Multi-source fusion traffic demand flow rate evaluation method and system, medium and product

Abstract

The invention discloses a multi-source fusion traffic demand flow rate evaluation method and system, a medium and a product, and relates to the field of intelligent traffic. By adopting the technical scheme, the multi-source fusion traffic demand flow rate evaluation system fuses three types of data sources including intersection fixed detector data, intelligent network connection sampling vehicle data and signal lamp control operation data; the demand flow rate is calculated from the four dimensions of the road section driving speed, the signal control parking frequency, the actual flow rate and the green beginning queuing vehicles, the demand flow rate confidence is determined, and the problem that the traffic demand flow rate is inaccurately evaluated by a single data source is effectively solved. By means of the multi-source fusion mode, the road section traffic capacity reflected by the road section driving speed is considered, the traffic blocking degree reflected by the signal control parking frequency is included, the actual demand overstock condition reflected by the green beginning queuing vehicles is included, and therefore the traffic demand flow rate can be comprehensively and accurately evaluated.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation, and particularly to a multi-source fusion traffic demand flow rate evaluation method, system, medium and product. Background Art

[0002] With the acceleration of the urbanization process, the number of motor vehicles in possession continues to grow, and the problem of urban traffic congestion becomes increasingly prominent. Accurately evaluating the traffic demand flow rate of urban road intersections is of great significance for formulating reasonable traffic control strategies and improving the traffic efficiency of road networks. Especially in the context of intelligent transportation, how to make full use of multi-source traffic data to achieve accurate evaluation of the traffic demand flow rate at intersections has become an important issue faced by current traffic management departments.

[0003] Currently, the evaluation of traffic demand flow rate mainly relies on fixed detectors installed at intersections. The fixed detectors collect information when vehicles pass by to count the traffic flow, and estimate the traffic demand in combination with the signal timing plan.

[0004] However, due to the limited coverage of fixed detectors, it is difficult to comprehensively capture the traffic state information in the upstream area of intersections. Moreover, in the case of rapid changes in traffic demand, the traffic demand flow rate evaluation method based on fixed detectors is relatively lagging, and it is difficult to reflect the dynamic changes of actual traffic demand in a timely manner. Summary of the Invention

[0005] This application provides a multi-source fusion traffic demand flow rate evaluation method, system, medium and product for accurately evaluating the traffic demand flow rate.

[0006] In a first aspect, the present application provides a multi-source fusion traffic demand flow rate evaluation method, which is applied to a multi-source fusion traffic demand flow rate evaluation system. The method includes: obtaining intersection fixed detector data, intelligent connected sampling vehicle data, and signal light control operation data. The intersection fixed detector data refers to traffic flow data collected by fixed detectors installed on the approach lanes of intersections. The intelligent connected sampling vehicle data refers to the driving data of vehicles equipped with vehicle networking communication devices on the approach lanes of intersections. The signal light control operation data refers to the signal light operation state data for controlling the approach lanes of intersections. The signal light operation state data includes the signal control cycle, and the signal control cycle is used to represent the duration for the signal light to complete one cycle of the stage chain; determining the section driving speed, the first signal control stop count, and the first actual flow rate according to the intelligent connected sampling vehicle data, determining the second signal control stop count, the second actual flow rate, and the queue length of vehicles at the start of the green phase according to the intersection fixed detector data. The section driving speed is used to represent the average driving speed of vehicles on the approach lanes of intersections. The first signal control stop count and the second signal control stop count respectively represent the number of stop waits of vehicles passing through the intersection on the approach lanes caused by waiting for the signal light collected by the vehicle networking communication device and the fixed detector. The first actual flow rate and the second actual flow rate respectively represent the number of flows actually passing through per unit time on the approach lanes of intersections collected by the vehicle networking communication device and the fixed detector. The queue length of vehicles at the start of the green phase is used to represent the queue length at the moment when the phase green light starts to light up on the approach lanes of intersections; determining the first demand flow rate according to the section driving speed, determining the second demand flow rate according to the first signal control stop count or the second signal control stop count and the first actual flow rate or the second actual flow rate, and determining the third demand flow rate according to the queue length of vehicles at the start of the green phase and the signal control cycle; determining the confidence level of the demand flow rate according to the first demand flow rate, the second demand flow rate, and the third demand flow rate.

