Real-Time Predictive Control Strategy Optimization

Urban traffic congestion has led to an increasing emphasis on management measures for more efficient utilization of existing infrastructure. In this context, this paper proposes a novel framework that integrates real-time optimization of control strategies (tolls, ramp metering rates, etc.) with the...

Full description

Bibliographic Details
Main Authors: Gupta, Samarth, Seshadri, Ravi, Atasoy, Bilge, Prakash, A Arun, Pereira, Francisco, Tan, Gary, Ben-Akiva, Moshe
Other Authors: Massachusetts Institute of Technology. Center for Computational Science and Engineering
Format: Article
Language:English
Published: SAGE Publications 2021
Online Access:https://hdl.handle.net/1721.1/132692
_version_ 1811075090376294400
author Gupta, Samarth
Seshadri, Ravi
Atasoy, Bilge
Prakash, A Arun
Pereira, Francisco
Tan, Gary
Ben-Akiva, Moshe
author2 Massachusetts Institute of Technology. Center for Computational Science and Engineering
author_facet Massachusetts Institute of Technology. Center for Computational Science and Engineering
Gupta, Samarth
Seshadri, Ravi
Atasoy, Bilge
Prakash, A Arun
Pereira, Francisco
Tan, Gary
Ben-Akiva, Moshe
author_sort Gupta, Samarth
collection MIT
description Urban traffic congestion has led to an increasing emphasis on management measures for more efficient utilization of existing infrastructure. In this context, this paper proposes a novel framework that integrates real-time optimization of control strategies (tolls, ramp metering rates, etc.) with the generation of traffic guidance information using predicted network states for dynamic traffic assignment systems. The efficacy of the framework is demonstrated through a fixed demand dynamic toll optimization problem, which is formulated as a non-linear program to minimize predicted network travel times. A scalable efficient genetic algorithm that exploits parallel computing is applied to solve this problem. Experiments using a closed-loop approach are conducted on a large-scale road network in Singapore to investigate the performance of the proposed methodology. The results indicate significant improvements in network-wide travel time of up to 9% with real-time computational performance.
first_indexed 2024-09-23T10:00:39Z
format Article
id mit-1721.1/132692
institution Massachusetts Institute of Technology
language English
last_indexed 2024-09-23T10:00:39Z
publishDate 2021
publisher SAGE Publications
record_format dspace
spelling mit-1721.1/1326922024-05-21T17:54:56Z Real-Time Predictive Control Strategy Optimization Gupta, Samarth Seshadri, Ravi Atasoy, Bilge Prakash, A Arun Pereira, Francisco Tan, Gary Ben-Akiva, Moshe Massachusetts Institute of Technology. Center for Computational Science and Engineering Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Singapore-MIT Alliance in Research and Technology (SMART) Urban traffic congestion has led to an increasing emphasis on management measures for more efficient utilization of existing infrastructure. In this context, this paper proposes a novel framework that integrates real-time optimization of control strategies (tolls, ramp metering rates, etc.) with the generation of traffic guidance information using predicted network states for dynamic traffic assignment systems. The efficacy of the framework is demonstrated through a fixed demand dynamic toll optimization problem, which is formulated as a non-linear program to minimize predicted network travel times. A scalable efficient genetic algorithm that exploits parallel computing is applied to solve this problem. Experiments using a closed-loop approach are conducted on a large-scale road network in Singapore to investigate the performance of the proposed methodology. The results indicate significant improvements in network-wide travel time of up to 9% with real-time computational performance. 2021-10-04T13:42:10Z 2021-10-04T13:42:10Z 2020-02-24 2021-10-01T17:04:44Z Article http://purl.org/eprint/type/JournalArticle 0361-1981 2169-4052 https://hdl.handle.net/1721.1/132692 Gupta S, Seshadri R, Atasoy B, et al. Real-Time Predictive Control Strategy Optimization. Transportation Research Record. 2020;2674(3):1-11 en 10.1177/0361198120907903 Transportation Research Record Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf SAGE Publications arXiv
spellingShingle Gupta, Samarth
Seshadri, Ravi
Atasoy, Bilge
Prakash, A Arun
Pereira, Francisco
Tan, Gary
Ben-Akiva, Moshe
Real-Time Predictive Control Strategy Optimization
title Real-Time Predictive Control Strategy Optimization
title_full Real-Time Predictive Control Strategy Optimization
title_fullStr Real-Time Predictive Control Strategy Optimization
title_full_unstemmed Real-Time Predictive Control Strategy Optimization
title_short Real-Time Predictive Control Strategy Optimization
title_sort real time predictive control strategy optimization
url https://hdl.handle.net/1721.1/132692
work_keys_str_mv AT guptasamarth realtimepredictivecontrolstrategyoptimization
AT seshadriravi realtimepredictivecontrolstrategyoptimization
AT atasoybilge realtimepredictivecontrolstrategyoptimization
AT prakashaarun realtimepredictivecontrolstrategyoptimization
AT pereirafrancisco realtimepredictivecontrolstrategyoptimization
AT tangary realtimepredictivecontrolstrategyoptimization
AT benakivamoshe realtimepredictivecontrolstrategyoptimization