Search

One of the focal points in the field of intelligent transportation is the intelligent control of traffic signals (TS), aimed at enhancing the efficiency of urban road networks through specific algorithms. Deep Reinforcement Learning (DRL) algorithms have become mainstream, yet they suffer from inefficient training sample selection, leading to slow convergence. Additionally, enhancing model robustness is crucial for adapting to diverse traffic conditions. Hence, this paper proposes an enhanced method for traffic signal control (TSC) based on DRL. This approach utilizes dueling network and double q-learning to alleviate the overestimation issue of DRL. Additionally, it introduces a priority sampling mechanism to enhance the utilization efficiency of samples in memory. Moreover, noise parameters are integrated into the neural network model during training to bolster its robustness. By representing high-dimensional real-time traffic information as matrices, and employing a phase-cycled action space to guide the decision-making of intelligent agents. Additionally, utilizing a reward function that closely mirrors real-world scenarios to guide model training. Experimental results demonstrate faster convergence and optimal performance in metrics such as queue length and waiting time. Testing experiments further validate the method's robustness across different traffic flow scenarios. [ABSTRACT FROM AUTHOR]

Traffic lights are crucial for urban traffic management, as they significantly impact congestion reduction and travel safety. Traditional methods relying on hand-crafted rules and operator experience are limited in their ability to adapt to changing traffic environments. To address this challenge, we have been exploring intelligent traffic light control using deep reinforcement learning techniques. However, current approaches often suffer from inadequate training data and unstable training processes, leading to suboptimal performance and real-world consequences. In this study, we propose RELight, a novel random ensemble reinforcement learning-based traffic light control framework. RELight effectively utilizes collected empirical data, ensuring a stable and efficient training process. To evaluate the performance of our proposed framework, we conducted a comprehensive set of experiments on a variety of datasets, including four synthetic datasets and a real traffic dataset collected from surveillance cameras at an intersection in Hangzhou, China. The results show that RELight outperforms existing approaches, demonstrating its superiority and potential for practical traffic light control applications. [ABSTRACT FROM AUTHOR]

Cooperation between intersections in large-scale road networks is critical in traffic congestion. Currently, most traffic signals cooperate via pre-defined timing phases, which is extremely inefficient in real-time traffic scenarios. Most existing studies on multi-agent reinforcement learning (MARL) traffic signal control have focused on designing efficient communication methods, but have ignored the importance of how agents interact in cooperative communication. To achieve more efficient cooperation among traffic signals and alleviate urban traffic congestion, this study constructs a Graph Cooperation Q-learning Network Traffic Signal Control (GCQN-TSC) model, which is a graph cooperation network with an embedded self-attention mechanism that enables agents to adjust their attention in real time according to the dynamic traffic flow information, perceive the traffic environment quickly and effectively in a larger range, and help agents achieve more effective collaboration. Moreover, the Deep Graph Q-learning (DGQ) algorithm is proposed in this model to optimize the traffic signal control strategy according to the spatio-temporal characteristics of different traffic scenes and provide the optimal signal phase for each intersection. This study also integrates the ecological traffic concept into MARL traffic signal control, which aims to reduce traffic exhaust emissions. Finally, the proposed GCQN-TSC is experimentally validated both in a synthetic traffic grid and a real-world traffic network using the SUMO simulator. The experimental results show that GCQN-TSC outperforms other traffic signal control methods in almost all performance metrics, including average queue length and waiting time, as it can aggregate information acquired from collaborative agents and make network-level signal optimization decisions. [ABSTRACT FROM AUTHOR]

Traffic volume data at fixed detectors are of great importance to track the time-varying states of urban traffic, and the volume of each turning movement (i.e., continuing straight, turning left, turning right) in an intersection plays a significant role in traffic control. It is a difficult issue to determine the complete road network volume due to the limited coverage of detector deployment. Existing traffic volume imputation methods seem to be hardly tractable to address this persistent missing data problem of fixed detectors because they mainly function by utilizing spatiotemporal patterns of historical data to address the problem of intermittent missing traffic data collected from probe vehicles. Considering the unattainable temporal information of the target movement, this paper aims to develop an end-to-end graph neural network-based imputation approach to impute traffic volume data with persistent missing patterns. We regard the road network as a directed graph with each turning movement as a node and employ a meta-learning-based graph attention mechanism with graph embedding in multiple spatial granularities to fully extract the relationship between the target node and its neighbours. In addition, a multitask learning mechanism is designed to improve the accuracy of the imputation results by setting auxiliary tasks according to the volume conservation constraints. The proposed approach has been validated with extensive simulation experiments and applied to field tests for Shenzhen and Shanghai, China, with considerable accuracy and reliability, satisfying the demand for traffic control. To the best of our knowledge, this is the first time that traffic volume has been imputed for persistent missing patterns with a graph neural network-based method. [ABSTRACT FROM AUTHOR]

