identifier>EISBN: 9781612847993</identifier><identifier>EISBN: 161284801X</identifier><identifier>EISBN: 9781612848013</identifier><identifier>EISBN: 9781467304573</identifier><identifier>DOI: 10.1109/CDC.2011.6160935</identifier><language>eng</language><publisher>IEEE</publisher><subject>Coherence ; Delay estimation ; Equations ; Matching pursuit algorithms ; Mathematical model ; Vectors</subject><ispartof>2011 50th IEEE Conference on Decision and Control and European Control Conference, 2011, p.791-798</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6160935$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6160935$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Sanandaji, B. M.</creatorcontrib><creatorcontrib>Vincent, T. L.</creatorcontrib><creatorcontrib>Wakin, M. B.</creatorcontrib><creatorcontrib>Toth, R.</creatorcontrib><creatorcontrib>Poolla, K.</creatorcontrib><title>Compressive System Identification of LTI and LTV ARX models</title><title>2011 50th IEEE Conference on Decision and Control and European Control Conference</title><addtitle>CDC</addtitle><description>In this paper, we consider identifying Auto Regressive with eXternal input (ARX) models for both Linear Time-Invariant (LTI) and Linear Time-Variant (LTV) systems. We aim at doing the identification from the smallest possible number of observations. This is inspired by the field of Compressive Sensing (CS), and for this reason, we call this problem Compressive System Identification (CSI). In the case of LTI ARX systems, a system with a large number of inputs and unknown input delays on each channel can require a model structure with a large number of parameters, unless input delay estimation is performed. Since the complexity of input delay estimation increases exponentially in the number of inputs, this can be difficult for high dimensional systems. We show that in cases where the LTI system has possibly many inputs with different unknown delays, simultaneous ARX identification and input delay estimation is possible from few observations, even though this leaves an apparently ill-conditioned identification problem. We discuss identification guarantees and support our proposed method with simulations. We also consider identifying LTV ARX models. In particular, we consider systems with parameters that change only at a few time instants in a piecewise-constant manner where neither the change moments nor the number of changes is known a priori. The main technical novelty of our approach is in casting the identification problem as recovery of a block-sparse signal from an underdetermined set of linear equations. We suggest a random sampling approach for LTV identification, address the issue of identifiability and again support our approach with illustrative simulations.</description><subject>Coherence</subject><subject>Delay estimation</subject><subject>Equations</subject><subject>Matching pursuit algorithms</subject><subject>Mathematical model</subject><subject>Vectors</subject><issn>0191-2216</issn><isbn>9781612848006</isbn><isbn>1612848001</isbn><isbn>1467304573</isbn><isbn>1612847994</isbn><isbn>9781612847993</isbn><isbn>161284801X</isbn><isbn>9781612848013</isbn><isbn>9781467304573</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotj01LAzEUACMq2NbeBS_5A7u-95JNNngq61ehIGgVbyVmXyDS7ZbNIvTfW7CnuQ0zQtwglIjg7pqHpiRALA0acKo6E1PUxirQlVXnYu5sjQap1jWAuRATQIcFEZorMc35BwBqMGYi7pu-2w-cc_pl-X7II3dy2fJuTDEFP6Z-J_soV-ul9Lv2yE-5ePuSXd_yNl-Ly-i3mecnzsTH0-O6eSlWr8_LZrEqEqEdCx3AWm2JTYiGavTB6mCZYwTlCMlCdBYCuMp8e121HvlYTpHqQKSqqGbi9t-bmHmzH1Lnh8PmNK7-AD5bR5E</recordid><startdate>201112</startdate><enddate>201112</enddate><creator>Sanandaji, B. M.</creator><creator>Vincent, T. L.</creator><creator>Wakin, M. B.</creator><creator>Toth, R.</creator><creator>Poolla, K.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201112</creationdate><title>Compressive System Identification of LTI and LTV ARX models</title><author>Sanandaji, B. M. ; Vincent, T. L. ; Wakin, M. B. ; Toth, R. ; Poolla, K.