Traffic Light Cycle Control using Deep Reinforcement Technique

2021 ◽  
Author(s):  
Satya Prakash Sahu ◽  
Deepak Kr. Dewangan ◽  
Archit Agrawal ◽  
T. Sai Priyanka
Keyword(s):  
Light Cycle ◽  
Traffic Light

scholarly journals Application of support vector machine in a traffic lights control

2020 ◽  
Vol 14 ◽  
pp. 37-42
Author(s):  
Artur Całuch ◽  
Adam Cieślikowski ◽  
Małgorzata Plechawska-Wójcik
Keyword(s):  
Support Vector Machine ◽  
Cycle Length ◽  
Support Vector ◽  
Light Cycle ◽  
Traffic Light ◽  
Traffic Lights ◽  
Using Data

This article presents the process of adapting support vector machine model’s parameters used for studying the effect of traffic light cycle length parameter’s value on traffic quality. The survey is carried out using data collected during running simulations in author’s traffic simulator. The article shows results of searching for optimum traffic light cycle length parameter’s value.

scholarly journals Developing Hybrid Simulation Model to Improve Road Traffic Management

2020 ◽  
Vol 4 (01) ◽  
pp. 56-65
Author(s):  
Hayati Mukti Asih
Keyword(s):  
Simulation Model ◽  
Urban Areas ◽  
Traffic Management ◽  
Road Traffic ◽  
Hybrid Simulation ◽  
Simulation Method ◽  
Vital Role ◽  
Light Cycle ◽  
Traffic Light ◽  
Traffic Lights

Yogyakarta has increasing trends in the number of vehicles and consequently intensifying the traffic volume and will effect to higher emission and air pollution. Traffic lights duration plays a vital role in congestion mitigation in the critical intersections of urban areas. This study has objective to minimize the number of vehicles waiting in line by developing the hybrid simulation method. First of all, the MKJI and Webster method were calculated to determine the green traffic light. Then, the simulation model was developed to evaluate the number of vehicles waiting in line according to different duration of green traffic lights from MKJI and Webster method. A case study will then be provided in Pelemgurih intersection located in Yogyakarta, Indonesia for demonstrating the applicability of the developed method. The result shows that the duration of green traffic lights calculated by Webster method provides lower number of vehicles waiting in line. It is due to the short duration of green traffic light resulted by Webster method so that the traffic light cycle becomes shorter and it effects the number of vehicles waiting in line which is lower than MKJI method. The results obtained can help the generating desired decision alternatives that will important for Department of Transportation, Indonesia to enhance the road traffic management with low number of vehicles waiting in line.

scholarly journals Bi-Level Optimization in a Transport Network

2015 ◽  
Vol 15 (5) ◽  
pp. 37-49 ◽  
Author(s):  
Todor Stoilov ◽  
Krasimira Stoilova ◽  
Markos Papageorgiou ◽  
Ioannis Papamichail
Keyword(s):  
Traffic Control ◽  
Optimization Problem ◽  
Transportation Network ◽  
Urban Transportation ◽  
Light Cycle ◽  
Constant Parameter ◽  
Optimal Solutions ◽  
Traffic Light ◽  
Control Space ◽  
Store And Forward

Abstract This paper applies a bi-level formalism for the optimal control of an urban transportation network. The well known store-and-forward model in traffic control is utilized in order to increase the control space of the optimization problem. Mainly, the store-and-forward models apply the split as a control argument, assuming the traffic light cycle as a constant parameter. The paper shows that by using a bi-level formalism the control problem can be defined within increased control space comprising both the split and the cycle. Both are found as optimal solutions of a bi-level optimization problem.

scholarly journals Development of Model for Traffic Flows on Urban Street and Road Network

2019 ◽  
Vol 18 (1) ◽  
pp. 47-54
Author(s):  
D. V. Kapskiy ◽  
D. V. Navoy ◽  
P. A. Pegin
Keyword(s):  
Traffic Management ◽  
Management System ◽  
Road Network ◽  
Complex Structure ◽  
Large City ◽  
Intelligent Transport System ◽  
Light Cycle ◽  
Traffic Light ◽  
Level Model ◽  
Traffic Management System

