An Approximate Dynamic Programming Algorithm for Large-Scale Fleet Management: A Case Application
We addressed the problem of developing a model to simulate at a high level of detail the movements of over 6,000 drivers for Schneider National, the largest truckload motor carrier in the United States. The goal of the model was not to obtain a better solution but rather to closely match a number of...
Gespeichert in:
| Veröffentlicht in: | Transportation science 2009-05, Vol.43 (2), p.178-197 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 197 |
|---|---|
| container_issue | 2 |
| container_start_page | 178 |
| container_title | Transportation science |
| container_volume | 43 |
| creator | Simao, Hugo P Day, Jeff George, Abraham P Gifford, Ted Nienow, John Powell, Warren B |
| description | We addressed the problem of developing a model to simulate at a high level of detail the movements of over 6,000 drivers for Schneider National, the largest truckload motor carrier in the United States. The goal of the model was not to obtain a better solution but rather to closely match a number of operational statistics. In addition to the need to capture a wide range of operational issues, the model had to match the performance of a highly skilled group of dispatchers while also returning the marginal value of drivers domiciled at different locations. These requirements dictated that it was not enough to optimize at each point in time (something that could be easily handled by a simulation model) but also over time. The project required bringing together years of research in approximate dynamic programming, merging math programming with machine learning, to solve dynamic programs with extremely high-dimensional state variables. The result was a model that closely calibrated against real-world operations and produced accurate estimates of the marginal value of 300 different types of drivers. |
| doi_str_mv | 10.1287/trsc.1080.0238 |
| format | Article |
| fullrecord | <record><control><sourceid>gale_jstor</sourceid><recordid>TN_cdi_jstor_primary_25769444</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A202079837</galeid><jstor_id>25769444</jstor_id><sourcerecordid>A202079837</sourcerecordid><originalsourceid>FETCH-LOGICAL-c535t-44691baefc0ae198bcc6a62fd2663f277e0febaa139bdc91ddff499a96a994f73</originalsourceid><addsrcrecordid>eNqFkd2L1DAUxYsoOK6--iYUH8SH7Zik6Ud8K6OrwoiC-hxuMzedDG0yJim6_70pXWSRAQkkEH7n5J6cLHtOyZaytnkTfVBbSlqyJaxsH2QbWrG6qDhvHmYbQjgtaF1Vj7MnIZwIoVVDq00Gnc2789m732aCiPm7WwuTUflX7wYP02TskHfj4LyJxynXzud78AMW3xSMmN-MiDH_DBYGnNDGt3mX7yDgYjkaBdE4-zR7pGEM-OzuvMp-3Lz_vvtY7L98-LTr9oWqyioWnNeC9oBaEUAq2l6pGmqmD6yuS82aBonGHoCWoj8oQQ8HrbkQIGoQguumvMperb4pzM8ZQ5STCQrHESy6OciySU5CiAS-_Ac8udnbNJtkpKw4E4QnqFihIeWUxmoXPagBLXoYnUVt0nXHCCONaMvl9e0FPq0Dpu-8KLi-J-jnYCyGtAUzHGMYYA7hor_yLgSPWp59aszfSkrkUr9c6pdL_XKpPwlerIJTiM7_pVnV1ILzewGXWf0U_u_3euWPacBfxq8hF2EKaoMykpeSSdq05R9oG8mo</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>203542904</pqid></control><display><type>article</type><title>An Approximate Dynamic Programming Algorithm for Large-Scale Fleet Management: A Case Application</title><source>INFORMS PubsOnLine</source><source>Business Source Complete</source><source>JSTOR Archive Collection A-Z Listing</source><creator>Simao, Hugo P ; Day, Jeff ; George, Abraham P ; Gifford, Ted ; Nienow, John ; Powell, Warren B</creator><creatorcontrib>Simao, Hugo P ; Day, Jeff ; George, Abraham P ; Gifford, Ted ; Nienow, John ; Powell, Warren B</creatorcontrib><description>We addressed the problem of developing a model to simulate at a high level of detail the movements of over 6,000 drivers for Schneider National, the largest truckload motor carrier in the United States. The goal of the model was not to obtain a better solution but rather to closely match a number of operational statistics. In addition to the need to capture a wide range of operational issues, the model had to match the performance of a highly skilled group of dispatchers while also returning the marginal value of drivers domiciled at different locations. These requirements dictated that it was not enough to optimize at each point in time (something that could be easily handled by a simulation model) but also over time. The project required bringing together years of research in approximate dynamic programming, merging math programming with machine learning, to solve dynamic programs with extremely high-dimensional state variables. The result was a model that closely calibrated against real-world operations and produced accurate estimates of the marginal value of 300 different types of drivers.