Accelerated on-line calibration of dynamic traffic assignment using distributed stochastic gradient approximation
Dynamic Traffic Assignment (DTA) system [Ben-Akiva et al., 1991] [Mahmassani, 2001] benefits travelers by providing accurate estimate of current traffic conditions, consistent anticipatory network information as well as reliable route guidance. Over the years, two types of model adjustment schemes h...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers
2013
|
| Online Access: | http://hdl.handle.net/1721.1/77566 https://orcid.org/0000-0003-0203-9542 |
| _version_ | 1811088778889003008 |
|---|---|
| author | Huang, Enyang Antoniou, Constantinos Lopes, Jorge Alves Wen, Yang, Ph. D. Massachusetts Institute of Technology Ben-Akiva, Moshe E |
| author2 | Massachusetts Institute of Technology. Center for Transportation & Logistics |
| author_facet | Massachusetts Institute of Technology. Center for Transportation & Logistics Huang, Enyang Antoniou, Constantinos Lopes, Jorge Alves Wen, Yang, Ph. D. Massachusetts Institute of Technology Ben-Akiva, Moshe E |
| author_sort | Huang, Enyang |
| collection | MIT |
| description | Dynamic Traffic Assignment (DTA) system [Ben-Akiva et al., 1991] [Mahmassani, 2001] benefits travelers by providing accurate estimate of current traffic conditions, consistent anticipatory network information as well as reliable route guidance. Over the years, two types of model adjustment schemes have been studied - DTA off-line calibration [Balakrishna, 2006] [Toledo et al., 2003] [van der Zijpp, 1997] and DTA on-line calibration [Antoniou et al., 2007] [Wang et al., 2007] [Ashok and Ben-Akiva, 2000]. The on-line calibration of DTA system allows real-time model self-corrections and has proven to be a useful complement to off-line calibration. In this paper, we explore distributed gradient calculations for the speed-up of on-line calibration of Dynamic Traffic Assignment (DTA) systems. Extended Kalman Filter (EKF) and Stochastic Gradient Descent (GD) are examined and their corresponding distributed versions (Para-EKF and Para-GD) are proposed. A case study is performed on a 25-km expressway in Western Portugal. We empirically show that the application of distributed gradient calculation significantly reduce the computational time of on-line calibration and thus provide attractive alternatives for speed-critical real-time DTA systems. |
| first_indexed | 2024-09-23T14:07:25Z |
| format | Article |
| id | mit-1721.1/77566 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:07:25Z |
| publishDate | 2013 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | mit-1721.1/775662022-09-28T18:39:41Z Accelerated on-line calibration of dynamic traffic assignment using distributed stochastic gradient approximation Huang, Enyang Antoniou, Constantinos Lopes, Jorge Alves Wen, Yang, Ph. D. Massachusetts Institute of Technology Ben-Akiva, Moshe E Massachusetts Institute of Technology. Center for Transportation & Logistics Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Massachusetts Institute of Technology. Intelligent Transportation Systems Laboratory Ben-Akiva, Moshe E. Huang, Enyang Antoniou, Constantinos Dynamic Traffic Assignment (DTA) system [Ben-Akiva et al., 1991] [Mahmassani, 2001] benefits travelers by providing accurate estimate of current traffic conditions, consistent anticipatory network information as well as reliable route guidance. Over the years, two types of model adjustment schemes have been studied - DTA off-line calibration [Balakrishna, 2006] [Toledo et al., 2003] [van der Zijpp, 1997] and DTA on-line calibration [Antoniou et al., 2007] [Wang et al., 2007] [Ashok and Ben-Akiva, 2000]. The on-line calibration of DTA system allows real-time model self-corrections and has proven to be a useful complement to off-line calibration. In this paper, we explore distributed gradient calculations for the speed-up of on-line calibration of Dynamic Traffic Assignment (DTA) systems. Extended Kalman Filter (EKF) and Stochastic Gradient Descent (GD) are examined and their corresponding distributed versions (Para-EKF and Para-GD) are proposed. A case study is performed on a 25-km expressway in Western Portugal. We empirically show that the application of distributed gradient calculation significantly reduce the computational time of on-line calibration and thus provide attractive alternatives for speed-critical real-time DTA systems. MIT-Portugal Program 2013-03-05T21:49:24Z 2013-03-05T21:49:24Z 2010-09 Article http://purl.org/eprint/type/ConferencePaper 978-1-4244-7657-2 2153-0009 INSPEC Accession Number: 11639450 http://hdl.handle.net/1721.1/77566 Huang, Enyang et al. “Accelerated On-line Calibration of Dynamic Traffic Assignment Using Distributed Stochastic Gradient Approximation.” 2010 13th International IEEE Conference on Intelligent Transportation Systems (ITSC), Madeira Island, Portugal, September 19-22, 2010, IEEE, 2010. 1166–1171. CrossRef. Web. © 2010 IEEE. https://orcid.org/0000-0003-0203-9542 en_US http://dx.doi.org/10.1109/ITSC.2010.5625109 Proceedings of the 2010 13th International IEEE Annual Conference on Intelligent Transportation Systems (ITSC) Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Institute of Electrical and Electronics Engineers IEEE |
| spellingShingle | Huang, Enyang Antoniou, Constantinos Lopes, Jorge Alves Wen, Yang, Ph. D. Massachusetts Institute of Technology Ben-Akiva, Moshe E Accelerated on-line calibration of dynamic traffic assignment using distributed stochastic gradient approximation |
| title | Accelerated on-line calibration of dynamic traffic assignment using distributed stochastic gradient approximation |
| title_full | Accelerated on-line calibration of dynamic traffic assignment using distributed stochastic gradient approximation |
| title_fullStr | Accelerated on-line calibration of dynamic traffic assignment using distributed stochastic gradient approximation |
| title_full_unstemmed | Accelerated on-line calibration of dynamic traffic assignment using distributed stochastic gradient approximation |
| title_short | Accelerated on-line calibration of dynamic traffic assignment using distributed stochastic gradient approximation |
| title_sort | accelerated on line calibration of dynamic traffic assignment using distributed stochastic gradient approximation |
| url | http://hdl.handle.net/1721.1/77566 https://orcid.org/0000-0003-0203-9542 |
| work_keys_str_mv | AT huangenyang acceleratedonlinecalibrationofdynamictrafficassignmentusingdistributedstochasticgradientapproximation AT antoniouconstantinos acceleratedonlinecalibrationofdynamictrafficassignmentusingdistributedstochasticgradientapproximation AT lopesjorgealves acceleratedonlinecalibrationofdynamictrafficassignmentusingdistributedstochasticgradientapproximation AT wenyangphdmassachusettsinstituteoftechnology acceleratedonlinecalibrationofdynamictrafficassignmentusingdistributedstochasticgradientapproximation AT benakivamoshee acceleratedonlinecalibrationofdynamictrafficassignmentusingdistributedstochasticgradientapproximation |