Search

Aiming at the problem of traffic congestion in freeway on-ramp entrance under the condition of high traffic flow, this paper proposed a cooperative merging control solution of connected and automated vehicles（CAVs） at freeway on-ramp entrance, which divided the problem into two parts: multi-vehicle sequential decision making and vehicle motion planning. Multi-vehicle sequential decision making played an important role in traffic efficiency, so this paper proposed a multi-vehicle sequential decision algorithm based on the state evaluation model（SEM）, the algorithm first established the state space and initialization, considered the traffic efficiency and the vehicle delay design state evaluation function, select the optimal state through the state transition relationship, and finally got the optimal passing order by backtracking. According to the state of the vehicles and the time to reach the conflict point, the controller deduced the analytic solution of the longitudinal velocity of each vehicle in real time to realize the vehicle motion planning. Simulation and experiment results show that the solution can not only meet the real-time requirements of the traffic system, but also effectively improve the efficiency of freeway on-ramp entrance, shorten vehicle delay and reduce fuel consumption. [ABSTRACT FROM AUTHOR]

VANET plays an increasingly important role in life. It can effectively prevent traffic congestion and reduce traffic accidents. However, in VANET, there are always illegal vehicles trying to access the VANET and publishing false information. In addition, most of the existing schemes have the problem of low computational efficiency. Aiming at the above problems, this paper proposed the conditional privacy-preserving authentication scheme based on fog computing and multi-TA. Under the condition of protecting the identity of vehicle users, it realized the identity authentication among vehicle, fog node and TA, and the real identity of vehicle users could be restored in the vehicle tracking stage, thus realizing conditional privacy protection. The use of fog computing reduced the calculation and communication overhead of the scheme, and the use of multi TA model also solved the problem of single TA single point fault. The results of security and performance analysis show that the scheme is safe and efficient. Finally, it summarized the current scheme and prospected the future research. [ABSTRACT FROM AUTHOR]

Ride-sharing is an effective way to solve traffic congestion. However, passengers’ lack of trust in ride-sharing behavior is a problem that affects the development of ride-sharing. To solve this problem, by introducing trust weight and user preferences to measure by the trust level, taking the shortest total driving distance of the vehicle and the highest total trust value as the objective function, and considering the vehicle loading capacity constraints, vehicle travel distance constraints, passenger demand response constraints and vehicle station service constraints, this paper constructed a ride-sharing model considering passenger trust degree, and used an improved genetic algorithm to solve the model. Finally, this paper used the data of operating vehicles in the surrounding areas of Beijing Xinfa to verify the algorithm. The results show that the model can effectively reduce the total vehicle distance while ensuring a high level of passenger ride-sharing trust. The distance cost is 14.8% less than the model only considering distance optimization, and the trust level is 3.3 times higher. This paper verified the effectiveness of the model and the algorithm through the comparative analysis of the optimization results. [ABSTRACT FROM AUTHOR]

At present, the congestion of highways in China is severe. Traffic flow prediction plays an important role in the intelligent transportation system. If it can achieve high-precision prediction, it will be able to efficiently manage traffic and alleviate congestion. To solve this issue, this paper proposed a multi-channel traffic flow prediction method (MCST-Transformer)considering spatiotemporal correlation. Firstly, it used Transformer to extract the internal laws of different data, and then introduced a spatial correlation module to mine the association features of different data. Finally, it integrated global information through channel attention. Using the data of Guangdong province highway, the proposed method realized the traffic flow prediction of 92 toll stations within two hours with high precision. The results show that MCST-Transformer is superior to traditional machine learning methods and time series models based on the attention mechanism. Under the prediction horizon of 120 min, MAPE decreases by 5. 1 % compared with Bayesian regression. Compared with deep learning algorithms like Seq2Seq-Att and Seq2Seq, the overall MAPE of the proposed method can also be reduced by 0. 5%. It indicates that the multi-channel approach can distinguish the characteristics of different data, so as to acquire better performance. [ABSTRACT FROM AUTHOR]

