Traffic Signal Timing Optimization Research Articles

Integrated optimization of traffic signal timings and vehicle trajectories considering mandatory lane-changing at isolated intersections

Intersections are the predominant bottlenecks in urban areas due to the intricate conflicts among vehicles with different movements. With the advent of connected and automated vehicles (CAVs), it is more effective to reorganize urban traffic in a coordinated manner, and integrate the planning of both the traffic signal timings and vehicle trajectories. Most existing studies in this field assume that all vehicles are in their intended lanes initially, and only optimize the trajectories in the longitudinal dimension for simplicity, which is ideal and unrealistic. Therefore, this paper considers mandatory lane-changing for the integrated optimization of traffic signal timings and vehicle trajectories at isolated intersections. The entire planning horizon is segmented into a series of time-slots, based on which we select phases and plan the trajectories. First, a single-layer mixed integer programming (MIP) model is formulated to obtain global optimal solutions. Nevertheless, for large-scale cases, the MIP model is not applicable due to its computational complexities. Thus, we regulate vehicles into multi-lane platoons that correspond to green phases to reduce the solution space, and propose a beam-search-based platoon formation planning (BPFP) framework for efficient optimization. A beam search procedure is proposed to select phases for each time-slot, which incorporates a vehicle assignment algorithm to design the platoon formation as a subroutine. The two-dimensional vehicle trajectories are subsequently planned according to the platoon formation profiles. Numerical experiments illustrate that BPFP is capable of acquiring near-optimal solutions and considerably outperforms the baselines, while the computation time is within seconds even in over-saturated scenarios.

Traffic Management using Real-time Density-Based Traffic Light Control System

Abstract: In modern times, cities commonly encounter a big challenge dealing with traffic issues. It's hard to find empty roads nowadays, and waiting at red lights takes forever. The traffic lights are set based on average traffic, but this causes issues at certain spots where traffic suddenly gets heavy. That's why we need a smart system that can handle traffic jams better by looking at how much traffic there is. This system would change the traffic lights in real-time, making things smoother and reducing wait times. In simple terms, we need a clever system to fix the traffic mess in our cities. One of the solution is to manage traffic on signal, traffic signal timing (TST) optimization is one of the fastest and most economical ways to curtail congestion at the intersections and improve traffic flow in the urban network. In this paper we are going to discuss some of the existing traffic light control systems, their drawbacks as well as our proposed system where we are trying to avoid the drawbacks of existing systems. The main objective of our project is to provide a smooth flow of traffic and to reduce the time duration for which one has to stand at the traffic signal. The cameras will monitor the density of vehicles standing at the signal using image processing.This camera takes pictures, and those pictures are analyzed to figure out the density of vehicles in particular lanes. The camera can also recognize sirens and, when it does, it changes the traffic light to green so that emergency vehicles like ambulances and fire trucks can pass through.

A Study of Traffic Signal Timing Optimization Based on PSO-BFO Algorithm

A Study of Traffic Signal Timing Optimization Based on PSO-BFO Algorithm

Vehicle Speed and Position Estimation considering Microscopic Heterogeneous Car-Following Characteristics in Connected Vehicle Environments

This paper proposes a method for estimating the speed and position of unsampled vehicles using sampled data from connected automated vehicles (CAVs). The determination of vehicle speed and position on the road is a challenging and crucial task, as they can effectively reflect traffic flow characteristics and contribute to traffic state estimation and intersection signal timing optimization. Connected automated vehicles have the capability to upload their own trajectory data while also capturing trajectory data of surrounding vehicles through onboard sensors. Therefore, this paper proposes a novel approach to estimate the speed and position of unsampled vehicles. Firstly, using real vehicle trajectory data, the correlation between the velocity of following vehicles and the velocity of leading vehicles under different densities is analyzed, leading to the development of a velocity estimation model incorporating a speed correction factor. Secondly, the correlation between time headway, the rate of change of following vehicle acceleration, and traffic density is examined. To address the issue of heterogeneous behavior in vehicle following described by the Intelligent Driver Model (IDM), a real-time optimization model for estimating vehicle position by optimizing IDM parameters is proposed. The velocity estimation model and the position estimation model are summarized as two nonlinear optimization problems. Finally, the proposed method is validated using actual vehicle trajectory data. Experimental results demonstrate that when the number of connected automated vehicles (CAVs) is 2, the proposed method reduces the average absolute error by 30.73% and the standard deviation of the average absolute error by 42.8% compared to a linear model-based speed estimation method under different density conditions. Compared to a method that estimates vehicle position by calibrating desired gaps, the proposed method reduces the average absolute error by 38.2% and the standard deviation of the average absolute error by 41.7% under different density conditions. Furthermore, the proposed method exhibits good practicality under different CAV penetration rates.

