Signal Timing Optimization Research Articles

Optimization of Signal Timing for the Contraflow Left-Turn Lane at Signalized Intersections Based on Delay Analysis

The exit-lanes for a left-turn (EFL) is an unconventional method of organizing traffic for left-turns at signalized intersections. In this paper, we propose a nonlinear optimization model to minimize delay by establishing a delay-time diagram for the left-turn traffic when the left-turn traffic is non-oversaturated, considering the relationship between the pre-signal start node of the exit-lanes for a left-turn and the queuing dissipation time of left-turn vehicles. Model validation is performed with example calculations to compare and analyze each operating index and fleet type after signal timing optimization of intersection lane borrowing left-turn lanes. The results show that compared with the conventional left-turn lane, the average delay of vehicles operating with the model decreased by 15.7%, exhaust emission decreased by 11.4%, and capacity increased by 65.7%. The model can support EFL pre-signal design, where signal control is related to queue dissipation time. In practice, a well-designed pre-signal control scheme based on traffic volume can improve capacity and reduce emissions while minimizing average vehicle delays.

Combined Dynamic Route Guidance and Signal Timing Optimization for Urban Traffic Congestion Caused by Accidents

When traffic congestion caused by accidents occurs on urban roads, the current signal control scheme may face failure. It is necessary to establish an effective dynamic route guidance scheme and formulate a reasonable signal timing scheme to alleviate the impact of the accident on urban traffic. In this paper, traffic congestion is divided into three states and the traffic evacuation strategies are formulated, respectively. Then, on the basis of analyzing the internal mechanism and spatiotemporal variation of queuing at intersections, a two-stage model is proposed to optimize the signal timing parameters. In the first stage, the basic timing parameters of each intersection, such as signal cycle and green ratio, are obtained. In the second stage, the offset optimization model is constructed to minimize the total delay time of the coordinated phase of all detour routes in the control scope, considering the early dissipation of queuing vehicles at the entrance of the intersection. This model is solved with a particle swarm optimization algorithm and simulated to the actual road network with VISSIM. As the experimental results show, this control method can greatly reduce the average vehicle delay, stop times, queue length, and the number of vehicles passing.

Based on MOPSO Algorithm of Real-Time Traffic Signal Optimization Control for Intelligent Transportation Intersections

In order to improve the traffic efficiency of intersections, this paper establishes a multi-objective optimization model with the minimum real-time delay time and maximum capacity as the optimization objectives by applying multi-objective particle swarm optimization algorithm, and simulates the actual intersections. By optimizing the multi-objective model, a set of Pareto optimal solution sets can be obtained, and the optimal timing scheme can be determined by using multi-attribute decision-making algorithm and real-time update of signal timing configuration parameters to achieve dynamic optimization of signal timing. The simulation model of city road intersection is established by SUMO software. By using multi-objective particle swarm optimization algorithm to optimize the intersection simulation model, the traffic capacity of the simulated intersection has been greatly improved, with the average traffic capacity increasing by about 3.69% and the average vehicle delay time decreasing by about 21.35%.

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

Optimal Traffic Signal Control of Isolated Oversaturated Intersections Using Predicted Demand

This paper tackles the optimal traffic signal control of isolated oversaturated intersections. An analytical signal control algorithm is proposed to find the global optimal signal timings with dynamic cycle lengths and phase splits to minimize the vehicle delay throughout the oversaturation period at a generic multi-phase junction. The traffic dynamics are modelled based on the kinematic wave theory and the predicted traffic flows. Moreover, spillback avoidance is incorporated during the queue formation oversaturated regime by adopting a mixed delay and probability of spillback objective function. Microsimulation experiments demonstrate the optimality, practicality, and robustness to system uncertainties of the proposed signal control method. The results pinpoint over 63%, 55%, and 40% reduction in total vehicle delay by implementing the proposed signal control respectively compared to an optimal fixed-time, actuated, and capacity-aware max pressure signal control methods.

Integrated Robust Optimization of Scheduling and Signal Timing for Bus Rapid Transit

The unbalanced nature of passenger demand and the uncertainty of delay at intersections are considered critical factors in the efficiency of public transportation operations. Considering the controllable characteristics of the bus rapid transit system (BRT), an integrated optimization model that includes multi-mode transit scheduling and signal timing is proposed. The robust optimization model copes with the fluctuations in passenger demand and bus operation. A non-linear programming is developed to minimize the total passenger travel time and optimize the transit departure time, dwelling strategies at stations, and signal timings at intersections. The constraints on the signal control, degree of saturation, transit scheduling, and passenger waiting time at stations are intended to reflect real traffic conditions. A case study and extensive sensitivity analyses were conducted to evaluate the performance of the proposed model. The results show that the proposed integrated model can adjust the BRT dwelling strategies based on different passenger demands and coordinate transit departure time and signal timing adjustment to mitigate the passenger delay. Furthermore, experimental results demonstrate improvements of 5.3% and 8.1% in the mean and maximum values of passenger travel time, respectively, using the proposed model, compared to those obtained using the conventional operation strategy.