Aiming at the problem that multi lane unsignalized intersections are prone to congestion at high traffic flow, this paper proposes a solution suitable for connected automated vehicle(CAV) at intersections, which decouples the problem into two problems: sequential decision-making and distributed control. Vehicle scheduling is the key point in the scheme, which has a great impact on traffic efficiency, and the complexity of the problem is exponential. this paper proposes a decision method named queue evaluation spanning tree(QEST) to solve this problem based on queue evaluation model, and establishes a cost function based on traffic efficiency and vehicle delay, so as to evaluate the queue, and continuously select the best queue, optimize the traffic sequence of vehicles at intersections and effectively improve the traffic efficiency. For the second problem, this paper proposes a distributed control framework to make vehicles pass through intersections in a predetermined order. The results show that the scheme can effectively improve the traffic efficiency and reduce vehicle delay and energy consumption at intersections with medium and high traffic flow. [ABSTRACT FROM AUTHOR]

The new intelligent transportation system plays an important role in improving traffic flow, optimizing fuel efficiency, reducing delays and improving the overall driving experience. Nowadays, traffic congestion is a very serious problem that disturbs human beings, especially the intersection with dense traffic in some cities may be more serious. Improves the reward mechanism of signal control system, the reward mechanism of all intersections to each intersection sharing a unique reward, and through the combination of intensive sampling strategy and multi-intersection signal control, using the popular deep reinforcement learning to solve the traffic signal timing problem. Simulation experiments are based on the current international mainstream traffic simulation software (SUMO). The experimental results show that the improved deep reinforcement learning multi-junction signal control method has better control effect than the traditional reinforcement learning method. [ABSTRACT FROM AUTHOR]

Focusing on the problem with traffic congestion under changing environmental conditions, this paper proposed a trajectory reward light (TR-light) model by combining reinforcement learning, neural network, multi-agent and traffic simulation technology to optimize the traffic at multi-intersections. This method had considerable merits in the following aspects. The traffic organization plan was formulated based on traffic lights; multi-agent reinforcement learning was used on traffic light control; regional traffic organization was optimized through the coordination of traffic lights; the agent implemented trajectory reconstruction after the execution of each behavior so as to change the vehicle travel path without changing the OD pair, and to calculate the final reward of the agent according to the plan and reconstructed trajectory. Finally, it conducted a traffic simulation experiment through SUMO. The comparison of traffic indicators verifies that the proposed model improves the smoothness of the road network and the traffic state at the multi-intersections. Experiments show that the model is feasible and effectively mitigates the traffic congestion. [ABSTRACT FROM AUTHOR]

To deal with the low accuracy of existing decision methods of traffic congestion under the condition of the uncertain and incomplete evidences, this paper proposed a weight-optimized neutral network. At first, this paper applied the quadraticform membership function to present the characteristics of evidences. It achieved the evidence contributions by using the information entropy, which could be considered as the weights on input layer in the neutral network. Moreover, the weights on the hidden and output layers were adaptively computed on the basis of initial weight and previous gradient sum. It reduced the accumulated error from the uncertain and incomplete evidences. Finally, the numerical example proved both accuracy and convergence of the proposed method in terms of actual traffic environment. The results indicate that the proposed method can make the stable decision on traffic congestion. [ABSTRACT FROM AUTHOR]

