Movatterモバイル変換


[0]ホーム

URL:


CN118968773B - A dynamic scheduling method and system for intelligent transportation network - Google Patents

A dynamic scheduling method and system for intelligent transportation network
Download PDF

Info

Publication number
CN118968773B
CN118968773BCN202411464864.9ACN202411464864ACN118968773BCN 118968773 BCN118968773 BCN 118968773BCN 202411464864 ACN202411464864 ACN 202411464864ACN 118968773 BCN118968773 BCN 118968773B
Authority
CN
China
Prior art keywords
motor vehicle
flow
bus
traffic
lane
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202411464864.9A
Other languages
Chinese (zh)
Other versions
CN118968773A (en
Inventor
沈丹平
张庆永
陈斌
林辉
苏建顺
陈德旺
余捷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
V Com Fujian Information Technology Co ltd
Original Assignee
V Com Fujian Information Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by V Com Fujian Information Technology Co ltdfiledCriticalV Com Fujian Information Technology Co ltd
Priority to CN202411464864.9ApriorityCriticalpatent/CN118968773B/en
Publication of CN118968773ApublicationCriticalpatent/CN118968773A/en
Application grantedgrantedCritical
Publication of CN118968773BpublicationCriticalpatent/CN118968773B/en
Activelegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Classifications

Landscapes

Abstract

Translated fromChinese

本发明公开了一种智能交通网络动态调度方法及系统,涉及交通网络技术领域,基于流量守恒方程建立目标函数并进行最小化操作,可以有效识别公交车临时占道对非机动车流量的影响,精准计算出非机动车的流动效率L,以提高后期对车流量预测的精准度;通过对预测流量和实际流量的对比分析,系统能够智能判断当前非机动车道的拥堵状况,并快速发出调度优化指令,不仅有助于缓解交通拥堵,还能减少非机动车的延误时间。此外,结合PyTorch技术构建的调度优化模型,使得调度评估指数Dgzs的计算更加精准,为公交车的派发方案提供科学依据。根据评估指数的数值大小,系统能够智能选择相应的公交车调度策略,该过程进一步实现了交通资源的高效配置。

The present invention discloses a method and system for dynamic scheduling of intelligent transportation networks, which relates to the technical field of transportation networks. Based on the flow conservation equation, an objective function is established and minimized, which can effectively identify the impact of temporary occupation of buses on non-motor vehicle traffic, accurately calculate the flow efficiency L of non-motor vehicles, so as to improve the accuracy of traffic flow prediction in the later stage; through comparative analysis of predicted traffic and actual traffic, the system can intelligently judge the congestion status of the current non-motor vehicle lanes, and quickly issue scheduling optimization instructions, which not only helps to alleviate traffic congestion, but also reduces the delay time of non-motor vehicles. In addition, the scheduling optimization model constructed in combination with PyTorch technology makes the calculation of the scheduling evaluation index Dgzs more accurate, providing a scientific basis for the bus dispatching plan. According to the numerical value of the evaluation index, the system can intelligently select the corresponding bus scheduling strategy, and this process further realizes the efficient allocation of transportation resources.

