Methodology for off-line assessment of advanced traffic signal control systems

2001 ◽  
Vol 28 (1) ◽  
pp. 111-119
Author(s):  
Abdulkader Alkadry ◽  
Ata Khan
Keyword(s):  
New York ◽  
Control Systems ◽  
Traffic Control ◽  
Central Business District ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Complex Nature ◽  
Optimization Simulation ◽  
Traffic Signal Control Systems ◽  
Business District

For the assessment of the effectiveness of major investments in advanced signal control systems prior to their implementation, it is necessary to quantify performance improvement and emission reduction. Owing to the complex nature of a traffic network, reliable estimates cannot be obtained from the use of handbook type of methods. Furthermore, reliance on the experience of other sites may not be justified because of a wide variation in results. This paper describes an off-line optimization-simulation methodology for the study of the effectiveness of advanced traffic control and its application to a real world case study, the central business district of Syracuse, New York. The methodology used incorporates TRAF-NETSIM and TRANSYT. It is well suited for off-line estimation of the measures of effectiveness of advanced signal control systems. Results show that advanced signal control has the potential to cause a highly significant improvement in user service and at the same time emissions can be reduced.Key words: traffic control, congestion, user service, delay, emissions, simulation, optimization.

scholarly journals DQN-BASED TRAFFIC SIGNAL CONTROL SYSTEMS

2021 ◽  
Vol 6 (7(57)) ◽  
pp. 16-18
Author(s):  
Ivan Vladimirovich Kondratov
Keyword(s):  
Reinforcement Learning ◽  
Control Systems ◽  
Real Time ◽  
Traffic Control ◽  
Optimization Methods ◽  
Traffic Signal ◽  
Modern World ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Traffic Signal Control Systems

Real-time adaptive traffic control is an important problem in modern world. Historically, various optimization methods have been used to build adaptive traffic signal control systems. Recently, reinforcement learning has been advanced, and various papers showed efficiency of Deep-Q-Learning (DQN) in solving traffic control problems and providing real-time adaptive control for traffic, decreasing traffic pressure and lowering average travel time for drivers. In this paper we consider the problem of traffic signal control, present the basics of reinforcement learning and review the latest results in this area.

Research on Path Optimization of Urban Traffic Guidance System

2014 ◽  
Vol 624 ◽  
pp. 520-523
Author(s):  
Dan Ping Wang ◽  
Kun Yuan Hu
Keyword(s):  
Control Systems ◽  
Traffic Control ◽  
Traffic Congestion ◽  
Design Patterns ◽  
Rapid Development ◽  
Urban Traffic ◽  
Guidance System ◽  
Traffic Signal Control ◽  
Traffic Guidance ◽  
Traffic Signal Control Systems

With the rapid development of economics and technology; the number of vehicles has largely increased. In this paper, traffic guidance and traffic control systems were researched as well as the Internet of Things (IOT). The author tried to combine these three parts to send traffic data to road users so as to let them choose the best route to travel. Meanwhile, traffic network optimization has been realized to reduce traffic congestion areas. This paper has optimized regional traffic signal control systems based on IOT, traffic guidance as well as traffic assignment, involved data sources, IOT design patterns, data collection as well as the relationship between guidance obeisance rate and traffic jam. It also involved the definition of ideal traffic shortest routes, planning and designing of traffic control systems. Results and researches could hope to combine with reality in order to reduce traffic congestion.

ACS-Lite Algorithmic Architecture: Applying Adaptive Control System Technology to Closed-Loop Traffic Signal Control Systems

2003 ◽  
Vol 1856 (1) ◽  
pp. 175-184 ◽  
Author(s):  
Felipe Luyanda ◽  
Douglas Gettman ◽  
Larry Head ◽  
Steven Shelby ◽  
Darcy Bullock ◽  
...  
Keyword(s):  
Adaptive Control ◽  
Control System ◽  
Control Systems ◽  
Closed Loop ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Adaptive Control System ◽  
Traffic Conditions ◽  
Run Time ◽  
Traffic Signal Control Systems

ACS-Lite is being developed by FHWA to be a cost-effective solution for applying adaptive control system (ACS) technology to current, state-of-the-practice closed-loop traffic signal control systems. This effort is intended to make ACS technology accessible to many jurisdictions without the upgrade and maintenance costs required to implement ACS systems that provide optimized signal timings on a second-by-second basis. The ACS-Lite system includes three major algorithmic components: a time-of-day (TOD) tuner, a run-time refiner, and a transition manager. The TOD tuner maintains plan parameters (cycle, splits, and offsets) as the long-term traffic conditions change. The run-time refiner modifies the cycle, splits, and offsets of the plan that is currently running based on observation of traffic conditions that are outside the normal bounds of conditions this plan is designed to handle. The run-time refiner also determines the best time to transition from the current plan to the next plan in the schedule, or, like a traffic-responsive system, it might transition to a plan that is not scheduled next in the sequence. The transition manager selects from the transition methods built in to the local controllers to balance the time spent out of coordination with the delay and congestion that is potentially caused by getting back into step as quickly as possible. These components of the ACS-Lite algorithm architecture are described and the similarities and differences of ACS-Lite with state-of-the-art and state-of-the-practice adaptive control algorithms are discussed. Closed-loop control system characteristics are summarized to give the context in which ACS-Lite is intended to operate.

Sign in / Sign up

Export Citation Format

Share Document