31 results about "Traffic flow control" patented technology

The invention relates to the technical field of traffic transportation, in particular to a CAV and HV vehicle mixed traffic flow control method and system and a storage medium, and the CAV and HV vehicle mixed traffic flow control method comprises the steps: S2, building a traffic flow control model which introduces a front vehicle speed effect and also introduces a gathering lane changing strategy; s2, obtaining related parameters of the traffic flow control model; s3, inputting the related parameters obtained in the step S2 into the traffic flow control model established in the step S1, and outputting a simulation result describing a traffic control result; compared with the prior art, the method has the advantages that according to road conditions, CAV queuing conditions of front and back vehicles can be acquired, and the gathering condition of homogeneous vehicles is further considered during lane changing decision making, so that more CACC car-following modes appear on a road, the road traffic flow efficiency is further improved, meanwhile, due to the high interconnection of the CAVs, the road safety is further improved, and the road traffic flow efficiency is improved. And the mutual interference between the CAV vehicle and the HAV vehicle is reduced.

The invention relates to the technical field of traffic flow control, and provides a multi-mode traffic flow control method and system, and the method comprises the steps: obtaining a traffic capacity parameter of a core traffic node based on the preset core traffic node; obtaining an instantaneous personnel entry rate of the core traffic node; calculating a personnel net accumulation rate according to the instantaneous personnel entry rate and the traffic capacity parameters; performing grading and shunting judgment based on the personnel net accumulation rate to obtain a grading judgment result; when the grading judgment result shows that the personnel net accumulation rate reaches a first preset threshold value, generating an information guide shunting instruction to guide the people stream to actively select an alternative traffic mode; and when the grading judgment result shows that the personnel net accumulation rate reaches a second preset threshold value, generating a physical isolation shunting instruction so as to drive a physical isolation device to change a people flow path. The method has the advantages that the cross-mode congestion transmission chain is accurately identified and cut off, and local congestion is prevented from spreading towards systematic paralysis.

The application discloses a large railway hub overhead off-ramp dynamic traffic flow control method, realizes dynamic self-adaptive adjustment of vehicle stay time threshold according to real-time traffic state (queue length, lane occupancy rate and driving-in flow) of the ramp, automatically compresses the allowed stay time to accelerate vehicle turnover in peak congestion period, and appropriately relaxes in low peak idle period to improve humanized experience; a multi-dimensional dynamic correction factor system is constructed, time period characteristics (peak / flat / low), environmental factors (adverse weather such as rain, snow and fog, holidays / large events), historical overtime statistical rules and the like are brought into a dynamic control calculation model, and the adaptability and robustness of the control strategy are improved; a self-learning mechanism based on historical overtime rate feedback is introduced, so that the algorithm can automatically adjust the laxity according to actual operation data, stabilize the overtime rate in a preset target range, and realize continuous optimization iteration of the control strategy.

A real-time air traffic flow prediction method based on aviation situational awareness includes: constructing a traffic flow dataset that integrates spatiotemporal features; achieving efficient conversion from trajectory data to air traffic flow data based on time slice partitioning; extracting multi-source spatiotemporal features; constructing a prediction model using LightGBM, the core of which lies in: using the Tweedie loss function to model the zero-inflation and long-tail distribution characteristics of traffic flow data, and ensuring model robustness through five-fold cross-validation; establishing a multi-dimensional evaluation system; and in the application phase, dividing the airspace into a dynamic grid and combining radar-returned trajectory data to predict flight traffic flow within the airspace for the next few minutes in real time. This invention supports dynamic feature extraction and traffic flow prediction based on real-time radar data. Practical testing has verified that it effectively supports air traffic flow control decisions, enabling rapid response when airspace traffic changes, meeting the timeliness requirements of dynamic air traffic control, and significantly improving the scientific nature and response speed of air traffic control decisions.

