Traffic Signal Control Problem Research Articles

High performance adaptive traffic control for efficient response in vehicular ad hoc networks

Nowadays, with the invention of CUDA, a parallel computing platform and programming model, there is a dramatic increase in computing performance by harnessing the power of the GPU. GPU computing with CUDA can be utilised to find efficient solutions for many real world complex problems. One such problem is traffic signal control problem, which takes care of conflicting movements at the intersections to avoid accidents and ensure smooth flow of traffic for the commuters in safe and efficient manner. Adaptive traffic control (ATC) algorithm is used in literature to reduce the average queue length at the intersections. This algorithm has serial implementation on a single CPU and hence takes large computation time. In this paper, we propose a high performance adaptive traffic control for proving efficient responses and hence reducing average queue length that results in decrease in the overall waiting time at the intersections. We tested our proposed approach with varying number of vehicles for two real world networks. The performance of the proposed algorithm is compared with its serial counterpart.

Analytical and Scalable Analysis of Transient Tandem Markovian Finite Capacity Queueing Networks

This paper proposes an analytical model to approximate the transient aggregate joint queue-length distribution of tandem finite (space) capacity Markovian networks. The methodology combines ideas from transient aggregation-disaggregation techniques as well as transient network decomposition methods. The complexity of the proposed method is linear in the number of queues and is independent of the space capacities of the individual queues. This makes it a suitable approach for the analysis of large-scale networks. The transient joint distributions are validated versus simulation estimates. The model is then used to describe urban traffic dynamics and to address a dynamic traffic signal control problem. The signal plan analysis shows the added value of using joint distributional information, and more generally spatial-temporal between-link dependency information, to enhance urban traffic operations. The online appendix is available at https://doi.org/10.1287/trsc.2015.0629 .

A Simulation-Based Optimization Algorithm for Dynamic Large-Scale Urban Transportation Problems

This paper addresses large-scale urban transportation optimization problems with time-dependent continuous decision variables, a stochastic simulation-based objective function, and general analytical differentiable constraints. We propose a metamodel approach to address, in a computationally efficient way, these large-scale dynamic simulation-based optimization problems. We formulate an analytical dynamic network model that is used as part of the metamodel. The network model formulation combines ideas from transient queueing theory and traffic flow theory. The model is formulated as a system of equations. The model complexity is linear in the number of road links and is independent of the link space capacities. This makes it a scalable model suitable for the analysis of large-scale problems. The proposed dynamic metamodel approach is used to address a time-dependent large-scale traffic signal control problem for the city of Lausanne. Its performance is compared to that of a stationary metamodel approach. The proposed approach outperforms the stationary approach. This comparison illustrates the added value of providing the algorithm with analytical dynamic problem-specific structural information. The performance of a signal plan derived by the proposed approach is also compared to that of an existing signal plan for the city of Lausanne, and to that of a signal plan derived by a mainstream commercial signal control software. The proposed method can systematically identify signal plans with good performance. The online appendix is available at https://doi.org/10.1287/trsc.2016.0717 .

Multi-agent immune networks to control interrupted flow at signalized intersections

Urban traffic is subject to disturbances that cause long queues and extended waiting times at signalized intersections. Although Multi-Agent Systems (MAS) were considered to control traffic at signalized intersections in a distributed way, their generic conceptual framework and lack of built-in adaptation mechanisms prevent them from achieving specific disturbance management capabilities. The traffic signal control problem is still a challenging open-ended problem for which learning and adaptation mechanisms need to be developed to deal with disturbances in an intelligent way. In this article, we rely on concepts and mechanisms inspired by biological immunity to design a distributed, intelligent and adaptive traffic signal control system. We suggest a heterarchical multi-agent architecture, where each agent represents a traffic signal controller assigned to a signalized intersection. Each agent communicates and coordinates with neighboring agents, and achieves learning and adaptation to disturbances based on an artificial immune network. The suggested Immune Network Algorithm based Multi-Agent System (INAMAS) provides intelligent mechanisms that capture disturbance-related knowledge explicitly and take advantage of previous successes and failures in dealing with disturbances through an adaptation of the reinforcement principle. To demonstrate the efficiency of the suggested control architecture, we assess its performance against two control strategies from literature, namely fixed-time control and a distributed adaptation of the Longest Queue First – Maximal Weight Matching (LQF-MWM) algorithm. Agents are developed using SPADE platform and used to control a network of signalized intersections simulated with VISSIM, a state-of-the-art traffic simulation software. The results show that INAMAS is able to handle different traffic scenarios with competitive performance (in terms of vehicle queue lengths and waiting times), and that it is particularly more successful than the other controllers in dealing with extreme situations involving blocked approaches and high traffic volumes.

