Network-Wide Traffic Signal Control Using Bilinear System Modeling and Adaptive Optimization
Abstract
This study proposes a new multi-input multi-output optimal bilinear signal control method in which a bilinear dynamic model approximation is used to capture the nonlinear dynamics of the urban traffic networks. With signal green time splits as the control input and traffic delay changes as the output for each intersections in the network, a bilinear system model was developed, which, on the basis of linear system modeling, takes interactions among traffic delays and signal timing splits into consideration. Based on the bilinear system modeling framework, we conducted two steps in each time interval to derive traffic control strategies: (1) we used the normalized least-squared algorithm to estimate system parameters; and (2) we solved an online optimization problem to obtain the updated traffic control inputs for the signal timing that minimizes future traffic delays. We evaluated the proposed method in a microscopic traffic simulation environment (VISSIM) with a 35-intersection network of Bellevue city in Washington. Two different traffic demand patterns: (1) normal traffic demands; and (2) time-varying traffic demands were simulated to compare the performance of different control strategies. Experimental results show that (1) the proposed bilinear system model can better describe traffic system dynamics than linear-model based methods, such asmore »
- Authors:
-
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Hong Kong University of Science and Technology (HKUST) (Hong Kong)
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Univ. of Virginia, Charlottesville, VA (United States)
- Univ. of Washington, Seattle, WA (United States)
- Publication Date:
- Research Org.:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1897010
- Grant/Contract Number:
- AC05-00OR22725
- Resource Type:
- Journal Article: Accepted Manuscript
- Journal Name:
- IEEE Transactions on Intelligent Transportation Systems
- Additional Journal Information:
- Journal Volume: 24; Journal Issue: 1; Journal ID: ISSN 1524-9050
- Publisher:
- IEEE
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 42 ENGINEERING; urban traffic network; traffic signal; bilinear control; multi-input multi-output (MIMO) system; VISSIM
Citation Formats
Wang, Hong, Zhu, Meixin, Hong, Wanshi, Wang, Chieh, Li, Wan, Tao, Gang, and Wang, Yinhai. Network-Wide Traffic Signal Control Using Bilinear System Modeling and Adaptive Optimization. United States: N. p., 2023.
Web. doi:10.1109/tits.2022.3215537.
Wang, Hong, Zhu, Meixin, Hong, Wanshi, Wang, Chieh, Li, Wan, Tao, Gang, & Wang, Yinhai. Network-Wide Traffic Signal Control Using Bilinear System Modeling and Adaptive Optimization. United States. https://doi.org/10.1109/tits.2022.3215537
Wang, Hong, Zhu, Meixin, Hong, Wanshi, Wang, Chieh, Li, Wan, Tao, Gang, and Wang, Yinhai. 2023.
"Network-Wide Traffic Signal Control Using Bilinear System Modeling and Adaptive Optimization". United States. https://doi.org/10.1109/tits.2022.3215537. https://www.osti.gov/servlets/purl/1897010.
@article{osti_1897010,
title = {Network-Wide Traffic Signal Control Using Bilinear System Modeling and Adaptive Optimization},
author = {Wang, Hong and Zhu, Meixin and Hong, Wanshi and Wang, Chieh and Li, Wan and Tao, Gang and Wang, Yinhai},
abstractNote = {This study proposes a new multi-input multi-output optimal bilinear signal control method in which a bilinear dynamic model approximation is used to capture the nonlinear dynamics of the urban traffic networks. With signal green time splits as the control input and traffic delay changes as the output for each intersections in the network, a bilinear system model was developed, which, on the basis of linear system modeling, takes interactions among traffic delays and signal timing splits into consideration. Based on the bilinear system modeling framework, we conducted two steps in each time interval to derive traffic control strategies: (1) we used the normalized least-squared algorithm to estimate system parameters; and (2) we solved an online optimization problem to obtain the updated traffic control inputs for the signal timing that minimizes future traffic delays. We evaluated the proposed method in a microscopic traffic simulation environment (VISSIM) with a 35-intersection network of Bellevue city in Washington. Two different traffic demand patterns: (1) normal traffic demands; and (2) time-varying traffic demands were simulated to compare the performance of different control strategies. Experimental results show that (1) the proposed bilinear system model can better describe traffic system dynamics than linear-model based methods, such as our previously developed linear-quadratic regulator control; and (2) the proposed method outperforms the state-of-the-art signal control strategies, namely the max-pressure and the self-organizing traffic light control methods. We have also shown that the proposed method is applicable to all other possible network layouts and signal controller phasing structures.},
doi = {10.1109/tits.2022.3215537},
url = {https://www.osti.gov/biblio/1897010},
journal = {IEEE Transactions on Intelligent Transportation Systems},
issn = {1524-9050},
number = 1,
volume = 24,
place = {United States},
year = {Sun Jan 01 00:00:00 EST 2023},
month = {Sun Jan 01 00:00:00 EST 2023}
}
Works referenced in this record:
IntelliLight: A Reinforcement Learning Approach for Intelligent Traffic Light Control
conference, July 2018
- Wei, Hua; Zheng, Guanjie; Yao, Huaxiu
- KDD '18: The 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control
journal, March 2020
- Chu, Tianshu; Wang, Jie; Codeca, Lara
- IEEE Transactions on Intelligent Transportation Systems, Vol. 21, Issue 3
Reinforcement Learning for True Adaptive Traffic Signal Control
journal, May 2003
- Abdulhai, Baher; Pringle, Rob; Karakoulas, Grigoris J.