[0007] By adopting the above technical solution, the multi-source fusion traffic demand flow rate evaluation system fuses three types of data sources, namely intersection fixed detector data, intelligent connected sampling vehicle data, and signal light control operation data, calculates the demand flow rate from four dimensions: section driving speed, signal control stop count, actual flow rate, and queue length of vehicles at the start of the green phase, and determines the confidence level of the demand flow rate, effectively solving the problem of inaccurate evaluation of traffic demand flow rate by a single data source. The intersection fixed detector provides traffic flow data at fixed positions on the approach lanes of intersections. The intelligent connected sampling vehicle provides driving data of vehicles on the approach lanes of intersections. The signal light control operation data reflects the traffic organization constraints on the approach lanes of intersections. The three complement each other's advantages. Through this multi-source fusion method, both the section passing capacity reflected by the section driving speed and the degree of traffic obstruction reflected by the signal control stop count are considered, and the actual demand backlog situation reflected by the queue length of vehicles at the start of the green phase is also included, so as to comprehensively and accurately evaluate the traffic demand flow rate.

[0008] In some embodiments in combination with some embodiments of the first aspect, the first actual flow rate is determined according to the data of the intelligent connected sampling vehicle. The data of the intelligent connected sampling vehicle includes the average queue length of the sampling vehicle, the average delay time of the sampling vehicle, and the standard queue space during the statistical period. Specifically, it includes: inputting the average queue length of the sampling vehicle, the standard queue space, the statistical period, and the average delay time of the sampling vehicle into a preset first actual flow rate calculation formula to obtain the first actual flow rate; the preset first actual flow rate calculation formula is: First actual flow rate = (average queue length of the sampling vehicle / standard queue space) × statistical period / average delay time of the sampling vehicle.

[0009] By adopting the above technical solution, the multi-source fusion traffic demand flow rate evaluation system calculates the first actual flow rate according to the average queue length of the sampling vehicle, the standard queue space, the statistical period, the average delay time of the sampling vehicle, and the preset first actual flow rate calculation formula. Among them, the average queue length of the sampling vehicle reflects the vehicle backlog situation on the approach lane of the intersection, the standard queue space reflects the vehicle distribution density, and the average delay time of the sampling vehicle characterizes the traffic efficiency on the approach lane of the intersection. By organically combining these parameters, the actual traffic capacity of the approach lane of the intersection can be accurately depicted, making full use of the real-time positioning and status perception capabilities of the vehicle networking communication equipment, which has better dynamics and spatial continuity compared with traditional fixed detectors, and thus can more accurately reflect the actual traffic flow operation state.

[0010] In some embodiments in combination with some embodiments of the first aspect, the second actual flow rate is determined according to the data of the fixed detector at the intersection. Specifically, it includes: obtaining the total number of vehicles passing through the fixed detector during the statistical period; obtaining the second actual flow rate according to the total number of vehicles, the passing interval time, and the number of lanes.

[0011] By adopting the above technical solution, the multi-source fusion traffic demand flow rate evaluation system calculates the second actual flow rate based on the data of the fixed detector at the intersection, and can accurately calculate the actual traffic volume passing through the approach lane of the intersection. The fixed detector is installed at key positions on the approach lane of the intersection, and can continuously collect vehicle passing data all day long, with the advantages of good stability and wide coverage. This calculation method is simple and reliable, can be used as an effective supplement and verification for the data of the intelligent connected sampling vehicle, and further improves the accuracy and reliability of the demand flow rate evaluation.