Traffic Signal Timing Optimization Model Based on Video Surveillance Data and Snake Optimization Algorithm.

With the continued rapid growth of urban areas, problems such as traffic congestion and environmental pollution have become increasingly common. Alleviating these problems involves addressing signal timing optimization and control, which are critical components of urban traffic management. In this paper, a VISSIM simulation-based traffic signal timing optimization model is proposed with the aim of addressing these urban traffic congestion issues. The proposed model uses the YOLO-X model to obtain road information from video surveillance data and predicts future traffic flow using the long short-term memory (LSTM) model. The model was optimized using the snake optimization (SO) algorithm. The effectiveness of the model was verified by applying this method through an empirical example, which shows that the model can provide an improved signal timing scheme compared to the fixed timing scheme, with a decrease of 23.34% in the current period. This study provides a feasible approach for the research of signal timing optimization processes.

Multi-Objective Optimization of Traffic Signal Timing at Typical Junctions Based on Genetic Algorithms

Multi-Objective Optimization of Traffic Signal Timing at Typical Junctions Based on Genetic Algorithms

Towards Differentiable Agent-Based Simulation

Simulation-based optimization using agent-based models is typically carried out under the assumption that the gradient describing the sensitivity of the simulation output to the input cannot be evaluated directly. To still apply gradient-based optimization methods, which efficiently steer the optimization towards a local optimum, gradient estimation methods can be employed. However, many simulation runs are needed to obtain accurate estimates if the input dimension is large. Automatic differentiation (AD) is a family of techniques to compute gradients of general programs directly. Here, we explore the use of AD in the context of time-driven agent-based simulations. By substituting common discrete model elements such as conditional branching with smooth approximations, we obtain gradient information across discontinuities in the model logic. On the examples of a synthetic grid-based model, an epidemics model, and a microscopic traffic model, we study the fidelity and overhead of the differentiable simulations as well as the convergence speed and solution quality achieved by gradient-based optimization compared with gradient-free methods. In traffic signal timing optimization problems with high input dimension, the gradient-based methods exhibit substantially superior performance. A further increase in optimization progress is achieved by combining gradient-free and gradient-based methods. We demonstrate that the approach enables gradient-based training of neural network-controlled simulation entities embedded in the model logic. Finally, we show that the performance overhead of differentiable agent-based simulations can be reduced substantially by exploiting sparsity in the model logic.

Traffic signal timing optimization for isolated urban intersections considering environmental problems and non-motorized vehicles by using constrained optimization solutions

Traffic signal timing optimization for isolated urban intersections considering environmental problems and non-motorized vehicles by using constrained optimization solutions

Short-Term Traffic Flow Prediction and Signal Timing Optimization Based on Deep Learning

The rapid development of traffic industry has caused traffic congestion and environmental pollution and other problems. Traffic flow prediction and signal timing optimization under different road environments can improve the current traffic environment. In this paper, based on historical traffic data and BP neural network, according to the characteristics of different deep learning modes, SVM neural network is integrated to achieve accurate prediction of traffic flow, fully analyze the characteristics of traffic flow in different traffic environments, and accurately estimate the current traffic capacity. Meanwhile, on the basis of traffic flow prediction data and fuzzy control method, the signal timing optimization of three-phase intersections is realized to ensure the maximum capacity and the lowest average delay time of intersections. Simulation experiments show that the accuracy of the traffic flow prediction method designed in this paper is about 19.5% higher than that of the traditional mean prediction method, and fusion neural network model is more accurate than single neural network model. The optimized signal timing method can accurately control the traffic process with different phases and has obvious improvement in traffic capacity and average delay time compared with the traditional method.