Investigating impacts of various operational conditions on fuel consumption and stop penalty at signalized intersections

When optimizing signals relevant traffic agencies adopt policies to either improve mobility performance measures (e.g., delay and stops), environmental aspects, or safety of signalized intersections. One of such policies, mainly implemented through so-called Performance Index (PI), advocates that reduction of excess fuel consumption (FC) should be achieved by minimizing the PI - a linear combination of delays and stops. The key factor of such a PI is the stop penalty “K”, which represents a weighting factor, or a stop equivalency measured in seconds of delay. In the contemporary signal optimization practice, this K is given a constant value (e.g., 10 seconds) and it is not recognized as a parameter that is dependent on various operational conditions. This study challenges that common view and presents a methodology to derive the K factor and investigate impacts of various operational conditions (e.g., cruising speed) on the K value. The study uses traffic simulation model coupled with a modal fuel consumption and emission model to investigate second-by-second FC during stopping events at a signalized intersection. The experiments are performed on a hypothetical, yet realistic, intersection under several operational scenarios. The findings show that the K varies significantly with all the investigated operational conditions. More importantly, results indicate that the K factor should be much larger than used by current signal timing practices. The implications of these findings may lead to significant changes in current polices for signal timing optimization. Future research shall validate these findings with second-by-second vehicle trajectory and FC data from the field.

Intersection control strategy optimization based on exchangeable lanes modeling

Purpose Due to the conflicts between left turn traffic and opposite straight-going traffic in urban traffic network, some of the traffic lanes cannot be used to discharge vehicles during its green phases and the intersection capacity can be greatly reduced. This study/paper aims to reduce the effect of conflicts and increase its capacity through the reasonable pre-signal phase time with the exchangeable lanes. Design/methodology/approach This paper took into consideration various influence factors to intersection capacity and formulated the capacity optimization model based on 0-1 mixed-integer programming model. This model is efficiently solved by standard branch-and-bound algorithms. Findings The authors took an intersection as an example and solved the optimal signal timing and entrance lane capacity via this model. Then, simulations were carried out to verify the effect of the exchangeable lanes strategy of this intersection through the simulation software VISSIM and take the traffic volume and delay as outputs, which indicated that this model has better performance. Originality/value The front-end control strategy can not only exploit the full potential of the intersection but also significantly improve the operational efficiency of the intersection. It plays a positive role in improving urban intersection congestion.

Priority-Based Traffic Signal Coordination System With Multi-Modal Priority and Vehicle Actuation in a Connected Vehicle Environment

This paper presents a priority-based coordination system that provides preferential treatment to vehicles traveling along a coordinated route. A mixed-integer linear program model is enhanced to consider coordination as a form of priority along with the multi-modal priority for eligible emergency, transit, and freight connected vehicles and provides dilemma zone protection to freight vehicles in a connected vehicle environment. The optimization model generates an optimal signal timing schedule that minimizes the total weighted delay of the coordination requests, priority requests, and dilemma zone requests, and maximizes the flexible implementation of the optimal signal timing schedule. The optimal signal timing schedule allows real-time vehicle actuation using traditional vehicle detection. The simulation experiments and statistical analysis show that priority-based coordination can achieve performance equivalent to a traditional coordination system. The priority-based coordination method is integrated into the priority control Multi-modal Intelligent Traffic Signal System and is implemented in the Maricopa County SMARTDrive ProgramSM test bed in Anthem, Arizona, and in Portland, Oregon.

Dynamic user optimal route choice problem on a signalized transportation network

In this paper, we present a new route-based discrete time variational inequality (VI) ideal dynamic user optimal route choice (DUO) model on a transportation network with fixed signal timing at signalized intersections and a relaxation with gradient projection algorithm to solve the model. The new trait of our study is the queue length in red time and the throughput in green time for each cycle at each intersection can be found when traffic is in DUO status. This is different from other studies, in which either only average queue length or average delay in a period composing of multiple cycles can be found or traffic is not in DUO status. Furthermore, the optimal signal timings can be found by the algorithm. Under optimal signal timing, the total queuing delay of the network reaches minimum when traffic is in DUO status.