</description><identifier>ISSN: 0041-1655</identifier><identifier>EISSN: 1526-5447</identifier><identifier>DOI: 10.1287/trsc.1080.0238</identifier><language>eng</language><publisher>Baltimore: INFORMS</publisher><subject>Aggregation ; Algorithms ; approximate dynamic programming ; Approximation ; driver management ; Dynamic programming ; Estimates ; Fleet management ; Freight ; Load ; Logistics ; Marginal value ; Modeling ; Motor carriers ; Motor vehicle fleets ; Objective functions ; Optimization ; Programming ; Road transport ; Simulation ; Simulation training ; Studies ; Transport economics ; Transportation ; Trucking ; truckload trucking ; Trucks ; U.S.A</subject><ispartof>Transportation science, 2009-05, Vol.43 (2), p.178-197</ispartof><rights>Copyright © 2009 Institute for Operations Research and the Management Sciences</rights><rights>COPYRIGHT 2009 Institute for Operations Research and the Management Sciences</rights><rights>Copyright Institute for Operations Research and the Management Sciences May 2009</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c535t-44691baefc0ae198bcc6a62fd2663f277e0febaa139bdc91ddff499a96a994f73</citedby><cites>FETCH-LOGICAL-c535t-44691baefc0ae198bcc6a62fd2663f277e0febaa139bdc91ddff499a96a994f73</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.jstor.org/stable/pdf/25769444$$EPDF$$P50$$Gjstor$$H</linktopdf><linktohtml>$$Uhttps://pubsonline.informs.org/doi/full/10.1287/trsc.1080.0238$$EHTML$$P50$$Ginforms$$H</linktohtml><link.rule.ids>314,780,784,803,3692,27924,27925,58017,58250,62616</link.rule.ids></links><search><creatorcontrib>Simao, Hugo P</creatorcontrib><creatorcontrib>Day, Jeff</creatorcontrib><creatorcontrib>George, Abraham P</creatorcontrib><creatorcontrib>Gifford, Ted</creatorcontrib><creatorcontrib>Nienow, John</creatorcontrib><creatorcontrib>Powell, Warren B</creatorcontrib><title>An Approximate Dynamic Programming Algorithm for Large-Scale Fleet Management: A Case Application</title><title>Transportation science</title><description>We addressed the problem of developing a model to simulate at a high level of detail the movements of over 6,000 drivers for Schneider National, the largest truckload motor carrier in the United States. The goal of the model was not to obtain a better solution but rather to closely match a number of operational statistics. In addition to the need to capture a wide range of operational issues, the model had to match the performance of a highly skilled group of dispatchers while also returning the marginal value of drivers domiciled at different locations. These requirements dictated that it was not enough to optimize at each point in time (something that could be easily handled by a simulation model) but also over time. The project required bringing together years of research in approximate dynamic programming, merging math programming with machine learning, to solve dynamic programs with extremely high-dimensional state variables. The result was a model that closely calibrated against real-world operations and produced accurate estimates of the marginal value of 300 different types of drivers.</description><subject>Aggregation</subject><subject>Algorithms</subject><subject>approximate dynamic programming</subject><subject>Approximation</subject><subject>driver management</subject><subject>Dynamic programming</subject><subject>Estimates</subject><subject>Fleet management</subject><subject>Freight</subject><subject>Load</subject><subject>Logistics</subject><subject>Marginal value</subject><subject>Modeling</subject><subject>Motor carriers</subject><subject>Motor vehicle fleets</subject><subject>Objective functions</subject><subject>Optimization</subject><subject>Programming</subject><subject>Road transport</subject><subject>Simulation</subject><subject>Simulation training</subject><subject>Studies</subject><subject>Transport economics</subject><subject>Transportation</subject><subject>Trucking</subject><subject>truckload