POINT: Partially Observable Imitation Network for Traffic Signal Control

• This is the first study in the area of traffic signal control that combines the optimization-based signal control algorithm with imitation learning network to generate optimal signal plans in real time. • The proposed model does not need 100% penetration rate of CVs or necessity of complete traffic information in online system. Instead, only partial observable traffic information collected in real time are required for the POINT model. • The proposed model accounts for the stochastic features of traffic flows and diversities of driving behaviors in offline expert signal plan collection. • The proposed model has largely reduced the online computational burden and ready to be implemented in real world. Smart traffic signals bring together transportation infrastructure and advance technologies to improve the mobility and efficiency of urban transportation network. Adaptive traffic signal control studies can be categorized into modeling-based approaches and learning-based approaches. In order to take advantages of these two systems, this study developed an offline-online combined Partial Observable Imitation Network for Traffic signal control (POINT). In the offline system, the traffic signal timing optimization problem was formulated as a Mixed Integer Nonlinear Programming (MINLP) given complete traffic information, i.e., second-by-second speeds and locations of all vehicles. The objective of MINLP is to minimize total travel delays considering individual vehicle trajectories under Connected Vehicle (CV) environment. The calculated optimal solutions under various traffic conditions were considered as the ”expert” decisions. In the online system, an imitation neural network model was developed to learn the ”expert” signal plans generated from offline system. Given partial observable traffic conditions in real time, e.g., the aggregate-level of traffic volume, the POINT model can compute the signal timing parameters in the online system. The numerical results demonstrated that the proposed method outperformed other state-of-the-art signal control method under high and unbalanced traffic demand levels in terms of reducing travel delays and queue length.

Adaptive Optimization of Traffic Signal Timing via Deep Reinforcement Learning

With rapid development of the urbanization, how to improve the traffic lights efficiency has become an urgent issue. The traditional traffic light control is a method that calculates a series of corresponding timing parameters by optimizing the cycle length. However, fixing sequence and duration of traffic lights is inefficient for dynamic traffic flow regulation. In order to solve the above problem, this study proposes a traffic light timing optimization scheme based on deep reinforcement learning (DRL). In this scheme, the traffic lights can output an appropriate phase according to the traffic flow state of each direction at the intersection and dynamically adjust the phase length. Specifically, we first adopt Proximal Policy Optimization (PPO) to improve the convergence speed of the model. Then, we elaborate the design of state, action, and reward, with the vehicle state defined by Discrete Traffic State Encoding (DTSE) method. Finally, we conduct experiments on real traffic data via the traffic simulation platform SUMO. The results show that, compared to the traditional timing control, the proposed scheme can effectively reduce the waiting time of vehicles and queue length in various traffic flow modes.

Field-Based Prediction Models for Stop Penalty in Traffic Signal Timing Optimization

Transportation agencies optimize signals to improve safety, mobility, and the environment. One commonly used objective function to optimize signals is the Performance Index (PI), a linear combination of delays and stops that can be balanced to minimize fuel consumption (FC). The critical component of the PI is the stop penalty “K”, which expresses an FC stop equivalency estimated in seconds of pure delay. This study applies vehicular trajectory and FC data collected in the field, for a large fleet of modern vehicles, to compute the K-factor. The tested vehicles were classified into seven homogenous groups by using the k-prototype algorithm. Furthermore, multigene genetic programming (MGGP) is utilized to develop prediction models for the K-factor. The proposed K-factor models are expressed as functions of various parameters that impact its value, including vehicle type, cruising speed, road gradient, driving behavior, idling FC, and the deceleration duration. A parametric analysis is carried out to check the developed models’ quality in capturing the individual impact of the included parameters on the K-factor. The developed models showed an excellent performance in estimating the K-factor under multiple conditions. Future research shall evaluate the findings by using field-based K-values in optimizing signals to reduce FC.