Traffic Signal Optimization to Improve Sustainability: A Literature Review

Optimizing traffic signals to improve traffic progression relies on minimizing mobility performance measures (e.g., delays and stops). However, delay and stop minimizations do not necessarily lead to minimal sustainability measures (e.g., fuel consumption and emissions). For that reason, researchers have focused, for decades, on integrating traffic models, signal optimization models, and fuel consumption and emissions models to minimize sustainability metrics while keeping acceptable levels of mobility metrics. Therefore, this paper reviews, classifies, and analyzes studies found in the literature regarding optimizing sustainable traffic signals. This paper provides researchers with a good starting point to further develop solutions which can address sustainable traffic control. To achieve that, this study details the most notable sustainable signal timing optimization studies from six perspectives: traffic models, fuel consumption and emissions models, optimization methods, objective functions, operating conditions, and reported sustainability savings. Outcomes of this research show that the previous studies deployed many combinations of elements from the six-perspective mentioned above, leading to a wide range of fuel consumption and emissions savings. The study also concludes that the available fuel consumption and emissions models are relatively old. Hence, future research is needed to develop new fuel consumption and emissions models based on recently collected data.

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.

Extracting interrelated information from road-related social media data

The social media data (SMD) have been viewed as a potential and promising information source of road conditions. However, most existing SMD-based sensing approaches (SMDSAs) either ignore interrelations among information items (e.g., name, direction, and status of the road) or rely on rigid grammar rules to establish entities’ interrelations. Additionally, current SMDSAs in the transportation domain are unable to link the extracted text-formatted information with domain-specific models (e.g., virtual road model, VRM). In order to fill such gaps, this work proposes an improved SMDSA of road conditions, which involves a three-stage (i.e., SMD classification, relation inference, and entity pair recognition) interrelated information extraction model, as well as a semantic converter to feed the SMD-provided text-formatted information into VRMs. The proposed SMDSA is demonstrated by the newly annotated datasets of tweets in Lexington, USA. The three-stage interrelated information extraction model outperforms conventional rule-based methods and deep-learning algorithms (e.g., Text CNN, Bi-LSTM, Piecewise CNN, and Capsule Net). The SMD-enabled VRM also preliminarily shows its capacity to optimize signal timings during incidents that change the road network topology. This work contributes to circumventing the reliance on human-made rules during SMDSAs’ development, bridging user-generated SMD with operable VRMs for potential real-world road management, and providing a standard tweet dataset annotated with interrelation triplets to help promote SMDSA studies.

An analysis of the value of optimal routing and signal timing control strategy with connected autonomous vehicles

With the emergence of connected and automated technologies, Connected Autonomous Vehicles (CAVs) are able to communicate and interact with other vehicles and signal controllers. Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I) communications open up an opportunity to improve routing and signal timing efficiency with additional information from CAVs, such as prior travel time and signal green time. Most of the existing research on routing and signal timing for Human Driven Vehicles (HDVs) has to face the fact that human drivers only have partial knowledge about travel costs and traffic status on the road network, which typically reduces the system efficiency. In this paper, the impacts of additional information from CAVs on routing and signal timing efficiency in terms of total travel time have been investigated. An Optimal Routing and Signal Timing (ORST) control strategy for CAVs has been proposed and compared with four existing routing and signal timing strategies where drivers have different levels of information. The results of the simulation demonstrate that with additional information from CAVs, ORST can reduce about 49% of the total travel time compared with Stochastic User Equilibrium (SUE) and about 10% of the total travel time compared with User Equilibrium (UE).

Integrating traffic signal optimization with vehicle microscopic control to reduce energy consumption in a connected and automated vehicles environment

Transportation systems face a variety of problems, especially in the aspects of traffic efficiency and energy consumption. The emerging of connected and automated vehicles (CAVs) technologies offers promising solutions to tackle these challenges. Integrating traffic signal control with vehicle trajectory optimization has significant potential to improve transportation sustainability and traffic efficiency. This paper presents an integrated traffic control framework for traffic signal optimization and vehicle microscopic control of CAVs at an isolated signalized intersection to reduce fuel consumption and improve transportation sustainability. Firstly, considering the higher controllability of CAVs, the Minimizing Overall Braking Induced by Lane Changes Model and the Intelligent Driver Model are redesigned to control the microscopic longitudinal behavior and lateral behavior of vehicles. Secondly, an optimal control model is established to optimize the trajectories of vehicles considering fuel consumption and driving comfort. The analytical, closed-form solutions are derived through Pontryagin's Maximum Principle. Thirdly, to alleviate vehicle delay, the Controlled Optimization of Phase model is applied to determine the optimal intersection signal timing plan, including signal cycle length and duration of green and red phases. Finally, a receding horizon framework is built to integrate these control strategies and conduct the optimization. Experimental results suggest that the proposed integrated traffic control framework can improve both traffic efficiency and energy efficiency. The reduced traffic delay, energy consumption, and pollutant emission can be as much as 33.51–44.25%, 18.44–22.14%, and 13.36–55.20%, respectively depending on the demand scenario.

