Ali Payıdar AKGÜNGÖR, Sevim YAVUZ, Ersin KORKMAZ, Erdem DOĞAN

İzole Sinyalize Kavşaklar için Çiçek Tozlaşma Algoritması Kullanılarak Devre Süresi Modellerinin Geliştirilmesi

Son zamanlarda nüfus ve ekonomideki büyüme karayollarında araç kullanımını arttırmakta, buna bağlı olarak dakavşakların kapasitesi yetersiz kalmaktadır. Kavşakların verimsiz çalışmasından dolayı gecikme, yakıt tüketimi,emisyon salınımı artarken sürücü davranışları da olumsuz etkilenmektedir. Kavşak geometrilerininiyileştirilmesinin yanı sıra, optimum devre süresinin doğru tespiti ve sinyal sürelerinin düzenlenmesi ile de busorunların minimuma indirilebilmesi mümkün olmaktadır. Bu çalışmada Çiçek Tozlaşma Algoritması (ÇTA)kullanılarak optimum devre süresi modelleri geliştirilmiştir. Ayrıca en düşük gecikmeye sahip olan devresürelerinin belirlenmesinde Diferansiyel Gelişim Algoritmasından (DGA) yararlanılmıştır. Kalibre edilen Webstermodeline ilave olarak sabit eklenmiş Webster model formu ve üstel formda devre süresi modelleri geliştirilmiştir.VISSIM simülasyon programı ile elde edilen gecikme değerlerine göre geliştirilen bütün modeller Webster modelive VISTRO optimizasyon programı ile karşılaştırılmış ve önerilen modellerin istatistiksel olarak daha iyiperformansa sahip olduğu görülmüştür. Bu modellerin özellikle yüksek trafik hacmine sahip trafik durumlarındayetersiz kalan Webster modelindeki eksiklikleri kapatarak alternatif bir devre süresi tahmin modeli olarakkullanılabileceği ön görülmektedir.

Development of Cycle Length Models using Flower Pollination Algorithm for Isolated Signalized Intersections

Recently, the growth in population and economy has increased the use of vehicles on highways and accordingly the capacity of the intersections is insufficient. Delay, fuel consumption and emissions are increased due to the inefficient operation of intersections, and driver behavior is adversely affected. In addition to improving intersection geometry, by correct determination of optimum cycle length and arrangement of signal times, it is possible to minimize these problems. In this study, optimum cycle length models have been developed by using Flower Pollination Algorithm (FPA). Additionally, Differential Evolution Algorithm has been used to determine the cycle length which has the minimum delay value for each traffic situation. In addition to the calibrated Webster model, Webster model with constant form and exponential form have been developed as cycle length models. All models developed according to the delay values obtained with the VISSIM simulation program were compared with the Webster model and the VISTRO optimization program and the proposed models were found to have statistically better performance. It has been seen that these models can be used as an alternative cycle length estimation model by defeating the deficiencies in Webster model which is insufficient especially in traffic situations with high traffic volume.

PDF

___

[1] Webster F.V. 1958. Traffic signal settings, road research technical paper. No: 39, Road Research Laboratory.
[2] Thomas G.B., Upchurch J.E. 1998. Effect of non-optimal cycle lengths and traffic volumes on progression. Institute of Transportation Engineers. ITE Journal, 68 (5): 38.
[3] Lan C.J. 2004. New optimal cycle length formulation for pretimed signals at isolated intersections. Journal of Transportation Engineering, 130 (5): 637-647.
[4] Cheng D., Tian Z.Z., Messer C. J. 2005. Development of an improved cycle length model over the highway capacity manual 2000 quick estimation method. Journal of Transportation Engineering, 131 (12): 890-897.
[5] Day C., Bullock D., Sturdevant J. 2009. Cycle-length performance measures: revisiting and extending fundamentals. Transportation Research Record: Journal of the Transportation Research Board, (2128): 48-57.
[6] Singh L., Tripathi S., Arora H. 2009. Time optimization for traffic signal control using genetic algorithm. International Journal of Recent Trends in Engineering, 2 (2): 4-6.
[7] Al-Kubaisi M.I. 2012. Optimum Cycle Time Prediction for Signalized Intersections at Baghdad City. Cankaya University Journal of Science and Engineering, 9 (2): 149-166.
[8] Sun S.N., Xiao W., Qiu X., Chen J.D., Ying L.X. 2012. Design and Simulation of Urban Road Intersection Signal Linear Control System. In: Applied Mechanics and Materials, 178: 2713- 2716.
[9] Dai L.L., Sun Z.L., Liu D.B., Li Y. 2013. An Improved Method of Traffic Control Period Division for Intersection Based on Signal Cycle Calculation. In Applied Mechanics and Materials 253: 1731-1735.
[10] Dell'Orco M., Baskan O., Marinelli M. 2013. A Harmony Search Algorithm approach for optimizing traffic signal timings. PROMET-Traffic & Transportation, 25 (4): 349-358.
[11] Wu Y., Lu J., Chen H., Yang H. 2015. Development of an optimization traffic signal cycle length model for signalized intersections in China. Mathematical Problems in Engineering, 954295: 1- 9.
[12] Çakıcı Z., Murat Y.Ş. 2015. Sezgisel Optimizasyon Algoritmalarının Taşıt Gecikmesi Problemi Üzerine Uygulaması.7. Kentsel Altyapı Sempozyumu, Trabzon, 615-625.
[13] Zakariya A.Y., Rabia S.I. 2016. Estimating the minimum delay optimal cycle length based on a time-dependent delay formula. Alexandria Engineering Journal, 55 (3): 2509-2514.
[14] Jovanović A., Nikolić M., Teodorović D. 2017. Area-wide urban traffic control: A Bee Colony Optimization approach. Transportation Research Part C: Emerging Technologies, 77: 329-350.
[15] Storn R., Price K. 1997. Differential evolution–a simple and efficient heuristic for global optimization over continuous spaces. Journal of global optimization, 11 (4): 341-359.
[16] Yang X.-S. 2014. Nature-inspired optimization algorithms. Elsevier.
[17] http://vision-traffic.ptvgroup.com/en-us/products/ptv-vissim/use-cases/ (Erişim Tarihi: 15.04.2019).
[18] Mallipeddi R., Suganthan P.N., Pan Q.-K., Tasgetiren M.F. 2011. Differential evolution algorithm with ensemble of parameters and mutation strategies. Appl. Soft Comput., 11 (2): 1679-1696.
[19] Yang X.-S. 2012. Flower pollination algorithm for global optimization. In: International conference on unconventional computing and natural computation, 240-249.