Modeling the traffic signal control system at an isolated intersection using queuing systems

As the population grows in cities worldwide, the number of vehicles present on the roadways also increases, resulting in slow-moving and congested traffic. Therefore, a widespread problem in large cities concerns the traffic in the streets. Traffic signals are one of the most powerful tools available to city authorities for urban traffic control. Their proper installation can improve both traffic flow and the safety of all road users. Extensive research has been conducted to reduce the impacts of long car queues, based mainly on traffic signal timing optimization. This paper estimates the average waiting time at an isolated intersection and optimizes the timing of the green and red phases using an analysis of queueing systems. The control system is assumed to be the fixed-time type, and the Poisson process is considered for the arrivals. The proposed model is applied to real traffic data at a two-phase intersection in Bojnurd, Iran. It needs to be noted that the current situation at the intersection under study reduces average waiting time only for one side, but the analytic model can reduce average waiting time for the whole intersection. Moreover, simulation experiments are carried out, the results of which verify the capabilities of the proposed methodology in traffic signal control applications.

How to Improve Urban Intelligent Traffic? A Case Study Using Traffic Signal Timing Optimization Model Based on Swarm Intelligence Algorithm.

Traffic congestion is a major problem in today’s society, and the intersection, as an important hub of urban traffic, is one of the most common places to produce traffic congestion. To alleviate the phenomenon of congestion at urban traffic intersections and relieve the traffic pressure at intersections, this paper takes the traffic flow at intersections as the research object and adopts the swarm intelligent algorithm to establish an optimization model of intersection traffic signal timing, which takes the average delay time of vehicles, the average number of stops of vehicles and the traffic capacity as the evaluation indexes. This model adjusts the intersection traffic signal timing intelligence according to the real-time traffic flow and carries out simulation experiments with MATLAB. Compared with the traditional timing schemes, the average delay time of vehicles is reduced by 10.25%, the average number of stops of vehicles is reduced by 24.55%, and the total traffic capacity of the intersection is increased by 3.56%, which verifies that the scheme proposed in this paper is effective in relieving traffic congestion.

Traffic Signal Timing and Trajectory Optimization in a Mixed Autonomy Traffic Stream

This study introduces a methodology for cooperative signal timing and trajectory optimization at intersections with a mix of connected automated vehicles (CAVs) and human-driven vehicles (HVs). We represent joint signal timing and trajectory control as a mixed-integer non-linear program, which is computationally complex. The developed methodology provides a balance between computational efficiency and solution quality by (a) linearizing the nonlinear constraints and reformulating the problem with a tight convex hull of the mixed-integer solutions and (b) decomposing the intersection-level program into several lane-level programs. Hence, a unique controller jointly optimizes the trajectories of CAVs on a lane and the signal timing parameters associated with that lane. This setting will allow finding near-optimal solutions with small duality gaps for complex intersections with different demand levels. Case study results show that the proposed methodology finds solutions efficiently with at most 0.1% duality gap. We compared the developed methodology with an existing signal timing and trajectory control approach and found 13% to 41% reduction in average travel time and 1% to 31% reduction in fuel consumption under different scenarios.

Adaptive collaborative optimization of traffic network signal timing based on immune-fireworks algorithm and hierarchical strategy

In contemporary urban areas, the construction speed of urban roads lags far behind the growth rate of the number of vehicles. The traffic delay caused by excessive vehicles is a major challenge for modern transportation systems. In this paper, we design an adaptive coordination traffic signal control system based on a three-level framework. In the framework, we propose a hierarchical strategy, which is helpful in avoiding possible offset conflicts and configuring the offsets reasonably. In addition, we establish a multi-intersection traffic signal control model with the goal of minimizing traffic delays. To solve the proposed model, we propose a new algorithm, called the Immune-Fireworks algorithm (IM-FWA), on the basis of the artificial immune and fireworks algorithms. Inspired by the antibody maintenance mechanism, diversity mechanism and communication mechanism of the artificial immune algorithm, IM-FWA can effectively overcome the shortcomings of the fireworks algorithm, such as its limited search range and lack of interaction among fireworks. The experiments show that the proposed model and algorithm have good practicability and that our control system can obtain a better signal timing schedule to effectively reduce traffic delays.

