We propose a real-time signal control framework based on a nonlinear decision rule (NDR), which defines a nonlinear mapping between network states and signal control parameters to actual signal controls based on prevailing traffic conditions, and such a mapping is optimized via off-line simulation. The NDR is instantiated with two neural networks: feedforward neural network (FFNN) and recurrent neural network (RNN), which have different ways of processing traffic information in the near past, and are compared in terms of their performances. The NDR is implemented within a microscopic traffic simulation (S-Paramics) for a real-world network in West Glasgow, where the off-line training of the NDR amounts to a simulation-based optimization aiming to reduce delay, CO2 and black carbon emissions. The emission calculations are based on the high-fidelity vehicle dynamics generated by the simulation, and the AIRE instantaneous emission model. Extensive tests are performed to assess the NDR framework, not only in terms of its effectiveness in reducing the aforementioned objectives, but also in relation to local vs. global benefits, trade-off between delay and emissions, impact of sensor locations, and different levels of network saturation. The results suggest that the NDR is an effective, flexible and robust way of alleviating congestion and reducing traffic emissions.
This is a preview of subscription content, log in to check access.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
This is the net price. Taxes to be calculated in checkout.
U.S. Environmental Protection Agency (2012) Report to Congress on Black Carbon. Department of the Interior, Environment, and Related Agencies Appropriations Act. EPA-450/R-12-001.
Transport ScotlandÕs Instantaneous Emissions Software AIRE. 2011. http://www.sias.com/2013/AIRE.html.
Transport Scotland. AIRE (Analysis of Instantaneous Road Emissions) User Guidance In, Scotland, 2011.
Arel L, Liu C, Urbanik T, Kohls AG (2010) Reinforcement learning-based multi-agent system for network traffic signal control. IET Intell Transp Syst 4 (2):128–135
Balaji PG, German X, Srinivasan D (2010) Urban traffic signal control using reinforcement learning agents. IET Intell Transp Syst 4(3):177–188
Banks A, Vincent J, Anyakoha C (2007) A review of particle swarm optimization. Part I: background and development. Nat Comput 6(4):467–484
Bertsimas D, Brown DB, Caramanis C (2011) Theory and applications of robust optimization. SIAM Rev 53(3):464–501
Cai C, Wong CK, Heydecker BG (2009) Adaptive traffic signal control using approximate dynamic programming. Transp Res Part C: Emerg Technol 17 (5):456–474
Castro GB, Hirakawa AR, Martini JS (2017) Adaptive traffic signal control based on bio-neural network. Procedia Comput Sci 109:1182–1187
Chang L, Hui W (2016) Traffic emission control based on emission pricing and signal timing. In: 2016 12th World congress on intelligent control and automation (WCICA). IEEE, pp 467–472
Chang TH, Sun GY (2004) Modeling and optimization of an oversaturated signalized network. Transp Res B 38(8):687–707
Chen H, Bai R, Ma J, Wang D (2012) Research on intersection signal timing model considering emissions effects. In; CICTP 2012. American Society of Civil Engineers, pp 1024–1034
Christofa E, Skabardonis A (2011) Traffic signal optimization with application of transit signal priority to an isolated intersection. Transp Res Record: J Transp Res Board 2259:192–201
Christofa E, Ampountolas K, Skabardonis A (2016) Arterial traffic signal optimization: a person-based approach. Transp Res C 66:27–47
Feng Y, Head K, Khoshmagham S, Zamanipour M (2015) A real-time adaptive signal control in a connected vehicle environment. Transp Res C 55:460–473
Friesz TL (2010) Dynamic optimization and differential games. Springer, New York