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i217t-4c077472e6cf6281ac74c7eeff03921270f970c0956ba45da1e6122f28c2235f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Coherence</topic><topic>Delay estimation</topic><topic>Equations</topic><topic>Matching pursuit algorithms</topic><topic>Mathematical model</topic><topic>Vectors</topic><toplevel>online_resources</toplevel><creatorcontrib>Sanandaji, B. M.</creatorcontrib><creatorcontrib>Vincent, T. L.</creatorcontrib><creatorcontrib>Wakin, M. B.</creatorcontrib><creatorcontrib>Toth, R.</creatorcontrib><creatorcontrib>Poolla, K.</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 Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Sanandaji, B. M.</au><au>Vincent, T. L.</au><au>Wakin, M. B.</au><au>Toth, R.</au><au>Poolla, K.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Compressive System Identification of LTI and LTV ARX models</atitle><btitle>2011 50th IEEE Conference on Decision and Control and European Control Conference</btitle><stitle>CDC</stitle><date>2011-12</date><risdate>2011</risdate><spage>791</spage><epage>798</epage><pages>791-798</pages><issn>0191-2216</issn><isbn>9781612848006</isbn><isbn>1612848001</isbn><eisbn>1467304573</eisbn><eisbn>1612847994</eisbn><eisbn>9781612847993</eisbn><eisbn>161284801X</eisbn><eisbn>9781612848013</eisbn><eisbn>9781467304573</eisbn><abstract>In this paper, we consider identifying Auto Regressive with eXternal input (ARX) models for both Linear Time-Invariant (LTI) and Linear Time-Variant (LTV) systems. We aim at doing the identification from the smallest possible number of observations. This is inspired by the field of Compressive Sensing (CS), and for this reason, we call this problem Compressive System Identification (CSI). In the case of LTI ARX systems, a system with a large number of inputs and unknown input delays on each channel can require a model structure with a large number of parameters, unless input delay estimation is performed. Since the complexity of input delay estimation increases exponentially in the number of inputs, this can be difficult for high dimensional systems. We show that in cases where the LTI system has possibly many inputs with different unknown delays, simultaneous ARX identification and input delay estimation is possible from few observations, even though this leaves an apparently ill-conditioned identification problem. We discuss identification guarantees and support our proposed method with simulations. We also consider identifying LTV ARX models. In particular, we consider systems with parameters that change only at a few time instants in a piecewise-constant manner where neither the change moments nor the number of changes is known a priori. The main technical novelty of our approach is in casting the identification problem as recovery of a block-sparse signal from an underdetermined set of linear equations. We suggest a random sampling approach for LTV identification, address the issue of identifiability and again support our approach with illustrative simulations.</abstract><pub>IEEE</pub><doi>10.1109/CDC.2011.6160935</doi><tpages>8</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 0191-2216
ispartof 2011 50th IEEE Conference on Decision and Control and European Control Conference, 2011, p.791-798
issn 0191-2216
language eng
recordid cdi_ieee_primary_6160935
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Coherence
Delay estimation
Equations
Matching pursuit algorithms
Mathematical model
Vectors
title Compressive System Identification of LTI and LTV ARX models
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T02%3A16%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Compressive%20System%20Identification%20of%20LTI%20and%20LTV%20ARX%20models&rft.btitle=2011%2050th%20IEEE%20Conference%20on%20Decision%20and%20Control%20and%20European%20Control%20Conference&rft.au=Sanandaji,%20B.%20M.&rft.date=2011-12&rft.spage=791&rft.epage=798&rft.pages=791-798&rft.issn=0191-2216&rft.isbn=9781612848006&rft.isbn_list=1612848001&rft_id=info:doi/10.1109/CDC.2011.6160935&rft_dat=%3Cieee_6IE%3E6160935%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1467304573&rft.eisbn_list=1612847994&rft.eisbn_list=9781612847993&rft.eisbn_list=161284801X&rft.eisbn_list=9781612848013&rft.eisbn_list=9781467304573&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6160935&rfr_iscdi=true