Large-scale Traffic Congestion Research Articles

Representation of Traffic Congestion Data for Urban Road Traffic Networks Based on Pooling Operations

In order to improve the efficiency of transportation networks, it is critical to forecast traffic congestion. Large-scale traffic congestion data have become available and accessible, yet they need to be properly represented in order to avoid overfitting, reduce the requirements of computational resources, and be utilized effectively by various methodologies and models. Inspired by pooling operations in deep learning, we propose a representation framework for traffic congestion data in urban road traffic networks. This framework consists of grid-based partition of urban road traffic networks and a pooling operation to reduce multiple values into an aggregated one. We also propose using a pooling operation to calculate the maximum value in each grid (MAV). Raw snapshots of traffic congestion maps are transformed and represented as a series of matrices which are used as inputs to a spatiotemporal congestion prediction network (STCN) to evaluate the effectiveness of representation when predicting traffic congestion. STCN combines convolutional neural networks (CNNs) and long short-term memory neural network (LSTMs) for their spatiotemporal capability. CNNs can extract spatial features and dependencies of traffic congestion between roads, and LSTMs can learn their temporal evolution patterns and correlations. An empirical experiment on an urban road traffic network shows that when incorporated into our proposed representation framework, MAV outperforms other pooling operations in the effectiveness of the representation of traffic congestion data for traffic congestion prediction, and that the framework is cost-efficient in terms of computational resources.

A future intelligent traffic system with mixed autonomous vehicles and human-driven vehicles

Autonomous vehicles (AVs) being an essential component of the future smart city traffic system is a hot topic in recent years, even though it is still in its development stage. It is conceivable that in the near future, AVs and human-driven vehicles (HVs) will have to co-exist in traffic systems. This is the first paper to study a mixed traffic system from a micro perspective based on the cellular automation model. In this system, by the use of sensors or mutual information exchange, each AV will have a ‘foresight’ and will be able to know the speeds and positions of vehicles in front of it. In the circular road scenario, we studied how the traffic capacity is influenced by the degree of foresight, the ratio of AVs to HVs, vehicle density, and the probability of random deceleration of HVs. Then we came up with the below conclusions: (a) The optimal foresight is k=5. An AV only needs to gather the information of the 5 vehicles in front of it. (b) The two critical factors to measure the capacity of a traffic network are the critical vehicle density and the maximum average flow. When the ratio of AVs to HVs is increased, these two critical factors increase at an accelerating rate. (c) Even if a low ratio of HVs is running in the system, it will have an appreciable negative impact. An increased probability of random deceleration can expand the hysteresis loop range and reduce average flow. (d) Within a specific range of vehicle density, there is an optimal ratio of AVs at which the traffic system has the maximum average flow. This has implications in controlling the ratio of AVs. Finally, theoretical solutions of critical vehicle density are obtained by using the mean-field theory in physics. If the vehicle density is larger than these critical values, the traffic system will be in a deadlock state, and all vehicles cannot move. These formulas are crucial to controlling the density and the ratio of AVs and HVs in future intelligent traffic systems and will help to avoid large-scale traffic congestion. The above findings will have practical ramifications for precise traffic management and traffic control in a mixed AV and HVs system.

Large-Scale Traffic Congestion Prediction Based on the Symmetric Extreme Learning Machine Cluster Fast Learning Method

The prediction of urban traffic congestion has emerged as one of the most pivotal research topics of intelligent transportation systems (ITSs). Currently, different neural networks have been put forward in the field of traffic congestion prediction and have been put to extensive use. Traditional neural network training takes a long time in addition to easily falling into the local optimal and overfitting. Accordingly, this inhibits the large-scale application of traffic prediction. On the basis of the theory of the extreme learning machine (ELM), the current paper puts forward a symmetric-ELM-cluster (S-ELM-Cluster) fast learning methodology. In this suggested methodology, the complex learning issue of large-scale data is transformed into different issues on small- and medium-scale data sets. Additionally, this methodology makes use of the extreme learning machine algorithm for the purpose of training the subprediction model on each different section of road, followed by establishing a congestion prediction model cluster for all the roads in the city. Together, this methodology fully exploits the benefits associated with the ELM algorithm in terms of accuracy over smaller subsets, high training speed, fewer parameters, and easy parallel acceleration for the realization of high-accuracy and high-efficiency large-scale traffic congestion data learning.

Deep Autoencoder Neural Networks for Short-Term Traffic Congestion Prediction of Transportation Networks.

Traffic congestion prediction is critical for implementing intelligent transportation systems for improving the efficiency and capacity of transportation networks. However, despite its importance, traffic congestion prediction is severely less investigated compared to traffic flow prediction, which is partially due to the severe lack of large-scale high-quality traffic congestion data and advanced algorithms. This paper proposes an accessible and general workflow to acquire large-scale traffic congestion data and to create traffic congestion datasets based on image analysis. With this workflow we create a dataset named Seattle Area Traffic Congestion Status (SATCS) based on traffic congestion map snapshots from a publicly available online traffic service provider Washington State Department of Transportation. We then propose a deep autoencoder-based neural network model with symmetrical layers for the encoder and the decoder to learn temporal correlations of a transportation network and predicting traffic congestion. Our experimental results on the SATCS dataset show that the proposed DCPN model can efficiently and effectively learn temporal relationships of congestion levels of the transportation network for traffic congestion forecasting. Our method outperforms two other state-of-the-art neural network models in prediction performance, generalization capability, and computation efficiency.

Traffic Congestion Forecasting Based on Possibility Theory

Traffic congestion state identification is one of the most important tasks of ITS. Traffic flow is a nonlinear complicated system. Traffic congestion state is affected by many factors, such as road channelization, weather condition, drivers’ different driving behavior and so on. It is difficult to collect all necessary traffic information. Traffic congestion auto identification result based on incomplete traffic information exists uncertain. Little work has been done to analyze the uncertainty. Possibility theory introduced by Zadeh is an efficient means to present incomplete knowledge. Possibility distribution determination is an important task of possibility theory. In this paper, possibility theory is used to describe the uncertainty of traffic state. The possibility distribution of traffic state is determined according to the probability distribution of traffic flow parameters, such as volume, speed and occupancy and so on. The multi-variable distribution of traffic flow parameters is determined with large-scale traffic flow data. Large-scale traffic congestion samples are generated with parallel k-mean clustering method. Traffic congestion forecasting is based on the forecasting of traffic flow parameters with SVM (Support Vector Machines). At last, a practical example is analyzed with the proposed method.

Formation and Propagation of Local Traffic Jam

Large scale traffic congestion often stems from local traffic jam in single road or intersection. In this paper, macroscopic method was used to explore the formation and propagation of local traffic jam. It is found that (1) the propagation of traffic jam can be seen as the propagation of traffic signal parameters, that is, virtual split and virtual green time; (2) for a road with endogenous flow, entrance location influences the jam propagation. With the same demand (upstream links flow and entrance flow), the upstream got more influence; (3) when a one-lane road is thoroughly congested, virtual signal parameters everywhere are the same as that at stop line; for a basic road, the virtual signals work in a cooperative manner; (4) phase sequence is one important parameter that influences traffic performances during peak hour where spill back of channelization takes place. The same phase plan for left-turn flow and through flow would be preferred; (5) signal coordination plays an important role in traffic jam propagation and hence effective network signal parameters should be designed to prevent jam from propagation to the whole network. These findings would serve as a basis for future network traffic congestion control.