Gartner NH (1983) OPAC: a demand-responsive strategy for traffic signal control. Transp Res Record 906:75–81
Gkatzoflias D, Kouridis C, Ntziachristos L, Samaras Z (2006) COPERT 4 manual. European Environment Agency (EEA)
Han K (2017) Framework for real-time traffic management with case studies. Transp Res Record: J Transp Res Board 2658:35–43
Han K, Gayah VV (2015) Continuum signalized junction model for dynamic traffic networks: offset, spillback, and multiple signal phases. Transp Res B 77:213–239
Han K, Gayah VV, Piccoli B, Friesz TL, Yao T (2014) On the continuum approximation of the on-and-off signal control on dynamic traffic networks. Transp Res B 61:73–97
Han K, Sun Y, Liu H, Friesz TL, Yao T (2015) A bi-level model of dynamic traffic signal control with continuum approximation. Transp Res C 55:409–431
Han K, Liu H, Gayah VV, Friesz TL, Yao T (2016) A robust optimization approach for dynamic traffic signal control with emission considerations. Transp Res C 70:3–26
Hauser TA, Scherer WT (2001) Data mining tools for real-time traffic signal decision support. 2001 IEEE International Conference on & Maintenance, Systems Man, and Cybernetics 3:1471–1477
He Q, Head K, Ding J (2014) Multi-modal traffic signal control with priority, signal actuation and coordination. Transp Res C 46:65–82
Henry JJ, Farges JL, Tuffal J (1983) The PRODYN real time traffic algorithm. In: Proceedings of the fourth IFAC-IFIP-IFORS conference on control in transportation systems, pp 307–311
Hunt PB, Robertson DI, Bretherton RD (1982) The SCOOT on-line traffic signal optimization technique. Traffic Eng Control 25:14–22
Jamshidnejad A, Papamichail I, Papageorgiou M, De Schutter B (2017) Sustainable model-predictive control in urban traffic networks: efficient solution based on general smoothening methods. IEEE Trans Control Syst Technol 26(3):813–827
Janssen NAH, Gerlofs-Nijland ME, Lanki T, Salonen RO, Cassee F, Hoek G, Fischer P, Brunekreef B, Krzyzanowski M (2013) Health effects of black carbon. In Europe WROf (ed)
Ji Y, Hu B, Han J, Tang D (2014) An improved algebraic method for transit signal priority scheme and its impact on traffic emission. Mathematical Problems in Engineering, 11 pages
Lefebvre W, Fierens F, Trimpeneers E, Janssen S, Van de Vel K, Deutsch F, Viaene P, Vankerkom J, Dumont G, Vanpoucke C, Mensink C, Peelaerts W, Vliegen J (2011) Modeling the effects of a speed limit reduction on traffic-related elemental carbon (EC) concentrations and population exposure to EC. Atmos Environ 45(1):197–207
Li L, Lv Y, Wang F (2016) Traffic signal timing via deep reinforcement learning. IEEE/CAA J Automatica Sinica 3(3):247–254
Lin S, De Schutter B, Xi Y, Hellendoorn H (2013) Integrated urban traffic control for the reduction of travel delays and emissions. IEEE Trans Intell Transp Syst 14(4):1609–1619
Liu H, Han K, Gayah VV, Friesz TL, Yao T (2015) Data-driven linear decision rule approach for distributionally robust optimization of on-line signal control. Transp Res C 59:260–277
Lowrie P (1982) The Sydney coordinated adaptive traffic system-principles, methodology, algorithms. International Conference on Road Traffic Signalling
Lucas D, Mirchandani P, Head K (2000) Remote simulation to evaluate real-time traffic control strategies. Transp Res Record: J Transp Res Board 1727:95–100
Mascia M, Hu K, Han K, North R (2015) Simulation output for traffic scenarios for the city of Glasgow. Technical report, CARBOTRAF, D3.4
Mascia M, Hu K, Han K, North R, Van Poppel M, Theunis J, Beckx C, Litzenberger M (2016) Impact of traffic management on black carbon emissions: a microsimulation study. Netw Spatial Econ 17(1):269–291
Osorio C, Nanduri K (2015) Urban transportation emissions mitigation: coupling high-resolution vehicular emissions and traffic models for traffic signal optimization. Transp Res B Methodol 81:520–538