trucking</subject><subject>Trucks</subject><subject>U.S.A</subject><issn>0041-1655</issn><issn>1526-5447</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2009</creationdate><recordtype>article</recordtype><sourceid>N95</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNqFkd2L1DAUxYsoOK6--iYUH8SH7Zik6Ud8K6OrwoiC-hxuMzedDG0yJim6_70pXWSRAQkkEH7n5J6cLHtOyZaytnkTfVBbSlqyJaxsH2QbWrG6qDhvHmYbQjgtaF1Vj7MnIZwIoVVDq00Gnc2789m732aCiPm7WwuTUflX7wYP02TskHfj4LyJxynXzud78AMW3xSMmN-MiDH_DBYGnNDGt3mX7yDgYjkaBdE4-zR7pGEM-OzuvMp-3Lz_vvtY7L98-LTr9oWqyioWnNeC9oBaEUAq2l6pGmqmD6yuS82aBonGHoCWoj8oQQ8HrbkQIGoQguumvMperb4pzM8ZQ5STCQrHESy6OciySU5CiAS-_Ac8udnbNJtkpKw4E4QnqFihIeWUxmoXPagBLXoYnUVt0nXHCCONaMvl9e0FPq0Dpu-8KLi-J-jnYCyGtAUzHGMYYA7hor_yLgSPWp59aszfSkrkUr9c6pdL_XKpPwlerIJTiM7_pVnV1ILzewGXWf0U_u_3euWPacBfxq8hF2EKaoMykpeSSdq05R9oG8mo</recordid><startdate>20090501</startdate><enddate>20090501</enddate><creator>Simao, Hugo P</creator><creator>Day, Jeff</creator><creator>George, Abraham P</creator><creator>Gifford, Ted</creator><creator>Nienow, John</creator><creator>Powell, Warren B</creator><general>INFORMS</general><general>Transportation Science & Logistic Society of the Institute for Operations Research and Management Sciences</general><general>Institute for Operations Research and the Management Sciences</general><scope>AAYXX</scope><scope>CITATION</scope><scope>N95</scope><scope>XI7</scope><scope>0U~</scope><scope>1-H</scope><scope>3V.</scope><scope>7WY</scope><scope>7WZ</scope><scope>7XB</scope><scope>87Z</scope><scope>88I</scope><scope>8BJ</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>8FL</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BEZIV</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FQK</scope><scope>FRNLG</scope><scope>F~G</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JBE</scope><scope>K60</scope><scope>K6~</scope><scope>L.-</scope><scope>L.0</scope><scope>L6V</scope><scope>M0C</scope><scope>M2P</scope><scope>M7S</scope><scope>PQBIZ</scope><scope>PQBZA</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PTHSS</scope><scope>PYYUZ</scope><scope>Q9U</scope></search><sort><creationdate>20090501</creationdate><title>An Approximate Dynamic Programming Algorithm for Large-Scale Fleet Management: A Case Application</title><author>Simao, Hugo P ; Day, Jeff ; George, Abraham P ; Gifford, Ted ; Nienow, John ; Powell, Warren B</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c535t-44691baefc0ae198bcc6a62fd2663f277e0febaa139bdc91ddff499a96a994f73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Aggregation</topic><topic>Algorithms</topic><topic>approximate dynamic programming</topic><topic>Approximation</topic><topic>driver management</topic><topic>Dynamic programming</topic><topic>Estimates</topic><topic>Fleet management</topic><topic>Freight</topic><topic>Load</topic><topic>Logistics</topic><topic>Marginal value</topic><topic>Modeling</topic><topic>Motor carriers</topic><topic>Motor vehicle fleets</topic><topic>Objective functions</topic><topic>Optimization</topic><topic>Programming</topic><topic>Road transport</topic><topic>Simulation</topic><topic>Simulation training</topic><topic>Studies</topic><topic>Transport economics</topic><topic>Transportation</topic><topic>Trucking</topic><topic>truckload trucking</topic><topic>Trucks</topic><topic>U.S.A</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Simao, Hugo P</creatorcontrib><creatorcontrib>Day, Jeff</creatorcontrib><creatorcontrib>George, Abraham P</creatorcontrib><creatorcontrib>Gifford, Ted</creatorcontrib><creatorcontrib>Nienow, John</creatorcontrib><creatorcontrib>Powell, Warren B</creatorcontrib><collection>CrossRef</collection><collection>Gale Business: Insights</collection><collection>Business Insights: Essentials</collection><collection>Global News & ABI/Inform Professional</collection><collection>Trade PRO</collection><collection>ProQuest Central (Corporate)</collection><collection>ABI/INFORM Collection</collection><collection>ABI/INFORM Global (PDF only)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>ABI/INFORM Global (Alumni Edition)</collection><collection>Science Database (Alumni Edition)</collection><collection>International Bibliography of the Social Sciences (IBSS)</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ABI/INFORM Collection (Alumni Edition)</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Business Premium Collection</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>International