[1] Bie Yiming, Wang Linhong, Wang Dianhai, Ma Dongfang, et al. A signal coordination algorithm for two adjacent intersectionsbased on approximate dynamic programming [J]. Journal of Southeast University (English Edition), 2012, 28 (1): 112-118. [doi:10.3969/j.issn.1003-7985.2012.01.019]

Copy

A signal coordination algorithm for two adjacent intersectionsbased on approximate dynamic programming()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

28

Issue:

2012 1

Page:

112-118

Research Field:

Traffic and Transportation Engineering

Publishing date:

2012-03-30

Info

Title:

A signal coordination algorithm for two adjacent intersectionsbased on approximate dynamic programming

Author(s):

Bie Yiming¹;  Wang Linhong¹;  Wang Dianhai²;  Ma Dongfang¹

¹ College of Transportation, Jilin University, Changchun 130022, China
² College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, China

Keywords:

signal coordination;  approximate dynamic programming;  vehicle emissions;  planning horizon

PACS:

U491

DOI:

10.3969/j.issn.1003-7985.2012.01.019

Abstract:

To reduce vehicle emissions in road networks, a new signal coordination algorithm based on approximate dynamic programming(ADP)is developed for two intersections. Taking the Jetta car as an experimental vehicle, field tests are conducted in Changchun Street of Changchun city and vehicle emission factors in complete stop and uniform speed states are collected. Queue lengths and signal light colors of approach lanes are selected as state variables, and green switch plans are selected as decision variables of the system. Then the calculation model of the optimization index during the planning horizon is developed based on the basis function method of the ADP. The temporal-difference algorithm is employed to update the weighting factor vector of the approximate function. Simulations are conducted in Matlab and the results show that the established algorithm outperforms the conventional coordination algorithm in reducing vehicle emissions by 8.2%. Sensitive analysis of the planning horizon length on the evaluation index is also conducted and the statistical results show that the optimal length of the planning horizon is directly proportional to the traffic load.

References:

[1] Bell M C, Bretherton R D. Ageing of fixed-time traffic signal plans [C]//Proceedings of the Second IEE Conference on Road Traffic Control. London, 1986:77-80.
[2] Robertson D I. TRANSYT: a traffic network study tool, RRL Report, LR 253 [R]. Crowthorne: Transport and Road Research Laboratory, 1969:391-394.
[3] Little J D C, Kelson M D, Gartner N H. MAXBAND: a program for setting signals on arterials and triangular networks [J]. Journal of Transportation Research Record, 1981(795): 40-46.
[4] Hunt P B, Robertson D I, Bretherton R D. The SCOOT on-line traffic signal optimization technique [J]. Traffic Engineering & Control, 1982, 23(4):190-192.
[5] Luk J Y K. Two traffic-responsive area traffic control methods: SCAT and SCOOT [J]. Traffic Engineering & Control, 1984, 125(1):14-22.
[6] Henry J J, Farges J L, Tuffal J. The PRODYN real time traffic algorithm [C]//Proceedings of the Fourth IFAC-IFIP-IFORS Conference on Control in Transportation Systems. Baden-Baden, Germany, 1983:305-310.
[7] Gartner N H. OPAC: a demand-responsive strategy for traffic signal control [J]. Transportation Research Record, 1983(906):75-81.
[8] Cai C, Wong C K, Heydecker B G. Adaptive traffic signal control using approximate dynamic programming [J]. Transportation Research Part C, 2009, 17(5): 456-474.
[9] Bellman R. Dynamic programming [M]. Princeton University Press, 1957:42-63.
[10] Powell W B. Approximate dynamic programming: solving the curses of dimensionality [M]. John Wiley & Sons, Inc., 2007: 85-149.
[11] Guo Dong. Research on vehicle emissions optimization on urban traffic network [D]. Changchun: College of Transportation of Jilin University, 2010.(in Chinese)
[12] Xu Jianmin. Traffic management and control [M].Beijing: China Communications Press, 2007: 172-198.(in Chinese)

Memo

Memo:

Biographies: Bie Yiming(1986—), male, graduate; Wang Dianhai(corresponding author), male, professor, wangdianhai@sohu.com.
Foundation items: The National High Technology Research and Development Program of China(863 Program)(No.2011AA110304), the National Natural Science Foundation of China(No.50908100).
Citation: Bie Yiming, Wang Linhong, Wang Dianhai, et al. A signal coordination algorithm for two adjacent intersections based on approximate dynamic programming[J].Journal of Southeast University(English Edition), 2012, 28(1):112-118.[doi:10.3969/j.issn.1003-7985.2012.01.019]

Common functions