- Journal of Transportation Engineering, Vol. 129, Issue 3
Reinforcement learning-based multi-agent system for network traffic signal control
journal, January 2010
- Arel, I.; Liu, C.; Urbanik, T.
- IET Intelligent Transport Systems, Vol. 4, Issue 2
On the limited memory BFGS method for large scale optimization
journal, August 1989
- Liu, Dong C.; Nocedal, Jorge
- Mathematical Programming, Vol. 45, Issue 1-3
Linear Optimal Control
journal, December 1971
- Anderson, B. D. O.; Pren, J. B.; Dickerson, S. L.
- Journal of Dynamic Systems, Measurement, and Control, Vol. 93, Issue 4
Multi-agent model predictive control of signaling split in urban traffic networks
journal, February 2010
- de Oliveira, Lucas Barcelos; Camponogara, Eduardo
- Transportation Research Part C: Emerging Technologies, Vol. 18, Issue 1
Review of road traffic control strategies
journal, December 2003
- Papageorgiou, M.; Kiakaki, C.; Dinopoulou, V.
- Proceedings of the IEEE, Vol. 91, Issue 12
Optimizing Signal Timing Control for Large Urban Traffic Networks Using an Adaptive Linear Quadratic Regulator Control Strategy
journal, January 2022
- Wang, Hong; Zhu, Meixin; Hong, Wanshi
- IEEE Transactions on Intelligent Transportation Systems, Vol. 23, Issue 1
Cost Effective Real-Time Traffic Signal Control Using the TUC Strategy
journal, January 2010
- Kraus, Werner; de Souza, Felipe A.; Carlson, Rodrigo C.
- IEEE Intelligent Transportation Systems Magazine, Vol. 2, Issue 4
Max pressure control of a network of signalized intersections
journal, November 2013
- Varaiya, Pravin
- Transportation Research Part C: Emerging Technologies, Vol. 36
Traffic congestion mitigation: combining engineering and economic perspectives
journal, October 2011
- Triantis, K.; Sarangi, S.; Teodorović, D.
- Transportation Planning and Technology, Vol. 34, Issue 7
Globalized Modeling and Signal Timing Control for Large-scale Networked Intersections
conference, September 2019
- Wang, Hong; Wang, Chieh Ross; Zhu, Meixin
- Proceedings of the 2nd ACM/EIGSCC Symposium on Smart Cities and Communities
Efficient Computation of Bilinear Approximations and Volterra Models of Nonlinear Systems
journal, February 2018
- Burt, Phillip Mark Seymour; de Morais Goulart, Jose Henrique
- IEEE Transactions on Signal Processing, Vol. 66, Issue 3
Traffic Signal Control With Adaptive Online-Learning Scheme Using Multiple-Model Neural Networks
journal, January 2022
- Hong, Wanshi; Tao, Gang; Wang, Hong
- IEEE Transactions on Neural Networks and Learning Systems
The Convergence of a Class of Double-rank Minimization Algorithms 1. General Considerations
journal, January 1970
- Broyden, C. G.
- IMA Journal of Applied Mathematics, Vol. 6, Issue 1
A multivariable regulator approach to traffic-responsive network-wide signal control
journal, February 2002
- Diakaki, Christina; Papageorgiou, Markos; Aboudolas, Kostas
- Control Engineering Practice, Vol. 10, Issue 2
A survey of model predictive control methods for traffic signal control
journal, May 2019
- Ye, Bao-Lin; Wu, Weimin; Ruan, Keyu
- IEEE/CAA Journal of Automatica Sinica, Vol. 6, Issue 3
Stability properties of constrained queueing systems and scheduling policies for maximum throughput in multihop radio networks
conference, January 1990
- Tassiulas, L.; Ephremides, A.
- 29th IEEE Conference on Decision and Control
A Deterministic and Stochastic Petri Net Model for Traffic-Responsive Signaling Control in Urban Areas
journal, February 2016
- Di Febbraro, Angela; Giglio, Davide; Sacco, Nicola
- IEEE Transactions on Intelligent Transportation Systems, Vol. 17, Issue 2