Because of the drawback of existing method, the paper proposed a traffic congestion detection method based on Internet of Vehicles and fuzzy logic. Firstly, this method constructed a neighbor table of vehicle based on the obtained real-time information of neighbor vehicles. Secondly, it created a fuzzy controller according to the speed, traffic density and traffic congestion rating system, and evaluated the local traffic congestion level. Thirdly, it realized the inquiry of traffic congestion status of neighbor vehicles based on real-time communication between neighbor vehicles, and verified the local traffic congestion level based on large sub-sample hypothesis test, then completed the detection of regional traffic congestion level. Finally, it built a simulated test scenario based on Veins platform, then it compared the accuracy of detecting traffic congestion, and calculated the backoff slots and received broadcast packets of vehicle nodes in the simulated test scenario. The results show that the accuracy of traffic congestion detection of the proposed method is increased by 5. 5% and 7 . 5% compared with " no trigger" method and CoTEC method, respectively. The proposed method reduces the network congestion of vehicle communication by 90. 8% compared with CoTEC method, and the communication load of communication nodes significantly decreases when there is no traffic congestion. [ABSTRACT FROM AUTHOR]

For intersection traffic congestion phenomenon, combined fog computing and reinforcement learning theory, this paper proposed a traffic light control model FRTL. The model performed intelligent coordinated control of traffic lights based on real-time traffic flow information. The fog node uploaded the collected real-time traffic flow information to the fog server, and the fog server realized information sharing on the fog platform, and the fog platform combined the processed shared data and Q learning to formulate a traffic light control algorithm. The algorithm used the detected real-time traffic data to calculate a suitable traffic light timing scheme, which was finally applied to the traffic light. The simulation results show that compared with the traditional time-phase control method and the main road control method (ATL), the FRTL control method improves the throughput of intersections, reduces the average waiting time of vehicles, and achieves the goal of properly regulating traffic lights and alleviating traffic congestion. [ABSTRACT FROM AUTHOR]

In view of the different impacts of different traffic periods on traffic congestion and single factor fail to accurately characterize the traffic congestion state, this paper proposed a multi-index fuzzy comprehensive evaluation method for traffic congestion state evaluation. The method used the particle swarm optimization algorithm to optimize the support vector regression to predict the average road speed and traffic flow, obtained the predicted values of the average speed v, traffic flow density D, and road saturation S. It input the three factor indexes to multi-index fuzzy comprehensive evaluation model to establish the set of factors and evaluation (level) for traffic congestion. It determined the weight coefficients of three factors under the morning peak, the evening peak and other periods by the entropy method, then determined the degree of membership of each index in each period by the trapezoidal membership function. Finally, it divided the traffic congestion state into six levels. The results of predictive evaluation at the traffic data of the 1405 highway in PeMS show that the traffic congestion state evaluated by the proposed method is basically consistent with the actual state, the proposed method has a high prediction accuracy, the correct rate can reach 94.79 % . [ABSTRACT FROM AUTHOR]

The existing traffic assignment theorem hardly dealt with the congested traffic state of link. To solve the above problem, based on the classic straight line inverse λ fundamental diagram, this paper presented a static traffic assignment method with given states of links. Firstly, through analyzing the fundamental diagram, it obtained the travel time function of link with two stages. Secondly, by introducing the indicating label of traffic state of link and constructing the flow conservation equations at nodes, it formulated the system optimal and user equilibrium traffic assignment models. At last, to solve the non-convex user equilibrium model, it proposed a branch and bound algorithm with relaxed partial objective function. This paper used numerical examples to demonstrate the effectiveness of the new model and algorithm. By extending the one-sided assumption of monotone increasing of link travel time function, the new theory can deal with the congested traffic state of link effectively and improve the practicality of existing theories. [ABSTRACT FROM AUTHOR]

This paper considered the congestion pricing to be the effective way to solve the traffic congestion, the main idea of road traffic congestion was to charge for some easy to cause road congestion, and appropriated compensation for other underutilized roads. It presented a subgradient heuristic traffic delay compensation strategy based on function. Firstly, it used a nonlinear programming model in the road toll/subsidies, Beckmann was the main realization based on minimizing the objective function, and used the Kuhn Hills-Lagrange multiplier model to construct the constraint condition. Secondly, the algorithm used the pricing compensation strategy to establish the road traffic model based on heuristic algorithm, and also used the marginal cost model to establish the delay function analysis model. Finally, the simulation experiments on real road networks show that the proposed algorithm has better performance in terms of travel time, traffic flow, convergence and so on, and the effectiveness of the proposed algorithm is verified. [ABSTRACT FROM AUTHOR]

