A new nondominated sorting genetic algorithm based to the regression line For fuzzy traffic signal optimization problem

Document Type : Article

Authors

1 Department of Industrial Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran

2 School of Industrial Engineering, College of Engineering, University of Tehran, Tehran, Iran

3 Department of Industrial Technology and Management, Vali-e-Asr University Of Rafsanjan, Iran

Abstract

Traffic jam is a daily problem in nearly all major cities in the world and continues to increase with population and economic growth of urban areas. Traffic lights, as one of the key components at intersections, play an important role in control of traffic flow. Hence, study and research on phase synchronization and time optimization of the traffic lights could be an important step to avoid creating congestion and rejection queues in a urban network. Here, we describe the application of NSGA-II, a multi-objective evolutionary algorithm, to optimize both vehicle and pedestrian delays in an individual intersection. Results show that parameters found by improved NSGA-II can be superior to those defined by a traffic engineer with respect to several objectives, including total   queue length of vehicles and pedestrians.
In this paper, we improve NSGA-II algorithm based to the regression line to find a Pareto-optimal solution or a restrictive set of Pareto-optimal solutions based on our solution approaches to the problem, named PDNSGA (Non-dominated Sorting Genetic Algorithm based on Perpendicular Distance). In this paper, our purpose is to present a solution methodology to obtain all Pareto-optimal solutions to optimize traffic signal timing and enable the decision-makers to evaluate a greater number of alternative solutions. The proposed algorithm has the capability of searching Pareto front of the multi-objective problem domain. Further jobs should be concerned on the signal timing optimization method for the oversaturated coordinated intersections or small-scale road network and real-field applications with the traffic signal controller. The high speed of the proposed algorithm and its quick convergence makes it desirable for large scheduling with a large number of phases. Furthermore, we have used the mean deviation from the ideal point (MDI) measure to compare the performance of the MOGA, PDNSGA, NSGA-II, and WBGA by the ANOVA method. It is demonstrated that the our proposed algorithm (PDNSGA) gives better outputs than those of MOGA, NSGA-II, and WBGA in traffic signal optimization problem, statistically .

