Konya-Türkiye'de Belirli Bir İzole Kavşakta Optimum Çevrim Uzunluğu ve Ortalama Gecikme Süresinin Çok Amaçlı Optimizasyonu

Yıl 2020, Cilt: 36 Sayı: 3, 333 - 344, 31.12.2020

Ali Karaşahin Tahir Sağ

Öz

Nüfus artışına paralel olarak şehirlerdeki araç sayısı
da artmaktadır. Artan araç sayısı trafik yönetimini zorlaştırmaktadır. Bu durum
daha yüksek yakıt tüketimi ve CO2 emisyonu ve benzeri zararlı emisyonların
salınımına yol açmaktadır. Bu nedenle, trafik ışıklarının gerçek zamanlı
optimizasyonu, yani sinyalizasyon sistemi, trafik yönetimini daha verimli hale
getirebilir. Bu çalışmada, Konya/Türkiye şehir merkezinde belirlenen bir sinyalizasyon
kavşağında, bekleme süreleri çok amaçlı optimizasyon algoritmaları ile optimize
edilmiştir. Optimum-döngü-uzunluğu ve ortalama bekleme süreleri amaç
fonksiyonları olarak tanımlanmıştır. Literatürün önde gelen algoritmalarından
olan Bastırılmamışlık Sıralamalı Genetik Algoritma II (NSGAII), Kuvvet Pareto
Evrimsel Algoritması 2 (SPEA2) ve Gösterge Tabanlı Evrimsel Algoritma (IBEA) bu
problem için çalıştırıldı. Kullanılan kavşağa ait veriler Konya Büyükşehir
Belediyesi Ulaştırma Trafik Planlama Şube Müdürlüğü'nden elde edildi. Deneysel
sonuçlar, sinyalize kavşaklarda optimum döngü süresinin çok amaçlı optimizasyon
algoritmaları ile verimli bir şekilde belirlenebileceğini göstermektedir.

Anahtar Kelimeler

Trafik sinyalizasyonu, Çok-amaçlı optimizasyon, NSGA-II, SPEA2, IBEA

Multiobjective Optimization of Optimum-Cycle-Length and Average-Delay-Time at a Specific Isolated Intersection in Konya-Turkey

Öz

Parallel to population growth, the number of vehicles
in cities is also increasing. The vehicle increase makes traffic management
difficult. This situation leads to higher fuel consumption and emissions of CO2
and similar harmful emissions. Therefore, real-time optimization of traffic
lights i.e. signalization can make traffic management more efficient. In this
study, the duration of the signals at an intersection where the signal light in the
center of Konya/Turkey is optimized by multi-objective optimization algorithms
using optimum-cycle-length and average-delay-time as objectives. Three
state-of-the-art algorithms are applied to this problem, which are named as
Non-dominated Sorting Genetic Algorithm (NSGAII), Strength Pareto Evolutionary
Algorithm (SPEA2) and Indicator-Based Evolutionary Algorithm (IBEA). The
dataset is obtained from Konya Metropolitan Municipality Transportation Traffic
Planning Branch Directorate. The experimental results show that the
optimum-cycle-time at signalized intersections can be determined by
multi-objective optimization algorithms.