Recursive least-squares temporal difference learning for adaptive traffic signal control at intersection

This paper presents a new method to solve the scheduling problem of adaptive traffic signal control at intersection. The method involves recursive least-squares temporal difference (RLS-TD(λ)) learning that is integrated into approximate dynamic programming. The learning mechanism of RLS-TD(λ) is to make an adaptation of linear function approximation by updating its parameters based on environmental feedback. This study investigates the method implementation after modeling a traffic dynamic system at intersection in discrete time. In the model, different traffic control schemes regarding signal phase sequence are considered, especially the defined adaptive phase sequence (APS). By simulating traffic scenarios, RLS-TD(λ) is superior to TD(λ) for updating functional parameters in the approximation, and APS outperforms other conventional control schemes on reducing traffic delay. By comparing with other traffic signal control algorithms, the proposed algorithm yields satisfying results in terms of traffic delay and computation time.

Modelling and Analysis of Oversaturated Intersections Using Jointly Hybrid Petri net and Hybrid Automata

The Urban traffic network is a typical example of a complex system called hybrid dynamic system. It is also a multivariable and multi-scale system having the interaction of two dynamics kinds. The difficulties encountered in the study of traffic and especially in the traffic signal control problem is how to model the traffic flow, how to define its variables and how to analyze their behavior. In this paper, we propose a modeling of oversaturated intersections traffic a view to designing a traffic control approach. This concept is based on the joint use of the two well-known hybrid representation tools: hybrid Petri networks and hybrid automata. The interest of this combination is to profit from the both models advantages while avoiding their disadvantages. A formal verification property is performed to refine this model. This technique is based on the computation of the reachable state spaces. Indeed, the new model captures important aspects of the traffic flow dynamics. Its favorable structure can be used in order to provide an efficient signal-timing plan to avoid oversaturation and to ease congestion. The numerical results show that the coordination traffic signal obtained by the proposed control approach outperforms those obtained using the widely utilized signal timing optimization software SYNCHRO under various demand scenarios from unsaturated to oversaturated.

Simulation-Based Optimization: Achieving Computational Efficiency Through the Use of Multiple Simulators

Transportation agencies often resort to the use of traffic simulation models to evaluate the impacts of changes in network design or network operations. They often have multiple traffic simulation tools that cover the network area where changes are to be made. These multiple simulators may differ in their modeling assumptions (e.g., macroscopic versus microscopic), in their reliability (e.g., quality of their calibration), as well as in their modeling scale (e.g., city-scale versus regional-scale). The choice of which simulation model to rely on, let alone of how to combine their use, is intricate. A larger-scale model may, for instance, capture more accurately the local-global interactions; yet may do so at a greater computational cost. This paper proposes an optimization framework that enables multiple simulation models to be jointly and efficiently used to address continuous urban transportation optimization problems. We propose a simulation-based optimization algorithm that embeds information from both a high-accuracy low-efficiency simulator and a low-accuracy high-efficiency simulator. At every iteration, the algorithm decides which simulator to evaluate. This decision is based on an analytical approximation of the accuracy loss as a result of running the lower-accuracy model. We formulate an analytical expression that is based on a differentiable and computationally efficient to evaluate traffic assignment model. We evaluate the performance of the algorithm with a traffic signal control problem on both a small network and a city network. We show that the proposed algorithm identifies signal plans with excellent performance, and can do so at a significantly lower computational cost than when systematically running the high-accuracy simulator. The proposed methodology contributes to enable large-scale high-resolution traffic simulation models to be used efficiently for simulation-based optimization. More broadly, it enables the use of multiple simulation models that may differ, for instance, in their scale, their resolution, or their computational costs, to be used jointly for optimization.