In order to improve the urban traffic congestion detection and control efficiency, this paper proposed a new clustering analysis method based on multi-processor and space potential field modification for traffic congestion analysis. Firstly, based on the city road congestion spatial-temporal model with GIS four-dimensional spatial temporal data, this paper constructed field correction method for multi-processor parallel clustering method by using parallel Euclidean distance matrix computation, parallel neighborhood radius computing and parallel density index calculation. Secondly, it gave the complexity theorems of the parallel computation procedure, so as to theoretically analysis the computational complexity of the; algorithm. Finally, taking Beijing city as a test area, it verified the performance of the algorithm in analyzing the traffic congestion. Experimental results show that the method can achieve effective detection for rapid analysis of urban traffic congestion, which can provide data support for traffic congestion management. [ABSTRACT FROM AUTHOR]

With the rapid development of highway,the emergence of increased congestion,monitoring difficulty and other issues are increasingly seriously. Firstly based on the urban traffic performance congestion index of Beijing,this paper proposed a method to evaluate the status of highways through utilizing traffic performance index. Then based on the big data platform of Storm,this paper implemented data process,data analysis and key algorithms of index background calculation. Finally it published the real-time traffic performance index in the form of mobile phone APPs and official accounts of Wechat. The experimental results show that highway traffic performance index not only can reflect the overall status of highways,but also can reflect the real-time congestion situation of specific highways or specific highways range,and can real-time monitor the congestion situation of highway road network,which provides a reference for people and plays a positive role to ease road congestion. [ABSTRACT FROM AUTHOR]

In order to predict the traffic congestion in city, this paper proposed the prediction model based on the deep learning. The traffic data like flow parameters, environmental situation, times of day and so on were summarized and composed into the feature vector, and defined four kinds of traffic flow pattern. It learned the unlabelled traffic dataset by the auto-encoder network to build the hidden layer function and generate the new feature dataset, and used the softmax regression to classify the traffic pattern based on the labeled feature dataset learning. Demonstrated by the simulation, the prediction model has better performance than the model without the feature learning, the average prediction accuracy can reach 85%. [ABSTRACT FROM AUTHOR]

In order to alleviate traffic congestion and detect the effect of speed limit scheme on transportation system, this paper investigated the traffic assignment problem in a general multi-mode network under a fixed speed limits scheme. It constructed an optimizing model and compared the distinctions between flow patterns in the network as well as the travel cost. It provided the solution algorithm and utilized the numerical example to demonstrate the feasibility of the model and algorithm. It shows that in a general multi-mode traffic network, the different traffic modes have different share ratio due to various values of diffusion coefficient. Analysis result proves that speed limit scheme has the effect to convert travel demand from private cars to public transit. This result is worth for the researches of optimizing schemes to mitigate congestion. [ABSTRACT FROM AUTHOR]

To tackle the network congestion issue caused by redundant traffic by users' repeated access to the same network resources, this paper proposed a weighted bipartite network (WBN) model which evolved with time. Through the analysis of users' network behavior and redundant traffic' formation and evolution mechanism, WBN model adopted ways of preferential connection and topology growth to complete network evolution. Simulation experiment results show that strength of user nodes has experienced from the exponential distribution to power-law distribution and then random distribution. It effectively simulates the evolution of real network redundant traffic. Simulation results are also consistent with theoretical analysis and show that WBN model is accurate and practical. [ABSTRACT FROM AUTHOR]