Description

Intelligent traffic network dynamic scheduling method and system
Technical Field
The invention relates to the technical field of traffic networks, in particular to an intelligent traffic network dynamic scheduling method and system.
Background
Intelligent Traffic Systems (ITS) are an important component of the modern traffic management and transportation field, aiming at improving traffic operation efficiency and safety by using advanced information technology and communication technology, focusing on optimizing traffic flow and resource allocation through data monitoring and analysis. In the field, the dispatching and management of buses are particularly important, and related researches and applications are deepened continuously so as to optimize traffic flow and promote travel experience. However, in actual operation, the bus may temporarily stop on the non-motor vehicle lane due to lack of a special bus station or stop point in the process of boarding and disembarking passengers, which not only affects the passing efficiency of the non-motor vehicle, but also may cause disturbance of traffic flow, further aggravate the congestion phenomenon of roads.
When analyzing the influence of the temporary lane occupation behavior of the bus on the flow of the non-motor vehicle lane, the current defects are mainly reflected in the lack of a system monitoring and analyzing mechanism. The existing method is often focused on monitoring the traffic situation of a motor vehicle lane in a traffic network and analyzing pedestrians on the road, and can possibly cause non-motor vehicle traffic delay and congestion caused by temporary stop of a bus, and the existing method often ignores some blocking points which suddenly appear in the traffic flow, namely, the severe change of the relationship between the traffic and the density.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an intelligent traffic network dynamic scheduling method and system, which solve the problems in the background art.
In order to achieve the purpose, the invention is realized by the following technical scheme that the intelligent traffic network dynamic scheduling method comprises the following steps,
S1, monitoring related traffic flow data in a non-motor vehicle lane by deploying a plurality of groups of monitoring equipment, setting a people flow meter at a bus station to monitor the related people flow data in real time, generating a traffic network data set after preprocessing, and uploading the traffic network data set to a cloud platform;
S2, setting up an objective function based on a flow conservation equationTo analyze the predicted value of the non-motor vehicle flow under the condition that the bus is in a temporary occupying roadThe difference between the flow value and the actual non-motor vehicle flow value Scz is changed, and the objective function is calculatedDetermining the flow efficiency L of the non-motor vehicle through the minimum operation, and constructing a final non-motor vehicle flow predicted value based on the flow efficiency L of the non-motor vehicle;
S3, based on the predicted vehicle flow value acquired in S2The actual non-motor vehicle flow value Scz is estimated and judged whether the congestion phenomenon exists in the current non-motor vehicle lane, and if the congestion phenomenon exists, a dispatching optimization instruction is sent out;
S4, after receiving a dispatching optimization instruction, analyzing the influence of the temporary stop behavior of the bus on the non-motor vehicle on the running delay of the non-motor vehicle to obtain delay time Ywsc, calculating the service demand ratio Fxb of the current bus station to the bus according to the related people flow data in the bus station, and fitting to obtain a dispatching evaluation index Dgzs by combining a dispatching optimization model constructed by PyTorch technology;
S5, an evaluation threshold W is preset, and is compared with a dispatching evaluation index Dgzs for analysis, so that the dispatching scheme of the current bus is intelligently deduced.
Preferably, the specific step S1 includes:
S11, monitoring relevant traffic flow data in the non-motor vehicle lane according to a plurality of groups of monitoring equipment deployed in the non-motor vehicle lane, wherein the relevant traffic flow data comprises actual non-motor vehicle flow Scz in each time period, density value md in the non-motor vehicle lane in each time period, maximum density value mdmax in the non-motor vehicle lane, duration Tstop of stay of the non-motor vehicle due to temporary occupation of a bus, speed Gcsd of the bus driving during temporary occupation of the bus and average speed of the non-motor vehicleSetting a people flow meter at the bus stop so as to monitor related people flow data in the bus stop in real time, wherein the related people flow data comprises the number of people RLL waiting for passengers in the bus stop;
S12, preprocessing the related traffic data and the related people traffic data to identify and remove noise repetition values and abnormal values in the related traffic data and the related people traffic data, processing missing values in the noise repetition values and the abnormal values by an interpolation method, and converting data with different scales into the same scale according to a dimensionless processing technology;
and S13, summarizing the preprocessed related traffic flow data and related people flow data to generate a traffic network data set, uploading the traffic network data set into a cloud platform in real time by using an internet technology through a streaming tool, and carrying out automatic backup and archiving operation after uploading the data, thereby providing service for subsequent analysis.
Preferably, the specific step S2 includes:
S21, analyzing the relationship between traffic flow and density through a flow conservation equation to preliminarily construct a non-motor vehicle flow predicted valueThe specific contents are as follows:
;
Wherein L represents the flow efficiency of the non-motor vehicle, md represents the density value in the non-motor vehicle lane, and mdmax represents the maximum density value in the non-motor vehicle lane;
S22, analyzing the flow predicted value of the non-motor vehicleThe difference between the actual non-motor vehicle flow value Scz is changed to establish an objective functionThe method comprises the following steps of:
;
The meaning of the formula is that the difference between the predicted value and the actual value is measured, where n is denoted as the monitoring period, i=1, 2, 3..n, sczi is denoted as the actual non-motor vehicle flow in the i-th period,A non-motor vehicle flow prediction value denoted as the i-th period.
Preferably, S2 further includes:
S23, solving an objective function by using a least square methodPartial derivative of the flow efficiency L of a non-motor vehicle to determine the objective functionAnd finally determining the value of the flow efficiency L of the non-motor vehicle through the minimization operation.
Preferably, S2 further includes:
S24, substituting the flow efficiency L of the non-motor vehicle finally determined in S23 into a non-motor vehicle flow predicted valueIn the formulae concerned, to recalculate the final non-motor vehicle flow prediction
Preferably, the specific step S3 includes:
S31, according to the final non-motor vehicle flow predicted valueAnd by combining with the actual non-motor vehicle flow value Scz in the corresponding monitoring period, estimating whether the congestion phenomenon exists in the current non-motor vehicle lane, wherein the specific judgment content is as follows:
S311, when the final non-motor vehicle flow predicted valueWhen the actual non-motor vehicle flow value Scz is not less than or equal to, estimating that the congestion risk exists in the current non-motor vehicle lane at the moment, and transmitting the result to S313 for further analysis operation;
s312, when the final non-motor vehicle flow predicted valueWhen the actual non-motor vehicle flow value Scz is smaller than the actual non-motor vehicle flow value Scz, estimating that the congestion risk does not exist in the current non-motor vehicle lane at the moment;
S313, after receiving the result in S311, predicting the flow of the non-motor vehicle in the corresponding monitoring periodExtracting the corresponding density value md in the non-motor vehicle lane, and extracting the density value md in the non-motor vehicle lane and the maximum density value mdmax in the non-motor vehicle laneThe times are compared to judge whether the shock wave phenomenon is generated, specifically:
s3131 if the density value md in the non-motor vehicle lane exceeds the maximum density value mdmax in the non-motor vehicle laneJudging that shock wave exists in the bus stop area in the current non-motor lane;