The application discloses a kind of urban high-density road network mixed traffic flow cell transmission simulation prediction methods, comprising: with urban high-density road network area as modeling object, with road boundary end as traffic flow input position and output position, the road section between input position and output position includes urban expressway basic road section, access ramp and interchange, and urban non-expressway basic road section and intersection, the road section between input position and output position is divided into cell, and mixed mixed traffic flow cell transmission model is established to the cell, and the state of urban road network is simulated and predicted.The application comprehensively considers the traffic flow of urban expressway and urban non-expressway, effectively connects the cell of urban expressway with the cell of urban non-expressway, and designs and improves the cell division and modeling method of interweaving area and intersection, which is beneficial to the comprehensive study of traffic flow change in urban road network area and the traffic flow state simulation prediction for traffic flow control.

This invention discloses a smart city traffic optimization method and system based on 5G networks, belonging to the field of smart city traffic management technology. It addresses the issues of information consistency and conflict resolution in urban traffic flow control and shared parking space guidance. The method includes uploading traffic flow and signal phase status, combining parking space occupancy status and vehicle owner location information for path guidance and parking space recommendation, and identifying and managing parking space status conflicts across multiple heterogeneous platforms. It constructs parking space status behavior sequences, heterogeneous contention indices, state disturbance propagation graphs, and conflict score clusters, performing state masking and path correction for high-conflict parking spaces. Simultaneously, it collects vehicle owner and vehicle behavior data to complete parking space usage records and settlements, identify and process illegal parking, and constructs a shared parking space reservation permission management mechanism. This method is applicable to optimization and guidance under dynamic urban traffic control and multi-platform access to parking space resources.

This invention discloses a method and system for resilient traffic flow control on highways under complex construction scenarios, relating to the field of traffic control. The method includes: zoning and calibrating the construction area and traffic sensing points to determine the road network construction topology; sampling and predicting real-time traffic flow data based on the traffic sensing network, and determining traffic congestion waves through wave eigenvector transformation; constructing resilient control units based on the road network construction topology and deploying them at the road network edge; intervening in the traffic congestion waves using wave interference offsetting and detour diversion, and then iteratively allocating the solutions to each zone using a trust region framework to determine the resilient control scheme; and performing dynamic control and management of traffic flow resilience. This application solves the technical problem of existing dynamic traffic flow control methods, which struggle to quantify and identify congestion evolution patterns in real time and implement precise and efficient interventions, achieving the technical effect of real-time quantification and identification of congestion evolution patterns and precise and efficient interventions for traffic flow.

The invention provides a method for deciding whether an emergency lane is opened on a highway under a large-flow road condition, which relates to the technical field of traffic management and comprises the following steps of: acquiring multi-interval vehicle driving data of a target road section, calculating a feature correlation degree by using tensor decomposition, extracting a frequency domain feature and a fluctuation period in combination with empirical mode decomposition and Fourier transform, and determining whether the emergency lane is opened on the highway; judging whether an emergency lane is opened or not; if yes, a traffic flow regulation and control system based on fluid dynamics is established, the optimal opening time sequence is calculated and dynamically corrected, and the traffic capacity of the expressway is improved, and traffic jam is relieved.

The invention provides a service flow control method and device, equipment, a medium and a product. The method is applied to a policy control unit, a policy control request sent by a policy execution unit is received, and the policy control request comprises a user identifier and network state information. And generating a dynamic strategy rule satisfying the network state information and the service configuration information based on the strategy control request and the service configuration information and the user behavior information in the unified data model. And sending the dynamic policy rule to a policy execution unit through a communication interface, so that the policy execution unit controls the service flow according to the dynamic policy rule. According to the method, the policy decision and the charging rule are based on the same data source, service interruption or charging errors caused by cross-system synchronization delay can be avoided, meanwhile, generation of personalized policies is supported by combining user behaviors, network states and charging states, and the resource utilization rate and the user experience are improved.