Software-defined networking (SDN), a novel network paradigm, separates the control plane and data plane into different network equipment to realize the flexible control of network traffic. Its excellent programmability and global view present many new opportunities. DDoS detection under the SDN context is an important and challenging research field. Some previous works attempted to collect and analyze statistics related to flows, usually recorded in switches, to address DDoS threats. In contrast, other works applied machine learning-based solutions to identify DDoS and achieved promising results. Generally, most previous works need to periodically request flow rules or packets to obtain flow statistics or features to detect stealthy exceptions. Nevertheless, the request for flow rules is very time-consuming and CPU-consuming; moreover may congest the communication channel between the controller and the switches. Therefore, we present FORT, a lightweight DDoS detection scheme, which spreads the rule-based detection algorithm at edge switches and determines whether to start it by periodically retrieving the ports state. A time-series algorithm, ARIMA, is utilized to determine the port statistics adaptively, and an SVM algorithm is applied to detect whether a DDoS attack does occur. Representative experiments demonstrate that FORT can significantly reduce the controller load and provide a reliable detection accuracy. Referring to the false alarm rate of 1.24% in the comparison scheme, the false alarm rate of this scheme is only 0.039%, which significantly reduces the probability of false alarm. Besides, by introducing the alarm mechanism, this scheme can reduce the load of the southbound channel by more than 60% in the normal state. [ABSTRACT FROM AUTHOR]

Traffic flow forecasting is of great significance to urban traffic control and public safety applications. The key challenge of traffic flow forecasting is how to capture the complex correlation of different time levels and learn time dependence. Some external information is closely related to traffic flow, such as accidental traffic accidents, weather, and Point of Interests (PoI) information. This paper proposes a deep learning-based model, called AttDeepSTN+, which is used to predict the inflow and outflow of each area of the entire city. Specifically, AttDeepSTN+ uses the structure of interactive attention and convolution to model the temporal closeness, trend, and periodicity of crowd flow, in the interactive attention layer, learn the importance of closeness to periodicity and trend respectively to model the long-term dependence of time, and then use feature fusion to capture complex correlations at different levels, thereby reducing model prediction accuracy. In addition, PoI information are combined with time factors to express the influence of location attributes on crowd flow, to learn prior knowledge of crowd flow. Finally, a new fusion mechanism is used to fuse the attention layer modules and PoI information and other information together into the module to capture the complex correlation between different levels of features, to predict the final crowd flow in each area, and further improve the prediction accuracy of the model. The New York City crowd flow experiment shows that the model is better than the current state-of-the-art baseline. [ABSTRACT FROM AUTHOR]

Though effective in theoretical simulation, the established traffic control models and optimization algorithms will result in model mismatch or even control strategy failure in actual application. However, they are commonly adopted in traffic signal control research, resulting in the unavailability of many exceptional control algorithms in practice. Simulation should function as a bridge between theoretical research and actual application, allowing the gap between the two to be communicated and made up for. However, an effective connection between the two has yet to be established to enable simulation methods in existing traffic control research. To this end, we designed and developed a simulation platform for "Online Application—HILS (Hardware-in-the-Loop Simulation)—Practice" integration over traffic signal control. In this paper, the architecture and characteristics of the integrated simulation platform were described. Besides, the function of each module of the platform was detailed, followed by listing simulation examples for six complex scenarios, with the active control scenario being selected for simulation comparison analysis. The findings demonstrated extensive road network simulation with the integrated simulation platform, multidimensional control variables, control strategies with support, as well as stable and reliable operation. It can be used to verify several sorts of traffic control simulation with variable dimensions. [ABSTRACT FROM AUTHOR]

Traffic flow forecasting or prediction plays an important role in the traffic control and management of a city. Existing works mostly train a model using the traffic flow data of a city and then test the trained model using the data of the same city. It may not be truly intelligent as there are many cities around us and there should be some shared knowledge among different cities. The data of a city and its knowledge can be used to help improve the traffic flow forecasting of other cities. To address this motivation, we study building a universal deep learning model for multi-city traffic flow forecasting. In this paper, we exploit spatial-temporal correlations among different cities with multi-task learning to approach the traffic flow forecasting tasks of multiple cities. As a result, we propose a M ulti-city T raffic flow forecasting N etwork (MTN) via multi-task learning to extract the spatial dependency and temporal regularity among multiple cities later used to improve the performance of each individual city traffic flow forecasting collaboratively. In brief, the proposed model is a quartet of methods: (1) It integrates three temporal intervals and formulates a multi-interval component for each city to extract temporal features of each city; (2) A spatial-temporal attention layer with 3D Convolutional kernels is plugged into the neural networks to learn spatial-temporal relationship; (3) As traffic peak distributions of different cities are often similar, it proposes to use a peak zoom network to learn the peak effect of multiple cities and enhance the prediction performance on important time steps in different cities; (4) It uses a fusion layer to merge the outputs from distinct temporal intervals for the final forecasting results. Experimental results using real-world datasets from DIDI show the superior performance of the proposed model. [ABSTRACT FROM AUTHOR]