s3132, if the density value md in the non-motor vehicle lane does not exceed the maximum density value mdmax in the non-motor vehicle laneThe shock wave phenomenon is judged to be not existed in the bus station area in the current non-motor vehicle lane;
S314, analyzing the shock phenomenon to calculate and acquire the propagation speed Jcsd of the shock, wherein the shock is acquired by the following formula:
;
Wherein Sczdown is represented as a non-motor vehicle flow value after temporary lane occupation of the bus, sczup is represented as a non-motor vehicle flow value before temporary lane occupation of the bus, mddown is represented as a density value after temporary lane occupation of the bus, and mdup is represented as a density value before temporary lane occupation of the bus;
S315, based on the value of the shock propagation speed Jcsd, when the shock propagation speed Jcsd is positive, the temporary occupation of the bus is indicated to enable shock waves appearing in the current non-motor lane to propagate downwards, and when the shock propagation speed Jcsd is negative, the temporary occupation of the bus is indicated to enable shock waves appearing in the current non-motor lane to propagate upwards, the congestion phenomenon in the current non-motor lane is estimated and judged, and meanwhile, a dispatching optimization instruction is sent outwards.
Preferably, the specific step S4 includes:
S41, after receiving a dispatching optimization instruction, analyzing the influence of the temporary stop behavior of the bus on the non-motor vehicle lane on the running delay of the non-motor vehicle to obtain a delay time Ywsc, wherein the delay time is obtained specifically by the following steps of:
;
Where Tstop is expressed as the length of time that the non-motor vehicle is stopped due to temporary occupancy of the road by the bus,Expressed as the average speed of the non-motor vehicle, gcsd as the speed of the bus when the bus is temporarily occupying the lane, and Lr as the length of the lane;
S42, calculating the service demand ratio Fxb of the current bus station to the bus based on the related people flow data in the bus station, and specifically acquiring the service demand ratio Fxb according to the following mode:
;
where RLL is expressed as the number of waiting passengers in the bus stop.
Preferably, S4 further includes:
s43, constructing a scheduling optimization model by using a convolutional neural network technology and combining PyTorch technologies, inputting delay time Ywsc and service demand ratio Fxb into the scheduling optimization model, and fitting to obtain a scheduling evaluation index Dgzs after dimensionless processing:
;
In the formula,AndAll are weight values, and U is expressed as a correction constant.
Preferably, the specific step S5 includes:
S51, comparing the dispatching evaluation index Dgzs with an evaluation threshold W for analysis so as to intelligently deduce a dispatching scheme of the current bus, wherein the specific content is as follows:
If the dispatching evaluation index Dgzs falls into the evaluation threshold W, at the moment, the departure time of the bus is adjusted, the departure time of the bus is shortened to 80% of the original departure time, and the latest departure information and the recommended route are timely issued to passengers through mobile phone application or a platform display screen;
If the dispatch evaluation index Dgzs does not fall within the evaluation threshold W, the departure time of the bus will continue to be executed according to the current scheme.
An intelligent traffic network dynamic scheduling system comprises an acquisition subsystem, a difference analysis subsystem, an instruction issuing subsystem, an optimization analysis subsystem and a scheduling subsystem;
The acquisition subsystem monitors related traffic flow data in a non-motor vehicle lane by deploying a plurality of groups of monitoring equipment, and a traffic flow meter is arranged at a bus station to monitor the related traffic flow data in real time, and a traffic network data set is generated after preprocessing and is uploaded to a cloud platform;
The differential analysis subsystem establishes an objective function based on a flow conservation equationTo analyze the predicted value of the non-motor vehicle flow under the condition that the bus is in a temporary occupying roadThe difference between the flow value and the actual non-motor vehicle flow value Scz is changed, and the objective function is calculatedDetermining the flow efficiency L of the non-motor vehicle through the minimum operation, and constructing a final non-motor vehicle flow predicted value based on the flow efficiency L of the non-motor vehicle;
The instruction issuing subsystem is based on a predicted vehicle flow valueThe actual non-motor vehicle flow value Scz is estimated and judged whether the congestion phenomenon exists in the current non-motor vehicle lane, and if the congestion phenomenon exists, a dispatching optimization instruction is sent out;
The optimization analysis subsystem is used for analyzing the influence of the temporary stop behavior of the bus on the non-motor vehicle on the running delay of the non-motor vehicle after receiving the dispatching optimization instruction so as to acquire delay time Ywsc, calculating the service demand ratio Fxb of the current bus station to the bus according to the related people flow data in the bus station, and fitting to acquire a dispatching evaluation index Dgzs by combining the dispatching optimization model constructed by PyTorch technology;
the dispatching subsystem is used for presetting an evaluation threshold W, and comparing and analyzing the evaluation threshold W with a dispatching evaluation index Dgzs so as to intelligently deduce the dispatching scheme of the current bus.
The invention provides an intelligent traffic network dynamic scheduling method and system, which have the following beneficial effects:
(1) The method comprises the steps of acquiring traffic flow and people flow data in real time through deployment of monitoring equipment, guaranteeing accuracy and timeliness of information, establishing an objective function based on a flow conservation equation, performing minimization operation, effectively identifying the influence of temporary occupation of a bus on the non-motor vehicle flow, accurately calculating the flow efficiency L of the non-motor vehicle to improve the accuracy of predicting the traffic flow in the later period, intelligently judging the congestion condition of the current non-motor vehicle lane through comparison analysis of the predicted flow and the actual flow, and rapidly sending a scheduling optimization instruction, so that the traffic congestion is relieved, delay time of the non-motor vehicle is reduced, and traveling experience is improved. In addition, the dispatching optimization model constructed by combining PyTorch technology ensures that the dispatching evaluation index Dgzs is calculated more accurately, and provides scientific basis for the dispatching scheme of the bus. When the evaluation index is compared with a preset threshold, the system can intelligently select a corresponding bus scheduling strategy, the process further realizes efficient configuration of traffic resources, reduces operation cost, and improves response speed and quality of bus service. In a word, the method fully considers the problem that the corresponding lane is blocked due to temporary stop of the public traffic, thereby providing a foundation for improving the management efficiency of traffic flow.
(2) The flow conservation equation in the step S2 is applied, so that scientific basis is provided for the prediction of the flow of the non-motor vehicle, the deep analysis between the traffic flow and the density is realized, the understanding of the traffic state is more accurate by establishing the relation between the flow efficiency L of the non-motor vehicle and the density and the maximum density, and the construction of the mathematical model is beneficial to accurately predicting the flow of the non-motor vehicle in different time periods and provides data support for urban traffic management. Through the difference analysis of the predicted value and the actual value in S22, the set objective function becomes an important tool for measuring the performance of the model, the objective function can quantify the prediction precision, promote the optimization and iteration of the model, ensure that the prediction accuracy can be continuously improved in the practical application, and the feedback mechanism based on data driving ensures that the traffic flow prediction is not only a static analysis, but also an important strategy for dynamically adapting to the urban traffic change. In addition, the flow prediction and the actual monitoring data are combined to form a closed-loop feedback system, and a traffic manager can quickly identify the deviation of the flow prediction through the continuously updated real-time data, so that the accuracy of a prediction result is timely adjusted.