The application discloses a kind of intelligent traffic light coordination control method and system of traffic flow optimization, it is related to intelligent control technical field.The method includes: real-time acquisition of the traffic flow data of each direction lane in target area by the heterogeneous sensor network deployed at each intersection;Traffic flow data is identified to obtain tidal flow characteristics;Dynamic intensity evaluation is carried out based on tidal flow characteristics, and tidal direction intensity index is obtained;A multi-agent collaborative network is constructed, and a continuous intersection green phase offset sequence is generated based on multi-agent collaborative network collaborative calculation;When tidal direction intensity index is greater than the preset threshold, the continuous intersection green phase offset sequence is input into the traffic signal control system to start the tidal green wave mode.The technical problems that traffic flow control is not flexible enough in the prior art, and traffic signal lights cannot be intelligently adjusted according to traffic conditions are solved, achieving the technical effects of improving road traffic efficiency and reducing congestion.

The invention discloses a smart highway active traffic flow control method and system, and relates to the field of traffic flow control. A roadside environment sensing unit, a vehicle-mounted state data acquisition terminal, an air auxiliary sensing system and an embedded road environment state monitoring device are deployed; and a driving behavior sensing function module is deployed in a smart phone terminal authorized by a driver to collect data to form multi-source real-time traffic state data. Then, by constructing a multi-agent reinforcement learning system based on a three-dimensional digital twin model environment, dynamic acquisition, fusion prediction and control strategy optimization of multi-source real-time traffic state data are realized, the operation efficiency and safety of the expressway are improved, and by combining a multi-target optimization model and a driver behavior compliance index, the driving safety of the expressway is improved. A differential control strategy is formed to generate an excitation and constraint linkage mechanism, and fine regulation and control of traffic congestion, high-risk driving behaviors and energy consumption emission are enhanced.

This central unit (CU) may comprise at least one processor. The at least one processor is configured to: transmit, to a radio link control (RLC) entity, a first message for requesting radio quality assistance information, according to a determination that an amount of downlink traffic stored in a buffer of a packet data convergence protocol (PDCP) entity of the CU exceeds a threshold value; determine, on the basis of receiving a second message including the radio quality assistance information from the RLC entity, whether congestion occurs in a downlink on the basis of the radio quality assistance information; and, according to a determination that the congestion occurs in the downlink, set an explicit congestion notification echo (ECE) flag in a transmission control protocol (TCP) header of uplink traffic, and then transmit the uplink traffic to a server.

This invention discloses a scalable multi-strategy collaborative optimization method for highway traffic flow control, comprising: S1. Defining corresponding reinforcement learning action spaces based on different types of traffic flow control strategies; S2. Defining corresponding reinforcement learning state spaces based on traffic flow observation states; S3. Defining reward functions for reinforcement learning based on different target coefficients; S4. Constructing a simulation training environment; S5. Constructing reinforcement learning agent strategies based on action spaces, state spaces, reward functions, and the simulation training environment; S6. Optimizing the constructed reinforcement learning agent strategies in the simulation training environment to obtain the optimal reinforcement learning agent strategy; S7. Obtaining the actual environmental state and calculating the optimal traffic flow control strategy for the actual environmental state based on the optimal reinforcement learning agent strategy.

The invention discloses a bridge load intelligent management method and system based on artificial intelligence and a medium, and belongs to the technical field of crossing of bridge engineering and artificial intelligence. The method comprises the following steps: S1, acquiring vehicle information, bridge information and environment information by using various monitoring devices to obtain first bridge data; s2, performing data preprocessing on the first bridge data to obtain second bridge data; s3, constructing a prediction model; identifying potential risks in advance to obtain an analysis result; s4, automatically adjusting a traffic flow control strategy of the bridge according to an analysis result; s5, continuously monitoring the change condition of the bridge state, and updating the prediction model and the traffic flow control strategy according to the change condition; and S6, recording the result of adjusting the traffic flow control strategy each time and feedback information, and continuously iterating the prediction model according to the feedback information. A sensor network and an artificial intelligence technology are utilized, real-time monitoring, prediction and optimization adjustment of the bridge load are achieved, and it is ensured that the bridge structure is in a safe state all the time.