Towards network-wide safe and efficient traffic signal timing optimization based on costly stochastic simulation

This study proposes a stochastic simulation-based network-wide signal timing optimization model with the balance consideration of traffic safety and efficiency, and solves it with a Bi-objective Stochastic Simulation-based Optimization (BOSSO) algorithm. During numerical experiments, an urban road network with 15 signalized and 5 non-signalized intersections in Changsha, China is modelled as an experimental scenario. The calibrated simulator VISSIM, Surrogate Safety Assessment Model (SSAM) and MATLAB are integrated to construct the VISSIM-SSAM-Matlab platform, based on which the network-wide signal timing optimization problems without and with coordination are solved by the BOSSO algorithm to trade-off traffic conflicts and total delay. Numerical results show that only hundreds of simulations are cost to obtain the ultimate non-dominated non-coordinated and coordinated signal timing plans, and validate a competing relationship between traffic conflicts and total delay. By the bi-objective comparison of three various signal plans from the overall and local aspects, the coordinated signal plan outperforms the non-coordinated one, which is followed by the field implemented one. It successfully demonstrates the effectiveness of the BOSSO method.

Metaheuristic Techniques in Optimizing Traffic Control Lights: A Systematic Review

Traffic congestion is a serious problem on every roadway and streets in many cities around the world. This systematic review is devoted to analyze research papers that deal with the optimization of traffic signal timing. The main objective of such optimization is maximizing the number of the vehicles leaving the network in a given period of time. This will lead to enhancing the performance of the road system. In this work, we researched the most recent metaheuristic optimized traffic light control techniques. It was shown that integrating optimization techniques in the field of traffic lights control had a great impact on the performance of traffic monitoring. During our research, we found that the most used method was the Genetic Algorithm (GA).

Travel Time Reliability-Based Signal Timing Optimization for Urban Road Traffic Network Control

Due to increasing traffic demand, many metropolitan areas are experiencing extensive traffic congestion, which demands for efficient traffic signal timing and optimization. However, conventional efficiency measure-based signal optimization cannot handle the ubiquitous uncertainty in the road networks, demanding for the incorporation of reliability measures into signal optimization, which is still in its early stage. Therefore, targeting this issue, based on the recent studies on recognizing travel time reliability (TRR) as an important reliability measure of road networks, a travel time reliability-based urban road traffic network signal timing optimization model is proposed in this paper, with the objective function to optimize a TTR measure, i.e., buffer time index. The proposed optimization model is solved using the heuristic particle swarm optimization approach. A case study is conducted using microscopic traffic simulation for a road network in the City of Nanjing, China. Results demonstrate that the proposed optimization model can improve travel time reliability of the road traffic network and the efficiency of the road traffic network as well. Future studies are recommended to expand the integration of travel time reliability into traffic signal timing optimization.

PGA: An Efficient Adaptive Traffic Signal Timing Optimization Scheme Using Actor-Critic Reinforcement Learning Algorithm

Advanced traffic signal timing method plays very important role in reducing road congestion and air pollution. Reinforcement learning is considered as superior approach to build traffic light timing scheme by many recent studies. It fulfills real adaptive control by the means of taking real-time traffic information as state, and adjusting traffic light scheme as action. However, existing works behave inefficient in complex intersections and they are lack of feasibility because most of them adopt traffic light scheme whose phase sequence is flexible. To address these issues, a novel adaptive traffic signal timing scheme is proposed. It''s based on actor-critic reinforcement learning algorithm, and advanced techniques proximal policy optimization and generalized advantage estimation are integrated. In particular, a new kind of reward function and a simplified form of state representation are carefully defined, and they facilitate to improve the learning efficiency and reduce the computational complexity, respectively. Meanwhile, a fixed phase sequence signal scheme is derived, and constraint on the variations of successive phase durations is introduced, which enhances its feasibility and robustness in field applications. The proposed scheme is verified through field-data-based experiments in both medium and high traffic density scenarios. Simulation results exhibit remarkable improvement in traffic performance as well as the learning efficiency comparing with the existing reinforcement learning-based methods such as 3DQN and DDQN.