The spread of traffic jams in urban networks has long been viewed as a complex spatio-temporal phenomenon that often requires computationally intensive microscopic models for analysis purposes. In this study, we present a framework to describe the dynamics of congestion propagation and dissipation of traffic in cities using a simple contagion process, inspired by those used to model infectious disease spread in a population. We introduce two macroscopic characteristics for network traffic dynamics, namely congestion propagation rate β and congestion dissipation rate μ. We describe the dynamics of congestion spread using these new parameters embedded within a system of ordinary differential equations, similar to the well-known susceptible-infected-recovered (SIR) model. The proposed contagion-based dynamics are verified through an empirical multi-city analysis, and can be used to monitor, predict and control the fraction of congested links in the network over time. Predicting and controlling traffic congestion propagation is an ongoing challenge in most urban settings. Here, Seberi et al. apply a contagion model describing epidemic spread in population to model traffic jams, and verify its validity using large-scale data from six different cities around the world. [ABSTRACT FROM AUTHOR]

Intersection control has an important role in the management of urban traffic to ensure safety, high traffic flow and to prevent congestion. Recently, a growing body of literature has been reported on the theme of non-signalised intersection control in which traffic lights are replaced with intelligent road side units. Data from several studies suggest that non-signalised control could reduce vehicle delays and fuel consumption significantly whilst ensuring safety. However, there is little published data on the impact of the mixed driving behaviour with human-driven vehicles and autonomous vehicles. This paper investigates the emerging role of connectivity and vehicle autonomy in the context of traffic control under the mixed driving behaviour scenario. The concepts of vehicle-to-infrastructure (V2I) communications and multi-agent systems are central to achieving a robust and reliable traffic-light-free intersection control. Comprehensive computer simulation results on a four-way intersection indicate over 96% reduced average vehicle delay and 37% less fuel consumption with the non-signalised control solution compared to the traffic light control. The outcome of this study offers some important insights into enabling cooperation between vehicles and traffic infrastructure via V2I communications, in order to make more efficient real-time decisions about traffic conditions, whilst ensuring a higher degree of safety. [ABSTRACT FROM AUTHOR]

In this study, dynamic traffic control strategies, namely dynamic ramp metering and dynamic speed limit control, have been examined through microscopic traffic simulation based on site measurements. In this context, the traffic flow data at a particular highway intersection have been analyzed to determine the pattern of the traffic. Then, the traffic model has been built in a traffic micro-simulation software and calibrated with the field data. The foci of the study are to measure the efficiency of the dynamic traffic control strategies and to compare it with the uncontrolled case considering various performance indicators such as total travel time, average delay time per vehicle, and average number of stops per vehicle. For the dynamic ramp metering strategies, the ALINEA (Asservissement Lineaire d'Entree Autoroutiere - French for Linear Utilization for Highway Entrances) control algorithm is implemented with different fixed-time cycle lengths. It has been observed that various ramp metering implementations decreased the average delay time per vehicle up to 30%. The dynamic speed limit control strategies are set according to the occupancy rates that are measured at the bottleneck downstream. The examined speed limit control strategies decreased the average delay time per vehicle to around 7%. The results also revealed that the implemented dynamic traffic control strategies help alleviate congestion by increasing the capacity of the bottleneck section. [ABSTRACT FROM AUTHOR]

The restriction (prohibition) of certain turns at intersections is a very common task employed by the managers of urban traffic networks. Surprisingly, this approach has received little attention in the research literature. The turning restriction design problem (TRDP) involves finding a set of turning restrictions at intersections to promote flow in a congested urban traffic network. This article uses a successive linear approximation (SLA) method for identifying approximate solutions to a nonlinear model of the TRDP. It aims to adjust the current turning restriction regime in a given network in order to minimize total user travel cost when route choice is driven by user equilibrium principles. Novel features of the method include the facts that it is based on link capacity-based arc travel costs and there is a budget constraint on the total cost of all turning restriction alterations. It has been tested using standard network examples from the literature. One of the tests utilized a multi-start approach which improved the solutions produced by the SLA method. The method was also employed to identify turning restrictions for an actual medium-sized urban traffic network in Brazil. Computational experience with the proposed method is promising. [ABSTRACT FROM AUTHOR]

We consider basic notions of the theory of S-hypernetworks. We show that in terms of that theory, one can describe many systems of network structure adequately enough to find solutions for the problems at hand. In fact, an analytic setting for the analysis and synthesis problems for the structures of the said systems is virtually an imitational model that can be used for problems related to optimization and control of city traffic systems. [ABSTRACT FROM AUTHOR]