» Download Article

Authors
Caramihai, Simona Iuliana; Dumitrache, Ioan; Voinescu, Monica

Digital Object Identifier (DOI)
10.3182/20101005-4-RO-2018.00064

Page Numbers:
213-218

Index Terms
traffic control

Abstract
One of the most acute problem of large urban agglomerations is the efficace management of their traffic infrastructure. Due to the socio-economical dynamics, it is a fact that the number of cars is increasing at a far more important rate than the infrastructure, resulting, especially at peak-hours, in traffic congestions that affect the quality of life, in terms of stress, noise, safety and pollution. These problems can be solved, at a certain level, by pollitical measures and public education, but they also need a technical approach related to the adaptation of urban traffic functioning at real context. More speciffically, traffic congestion can and should be avoided, in certain circumstances, by adaptating the duration of traffic lights to the car flow, this being an approach that necessitates the lowest investments in infrastructure modifications. Higher investments and different approaches can be justified when the problem became insolvable by traffic light control. The paper presents a software platform that was conceived for supporting the traffic light control approach for avoiding traffic congestions. The structure and functioning of the platform is related to the agent-oriented modelling approach for the traffic infrastructure, that will be described in section I. The agent-oriented approach is justified both by the difficulty of globally modelling a traffic network, with high dynamics and large-scale, complex structure and by the necessity to offer to the platform users a flexible, open-system environment for building their own process to analize. Basically, an agent is managing a crossroad, thus including information on its physical structure (number of input/ output car flows, structure of light cycles), links with adjacent agents (capacity of input roads) and functioning context (car-flows, actual durations for traffic light cycles etc.). The formal modelling approach is a hybrid one, taking into account both the continuous approximation of the car flow and the discrete structure of traffic lights cycle.

References

REFERENCES
Hoogendoorn, S. P., (2001). “State-of-the-art of Vehicular Traffic Flow Modelling”, Special Issue on Road Traffic Modelling and Control of the Journal of Systems and Control Engineering
Maeoka, A., Tajima, T., (2000).“System Architecture for Traffic Management in Japan”,  Proceedings of the 7th Annual World Congress on ITS, Torino
Prikryl, J., (2006). Overview of Distributed Decision-Making for Urban Traffic Control, Proceedings of Abstracts of the 7th International PhD Workshop on Interplay of societal and technical decision-making, pp. 49-51
Caramihai, S., Voinescu, M., Munteanu, C., Dumitrache, I. (2009), “An Agent-Based Approach for Urban Traffic Simulation and Control”, Proceedings of the 6-th IFAC International Workshop on Knowledge and Technology Transfer in/to Developing countries: Automation and  Infrastructure, September 26-29, 2009, Ohrid, Macedonia
Udrea, A., Voinescu,  M., Caramihai, S., Lupu, C., (2009).  "A Dual Approach for Modelling Urban Traffic", Proceedings of the 13th IFAC Symposium on Information Control Problems in Manufacturing, 3-5 June 2009, Moscow, Russia
Logi, F. and Ritchie, S.G., (2001). “Development and evaluation of a knowledge-based system for traffic congestion management and control”, Transportation Research Part C: Emerging Technologies, 9, 6, 433—459
GiYoung, L., et al. (2001), “The Optimization of Traffic Signal Light using Artificial Intelligence”, Proceedings of the 10th IEEE Conference on Fuzzy Systems, vol. 3, 1279-1282
Lopez, S., Hernández, P., Hernández, A., García, M.,  (1999) “Artificial Neural Networks as Useful Tools for the Optimization of the Relative Offset between Two Consecutive Sets of Traffic Lights”, Engineering Applications of Bio-Inspired Artificial Neural Networks, International Work-Conference on Artificial and Natural Neural Networks, IWANN '99, Alicante, Spain, June 2-4, 1999, Proceedings, Volume II 1999 
Rouphail, N., et al. (2000), “Direct Signal Timing Optimization: Strategy Development and Results”, The XI Pan American Conference in Traffic and Transportation Engineering
Sanchez Medina, J. J., Galan Moreno, M. J., Rubio Royo, E., (2008), “Evolutionary Computation Applied to Urban Traffic Optimization”, Advances in Evolutionary Algorithms, ISBN: 987-953-7619-11-4, pp. 468- , November 
Spall, J. C., D. C. Chin (1994), “A model-free approach to optimal signal timing for system-wide traffic control”, Proceedings of the 1994 IEEE Conference on Decision and Control, ed. M. Peshkin, 1868-1875. Institute of Electrical and Electronics Engineers, Lake Buena Vista, Florida
Voinescu, M., Udrea, A., Caramihai, S. (2009), "On Urban Traffic Modelling and Control", Journal of Control Engineering and Applied Informatics, Vol 11, No 1
You Sik, H., JongSoo, K., Kwangson, J., Park, C., (1999), "Estimation of optimal green time simulation using fuzzy neural network," Fuzzy Systems Conference Proceedings, 1999. FUZZ-IEEE '99. 1999 IEEE International , vol.2, no., pp.761-766 vol.2