Neuroadapive Control of Traffic Flows in Urban Road Network
Authors: Diveev A.I., Sofronova Е.A., Mikhalev V.A. | Published: 09.02.2018 |
Published in issue: #1(118)/2018 | |
DOI: 10.18698/0236-3933-2018-1-49-58 | |
Category: Informatics, Computer Engineering and Control | Chapter: Mathematical Modelling, Numerical Methods, and Program Complexes | |
Keywords: neuroadaptive control, optimal control, traffic flow, artificial neural networks, controlled network theory |
The article deals with a neuroadaptive control problem for urban traffic flows. In our research we used an expandable mathematical model of traffic flows. To adjust network parameters, traffic capacity of road sections and flow distributions, we introduced an artificial neural network. Moreover, we developed a special structure of the neural network. Neural network training was performed by backpropagation. Finally, we gave example of adaptive optimal control system performance for four crossroads
References
[1] Ligthill M.J., Whitham F.R.S. On kinetic waves II. A theory of traffic flow on crowded roads. Proc. of the Royal Society Ser. A, 1955, vol. 229, iss. 1178, pp. 317–345. DOI: 10.1098/rspa.1955.0089
[2] Mauro V. Road network control. In: Concise Encyclopedia of Traffic and Transportation Systems. In: Advances in Systems, Control in Information Engineering. Pergamon Press, 1991. Pp. 361–366.
[3] Ardekani S.A., Herman R. Urban network-wide variables and their relations. Transportation Science, 1987, vol. 21, no. 1, pp. 1–16.
[4] Assad A.A. Multicommodity network flows — a survey. Networks, 1978, vol. 8, iss. 1, pp. 37–91. DOI: 10.1002/net.3230080107
[5] Peter T. Modeling nonlinear road traffic networks for junction control. Int. J. of Applied Mathematics and Computer Sciences, 2012, vol. 22, iss. 3, pp. 723–732. DOI: 10.2478/v10006-012-0054-1 Available at: https://www.degruyter.com/view/j/amcs.2012.22.issue-3/v10006-012-0054-1/v10006-012-0054-1.xml
[6] Chao K.-H., Lee R.-H., Wang M.-H. An intelligent traffic light control based on extension neural network. Proc. 12th Int. Conf. KES 2008. Part I, 2008, Springer-Verlag, pp. 17–24.
[7] Hu J., Zhao D., Zhu F. Neural network based online traffic signal controller design with reinforcement training. Proc. 14th Int. IEEE Conf. on Intelligent Transportation Systems (ITSC), 2011, IEEE, pp. 1045–1050.
[8] Diveev A.I. Controlled networks and their applications. Computational Mathematics and Mathematical Physics, 2008, vol. 48, iss. 8, pp. 1428–1442. DOI: 10.1134/S0965542508080125
[9] Diveev A.I., Sofronova E.A. Synthesis of intelligent control of traffic flows in urban roads based on the logical network operator method. Proc. European Control Conf. (ECC 2013), 2013, IEEE, pp. 3512–3517.
[10] Diveev A.I., Sofronova E.A., Mikhalev V.A. Model predictive control for urban traffic flows. Proc. 2016 IEEE Int. Conf. on Systems, Man, and Cybernetics (SMC 2016), 2016, IEEE, pp. 3051–3056.
[11] Fomin V.N., Fradkov A.L., Yakubovich V.A. Adaptivnoe upravlenie dinamicheskimi obektami [Adaptive control on dynamic objects]. Moscow, Nauka Publ., 1981. 448 p.
[12] Terekhov V.A., Efimov D.V., Tyukin I.Yu. Neyrosetevye sistemy upravleniya [Neural control systems]. Moscow, Vysshaya shkola Publ., 2002. 183 p.
[13] Callan R. The essence of neural network. Prentice Hall, 1998. 248 p.
[14] Venttsel E.S., Ovcharov L.A. Teoriya veroyatnostey i ee inzhenernye prilozheniya [The probability theory and its engineering applications]. Moscow, Akademiya Publ., 2003. 464 p.