(3) In the step S3, by comparing the predicted value of the flow of the non-motor vehicle with the actual flow value Scz, the system can effectively identify the congestion risk in the non-motor vehicle lane, and the innovation of the process is that the traffic condition is monitored in real time in a data driving mode, so as to provide accurate congestion judgment. Specifically, when the predicted value of the non-motor vehicle flow is greater than or equal to the actual flow value, the system actively identifies the potential congestion risk and transmits information to a subsequent analysis link, and the pre-warning mechanism enables a traffic manager to make a coping strategy in advance so as to avoid further worsening of the congestion. By comparing the density value with the maximum density value, the system not only can judge the generation of the shock phenomenon, but also can provide deep analysis in a dynamic traffic environment and data support for traffic flow optimization. Further, by calculating the shock propagation speed Jcsd, the system can be informed of the dynamic evolution of the congestion condition, and the dynamic feedback mechanism provides basis for real-time scheduling and resource allocation, so that the efficient operation of traffic flow is ensured. In addition, the method is creative in universality and flexibility, and can adapt to different cities and specific traffic conditions thereof.
(4) By combining quantification of delay time Ywsc and service demand ratio Fxb in the step S4, the intelligent traffic network can further realize dynamic feedback and real-time scheduling to form closed-loop management, and by analyzing the mutual influence between buses and non-motor vehicle flows, the system can not only adjust the bus departure interval in real time, but also optimize the traffic strategy of non-motor vehicles lanes in peak time, thereby effectively relieving traffic jam. In addition, by using the service demand ratio Fxb, the system can arrange additional public transportation resources in advance when the passenger flow rate suddenly increases, so that the service level of public transportation is further improved. In general, the method not only improves the running efficiency of traffic flow, but also provides an innovative solution for urban traffic management through accurate data analysis and dynamic adjustment, and the assistance construction is more intelligent and efficient.
Drawings
FIG. 1 is a schematic flow chart of a dynamic scheduling method of an intelligent traffic network;
FIG. 2 is a block diagram of a dynamic scheduling system for intelligent traffic network according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, the present invention provides a dynamic scheduling method for intelligent traffic network, comprising the following steps,
S1, monitoring related traffic flow data in a non-motor vehicle lane by deploying a plurality of groups of monitoring equipment, setting a people flow meter at a bus station to monitor the related people flow data in real time, generating a traffic network data set after preprocessing, and uploading the traffic network data set to a cloud platform;
S2, setting up an objective function based on a flow conservation equationTo analyze the predicted value of the non-motor vehicle flow under the condition that the bus is in a temporary occupying roadThe difference between the flow value and the actual non-motor vehicle flow value Scz is changed, and the objective function is calculatedDetermining the flow efficiency L of the non-motor vehicle through the minimum operation, and constructing a final non-motor vehicle flow predicted value based on the flow efficiency L of the non-motor vehicle;
S3, based on the predicted vehicle flow value acquired in S2The actual non-motor vehicle flow value Scz is estimated and judged whether the congestion phenomenon exists in the current non-motor vehicle lane, and if the congestion phenomenon exists, a dispatching optimization instruction is sent out;
S4, after receiving a dispatching optimization instruction, analyzing the influence of the temporary stop behavior of the bus on the non-motor vehicle on the running delay of the non-motor vehicle to obtain delay time Ywsc, calculating the service demand ratio Fxb of the current bus station to the bus according to the related people flow data in the bus station, and fitting to obtain a dispatching evaluation index Dgzs by combining a dispatching optimization model constructed by PyTorch technology;
S5, an evaluation threshold W is preset, and is compared with a dispatching evaluation index Dgzs for analysis, so that the dispatching scheme of the current bus is intelligently deduced.
In the embodiment, by deploying the monitoring equipment and the people flow meter, the traffic flow and people flow data of the non-motor vehicle lane and the bus station can be further collected in real time, and the real-time monitoring capability provides accurate basis for subsequent data analysis and decision making, so that the scientificity and rationality of a scheduling scheme are ensured. The method can further accurately analyze the influence of the temporary occupation of the bus on the flow of the non-motor vehicle based on the objective function established by the flow conservation equation, further determine the flow efficiency L of the non-motor vehicle by minimizing the difference between the predicted flow and the actual flow, and can be regarded as the number of vehicles passing through per unit time and per unit density, and determine the flow efficiency L of the non-motor vehicle so as to obtain the final predicted value of the flow of the non-motor vehicleAfter the congestion phenomenon in the non-motor vehicle lane is identified, the system can immediately send out a dispatching optimization instruction, and the quick response mechanism can further reduce the occurrence frequency of traffic jams and delay of the non-motor vehicle, thereby improving the overall traffic fluidity. By analyzing the delay influence of temporary stop of the bus on the non-motor vehicle and calculating the service demand ratio by combining the people flow data, the bus service and people flow demands can be matched more accurately, and the dynamic adjustment can reasonably allocate bus resources in the peak period so as to ensure the travel experience of passengers. And a dispatching optimization model constructed by utilizing PyTorch technology is utilized, so that the calculation of dispatching evaluation indexes is more scientific and intelligent. By setting and analyzing the evaluation threshold value, the dispatching scheme of the current bus can be effectively judged, the flexibility and adaptability of dispatching are improved, and the continuously-changing traffic demands are met. By optimizing the scheduling strategy of the buses, the traffic efficiency can be improved, and the congestion condition of non-motor lanes can be further reduced, so that positive contribution is made to environmental protection and sustainable development. In a word, the method provides a high-efficiency solution for intelligent traffic management, and can lay a foundation for the intellectualization and modernization of urban traffic management while improving the service quality of public traffic and considering the whole traffic mobility.
Example 2
Referring to fig. 1, the specific steps of S1 include:
S11, monitoring relevant traffic flow data in the non-motor vehicle lane according to a plurality of groups of monitoring equipment deployed in the non-motor vehicle lane, wherein the relevant traffic flow data comprises actual non-motor vehicle flow Scz in each time period, density value md in the non-motor vehicle lane in each time period, maximum density value mdmax in the non-motor vehicle lane, duration Tstop of stay of the non-motor vehicle due to temporary occupation of a bus, speed Gcsd of the bus driving during temporary occupation of the bus and average speed of the non-motor vehicleSetting a people flow meter at the bus stop so as to monitor related people flow data in the bus stop in real time, wherein the related people flow data comprises the number of people RLL waiting for passengers in the bus stop;
The density value md in the non-motor vehicle lane can be obtained through monitoring by a ground sensor or a video monitoring system, wherein the video monitoring system analyzes video streams through an image processing technology and calculates the number of vehicles in unit length;
The stay time Tstop of the non-motor vehicle due to temporary road occupation of the public traffic vehicle can be monitored by a ground sensor;