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

A Deep Reinforcement Learning Approach to Traffic Signal Control With Temporal Traffic Pattern Mining

Traffic signal control is a critical method that ensures the efficiency of traffic flow in cities across the world. There are massive studies that focus on generating optimal signal timing plans. Most of the these studies are model-based, where the signal plan is determined by optimization models with fixed parameters. Reinforcement learning (RL) is a model-free method that learns the optimal control policy over time which avoids limitations of traditional methods. In the past a few years, deep RL methods become particularly attractive since deep neural networks can provide scalable learning capability given the complex traffic condition in real life. In this manuscript, we develop a deep actor-critic method that can provide efficient traffic signal plans. First, a novel deep neural network model is applied to mine the recent traffic condition information as a sequence of temporally sequential image representations of the intersection, which improves from relying solely on limited traffic information such as queue length; then the deep neural network model is integrated with an actor-critic model which avoids drawbacks from the value-based or the policy-based methods. Simulation experiments illustrate that the deep actor-critic method outperforms the classic model-based method and several existing deep reinforcement learning methods according to different measures such as queue length, average delay time, and throughput.

A new queue shock wave theory based on platoon dispersion modeling

Statistical platoon dispersion models are developed mainly for traffic flow macro-simulation. While the queueing theory outputs the same delay results as those applied in shock wave theory, the dynamic process of queue forming and dissipating can be simulated only by the latter. Traditional shock wave theory treats traffic flow as a compressible fluid; hence, shock waves form whenever the state of speed–density changes. Similarly, shock waves form because of signal lights when simulating traffic flow with platoon dispersion models. This paper theoretically analyzes the queueing process based on a newly proposed platoon dispersion model, with the assumption that speed follows truncated normal distribution. Besides solving the queueing equations approximately with mathematical methods, an analytical table method is proposed to find the boundary solutions. Application methods are also presented for both static and dynamic scenarios. This theory can be applied to optimize signal timing for queue management, particularly for congestion control.

Traffic Signal Timing Optimisation for Several Intersections in High-Priority Congested Networks Improved on Genetic Algorithm

Nowadays, getting around has become an essential aspect of everyday life, whether it be public transport or personal vehicles, the vast network formed by these means of transport is immensely complex to manage. Unfortunately, this activity presents serious problems in most cities around the world. In this paper we upgrade traffic capacity of intersections using Genetic algorithm in order to decrease traffic congestion and crossing time of a road network. The main focus of this study is on improving the quality of solutions for the traffic light optimization problem. This proposition calculated and simulated through programming. As it shows, It improve results for solving the cycle traffic light problem (CTLP).

CVLight: Decentralized learning for adaptive traffic signal control with connected vehicles

This paper develops a decentralized reinforcement learning (RL) scheme for multi-intersection adaptive traffic signal control (TSC), called “CVLight”, that leverages data collected from connected vehicles (CVs). The state and reward design facilitates coordination among agents and considers travel delays collected by CVs. A novel algorithm, Asymmetric Advantage Actor-critic (Asym-A2C), is proposed where both CV and non-CV information is used to train the critic network, while only CV information is used to execute optimal signal timing. Comprehensive experiments show the superiority of CVLight over state-of-the-art algorithms under a 2-by-2 synthetic road network with various traffic demand patterns and penetration rates. The learned policy is then visualized to further demonstrate the advantage of Asym-A2C. A pre-train technique is applied to improve the scalability of CVLight, which significantly shortens the training time and shows the advantage in performance under a 5-by-5 road network. A case study is performed on a 2-by-2 road network located in State College, Pennsylvania, USA, to further demonstrate the effectiveness of the proposed algorithm under real-world scenarios. Compared to other baseline models, the trained CVLight agent can efficiently control multiple intersections solely based on CV data and achieve the best performance, especially under low CV penetration rates.