The paper considers issues pertaining to creation of a model for controlling road traffic with the purpose to minimize delays on street and road network, which is proposed as an innovative one while developing an intelligent transport system of the large city that is Minsk. The developed model has a complex structure of algorithmic support. The first-level model has been implemented on the basis of fuzzy logic, for which a program has been developed and conditions have been determined, and operation of traffic light at a real local intersection of Minsk, which is included in the automated traffic management system, has been simulated. Innovation in the first-level model is an approach in determining conditions while detecting a fuzzy set without using a standard algorithm that is an algorithm of local flexible regulation. The paper proposes and investigates a model that works on the basis of operationally obtained parameters of traffic flow intensity at characteristic points (sections) of street and road network. Efficiency of the first-level model has been equal to 8 % due to optimization of a traffic light cycle (reduction of transport delays during passage of stop lines). Results of the simulation using the proposed computer program have made it possible to improve efficiency of traffic management on the studied highway (Logoysky trakt) in Minsk city of Minsk by 15 % due to decrease of delay level in case of unilateral coordination. The algorithm has been already implemented as part of the current automated traffic management system in the city of Minsk and it has shown its efficiency. However this efficiency can be increased if it is used together with an algorithm for searching maximum volume of motion in a cycle with a distributed intensity pulse. It has been planned to take into account this specific feature when increasing possibilities for algorithmization of traffic management.

scholarly journals Saturation flow mathematical model based on multiple combinations of lane groups

2016 ◽  
Author(s):  
Laurentiu Racila
Keyword(s):  
Flow Rate ◽  
Light Cycle ◽  
Traffic Light ◽  
Mathematical Methods ◽  
Traffic Stream ◽  
Saturation Flow Rate ◽  
Group Concept ◽  
Pass Through ◽  
Saturation Flow ◽  
The Ideal

The ideal value of the traffic stream that can pass through an intersection is known as the saturation flow rate per hour on vehicle green time. The saturation flow is important in the understanding of the traffic light cycle and from there the understanding the Level of Service. The paper wishes to evaluate through a series of applied mathematical methods the effect of different lane grouping and critical lane group concept on the saturation flow rate. The importance of this method is that it creates a base for a signalized intersections timing plan.DOI: http://dx.doi.org/10.4995/CIT2016.2016.4254

scholarly journals New Transportation Systems for Smart Cities

2016 ◽  
pp. 1569-1593
Author(s):  
Christos G. Cassandras
Keyword(s):  
Traffic Management ◽  
Smart Cities ◽  
Transportation Systems ◽  
Urban Environments ◽  
Gradient Estimates ◽  
Light Cycle ◽  
Traffic Light ◽  
Cycle Lengths ◽  
Smart Parking ◽  
Charging Stations

Poor traffic management in urban environments is responsible for congestion, unnecessary fuel consumption and pollution. Based on new wireless sensor networks and the advent of battery-powered vehicles, this chapter describes three new systems that affect transportation in Smart Cities. First, a Smart Parking system which assigns and reserves an optimal parking space based on the driver's cost function, combining proximity to destination and parking cost. Second, a system to optimally allocate electric vehicles to charging stations and reserve spaces for them. Finally, we address the traffic light control problem by viewing the operation of an intersection as a stochastic hybrid system. Using Infinitesimal Perturbation Analysis (IPA), we derive on-line gradient estimates of a cost metric with respect to the controllable green and red cycle lengths and iteratively adjust light cycle lengths to improve (and possibly optimize) performance, as well as adapt to changing traffic conditions.

scholarly journals Optimization of Traffic Flow On KS Tubun Street using Greenberg Model