[0012] In some embodiments in combination with some embodiments of the first aspect, determining the first demand flow rate according to the driving speed of a road section specifically includes: inputting the driving speed of the road section, the saturation flow rate, and the saturation flow rate speed into a preset first demand flow rate calculation formula to obtain the first demand flow rate. The saturation flow rate is used to represent the maximum flow rate rating on the approach lane of an intersection, and the saturation flow rate speed is used to represent the average driving speed of vehicles passing through the approach lane of the intersection when the saturation flow rate is reached; the preset first demand flow rate calculation formula is: First demand flow rate = saturation flow rate × (2 - actual driving speed / saturation flow rate speed).

[0013] By adopting the above technical solution, the multi-source fusion traffic demand flow rate evaluation system calculates the first demand flow rate based on the driving speed of the road section, introduces two benchmark parameters, namely the saturation flow rate and the saturation flow rate speed. By substituting the driving speed of the road section, the saturation flow rate, and the saturation flow rate speed into the preset first demand flow rate calculation formula, the traffic demand flow rate can be accurately evaluated. This calculation method fully considers the non-linear relationship between speed and flow rate: when the driving speed of the road section is close to the saturation flow rate speed, it indicates that the traffic condition on the approach lane of the intersection is good, and the demand flow rate is close to the saturation flow rate; when the driving speed of the road section is much lower than the saturation flow rate speed, it indicates that the approach lane of the intersection is severely congested, and the demand flow rate will increase accordingly.

[0014] In some embodiments in combination with some embodiments of the first aspect, determining the second demand flow rate according to the first signal control stop times or the second signal control stop times and the first actual flow rate or the second actual flow rate specifically includes: inputting the first signal control stop times or the second signal control stop times, the first actual flow rate or the second actual flow rate, the compactness calibration coefficient, and the stop times calibration coefficient into a preset second demand flow rate calculation formula to obtain the second demand flow rate. The compactness calibration coefficient is used to represent the driving density of vehicles on the approach lane of the intersection, and the stop times calibration coefficient is used to represent the theoretical minimum stop times under the signal timing plan; the preset second demand flow rate calculation formula is: Second demand flow rate = actual flow rate × compactness calibration coefficient × max(signal control stop times / stop times calibration coefficient, 1).

[0015] By adopting the above technical solution, the multi-source fusion traffic demand flow rate evaluation system calculates the second demand flow rate based on the signal control stop times and the actual flow rate, introduces the compactness calibration coefficient and the stop times calibration coefficient, and corrects the actual flow rate through these two coefficients. The compactness calibration coefficient reflects the driving density of vehicles and can correct the flow rate error caused by uneven vehicle distribution; the stop times calibration coefficient represents the theoretical minimum stop times under the signal timing plan and can correct the traffic obstruction caused by signal control. This dual calibration mechanism makes the calculation of the demand flow rate more accurate, can effectively reflect the actual traffic demand situation on the approach lane of the intersection, and provides a reliable basis for signal timing optimization.

[0016] In combination with some embodiments of the first aspect, in some embodiments, the third demand flow rate is determined based on the green initial queue vehicles and the signal control cycle, specifically including: inputting the green initial queue vehicles and the signal control cycle into a preset third demand flow rate calculation formula to obtain the third demand flow rate; the preset third demand flow rate calculation formula is: third demand flow rate = green initial queue vehicles × (unit time / signal control cycle).

[0017] By adopting the above technical solution, the multi-source fusion traffic demand flow rate evaluation system calculates the third demand flow rate based on the green initial queue vehicles and the signal control cycle, and can accurately evaluate the traffic demand flow rate per unit time. The green initial queue vehicles directly reflect the backlog of traffic demand within a signal cycle, and converting it into a demand flow rate per unit time can be compared with other evaluation dimensions. This calculation method is simple and intuitive, and has strong real-time performance. It can timely reflect the changing trend of traffic demand and is particularly suitable for evaluating the characteristics of cyclically changing traffic demand.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining the demand flow rate confidence based on the first demand flow rate, the second demand flow rate and the third demand flow rate, the method also includes: weighted fusion of the first demand flow rate, the second demand flow rate and the third demand flow rate based on the demand flow rate confidence to obtain the final demand flow rate; and generating traffic organization optimization suggestions based on the final demand flow rate and a preset demand flow rate-traffic suggestion correspondence table.