The invention relates to an urban bus priority active management and control method and system based on vehicle and road cloud integration. The method comprises the following steps: acquiring road network data in a research area; dividing a core area boundary and a core area of the research area; dividing a peripheral traffic control sub-area and a peripheral critical line; constructing a three-dimensional macroscopic fundamental diagram model, and determining a traffic flow control threshold value of social vehicles adjacent to the intersection; predicting the traffic flow of social vehicles and public traffic vehicles at the upstream intersection; and comparing the social vehicle flow predicted value with a traffic flow control threshold value, and formulating a management and control strategy including an optimal vehicle route according to a comparison result, the public transport vehicle flow predicted value and the road network data. According to the invention, social vehicles can be actively guided to enter a core area with an optimal route, regional management is realized with less data processing amount, traffic congestion of a large area is avoided, the problems of urban road congestion and space-time resource waste are solved, and the efficiency of urban bus operation is improved.

The invention discloses a traffic flow cooperative control method for a lane reduction area under an expressway emergency, and the method comprises the steps: obtaining the traffic flow state information of the lane reduction area of an expressway and an upstream road section in real time, and constructing a mixed traffic flow fundamental diagram model to determine and control the starting density and the stopping density; if the traffic flow density of the lane in the lane reduction area is larger than the control starting density, a congested lane is marked, and a lane changing control area and a variable speed limiting control area are determined; guiding a lane changing vehicle in the lane changing control area to change a lane and controlling a CAV in the lane changing control area to slow down and give way; designing a variable speed-limiting objective function considering efficiency and safety indexes, predicting traffic flow state information by using a cellular transmission model, inputting the traffic flow state information into the variable speed-limiting objective function, and carrying out optimization solution to obtain a speed-limiting value of each lane in a variable speed-limiting control region; and if the traffic flow density of the congested lanes in the lane reduction area is smaller than the stop density, ending the traffic flow control of the control area. According to the invention, the congestion condition of the lane reduction area is relieved, and the vehicle operation efficiency is improved.

The application relates to the technical field of traffic transportation, in particular to a CAV and HV vehicle mixed traffic flow control method and system and a storage medium, the CAV and HV vehicle mixed traffic flow control method comprising the following steps: S2, a traffic flow control model is established, which introduces both the preceding vehicle speed effect and the lane-changing strategy; S2, related parameters of the traffic flow control model are acquired; and S3, the related parameters acquired in the step S2 are input into the traffic flow control model established in the step S1, and simulation results describing the traffic control results are output; according to the road conditions, the CAV vehicle queuing conditions of front and rear vehicles can be acquired, the homogenous vehicle aggregation condition is further considered during the lane-changing decision, more CACC following modes appear on the road, the road traffic flow efficiency is further improved, the road safety is further improved due to the high interconnection of the CAV vehicles, and the mutual interference between the CAV vehicles and the HV vehicles is reduced.

This invention discloses a hybrid traffic flow simulation method based on an improved multi-type traffic flow cellular transmission model. The method achieves hybrid traffic flow simulation by making the following four improvements to the multi-type traffic flow cellular transmission model: 1) Changing the vehicle equivalent conversion from being based on fixed vehicle length to dynamically calculating the equivalent function of a small car based on vehicle speed differences; 2) Changing the determination method of the maximum capacity of the link and the downstream shock wave coefficient from exogenous calibration to dynamic lookup of a segmented index table based on historical monitoring data; 3) Removing the relative occupancy rate from the downstream cell reception calculation to avoid redundant calculations; 4) Introducing a state adaptive correction term in the calculation of the actual transmission flow between upstream and downstream cells to achieve accurate flow allocation. The advantages are that it can accurately describe the dynamic evolution characteristics of real hybrid traffic flow, provide an accurate assessment basis for the road capacity of hybrid traffic flow, and improve the scientificity and effectiveness of traffic flow control for hybrid traffic flow on highways.