the speed Gcsd of the bus when the bus temporarily occupies the road can be monitored in real time through the GPS equipment on the bus, or real-time speed data can be obtained by using a vehicle-mounted sensor;
Average speed of non-motor vehicleThe monitoring and acquisition can be performed through a speed measuring radar or a ground sensor.
S12, preprocessing the related traffic data and the related people traffic data to identify and remove noise repetition values and abnormal values in the related traffic data and the related people traffic data, processing missing values in the noise repetition values and the abnormal values by an interpolation method, and converting data with different scales into the same scale according to a dimensionless processing technology;
And S13, summarizing the preprocessed related traffic flow data and related people flow data to generate a traffic network data set, uploading the traffic network data set into a cloud platform in real time through streaming tools (such as Kafka, AWS KINESIS and Google Pub/Sub) by utilizing an Internet technology, and carrying out automatic backup and archiving operation after uploading the data, thereby providing service for subsequent analysis.
In the embodiment, in the step S1 of the method, the real-time data acquisition of the non-motor vehicle lanes by the plurality of groups of monitoring equipment realizes the multidimensional monitoring of traffic flow and people flow, and the accurate data acquisition not only improves the scientificity of traffic management, but also provides a solid foundation for subsequent analysis. Specifically, various data monitored in the step S11, such as actual non-motor vehicle flow Scz, density value md, maximum density value mdmax, and stay time Tstop caused by temporary road occupation of the bus, can help traffic managers to comprehensively understand traffic conditions, and the monitoring of the data is helpful for accurately evaluating the driving condition of the non-motor vehicle and the influence degree of the temporary road occupation of the bus, so that a key basis is provided for future scheduling decisions. In step S12, by performing noise cancellation, outlier recognition and processing on the related data, high quality and reliability of the data are ensured. Meanwhile, the interpolation method is adopted to process the missing values and dimensionless processing technology, so that data with different scales can be analyzed uniformly, the process of data cleaning and standardization improves the accuracy and effectiveness of subsequent analysis as much as possible, and a good foundation is laid for the establishment of an intelligent scheduling model. And S13, the real-time uploading of the data is realized through a streaming technology, so that the data transmission efficiency is improved, the automatic backup and archiving of the data after the uploading are ensured, the risk of data loss is reduced, and continuous support is provided for subsequent real-time analysis and decision. In addition, through the application of the Internet technology, the traffic data is updated and shared rapidly, so that each relevant party can acquire the latest information in time, and the response capacity and the management efficiency of the whole traffic system are improved. In summary, the method further improves the efficiency and the management level of the intelligent traffic network through multi-aspect monitoring, data cleaning and real-time uploading, and provides an innovative solution for future traffic scheduling and optimization.
Example 3
Referring to fig. 1, the specific steps of S2 include:
S21, analyzing the relationship between traffic flow and density through a flow conservation equation to preliminarily construct a non-motor vehicle flow predicted valueThe specific contents are as follows:
;
Wherein L represents the flow efficiency of the non-motor vehicle, md represents the density value in the non-motor vehicle lane, and mdmax represents the maximum density value in the non-motor vehicle lane;
S22, analyzing the flow predicted value of the non-motor vehicleThe difference between the actual non-motor vehicle flow value Scz is changed to establish an objective functionThe method comprises the following steps of:
;
The meaning of the formula is that the difference between the predicted value and the actual value is measured, where n is denoted as the monitoring period, i=1, 2, 3..n, sczi is denoted as the actual non-motor vehicle flow in the i-th period,A non-motor vehicle flow prediction value denoted as the i-th period.
It should be noted that, the flow conservation equation is used to describe the relationship between the change of traffic flow and the number of vehicles in a specific area, and the expression is: wherein, the method comprises the steps of,Expressed as the number of vehicles at location x and time t; expressed as flow (number of vehicles passing a certain point per unit time) at the point x and time t; representing the partial derivative of time t, describing the rate of change of the number of vehicles over time; Representing the partial derivative of position x, describing the rate of change of vehicle flow with position; is a partial derivative operator that represents the rate of change of a function with respect to a certain variable.
In the embodiment, in step S2, an objective function is set up to analyze the variation of the difference between the predicted value of the non-motor vehicle flow and the actual non-motor vehicle flow Scz, and this process provides a quantization index for the optimization of the model, and the design of the objective function enables the traffic manager to explicitly evaluate the prediction accuracy, so as to adjust the scheduling policy in a targeted manner. Furthermore, by setting the monitoring period, the system can analyze the flow change trend in different time periods, so that a dynamic view angle is provided for monitoring the real-time traffic condition, historical data support is provided for future traffic flow prediction, and a benign feedback loop is formed. In addition, through continuous flow and density analysis, the traffic management system can realize self-adaptive scheduling, timely respond to the change of the flow of the non-motor vehicle, effectively relieve the congestion condition and optimize the traffic efficiency. In summary, the method constructs a non-motor vehicle flow prediction and analysis method based on data driving through the combination of a flow conservation equation and an objective function, not only improves the accuracy of flow prediction, but also provides important technical support for the intellectualization of urban traffic management, and helps to construct a more efficient and sustainable urban traffic network.
Example 4
Referring to fig. 1, the following details are:
s2 also comprises that S2 also comprises:
S23, solving an objective function by using a least square methodPartial derivative of the flow efficiency L of a non-motor vehicle to determine the objective functionAnd finally determining the value of the flow efficiency L of the non-motor vehicle through the minimization operation.
The least square method is used to solve the problems that firstly, the error value is calculatedThen, using an objective function to actually carry out error square sum, then, calculating partial derivative of the objective function, in order to minimize the error square sum, calculating the flow efficiency L of the non-motor vehicle, and setting the partial derivative to be 0 so as to solve the finally determined flow efficiency L of the non-motor vehicle;
S24, substituting the flow efficiency L of the non-motor vehicle finally determined in S23 into a non-motor vehicle flow predicted valueIn the formulae concerned, to recalculate the final non-motor vehicle flow prediction
In this embodiment, in step S2, the implementation of S23 and S24 provides a more accurate and scientific basis for non-motor vehicle flow prediction. By using the least square method to solve the objective function, researchers can effectively identify and optimize the flow efficiency L of the non-motor vehicle, and the method not only realizes systemization and standardization of flow prediction of the non-motor vehicle, but also ensures the sensitivity and accuracy of the model to the flow efficiency through solving partial derivatives. The method has the advantages that the minimization operation is carried out by combining the gradient descent method, so that the objective function has higher operability and flexibility in practical application, the flow efficiency L of the non-motor vehicle can be quickly adjusted in the iterative process of the algorithm, the prediction model is further optimized in real time, the reliability of traffic flow prediction is improved by the dynamic adjustment mechanism, and the continuously-changing traffic environment can be better dealt with. And S24, substituting the finally determined flow efficiency L into a flow prediction formula further enhances the practicability of the model, and through the process, researchers can update the flow prediction value of the non-motor vehicle in real time to ensure that the prediction result reflects the latest traffic condition, thereby not only being beneficial to improving the response speed of traffic management, but also providing a basis for a decision maker and being convenient for timely adjustment in a peak period or under special conditions. In addition, the innovation of the method is that a data-driven feedback mechanism is utilized to enable traffic flow prediction to be in close connection with actual operation data, and the mechanism not only improves the adaptability of a model, but also lays a foundation for the subsequent development of an intelligent traffic system. In a word, through accurate flow efficiency optimization and dynamic flow prediction, a foundation is laid for the subsequent analysis of non-motor vehicle lane congestion caused by temporary bus occupation.