2019 ◽  
Vol 8 (2S7) ◽  
pp. 83-86
Keyword(s):  
Traffic Flow ◽  
Red Light ◽  
Green Light ◽  
Light Cycle ◽  
Traffic Light ◽  
Traffic Jam ◽  
Traffic Lights ◽  
The Road ◽  
Road Users ◽  
Time Parameters

KS Tubun Street is a street in Bogor, which has a fairly high vehicle volume and become one of a high-traffic jam area. This is caused by KS Tubun Street is the main road for road users from Jakarta and Bogor. Traffic jam problem that occurs due to the confluence interchange of traffic flow and traffic lights settings that are not proportional to the volume of vehicles across the road. Optimization of traffic flow at KS Tubun Street performed by the stages of forming a model of traffic flow, determining the density and velocity of the vehicle is based on the Greenberg model, and determining the length of the traffic lights to avoid a buildup of vehicles. The result is a traffic flow model with distance and time parameters. The density of vehicles that occurs on the streets of KS. Tubun street based on the Greenberg model between 180 to 240 unit car of passanger (ucp) with the average velocity of vehicles 15 to 19.5 km per hour. The density of vehicles on KS. Tubun street can be break down by increasing time. Traffic light cycle time can be reduced for 8 seconds with the red light glowing time is 80 seconds and the green light glowing time is 62 seconds.

scholarly journals INTELLIGENT SYSTEM OF TRAFIC LIGHT CONTROL WITH DYNAMIC CHANGE PHASES OF TRAFFIC FLOWS ON UNCONTROLLED INTERSECTIONS

World Science ◽  
2018 ◽  
pp. 15-19
Author(s):  
Мoroz B. I. ◽  
Alekseieiev M. O. ◽  
Shvachych G. G. ◽  
Pasichnik A. M. ◽  
Miroshnichenko S. V.
Keyword(s):  
Traffic Control ◽  
Intelligent System ◽  
Dynamic Change ◽  
Light Cycle ◽  
Traffic Flows ◽  
Light Control ◽  
Traffic Light ◽  
Traffic Light Control ◽  
Effective System ◽  
Traffic Control System

There was method of making an effective system of traffic-light control of the traffic through the intersections in one direction according to which the phase coefficients for each cycle of traffic-light control are computed in real-time using the data of traffic intensity detected by transport detectors. Thus, the built-in traffic control system will be dynamically adapted to the change in the intensity of traffic flows, and the structure of the cycle and its duration will be changed taking into account the parameters of the traffic flow at the intersection. Accordingly, the traffic light cycle, where each cycle has the minimum required duration, will be most effective and will ensure uninterrupted traffic, the lack of traffic jams and the convenience for the pedestrian crossings.

scholarly journals Recent development of smart traffic lights

2021 ◽  
Vol 10 (1) ◽  
pp. 224
Author(s):  
A’isya Nur Aulia Yusuf ◽  
Ajib Setyo Arifin ◽  
Fitri Yuli Zulkifli
Keyword(s):  
Traffic Flow ◽  
Time Allocation ◽  
Traffic Density ◽  
Light Cycle ◽  
Traffic Light ◽  
Large Cities ◽  
Traffic Lights ◽  
Smart Traffic ◽  
Very High ◽  
Signal Time

<span id="docs-internal-guid-288f4dcc-7fff-1e8c-0350-5032593b6e4f"><span>Increased traffic flow causes congestion, especially in large cities. Even though congestion is not unusual, traffic jams still result in very high economic and social losses. Several factors cause congestion, one of which is traffic lights. Therefore, a mechanism is needed so that traffic lights can intelligently and adaptively manage signal time allocation according to traffic flow conditions. A traffic light with this type of mechanism is known as a smart traffic light. Smart traffic light cycle settings can be grouped based on the traffic density, scenarios for emergency vehicles, and the interests of pedestrians. This paper analyzes the methods and technologies used in the development of smart traffic light technology from the perspective of these three situations as well as the development of smart traffic light technology in the future.</span></span>

Sign in / Sign up

Export Citation Format

Share Document