Iterative learning approach for traffic signal control of urban road networks

In this study, the authors apply iterative learning control (ILC) theory to address the urban traffic signal control problem in a macroscopic level traffic environment. The original urban traffic signal control problem is first formulated into an output regulating and disturbance rejection problem, and the ILC approach is applied to deal with this class of control problem using the repeatability feature of traffic flow. Then, the ILC strategy is further integrated with the traffic-responsive urban control framework to cope with the random disturbances of traffic conditions in iteration cycle. Theoretical analysis shows that the proposed ILC-based traffic signal control methods can guarantee the asymptotic convergence of the link occupancies to the desired ones. The main advantage of the proposed approaches is that they require less prior modelling knowledge in the control system design. The effectiveness of the proposed methods is further verified by extensive simulations.

Traffic Signal Control based on Markov Decision Process**This work is supported in part by the National Science Foundation of China (Grant No. 61374110, 61433002, 61221003), NSFC International Cooperation Project (Grant No. 71361130012).

Abstract: This paper proposes a Morkov state transition model for an isolated intersection in urban traffic and formulates the traffic signal control problem as a Markov Decision Process(MDP). In order to reduce computational burden, a sensitivity-based policy iteration(PI) algorithm is introduced to solve the MDP. The proposed model is stage-varying according to traffic flow variation around the intersection, and the state transition matrices and cost matrices are updated so that a new optimal policy can be searched by the PI algorithm. The proposed model also can be easily extended from an isolated intersection to a traffic network based on the space-time distribution characteristics of traffic flow, so as the PI algorithm. The numerical experiments of a small traffic network show that this approach is capable of reducing the number of vehicles substantially compared with the fixed-time control particularly for high traffic demand, while being computationally efficient.

A Computationally Efficient Simulation-Based Optimization Algorithm for Large-Scale Urban Transportation Problems

This paper proposes a computationally efficient simulation-based optimization (SO) algorithm suitable to address large-scale generally constrained urban transportation problems. The algorithm is based on a novel metamodel formulation. We embed the metamodel within a derivative-free trust region algorithm and evaluate the performance of this SO approach considering tight computational budgets. We address a network-wide traffic signal control problem using a calibrated microscopic simulation model of evening peak period traffic of the full city of Lausanne, Switzerland, which consists of more than 600 links and 200 intersections. We control 99 signal phases of 17 intersections distributed throughout the entire network. This SO problem is a high-dimensional nonlinear constrained problem. It is considered large-scale and complex in the fields of derivative-free optimization, traffic signal optimization, and simulation-based optimization. We compare the performance of the proposed metamodel method to that of a traditional metamodel method and that of a widely used commercial signal control software. The proposed method systematically and efficiently identifies signal plans with improved average city-wide travel times.

Solving Large-scale Urban Transportation Problems by Combining the Use of Multiple Traffic Simulation Models

Transportation agencies often resort to the use of traffic simulation models to evaluate the impacts of changes in network design or network operations. They often have multiple traffic simulation tools that cover the network area where changes are to be made. Nonetheless, these multiple simulators may differ in their modeling assumptions (e.g., macroscopic versus microscopic), in their reliability (e.g., quality of their calibration) as well as in their modeling scale (e.g., city-scale model versus regional-scale model). The choice of which simulation model to rely on, let alone of how to combine their use, is intricate. A larger-scale model may, for instance, capture more accurately the local-global interactions; yet may do so at a greater computational cost. This paper proposes a methodology that enables the simultaneous use of multiple traffic simulation models.We propose a simulation-based optimization algorithm that embeds information from simulation models with different levels of accuracy and with different levels of computational efficiency. The algorithm combines the use of high-accuracy low-efficiency models with low-accuracy high-efficiency models. This combination leads to an algorithm that can identify points with good performance at a reduced computational cost.We evaluate the performance of the algorithm with a traffic signal control problem on a small network. We show that the proposed algorithm identifies signal plans with excellent performance, i.e., with reduced average trip travel times, while doing so with a reduction in the computational cost.