Example 5
Referring to fig. 1, the specific steps of S3 include:
S31, according to the final non-motor vehicle flow predicted valueAnd by combining with the actual non-motor vehicle flow value Scz in the corresponding monitoring period, estimating whether the congestion phenomenon exists in the current non-motor vehicle lane, wherein the specific judgment content is as follows:
S311, when the final non-motor vehicle flow predicted valueWhen the actual non-motor vehicle flow value Scz is not less than or equal to, estimating that the congestion risk exists in the current non-motor vehicle lane at the moment, and transmitting the result to S313 for further analysis operation;
s312, when the final non-motor vehicle flow predicted valueWhen the actual non-motor vehicle flow value Scz is smaller than the actual non-motor vehicle flow value Scz, estimating that the congestion risk does not exist in the current non-motor vehicle lane at the moment;
Wherein the actual non-motor vehicle flow rate Scz is the number of vehicles passing through a certain place in a certain time, such as the number of vehicles passing through per hour, and the final non-motor vehicle flow rate predicted valueThe characteristics of traffic flow, including the influence of density on flow, are taken into account, which under certain conditions (e.g. specific traffic regulations, road conditions, etc.), reflect the maximum flow that can be theoretically achieved if the vehicle density on the road is md, that is to say at a specific density.
S313, after receiving the result in S311, predicting the flow of the non-motor vehicle in the corresponding monitoring periodExtracting the corresponding density value md in the non-motor vehicle lane, and extracting the density value md in the non-motor vehicle lane and the maximum density value mdmax in the non-motor vehicle laneThe times are compared to judge whether the shock wave phenomenon is generated, specifically:
s3131 if the density value md in the non-motor vehicle lane exceeds the maximum density value mdmax in the non-motor vehicle laneJudging that shock wave exists in the bus stop area in the current non-motor lane;
s3132, if the density value md in the non-motor vehicle lane does not exceed the maximum density value mdmax in the non-motor vehicle laneThe shock wave phenomenon is judged to be not existed in the bus station area in the current non-motor vehicle lane;
S314, analyzing the shock phenomenon to calculate and acquire the propagation speed Jcsd of the shock, wherein the shock is acquired by the following formula:
;
Wherein Sczdown is represented as a non-motor vehicle flow value after temporary lane occupation of the bus, sczup is represented as a non-motor vehicle flow value before temporary lane occupation of the bus, mddown is represented as a density value after temporary lane occupation of the bus, and mdup is represented as a density value before temporary lane occupation of the bus;
S315, based on the value of the shock propagation speed Jcsd, when the shock propagation speed Jcsd is a positive value, it indicates that the temporary occupation of the bus makes the shock occurring in the current non-motor lane propagate towards the downstream, possibly because the subsequent flow starts to increase, and the congestion is gradually relieved;
When the shock wave propagation speed Jcsd is a negative value, the temporary occupation of the bus is indicated, so that shock waves in the current non-motor vehicle lane propagate towards the upstream, the congestion is diffused, the congestion phenomenon in the current non-motor vehicle lane is estimated, and a dispatching optimization instruction is sent outwards.
It should be noted that, temporary occupation of the bus may decrease the effective traffic width of the non-motor vehicle lane, thereby increasing the traffic density of the local area, and if the density increases to a certain threshold value, the traffic may reach saturation or even congestion, so as to generate a shock wave phenomenon.
In the embodiment, based on the step S2, the predicted value of the flow of the non-motor vehicle is accurately determined, so that the congestion condition of the non-motor vehicle lane is judged in the comparative analysis of the predicted value of the flow of the non-motor vehicle and the actual flow value, thereby effectively relieving the traffic pressure. In S313, the occurrence of the shock wave phenomenon can be further accurately determined by the value of the density value md, and the determination mode based on the density provides a basis for quantitative analysis of the traffic flow state, so that the traffic manager can make a scientific decision according to the real-time data. For example, if the shock phenomenon is found, the traffic management system can immediately adjust the timing of the signal lights, optimize the bus departure interval or guide the non-motor vehicles to select other paths so as to reduce the traffic pressure, and further, S314 and S315 provide a quantization index for analyzing the congestion condition by calculating the shock propagation speed Jcsd. And on the contrary, the congestion is shown to be aggravated, so that the traffic management does not depend on single data any more, and can be adjusted and responded in real time, thereby ensuring the efficient operation of the traffic system. In addition, the creative effect of the method is also reflected in adaptability and expansibility, by continuously collecting and analyzing real-time data, the system can learn and optimize own judgment logic, an intelligent scheduling model is gradually formed, the method can adapt to the changes of different time periods and traffic conditions, and the flexible scheduling capability not only provides a new thought for urban traffic management, but also lays a solid foundation for the development of future intelligent traffic systems. In a word, through congestion judgment and shock wave analysis based on data driving, the invention not only improves the judgment of the flow efficiency of the non-motor vehicle lanes, but also provides a scientific and effective solution for intelligent traffic scheduling, thereby promoting the intelligent and modern processes of urban traffic management.
Example 6
Referring to fig. 1, the specific steps of S4 include:
S41, after receiving a dispatching optimization instruction, analyzing the influence of the temporary stop behavior of the bus on the non-motor vehicle lane on the running delay of the non-motor vehicle to obtain a delay time Ywsc, wherein the delay time is obtained specifically by the following steps of:
;
Where Tstop is expressed as the length of time that the non-motor vehicle is stopped due to temporary occupancy of the road by the bus,Expressed as the average speed of the non-motor vehicle, gcsd as the speed of the bus while temporarily occupying the lane, lr as the length of the lane, wherein,Expressed as the length of time that a non-motor vehicle needs to pass without the bus temporarily occupying the road; The method is characterized by comprising the steps of representing the time length of a bus passing by a non-motor vehicle under the condition of temporary occupation, wherein the occupation length Lr can be determined according to the length of the bus.
S42, calculating the service demand ratio Fxb of the current bus station to the bus based on the related people flow data in the bus station, and specifically acquiring the service demand ratio Fxb according to the following mode:
;
In the formula, RLL is expressed as the number of passengers waiting in a bus stop, wherein the purpose of adding one in a denominator is to avoid zero error, and in calculation, if a certain amount is possibly zero, direct division may cause calculation error, and by adding one in the denominator, the safety of division operation can be ensured.