Road traffic congestion pressure becomes more serious as the number of vehicles increases. Accurate traffic situation detection methods are needed to help in alleviating them. This paper proposed a TraSD-VANET method to detect the traffic situation. In this method, vehicles constituted clusters autonomously and then sent their speed and locations to cluster heads. After receiving data from cluster members, the cluster head calculated the lane weighted average speed and the traffic density adaptively. Afterwards, it estimated the traffic situation in its cluster according to the above calculation results by using fuzzy theory. The simulation results show that the average precision of estimation is improved 16% compared with the CoTEC in four traffic scenarios. This method has important practical value in traffic congestion detection on road. [ABSTRACT FROM AUTHOR]

Extracting high-efficient routing strategy is important to improve network throughput and reduce traffic congestion. From the viewpoint of gravitational-field theory, this paper studied the aggregation effect of node on traffic flow during transmission, defined the gravitational-field model with considering the unblocked reliability of node itself and its neighbors and the travel path length.and proposed a gravitational-field routing strategy based on node aggregation ability. In order to testify the efficiency of the routing strategy, the experiments for different routing algorithm were simulated for comparison. The results show that compared with the shortest-palh routing algorithm, this proposed method not only greatly improves the network throughput, but also is stable and reliable. [ABSTRACT FROM AUTHOR]

To resolve the problems of network congestion leading to high end-to-end delay and low throughput in MANET (mobile Ad hoc network), this paper proposed an algorithm of load-balancing based on probability. In this algorithm, nodes mapped the load state of network historical load information and judge route access by probability to balance the load in the networks. Mapping the load state of network by historical load information was an effective solution to the problem of difficult to judge load state in distributed operation. Probabilistic algorithms could effectively overcome the problem of fuzzy recognition in the rule of threshold, while a significant reduction the flooding of broadcast and saving channel resources. Combined with classical reactive routing protocol, it developed a new routing protocol called H&P_DSR. The computer simulation confirms the theoretical analysis and shows the load balancing algorithm could balance network load accurately and efficiently, H&P_DSR protocol improves network throughput and reduces the end-to-end delay effectively without extra route overhead. [ABSTRACT FROM AUTHOR]

In order to get insight into the dynamics of transportation network congestion and develop an effective decision making tool for transportation network congestion government, this paper presented a complex network based simulation model for transportation network congestion evaluation. Through introducing the concept of road impedance in complex network theory, complex network model and traffic simulation model were combined successfully to form a complete transportation network congestion simulation model. In addition, this paper also presented a transportation network capacity assessment method based on virtual test vehicle traversing. This approach could efficiently and comprehensively evaluate the network capacity under different conditions. Finally, it implemented a complete transportation network congestion assessment simulation system on PC system based on the above model and conducted simulation experiments to analyze the influence on the transportation network traffic capacity imposed by the number of congested road sections, traffic flow and road network topology. The results of simulation experiments match the classical transportation theory well and it disclosed more dynamic information of transportation network congestion evolution, which means this model can work well for transportation congestion government decision-making. [ABSTRACT FROM AUTHOR]

For the two traffic management strategies of information providing and congestion pricing, this paper studied a union pricing strategy. Firstly, it constructed the decision space of the government and the traffic information supplier, calculated the information market penetration. Then, based on the assumption of elastic demand, it presented an equilibrium model which included two travelers (with/without information), and got the travelers' decision space. It also presented a union pricing model based on the game theory at the same time. Last, it used a testing network to analyze the model. The results show that the level of social benefits influence the information and the congestion pricing more significantly. It also find some results of the model which are in accordance with the practical experience. All of these show the reasonable of the model. [ABSTRACT FROM AUTHOR]

As an active queue management algorithm, BLUE lacks incipient congestion detecting mechanism, and has some insufficiencies in parameter setting. This paper proposed a novel BLUE algorithm based on dynamic threshold. By managing the buffer, through the predicted congestion in advance, it determined the packet drop probability by packet loss event, link idle event and the buffer usage. NS simulation results show that the proposed algorithm can mitigate the queue overflow and underflow, stabilize the queue occupation and improve link utilization effectively. [ABSTRACT FROM AUTHOR]