Parallel Reinforcement Learning for Traffic Signal Control

Developing Adaptive Traffic Signal Control strategies for efficient urban traffic management is a challenging problem, which is not easily solved. Reinforcement Learning (RL) has been shown to be a promising approach when applied to traffic signal control (TSC) problems. When using RL agents for TSC, difficulties may arise with respect to convergence times and performance. This is especially pronounced on complex intersections with many different phases, due to the increased size of the state action space. Parallel Learning is an emerging technique in RL literature, which allows several learning agents to pool their experiences while learning concurrently on the same problem. Here we present an extension to a leading published work on RL for TSC, which leverages the benefits of Parallel Learning to increase exploration and reduce delay times and queue lengths.

Network Traffic Signal Control with Nonconvex Alternating Direction Method of Multipliers Formulations

This paper considers the distributed solution of the online network traffic signal control problem. Toward systemwide optimality, the problem is modeled as a large-scale mixed-integer linear program with the traffic dynamics captured by the cell transmission model. The alternating direction method of multipliers (ADMM) is used to achieve spatial problem decomposition and to design an iterative approach that achieves networkwide solution under a fully distributed architecture, where computation, communication, and control are performed locally at individual intersections. Two ADMM-based algorithms were developed on the basis of appropriate problem reformulations; these algorithms resulted in the solution of convex–nonconvex subproblems with distinct properties. The performance of the algorithms was demonstrated to be close to global optimality and comparative to that of genetic algorithms. Each algorithm offers a different trade-off between communication and computation complexity.

Supervised learning from human performance at the computationally hard problem of optimal traffic signal control on a network of junctions.

Optimal switching of traffic lights on a network of junctions is a computationally intractable problem. In this research, road traffic networks containing signallized junctions are simulated. A computer game interface is used to enable a human ‘player’ to control the traffic light settings on the junctions within the simulation. A supervised learning approach, based on simple neural network classifiers can be used to capture human player's strategies in the game and thus develop a human-trained machine control (HuTMaC) system that approaches human levels of performance. Experiments conducted within the simulation compare the performance of HuTMaC to two well-established traffic-responsive control systems that are widely deployed in the developed world and also to a temporal difference learning-based control method. In all experiments, HuTMaC outperforms the other control methods in terms of average delay and variance over delay. The conclusion is that these results add weight to the suggestion that HuTMaC may be a viable alternative, or supplemental method, to approximate optimization for some practical engineering control problems where the optimal strategy is computationally intractable.

Distributed Traffic Signal Control Using the Cell Transmission Model via the Alternating Direction Method of Multipliers

Traffic signal control is a key ingredient in intelligent transportation systems to increase the capacity of existing urban transportation infrastructure. However, to achieve optimal system-wide operation, it is essential to coordinate traffic signals at various intersections. In this paper, we model the multiple-intersection traffic signal control problem using the cell transmission model as a mixed-integer linear program. The solution of the problem is facilitated by its special structure, which allows both temporal and spatial decomposition. Temporal decomposition is employed to reduce the problem size by solving subproblems of a smaller time window compared to the original problem. Temporal subproblems can be further spatially decomposed into subproblems associated with different intersections, which are jointly solved by exchanging messages between neighboring intersections. The proposed distributed solution strategy is comprised of two phases. First, the relaxed linear problem is reformulated and distributedly solved via the alternating direction method of multipliers. Second, two distributed rounding schemes are developed to solve the original problem. Simulation results indicate that the proposed solution strategy is scalable to large transportation topologies, which is suitable for online execution, and provides close-to-optimal results.

Analytical Formulation of the Trip Travel Time Distribution

This paper validates an analytical and tractable approximation of trip travel time variance for general topology networks. The main challenge in the derivation of such an approximation is to account for spatial between-link dependencies in an analytical yet also tractable manner. The approximation considered in this paper achieves tractability by extending Little's law for higher-order moments of finite capacity Markovian queueing networks. This paper presents a detailed validation of this approach. We compare the analytical approximations of path travel time variance to simulation-based estimates for two general topology queueing networks. Ongoing work, to be presented at the conference, uses this approach to address an urban traffic signal control problem that explicitly accounts travel time variability.