In the embodiment, in step S4, by analyzing the temporary stop behavior of the bus in the non-motor vehicle lane, the system can calculate the non-motor vehicle running delay time Ywsc caused by the occupation of the bus, and the innovative delay calculation method comprehensively considers various factors including the stop time Tstop of the non-motor vehicle, the average speed, the running speed Gcsd of the bus and the occupation length Lr, so that a more comprehensive delay evaluation mechanism is provided, and the refined analysis can not only provide basis for real-time traffic scheduling, but also help traffic managers to formulate more scientific coping strategies so as to reduce traffic jam. Specifically, by explicitly calculating the passing time of the non-motor vehicle under different conditions, the system can effectively identify the influence of the occupied road on the traffic flow, and the dynamic evaluation mode can be flexibly applied in the actual traffic environment to timely reflect the change of the traffic state and provide real-time data support for traffic management. For example, when the delay period Ywsc exceeds a certain threshold, the system may quickly issue a dispatch optimization command directing the bus to leave the non-motorized lane in time to reduce interference with traffic flow. In addition, the system further improves the intelligent level of scheduling by calculating the service demand ratio Fxb based on the traffic data in the bus station, and the design of adding one to the denominator is introduced into the calculation formula, so that the safe calculation can be performed when the number of passengers is zero, zero removal errors are avoided, and the design thought shows the flexibility of the system in the aspects of realizing efficient data processing and safe calculation, and the robustness of the whole analysis process is ensured. By combining the two innovations, the system not only can improve the dispatching efficiency of buses, but also can improve the passing efficiency of non-motor vehicles, and the traffic fluidity is optimized as a whole. In addition, through continuous data monitoring and analysis, the intelligent traffic scheduling method can provide valuable insight for urban traffic management, promote scientific formulation of future traffic policies, and further promote the overall traffic environment of cities. Finally, the implementation of the method is helpful for constructing an intelligent traffic network which is more efficient, convenient and safe, and promotes sustainable urban development.
Example 7
Referring to fig. 1, the specific steps S4 further include:
s43, constructing a scheduling optimization model by using a convolutional neural network technology and combining PyTorch technologies, inputting delay time Ywsc and service demand ratio Fxb into the scheduling optimization model, and fitting to obtain a scheduling evaluation index Dgzs after dimensionless processing:
;
In the formula,AndAre weight values, U is expressed as a correction constant, wherein 0<≤1,0<Is less than or equal to 1, and+=1, The weight value can be obtained by reference to analytic hierarchy process;
s5, the specific steps include:
S51, comparing the dispatching evaluation index Dgzs with an evaluation threshold W for analysis so as to intelligently deduce a dispatching scheme of the current bus, wherein the specific content is as follows:
if the dispatching evaluation index Dgzs falls within the evaluation threshold W, at this time, the departure time of the bus is adjusted, the departure time of the bus is shortened to 80% of the original departure time, so that the getting-on and getting-off experience of passengers is optimized, and the latest departure information and the recommended route are timely issued to the passengers through mobile phone application or platform display screens, so that unnecessary waiting is reduced;
If the dispatch evaluation index Dgzs does not fall within the evaluation threshold W, the departure time of the bus will continue to be executed according to the current scheme.
It should be noted that the analytic hierarchy process is a qualitative and quantitative combined analytic method, which can decompose a complex problem into multiple layers, and by comparing the importance of the factors of the layers, it can help a decision maker to make a decision on the complex problem, and determine a final decision scheme, and in this process, the analytic hierarchy process can be used to determine the weight values of the indexes.
In the embodiment, in the steps S4 and S5, by applying the scheduling optimization model constructed by the Convolutional Neural Network (CNN) and PyTorch technologies, the system can analyze the delay time Ywsc and the service demand ratio Fxb in real time, so as to generate the scheduling evaluation index Dgzs. The calculation of the dispatching evaluation index Dgzs and the comparison with the evaluation threshold W provide scientific basis for the departure scheme of the bus. When the dispatching evaluation index Dgzs falls into the threshold range, the system can automatically adjust the departure time of the bus to 80% of the original departure time, so that the getting-on and getting-off experience of passengers is optimized. In addition, the latest departure information and the recommended route are issued in real time through the mobile phone application and the platform display screen, so that passengers can acquire dynamic information in time, travel selection of the passengers is optimized, satisfaction and convenience of the passengers are enhanced, and the information transparentizing strategy effectively reduces anxiety of the passengers caused by information asymmetry and improves the utilization rate of public transportation. When the dispatching evaluation index does not fall into the evaluation threshold, the system keeps the existing departure plan, ensures the stability and predictability of traffic management, and the dual dispatching strategy not only improves the response speed of the public transportation system, but also effectively copes with various emergency situations and ensures the continuity of public transportation service. In summary, by combining deep learning and intelligent scheduling, the system not only can deal with traffic changes in real time, but also can promote the traveling experience of passengers, thereby forming a more intelligent, efficient and humanized public transportation network.
Example 8
Referring to fig. 2, the intelligent traffic network dynamic scheduling system specifically includes an acquisition subsystem, a difference analysis subsystem, a command issuing subsystem, an optimization analysis subsystem and a scheduling subsystem;
The acquisition subsystem monitors related traffic flow data in a non-motor vehicle lane by deploying a plurality of groups of monitoring equipment, and a traffic flow meter is arranged at a bus station to monitor the related traffic flow data in real time, and a traffic network data set is generated after preprocessing and is uploaded to a cloud platform;
The differential analysis subsystem establishes an objective function based on a flow conservation equationTo analyze the predicted value of the non-motor vehicle flow under the condition that the bus is in a temporary occupying roadThe difference between the flow value and the actual non-motor vehicle flow value Scz is changed, and the objective function is calculatedDetermining the flow efficiency L of the non-motor vehicle through the minimum operation, and constructing a final non-motor vehicle flow predicted value based on the flow efficiency L of the non-motor vehicle;
The instruction issuing subsystem is based on a predicted vehicle flow valueThe actual non-motor vehicle flow value Scz is estimated and judged whether the congestion phenomenon exists in the current non-motor vehicle lane, and if the congestion phenomenon exists, a dispatching optimization instruction is sent out;
The optimization analysis subsystem is used for analyzing the influence of the temporary stop behavior of the bus on the non-motor vehicle on the running delay of the non-motor vehicle after receiving the dispatching optimization instruction so as to acquire delay time Ywsc, calculating the service demand ratio Fxb of the current bus station to the bus according to the related people flow data in the bus station, and fitting to acquire a dispatching evaluation index Dgzs by combining the dispatching optimization model constructed by PyTorch technology;
the dispatching subsystem is used for presetting an evaluation threshold W, and comparing and analyzing the evaluation threshold W with a dispatching evaluation index Dgzs so as to intelligently deduce the dispatching scheme of the current bus.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (10)