Keywords

Main Subjects


References
1. Ishaque, M.M. and Noland, R.B. Multimodal microsimulation
of vehicle and pedestrian signal timings",
In Transportation Research Record 1939, TRB,
National Research Council, Washington, D.C, pp. 107-
114 (2005).
2. Ishaque, M.M. and Noland, R.B. Trade-o s between
vehicular and pedestrian trac using micro-simulation
methods", In Transportation Policy, 14, pp. 124-138
(2007).
3. Bhattacharya, P. Methodology to optimize for pedestrian
delay and vehicular delay in a signal network",
M.S. Thesis, University of Missouri-Columbia (2004).
4. Bhattacharya, P. and Virkler, M.R. Optimization for
pedestrian and vehicular delay in a signal network",
In Transportation Research Record 1939, TRB, National
Research Council,Washington, D.C, pp. 115-122
(2005).
5. Li, M., Alhajyassen, W.K.M., and Nakamura, H. A
trac signal optimization strategy considering both
vehicular and pedestrian
ows", Presented at the 89th
Annual Meeting of the Transportation Research Board,
Washington, D.C. (2009).
6. Mehan, S. Introduction of trac light controller
with fuzzy control system", International Journal of
Electronics & Communication Technology, 2(3), pp.
119-122 (2011).
7. Barzegar, B. Fuzzy logic controller for trac signal
controller unit system and modelling with colored petri
net", Indian Journal of Science and Technology, 4(11),
pp. 1420-1428 (2011).
8. Gokulan, B.P. and Srinivasan, D. Distributed geometric
fuzzy multiagent urban trac signal control",
IEEE Trans. Intell. Transp. Syst., 11(3), pp. 714-727
(September 2010).
9. Blum, C. and Roli, A. Metaheuristics in combinatorial
optimization: overview and conceptual comparison",
ACM Comput. Surveys (CSUR), 35(3), pp. 268-
308 (2003)
10. Holm, P., Tomich, D., Sloboden, J., and Lowrance,
C. Trac analysis toolbox volume iv: guide-lines
for applying corsim microsimulation modeling software",
Technical Report, National Technical Information
Service-5285 Port Royal Road Spring eld, VA
22161, USA-Final Report (2007)
11. Turky, A.M., Ahmad, M.S., Yuso , M.Z., and Hammad,
B.T. Using genetic algorithm for trac light
control system with a pedestrian crossing", RSKT '09:
Proceedings of the Fourth International Conference
on Rough Sets and Knowledge Technology, Berlin,
Heidelberg, pp. 512-519 (2009).
12. Odeh, S.M., Mora, A.M., Moreno, M.M., and Merelo,
J.J., A Hybrid Fuzzy Genetic Algorithm for an Adaptive
Trac Signal System, Hindawi Publishing Corporation
Advances in Fuzzy Sys-tems, Article ID 378156
(2015).
13. Aboudolas, K., Papageorgiou, M., Kouvelas, A.,
and Kosmatopoulos, E. A rolling-horizon quadraticprogramming
approach to the signal control problem
in large-scale congested urban road networks", Transportation
Research. Part C: Emerging Technologies,
18, pp. 680-9(2010).
14. Gottlich, S., Herty, M., and Ziegler, U. Modeling
and o timing trac light settings in road networks",
Computers & Operations Research, 55, pp. 36-51
(2015).
15. Collotta, M., Bellb, L., and Pau, G. A novel approach
for dynamic trac lights management based
on wireless sensor networks and multiple fuzzy logic
controllers", Expert Systems with Applications, 42, 13,
pp. 5403-5415 (2015).
16. Shahsavari Pour, N., Asadi, H., and Pour Kheradmand,
M. Fuzzy multiobjective trac light signal
optimization", Journal of Applied Mathematics, 7, pp.
01-07 (2013).
17. Duerr, P. Dynamic right-of-way for transit vehicles:
integrated modeling approach for optimizing signal
control on mixed trac arterials. In transportation research
broad", Journal of the Transportation Research
Board, 1731, pp. 31-39 (2000).
18. Girianna, M. and Benekohal, R.F. Dynamic signal
coordination for networks with oversaturated intersections",
In Transportation Research Record 1811, TRB,
National Research Council, Washington, D.C., pp.
122-132 (2002).
19. Girianna, M. and Benekohal, R.F. Using genetic algorithms
to design signal coordination for oversaturated
networks", In Journal of ITS: Technology, Planning,
and Operations, 8(2), pp. 117-129 (2004).
20. Srinivas, N. and Deb, K. Multiobjective optimization
using nondominated sorting in genetic algorithms", J
Evol Comput, 2(3), pp. 221-48 (1994).
21. Deb, K., Pratap, A., Agarwal, S., and Meyarivan, T.
A fast and elitist multiobjective genetic algorithm",
NSGA-II. IEEE Trans. Evol. Comput., 6(2), pp. 182-
97 (2002).
22. Jones, D.F., Mirrazavi, S.K., and Tamiz, M. Multiobjective
metaheuristics an overview of the current
state-of-the-art", Eur. J. Oper. Res., 137(1), pp. 1-9
(2002).
23. Scha er, J.D. Multiple objective optimization with
vector evaluated genetic algorithms", In: Proceedings
H. Asadi et al./Scientia Iranica, Transactions E: Industrial Engineering 25 (2018) 1712{1723 1723
of the International Conference on Genetic Algorithm
and Their Applications (1985).
24. Chavez, S., Willmer, J., and Echeverri, E.M.G. A
multi-objective Pareto ant colony algorithm for the
multi-depot vehicle routing problem with backhauls",
International Journal of Industrial Engineering Computations,
7, pp. 35-48 (2016).
25. Zhao, X., Hsu, Y.C., ChangB, P.C., and Li, L. A
genetic algorithm for the multi-objective optimization
of mixed-model assembly line based on the mental
workload", Engineering Applications of Arti cial Intelligence,
47, pp. 140-146 (2016).
26. Zhu, Z., Xiao, J., He, S., Zhen, J., and Sun,
Y. A multi-objective memetic algorithm based on
locality-sensitive hashing for one-to-many-to-one dynamic
pickup-and-delivery problem", Information Sciences,
329, pp. 73-89 (2016).
27. Hajipour, V., Mehdizadeh, E., and Tavakkoli-
Moghaddam, R. A novel Pareto-based multi-objective
vibration damping optimization algorithm to solve
multi-objective optimization problems", Scientia Iranica
E, 21(6), pp. 2368-2378 (2014).
28. Horn, J., Nafpliotis, N., and Goldberg, D.E. A niched
Pareto genetic algorithm for multiobjective optimization",
In: Proceedings of the First IEEE Conference
on Evolutionary Computation. IEEE World Congress
on Computational Intelligence, pp. 27-29 June, 1994.
Orlando, FL, USA: IEEE (1994).
29. Spieksma, F.C.R. and Woeginger, G.J. The no-wait

flow-shop paradox", Operation Research Letter, 33, pp.
603-608 (2005).