The application discloses a mixed traffic flow control method, device and equipment and a storage medium. The method comprises the following steps: determining a first relationship in a preset offline control period according to the traffic flow of each road section in a target road network, the passing time of each road section and the non-admission traffic flow matched by each start-stop point combination; determining the target value of the traffic flow of each road section when the first relationship satisfies a first constraint condition; wherein the first constraint condition comprises a flow distribution constraint, a first road capacity constraint, a signal lamp time constraint, a signal lamp phase difference constraint, a road section passing time constraint and a first relationship value constraint; and determining the green light on duration of each road section signal lamp according to the target value of the traffic flow of each road section, so as to realize the mixed traffic flow control in the target road network. The technical scheme solves the problem that the over-saturation phenomenon of the mixed traffic flow is difficult to effectively eliminate, and can greatly reduce the passing cost while improving the signal control coordination of the road network.

The invention discloses a mixed traffic flow control method based on a cross attention mechanism and MPC, and the method comprises the steps: collecting traffic flow data, processing multi-source heterogeneous information fusion through employing a Kalman filtering algorithm, and obtaining the real-time dynamic state information of a vehicle; constructing a Transformer model based on a cross attention mechanism, and generating a predicted trajectory of a target vehicle by using historical trajectory sequence interaction characteristics of the intelligent network connection vehicle and the target human-driven vehicle; in combination with a model predictive control framework, establishing a vehicle discrete kinetic equation and defining a trajectory tracking cost function, and solving an optimal control instruction; a federal learning mechanism is introduced to train parameters of the Transform model; and deploying the integrated model to a vehicle-mounted control system to realize real-time cooperative control of the intelligent network connection vehicle on the mixed traffic flow. According to the method, the cross-model coupling problem of a prediction-control link is solved, and the control safety and the passing efficiency under high dynamic scenes such as ramp convergence and congestion following can be effectively improved.

The invention discloses a traffic flow processing system based on the Internet of Things, and belongs to the technical field of the Internet of Things. The traffic flow processing system comprises a plurality of terminal nodes, a plurality of edge nodes and a cloud node which are in communication connection, the terminal nodes are used for acquiring a plurality of pieces of vehicle state data and driving behavior data and uploading the data to the corresponding edge nodes; the edge node is used for carrying out space-time alignment and feature fusion on the vehicle state data, the driving behavior data and the collected traffic perception data to obtain vehicle fusion data, uploading the vehicle fusion data to the cloud node, carrying out regional flow prediction and generating a regional diversion strategy; and the cloud node is used for performing global traffic flow prediction based on the vehicle fusion data and the auxiliary traffic data uploaded by the plurality of edge nodes, and generating a global diversion strategy. The traffic flow processing system can execute traffic flow management and control with different frequencies and different intensities for different regional granularities, and the flexibility and effectiveness of traffic flow management and control are improved.

The application discloses a kind of traffic AI scheduling decision-making methods based on multi-source geographic big data, it is related to intelligent transportation technology field, including, collection multi-source traffic data and pre-processing, generate after processing traffic dataset;Using trained long short-term memory network, the multi-scale time series analysis is carried out to after processing traffic dataset, generates traffic flow prediction result;Using particle swarm optimization algorithm, traffic flow prediction result is adjusted, generates candidate traffic scheduling scheme;Candidate traffic scheduling scheme is dynamically optimized, generates after optimization traffic flow control scheme;Optimization after traffic flow control scheme is compared and analyzed with newly collected multi-source traffic data, generates adjusted traffic flow control scheme, and based on real-time traffic flow feedback, adjusted traffic flow control scheme is dynamically adjusted, forms continuous feedback cycle.The application improves the traffic capacity of road and resource use efficiency.