S11, monitoring relevant traffic flow data in the non-motor vehicle lane according to a plurality of groups of monitoring equipment deployed in the non-motor vehicle lane, wherein the relevant traffic flow data comprises actual non-motor vehicle flow Scz in each time period, density value md in the non-motor vehicle lane in each time period, maximum density value mdmax in the non-motor vehicle lane, duration Tstop of stay of the non-motor vehicle due to temporary occupation of a bus, speed Gcsd of the bus driving during temporary occupation of the bus and average speed of the non-motor vehicleSetting a people flow meter at the bus stop so as to monitor related people flow data in the bus stop in real time, wherein the related people flow data comprises the number of people RLL waiting for passengers in the bus stop;
CN202411464864.9A2024-10-212024-10-21 A dynamic scheduling method and system for intelligent transportation networkActiveCN118968773B (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202411464864.9ACN118968773B (en)2024-10-212024-10-21 A dynamic scheduling method and system for intelligent transportation network

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202411464864.9ACN118968773B (en)2024-10-212024-10-21 A dynamic scheduling method and system for intelligent transportation network

Publications (2)

Publication NumberPublication Date
CN118968773A CN118968773A (en)2024-11-15
CN118968773Btrue CN118968773B (en)2025-02-07

Family

ID=93397318

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202411464864.9AActiveCN118968773B (en)2024-10-212024-10-21 A dynamic scheduling method and system for intelligent transportation network

Country Status (1)

CountryLink
CN (1)CN118968773B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN112738209A (en)*2020-12-262021-04-30顾小菊Data analysis method based on big data and artificial intelligence and cloud computing server
CN112990694A (en)*2021-03-112021-06-18平安科技(深圳)有限公司Bus stop traffic capacity analysis method, device, equipment and storage medium

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN114418468B (en)*2022-03-292022-07-05成都秦川物联网科技股份有限公司Smart city traffic scheduling strategy control method and Internet of things system
CN115293519A (en)*2022-07-142022-11-04深圳云天励飞技术股份有限公司Bus route scheduling processing method, device and equipment and readable storage medium
CN117351702A (en)*2023-09-152024-01-05中科国力电子技术有限公司Intelligent traffic management method based on adjustment of traffic flow
CN118015817A (en)*2024-03-072024-05-10江苏天安智联科技股份有限公司C-V2X-based intelligent network bus dispatching system and method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN112738209A (en)*2020-12-262021-04-30顾小菊Data analysis method based on big data and artificial intelligence and cloud computing server
CN112990694A (en)*2021-03-112021-06-18平安科技(深圳)有限公司Bus stop traffic capacity analysis method, device, equipment and storage medium

Also Published As

Publication numberPublication date
CN118968773A (en)2024-11-15

Similar Documents

PublicationPublication DateTitle
CN111371904A (en)Cloud-side-end-coordinated highway cloud control system and control method
CN106530762A (en)Traffic signal control method and device
CN119026870B (en)Sanitation vehicle management method, device, equipment and storage medium
CN111091295A (en)Urban area boundary control system
CN109300326B (en)Bus short-time dynamic scheduling method based on real-time GPS
CN119047666A (en)Intelligent traffic vehicle capacity scheduling method, system, equipment and storage medium
CN117765735B (en)Traffic control method, device, computer equipment and storage medium
CN119090382A (en) A method and system for intelligent logistics scheduling optimization based on AI technology
CN117746626A (en)Intelligent traffic management method and system based on traffic flow
CN112185124A (en)Method and device for predicting traffic state of whole road network
KR20200090528A (en)System and method for controlling traffic signals based on distributed prediction
CN119682818A (en)Intelligent rail transit control system and method based on Internet of things
CN115841745A (en)Vehicle scheduling method and device and electronic equipment
CN118747961A (en) A road traffic management control method and system based on traffic flow monitoring
CN117985557A (en)Elevator cluster control method and system
CN106096793A (en)The charging electric vehicle decision method that periodicity based on congestion aware optimizes
CN116485137B (en)Intelligent bus scheduling method, device and medium based on big data
CN113487860A (en)Intelligent traffic signal control method
CN119623875B (en)Scenic spot intelligent management and control system and method based on Internet of things and big data analysis
CN114283590A (en) Traffic flow peak forecasting method and device, electronic equipment
CN118968773B (en) A dynamic scheduling method and system for intelligent transportation network
Aydos et al.SCATS ramp metering: strategies, arterial integration and results
CN119692939A (en) Water conservancy construction project management system based on data analysis
CN119479353A (en) A method and system for operation control based on smart bus shelter
CN117351744A (en)Crossing traffic management method and device, computer equipment and storage medium

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant
GR01Patent grant

[8]ページ先頭

©2009-2025 Movatter.jp