Spatial iterative coordination for parallel simulation-based optimization of large-scale traffic signal control

Applying simulation-based optimization to city-scale traffic signal optimization can be challenging due to the large search space resulting in high computational complexity. A divide-and-conquer approach can be used to partition the problem and optimized separately, which leads to faster convergence...

Full description

Saved in:
Bibliographic Details
Main Authors: Tan, Wen Jun, Andelfinger, Philipp, Cai, Wentong, Eckhoff, David, Knoll, Alois
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2023
Subjects:
Online Access:https://hdl.handle.net/10356/168958
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-168958
record_format dspace
spelling sg-ntu-dr.10356-1689582023-06-23T08:22:05Z Spatial iterative coordination for parallel simulation-based optimization of large-scale traffic signal control Tan, Wen Jun Andelfinger, Philipp Cai, Wentong Eckhoff, David Knoll, Alois School of Computer Science and Engineering Engineering::Computer science and engineering Traffic Signal Optimization Spatial Coordination Applying simulation-based optimization to city-scale traffic signal optimization can be challenging due to the large search space resulting in high computational complexity. A divide-and-conquer approach can be used to partition the problem and optimized separately, which leads to faster convergence. However, the lack of coordination among the partial solutions may yield a poor-quality global solution. In this paper, we propose a new method for simulation-based optimization of traffic signal control, called spatially iterative coordination for parallel optimization (SICPO), to improve coordination among the partial solutions and reduce synchronization between the partitioned regions. The traffic scenario is simulated to obtain the interactions, which is used to spatially decompose the scenario into regions and identify interdependencies between the regions. Based on the regions, the problem is divided into subproblems which are optimized separately. To coordinate between the subproblems, the interactions between partial solutions are synchronized in two ways. First, multiple iterations of the optimization process can be executed to coordinate the partial solutions at the end of each optimization process. Second, the partial solutions can also be coordinated among the regions by synchronizing the trips across the regions. To reduce computational complexity, parallelism can be applied on two levels: each region is optimized concurrently, and each solution for a region is evaluated in parallel. We demonstrate our method on a real-world road network of Singapore, where SICPO converges to an average travel time 21.6% faster than global optimization at 62.8× shorter wall-clock time. National Research Foundation (NRF) This work was financially supported by the Singapore National Research Foundation under its Campus for Research Excellence And Technological Enterprise (CREATE) program and the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) (grant no. 497901036). 2023-06-23T08:22:04Z 2023-06-23T08:22:04Z 2023 Journal Article Tan, W. J., Andelfinger, P., Cai, W., Eckhoff, D. & Knoll, A. (2023). Spatial iterative coordination for parallel simulation-based optimization of large-scale traffic signal control. Simulation, 003754972311599-. https://dx.doi.org/10.1177/00375497231159944 0037-5497 https://hdl.handle.net/10356/168958 10.1177/00375497231159944 2-s2.0-85150908533 003754972311599 en Simulation © 2023 The Author(s). All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Traffic Signal Optimization
Spatial Coordination
spellingShingle Engineering::Computer science and engineering
Traffic Signal Optimization
Spatial Coordination
Tan, Wen Jun
Andelfinger, Philipp
Cai, Wentong
Eckhoff, David
Knoll, Alois
Spatial iterative coordination for parallel simulation-based optimization of large-scale traffic signal control
description Applying simulation-based optimization to city-scale traffic signal optimization can be challenging due to the large search space resulting in high computational complexity. A divide-and-conquer approach can be used to partition the problem and optimized separately, which leads to faster convergence. However, the lack of coordination among the partial solutions may yield a poor-quality global solution. In this paper, we propose a new method for simulation-based optimization of traffic signal control, called spatially iterative coordination for parallel optimization (SICPO), to improve coordination among the partial solutions and reduce synchronization between the partitioned regions. The traffic scenario is simulated to obtain the interactions, which is used to spatially decompose the scenario into regions and identify interdependencies between the regions. Based on the regions, the problem is divided into subproblems which are optimized separately. To coordinate between the subproblems, the interactions between partial solutions are synchronized in two ways. First, multiple iterations of the optimization process can be executed to coordinate the partial solutions at the end of each optimization process. Second, the partial solutions can also be coordinated among the regions by synchronizing the trips across the regions. To reduce computational complexity, parallelism can be applied on two levels: each region is optimized concurrently, and each solution for a region is evaluated in parallel. We demonstrate our method on a real-world road network of Singapore, where SICPO converges to an average travel time 21.6% faster than global optimization at 62.8× shorter wall-clock time.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Tan, Wen Jun
Andelfinger, Philipp
Cai, Wentong
Eckhoff, David
Knoll, Alois
format Article
author Tan, Wen Jun
Andelfinger, Philipp
Cai, Wentong
Eckhoff, David
Knoll, Alois
author_sort Tan, Wen Jun
title Spatial iterative coordination for parallel simulation-based optimization of large-scale traffic signal control
title_short Spatial iterative coordination for parallel simulation-based optimization of large-scale traffic signal control
title_full Spatial iterative coordination for parallel simulation-based optimization of large-scale traffic signal control
title_fullStr Spatial iterative coordination for parallel simulation-based optimization of large-scale traffic signal control
title_full_unstemmed Spatial iterative coordination for parallel simulation-based optimization of large-scale traffic signal control
title_sort spatial iterative coordination for parallel simulation-based optimization of large-scale traffic signal control
publishDate 2023
url https://hdl.handle.net/10356/168958
_version_ 1772825943131291648