Anahtar Kelimeler

Traffic signalization, multi-objective optimization, NSGA-II, SPEA2, IBEA

Kaynakça

• E. Öztürk, M. Çubuk, and S. Hatipoğlu, "Ankara için Bir Sinyal Zamanlaması Modeli: Besevler Kavsagı Örnegi," Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, vol. 12, pp. 49-57 2009, doi: 10.19113/sdufbed.83379.
• P. Lowrie, "The Sydney coordinated adaptive traffic system - principles, methodology, algorithms," in International conference on road traffic signalling, London, 1982: Institution of Electrical Engineers.
• G. Çetinkaya, "Işıklı Kavşaklarda Değişik Hesaplama Yöntemlerinin Karşılaştırılması," Master, Graduate Program in Transportation Engineering, İstanbul Technical University, Institute of Science and Technology, 2008. [Online]. Available: http://hdl.handle.net/11527/4881
• R. K. Kıyıldı, "Türkiye için Yapay Sinir Ağları Yöntemi ile Trafik Kazası Tahmini Araştırması," in 5th International Symposium on Innovative Technologies in Engineering and Science, Baku - Azerbaijan, 2017, pp. 1642-1651.
• Z. Çakıcı and Y. Ş. Murat, "The Optimization of Traffic Signal Timing with Meta-Heuristic Differential Evolution Algorithm," presented at the International Conference on Intelligence Transportation Systems, Bandırma-Turkey, 2018.
• P. Hao and C. Feng, "An optimization approach for intersection signal timing based on Multi-Objective Particle Swarm Optimization," in 2008 IEEE Conference on Cybernetics and Intelligent Systems, 21-24 Sept. 2008 2008, pp. 771-775, doi: 10.1109/ICCIS.2008.4670973.
• F. Shen and X. Yang, "Optimization Algorithm of Urban Road Traffic Signal Plan Based on NSGAII," in 2008 International Conference on Intelligent Computation Technology and Automation (ICICTA), 20-22 Oct. 2008 2008, vol. 2, pp. 398-401, doi: 10.1109/ICICTA.2008.316.
• H. Hu, Y. Gao, and X. Yang, "Multi-objective Optimization Method of Fixed-Time Signal Control of Isolated Intersections," in 2010 International Conference on Computational and Information Sciences, 17-19 Dec. 2010 2010, pp. 1281-1284, doi: 10.1109/ICCIS.2010.316.
• K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, "A fast and elitist multiobjective genetic algorithm: NSGA-II," IEEE T Evolut Comput, vol. 6, no. 2, pp. 182-197, 2002.
• E. Zitzler, M. Laumanns, and L. Thiele, "SPEA2: Improving the strength Pareto evolutionary algorithm," TIK-report, vol. 103, 2001.
• E. Zitzler and S. Künzli, "Indicator-based selection in multiobjective search," in International Conference on Parallel Problem Solving from Nature, 2004: Springer, pp. 832-842.
• F. V. Webster, Traffic signal settings (Road research technical paper, no. 39.). London : H.M.S.O.: Government publication, National government publication, 1958, p. 44.
• H. C. Manual, "Transportation Research Board of the National Academies," Washington, DC, p. 2010, 2010.
• R. Akcelik, Traffic signals: capacity and timing analysis (Publication of: Australian Road Research Board). Melbourne, Victoria Australia: ARRB, 1981, p. 109.
• C. A. C. Coello, G. B. Lamont, and D. A. Van Veldhuizen, Evolutionary algorithms for solving multi-objective problems (Genetic and Evolutionary Computation Series book series (GEVO)). Springer, 2007.
• A. Osyczka, Evolutionary algorithms for single and multicriteria design optimization. New York: Physica Verlag, 2002.
• D. W. Corne, N. R. Jerram, J. D. Knowles, and M. J. Oates, "PESA-II: region-based selection in evolutionary multiobjective optimization," presented at the Proceedings of the 3rd Annual Conference on Genetic and Evolutionary Computation, San Francisco, California, 2001.
• Y. Jin, T. Okabe, and B. Sendho, "Adapting Weighted Aggregation for Multiobjective Evolution Strategies," Berlin, Heidelberg, 2001: Springer Berlin Heidelberg, in Evolutionary Multi-Criterion Optimization, pp. 96-110.
• H. Ishibuchi and T. Murata, "A multi-objective genetic local search algorithm and its application to flowshop scheduling," Trans. Sys. Man Cyber Part C, vol. 28, no. 3, pp. 392-403, 1998, doi: 10.1109/5326.704576.
• Q. Zhang and H. Li, "MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition," Ieee T Evolut Comput, vol. 11, no. 6, pp. 712-731, 2007, doi: 10.1109/TEVC.2007.892759.
• E. Zitzler and S. Künzli, "Indicator-Based Selection in Multiobjective Search," Berlin, Heidelberg, 2004: Springer Berlin Heidelberg, in Parallel Problem Solving from Nature - PPSN VIII, pp. 832-842.
• N. Beume, B. Naujoks, and M. Emmerich, "SMS-EMOA: Multiobjective selection based on dominated hypervolume," Eur J Oper Res, vol. 181, no. 3, pp. 1653-1669, 2007/09/16/ 2007, doi: https://doi.org/10.1016/j.ejor.2006.08.008.
• N. Riquelme, C. V. Lücken, and B. Baran, "Performance metrics in multi-objective optimization," in 2015 Latin American Computing Conference (CLEI), 19-23 Oct. 2015 2015, pp. 1-11, doi: 10.1109/CLEI.2015.7360024.
• E. Zitzler and L. Thiele, "Multiobjective optimization using evolutionary algorithms — A comparative case study," Berlin, Heidelberg, 1998: Springer Berlin Heidelberg, in Parallel Problem Solving from Nature — PPSN V, pp. 292-301.
• Z. Aimin, J. Yaochu, Z. Qingfu, B. Sendhoff, and E. Tsang, "Combining Model-based and Genetics-based Offspring Generation for Multi-objective Optimization Using a Convergence Criterion," in 2006 IEEE International Conference on Evolutionary Computation, 16-21 July 2006 2006, pp. 892-899, doi: 10.1109/CEC.2006.1688406.
• T. T. Binh and U. Korn, "Multiobjective evolution strategy with linear and nonlinear constraints," in Proc. of the 15th IMACS World Congress on Scientific Computation, Modeling and Applied Mathematics, 1997, pp. 357-362.
• C. A. C. Coello and N. C. Cortés, "Solving Multiobjective Optimization Problems Using an Artificial Immune System," Genetic Programming and Evolvable Machines, journal article vol. 6, no. 2, pp. 163-190, June 01 2005, doi: 10.1007/s10710-005-6164-x.
• D. Hadka, "Platypus: A free and open source python library for multiobjective optimization," Available on Github, vol. https://github.com/Project-Platypus/Platypus, 2017.