Paramics S, Paramics S (2011) Reference manual. In: SIAS limited. Edinburg
Papatzikou E, Stathopoulos A (2015) An optimization method for sustainable traffic control in urban areas. Transp Res C 55:179–190
Samah E, Baher A, Hossam A (2013) Multiagent reinforcement learning for integrated network of adaptive traffic signal controllers (MARLIN-ATSC): methodology and large-scale application on downtown Toronto. IEEE Trans Intell Transp Syst 14 (3):1140–1150
Savsani V, Rao RV, Vakharia DP (2010) Optimal weight design of a gear train using particle swarm optimization and simulated annealing algorithms. Mech Mach Theory 45(3):531–541
Sha DY, Hsu CY (2008) A new particle swarm optimization for the open shop scheduling problem. Comput Oper Res 35(10):3243–3261
Smith S, Barlow G, Xie X-F, Rubinstein Z (2013) SURTRAC: scalable urban traffic control. Transportation Research Board 92nd Annual Meeting, Jan. 2013
Sobrino N, Monzon A, Hernandez S (2016) Reduced carbon and energy footprint in highway operations: the Highway Energy Assessment (HERA) methodology. Netw Spatial Econ 16:395–414
Srinivasan D, Choy MC, Cheu RL (2006) Neural networks for real-time traffic signal control. IEEE Trans Intell Transp Syst 7(3):261–272
Stevanovic A, Stevanovic J, So J, Ostojic M (2015) Multi-criteria optimization of traffic signals: mobility, safety, and environment. Transp Res C 55:46–68
Sun D, Benekohal RF, Waller ST (2006) Bi-level programming formulation and heuristic solution approach for dynamic traffic signal optimization. Comput-Aided Civil Infrastruct Eng 21(5):321–333
Sundaram S, Kumar SS, Divya Shree MS (2015) Hierarchical clustering technique for traffic signal decision support. Int J Innov Sci 2(6):72–82
Sunkari S (2004) The benefits of retiming traffic signals. Institute Transp Eng ITE J 74(4):26
Ukkusuri SV, Ramadurai G, Patil G (2010) A robust transportation signal control problem accounting for traffic dynamics. Comput Oper Res 37(5):869–879
Wiering MA (2000) Multi-agent reinforcement learning for traffic light control. In: Proceedings of the 17th international conference on machine learning, pp 1151–1158
Yin PY (2006) Particle swarm optimization for point pattern matching. J Vis Commun Image Represent 17(1):143–162
Yin Y (2008) Robust optimal traffic signal timing. Transp Res B 42(10):911–924
Zhang L, Yin Y, Lou Y (2010) Robust signal timing for arterials under day-to-day demand variations. Transp Res Record: J Transp Res Board 2192:156–166
Zhang K, Batterman S, Dion F (2011) Vehicle emissions in congestion: comparison of work zone, rush hour and free-flow conditions. Atmos Environ 45 (11):1929–1939
Zhang L, Yin Y, Chen S (2013) Robust signal timing optimization with environmental concerns. Transp Res C 29:55–71
Zhou Z, Cai M (2014) Intersection signal control multi-objective optimization based on genetic algorithm. J Traffic Transp Eng (English Edition) 1(2):153–158
This study was partially supported by the EU 7th Framework Program project CARBOTRAF (28786), National Social Science Foundation of China (15BGL143), and the Zhejiang University/University of Illinois at Urbana-Champaign Institute.
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix: : the PSO Algorithm
Appendix: : the PSO Algorithm
Given the objective function to be minimized, denoted f(⋅), and the feasible domain S, the following pseudo code summarizes the PSO procedure.
About this article
Cite this article
Song, J., Hu, S., Han, K. et al. Nonlinear Decision Rule Approach for Real-Time Traffic Signal Control for Congestion and Emission Mitigation. Netw Spat Econ (2020). https://doi.org/10.1007/s11067-020-09497-3
- Real-time signal control
- Nonlinear decision rule
- Neural networks