This invention relates to the field of tunnel traffic lighting engineering and intelligent adaptive control technology, specifically to a wireless network-based intelligent timing control system for tunnel lighting and its control method. The system includes: a data acquisition hardware group that collects real-time velocity vectors of moving objects and ambient brightness values ​​of the tunnel environment; a central control processor configured to perform the following operations: constructing a virtual fluid medium model; calculating the virtual shear viscosity parameters of the virtual fluid medium based on human visual adaptation characteristics and ambient brightness values ​​of the tunnel environment; substituting the real-time velocity vector as a disturbance source into the fluid dynamics control equations to generate a spatiotemporally continuous virtual light pressure control data field; and parsing the virtual light pressure control data field into discrete pulse width modulation commands according to spatial coordinates, sending them to the drive power supply via a wireless ad hoc network to control the brightness of the corresponding lighting units. This invention effectively reduces the risk of rear-end collisions and achieves deep integration of the lighting system and traffic flow control.

This invention provides a decision-making method for whether to open emergency lanes on highways under high traffic conditions, relating to the field of traffic management technology. The method includes acquiring vehicle driving data from multiple sections of a target road segment, calculating feature correlation using tensor decomposition, extracting frequency domain features and fluctuation periods using empirical mode decomposition and Fourier transform, and determining whether to open the emergency lane. If opened, a traffic flow control system based on fluid dynamics is established to calculate the optimal opening timing and dynamically correct it, thereby improving highway capacity and alleviating traffic congestion.

Packet traffic flow control includes receiving a packet, by a first virtual machine network security appliance (VMNSA), and determining whether the packet is to be processed by a first path or a second path; in response to determining that the packet is to be processed by the first path, processing the packet by a first traffic flow controller (TFC) of the VMNSA, forwarding the packet by the first TFC to a first transmitter, and sending the packet by the first transmitter; and in response to determining that the packet is to be processed by the second path, processing the packet by the first TFC, forwarding the packet by the first TFC to a second TFC of the VMNSA, processing the packet by the second TFC, forwarding the packet by the second TFC to a second transmitter, and sending the packet by the second transmitter.

The invention belongs to the technical field of power distribution network post-disaster load rescue, and particularly relates to a power distribution network emergency scheduling method considering micro-grid group and traffic flow cooperative regulation and control. Comprising the following steps: constructing a traffic flow control model considering restrictions on passing of vehicles with special license plates; constructing a mobile power supply flexible space-time energy transmission model compatible with specified transportation time; on the basis, a post-disaster power distribution network load rescue model is constructed, so that the total cost formed by the electric power safety guarantee cost and the social traffic circulation cost is minimum; by designing a two-stage algorithm composed of a linearization stage and an accelerated solution stage, the scheduling problem is efficiently solved. According to the invention, the problem that the toughness of a post-disaster power distribution system is not enough to be enhanced because a traditional large-scale mobile power supply always passively follows a given operation time to carry out load rescue is solved.

The invention belongs to the technical field of atmospheric monitoring. According to the Nash equilibrium-based atmospheric pollution multi-subject cooperative regulation and control method and system, for any pollution discharge enterprise, the pollution contribution ratio of the pollution discharge enterprise is determined; taking each main road as a discharge unit, and determining a main road pollution contribution ratio for any main road; and calling a multi-agent decision engine according to the emission control target value of the pollutant station, the pollution contribution ratio of the pollution discharge enterprise and the pollution contribution ratio of the main road, adopting a pollution discharge enterprise agent and a traffic agent, calling a Nash equilibrium optimizer, and taking the optimal emission reduction cost as a target to obtain an emission reduction and traffic flow control scheme. According to the invention, by establishing a multi-source overall pollution contribution rate calculation model and a dynamic optimization mechanism, more accurate atmospheric monitoring and more accurate multi-subject coordination control are realized.

A method for modeling and controlling traffic flow in a traffic flow system is provided. The method includes establishing a mathematical model of the traffic flow system, constructing an environment simulator that transforms the boundary control problem of the system into a Markov process, and designing a control method utilizing reinforcement learning algorithms to stabilize the traffic flow system. The control method interacts with the environment simulator to train an Actor-Critic network. The optimal traffic flow controller is implemented through the output of the Actor network, thereby enabling effective control of the traffic flow.