An Intelligent Secure Traffic Management System Based On Vanet

In this paper, vehicular ad hoc networks (VANETs) is used to collect and aggregate real-time speed and position information on individual vehicles to optimize signal control at traffic intersections.First formulate the vehicular traffic signal control problem as a job scheduling problem on processors ,with jobs corresponding to platoons of vehicles. Under the assumption that all jobs are equal size, By using an online algorithm,which referred to as the oldest job first (OJF) algorithm ,to minimize the delay across the intersection. The OJF algorithm is 2-competitive ,implying that the delay is less than or equal to twice the delay of an optimal offline schedule with perfect knowledge of the arrivals .It show that ,how a VANET is used to group vehicles into approximately equal-sized platoons ,which can then be scheduled using OJF .The two-phase approach are used ,where first approach is to group the vehicular traffic into platoons and then apply the OJF algorithm ,i.e.,the oldest arrival first (OAF) algorithm .Our simulation(NS2) results shows that ,under light and medium traffic loads ,the OAF algorithm reduce the delay experienced by vehicles as they pass through the intersection ,as compared with vehicle-actuated methods ,Webster's method ,and pre-timed signal control methods .Under heavy vehicular traffic load ,the OAF algorithm performs the same as the vehicle-actuated traffic method but still produces the lowest delay ,as when compared with Webster's method and the pre-timed signal control method.

A Simulation-Based Optimization Framework for Urban Transportation Problems

This paper proposes a simulation-based optimization (SO) method that enables the efficient use of complex stochastic urban traffic simulators to address various transportation problems. It presents a metamodel that integrates information from a simulator with an analytical queueing network model. The proposed metamodel combines a general-purpose component (a quadratic polynomial), which provides a detailed local approximation, with a physical component (the analytical queueing network model), which provides tractable analytical and global information. This combination leads to an SO framework that is computationally efficient and suitable for complex problems with very tight computational budgets. We integrate this metamodel within a derivative-free trust region algorithm. We evaluate the performance of this method considering a traffic signal control problem for the Swiss city of Lausanne, different demand scenarios, and tight computational budgets. The method leads to well-performing signal plans. It leads to reduced, as well as more reliable, average travel times.

Adaptive Traffic Signal Control With Vehicular Ad hoc Networks

In this paper, we propose to use vehicular ad hoc networks (VANETs) to collect and aggregate real-time speed and position information on individual vehicles to optimize signal control at traffic intersections. We first formulate the vehicular traffic signal control problem as a job scheduling problem on processors, with jobs corresponding to platoons of vehicles. Under the assumption that all jobs are of equal size, we give an online algorithm, referred to as the oldest job first (OJF) algorithm, to minimize the delay across the intersection. We prove that the OJF algorithm is 2-competitive, implying that the delay is less than or equal to twice the delay of an optimal offline schedule with perfect knowledge of the arrivals. We then show how a VANET can be used to group vehicles into approximately equal-sized platoons, which can then be scheduled using OJF. We call this the two-phase approach, where we first group the vehicular traffic into platoons and then apply the OJF algorithm, i.e., the oldest arrival first (OAF) algorithm. Our simulation results show that, under light and medium traffic loads, the OAF algorithm reduces the delays experienced by vehicles as they pass through the intersection, as compared with vehicle-actuated methods, Webster's method, and pretimed signal control methods. Under heavy vehicular traffic load, the OAF algorithm performs the same as the vehicle-actuated traffic method but still produces lower delays, as when compared with Webster's method and the pretimed signal control method.

Multi-Agent System in Urban Traffic Signal Control

Multi-agent system is a rapidly developing field of distributed artificial intelligence that has gained significant importance because of its ability to solve complex real-world problems. It provides a highly flexible and modular structure, which incorporates the domain expertise in the system, to achieve the optimal solution. Multi-agent system also allows a problem to be divided into smaller sub-problems that require less domain expertise compared to solving the problem as a whole. In recent years, multi-agent system has gained significant attention in solving traffic signal control problems because of the advantages it offers in solving complex problems with uncertainties. In this paper, two different types of multi-agent architectures that have been implemented on a simulated complex urban traffic network in Singapore for adaptive intelligent signal control are discussed. The results obtained indicate the superior performance of the multi-agent signal controller in comparison to pre-timed and signal control methods which are currently in use.