Bibliography of the Social Sciences</collection><collection>Business Premium Collection (Alumni)</collection><collection>ABI/INFORM Global (Corporate)</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>International Bibliography of the Social Sciences</collection><collection>ProQuest Business Collection (Alumni Edition)</collection><collection>ProQuest Business Collection</collection><collection>ABI/INFORM Professional Advanced</collection><collection>ABI/INFORM Professional Standard</collection><collection>ProQuest Engineering Collection</collection><collection>ABI/INFORM Global</collection><collection>Science Database</collection><collection>Engineering Database</collection><collection>ProQuest One Business</collection><collection>ProQuest One Business (Alumni)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Engineering Collection</collection><collection>ABI/INFORM Collection China</collection><collection>ProQuest Central Basic</collection><jtitle>Transportation science</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Simao, Hugo P</au><au>Day, Jeff</au><au>George, Abraham P</au><au>Gifford, Ted</au><au>Nienow, John</au><au>Powell, Warren B</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An Approximate Dynamic Programming Algorithm for Large-Scale Fleet Management: A Case Application</atitle><jtitle>Transportation science</jtitle><date>2009-05-01</date><risdate>2009</risdate><volume>43</volume><issue>2</issue><spage>178</spage><epage>197</epage><pages>178-197</pages><issn>0041-1655</issn><eissn>1526-5447</eissn><abstract>We addressed the problem of developing a model to simulate at a high level of detail the movements of over 6,000 drivers for Schneider National, the largest truckload motor carrier in the United States. The goal of the model was not to obtain a better solution but rather to closely match a number of operational statistics. In addition to the need to capture a wide range of operational issues, the model had to match the performance of a highly skilled group of dispatchers while also returning the marginal value of drivers domiciled at different locations. These requirements dictated that it was not enough to optimize at each point in time (something that could be easily handled by a simulation model) but also over time. The project required bringing together years of research in approximate dynamic programming, merging math programming with machine learning, to solve dynamic programs with extremely high-dimensional state variables. The result was a model that closely calibrated against real-world operations and produced accurate estimates of the marginal value of 300 different types of drivers.</abstract><cop>Baltimore</cop><pub>INFORMS</pub><doi>10.1287/trsc.1080.0238</doi><tpages>20</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0041-1655 |
| ispartof | Transportation science, 2009-05, Vol.43 (2), p.178-197 |
| issn | 0041-1655 1526-5447 |
| language | eng |
| recordid | cdi_jstor_primary_25769444 |
| source | INFORMS PubsOnLine; Business Source Complete; JSTOR Archive Collection A-Z Listing |
| subjects | Aggregation Algorithms approximate dynamic programming Approximation driver management Dynamic programming Estimates Fleet management Freight Load Logistics Marginal value Modeling Motor carriers Motor vehicle fleets Objective functions Optimization Programming Road transport Simulation Simulation training Studies Transport economics Transportation Trucking truckload trucking Trucks U.S.A |
| title | An Approximate Dynamic Programming Algorithm for Large-Scale Fleet Management: A Case Application |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T08%3A59%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_jstor&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=An%20Approximate%20Dynamic%20Programming%20Algorithm%20for%20Large-Scale%20Fleet%20Management:%20A%20Case%20Application&rft.jtitle=Transportation%20science&rft.au=Simao,%20Hugo%20P&rft.date=2009-05-01&rft.volume=43&rft.issue=2&rft.spage=178&rft.epage=197&rft.pages=178-197&rft.issn=0041-1655&rft.eissn=1526-5447&rft_id=info:doi/10.1287/trsc.1080.0238&rft_dat=%3Cgale_jstor%3EA202079837%3C/gale_jstor%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=203542904&rft_id=info:pmid/&rft_galeid=A202079837&rft_jstor_id=25769444&rfr_iscdi=true |