[0019] By adopting the above technical solutions, the multi-source fusion traffic demand flow rate evaluation system performs weighted fusion of multi-source data based on the demand flow rate confidence level, and generates traffic organization optimization suggestions based on the final demand flow rate, providing direct support for traffic management decisions and improving the practicality and operability of the evaluation results.

[0020] In the second aspect, an embodiment of the present application provides a multi-source fusion traffic demand flow rate assessment system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, and the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the multi-source fusion traffic demand flow rate assessment system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In the third aspect, an embodiment of the present application provides a computer program product comprising instructions. When the above-mentioned computer program product is run on a multi-source fusion traffic demand flow rate assessment system, the above-mentioned multi-source fusion traffic demand flow rate assessment system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0022] Fourthly, an embodiment of the present application provides a computer-readable storage medium, including instructions, which, when running on the multi-source fusion traffic demand flow rate evaluation system, cause the multi-source fusion traffic demand flow rate evaluation system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0023] It can be understood that the multi-source fusion traffic demand flow rate evaluation system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be elaborated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By adopting the above technical solution, the multi-source fusion traffic demand flow rate evaluation system fuses three types of data sources, namely intersection fixed detector data, intelligent network-connected sampling vehicle data, and signal control operation data, calculates the demand flow rate from four dimensions of section driving speed, signal control stop times, actual flow rate, and green start queuing vehicles, and determines the confidence level of the demand flow rate, effectively solving the problem of inaccurate evaluation of traffic demand flow rate by a single data source. The intersection fixed detector provides traffic flow data at fixed positions on the approach lanes of the intersection, the intelligent network-connected sampling vehicle provides driving data of vehicles on the approach lanes of the intersection, and the signal control operation data reflects the traffic organization constraints on the approach lanes of the intersection. The three complement each other's advantages. Through this multi-source fusion method, not only the section passing capacity reflected by the section driving speed is considered, but also the degree of traffic obstruction reflected by the signal control stop times is included, and the actual demand backlog situation reflected by the green start queuing vehicles is also included, so as to comprehensively and accurately evaluate the traffic demand flow rate.

[0025] 2. By adopting the above technical solution, the multi-source fusion traffic demand flow rate evaluation system calculates the first actual flow rate according to the average queuing length of the sampling vehicle, the standard queuing space between vehicles, the statistical duration, the average delay duration of the sampling vehicle, and a preset first actual flow rate calculation formula. Among them, the average queuing length of the sampling vehicle reflects the vehicle backlog situation on the approach lanes of the intersection, the standard queuing space between vehicles reflects the vehicle distribution density, and the average delay duration of the sampling vehicle characterizes the traffic efficiency on the approach lanes of the intersection. By organically combining these parameters, the actual passing capacity of the approach lanes of the intersection can be accurately depicted, making full use of the real-time positioning and status perception capabilities of vehicle networking communication devices, and having better dynamics and spatial continuity compared with traditional fixed detectors, so as to more accurately reflect the actual traffic flow operation state.

[0026] 3. By adopting the above technical solution, the multi-source fusion traffic demand flow rate evaluation system can calculate the second actual flow rate based on the data of fixed detectors at intersections, and can accurately calculate the actual traffic flow passing through the approach lanes of intersections. The fixed detectors are deployed at key positions on the approach lanes of intersections, can collect vehicle passing data all-weather and continuously, and have the advantages of good stability and wide coverage. This calculation method is simple and reliable, can be used as an effective supplement and verification for the data of intelligent networked sampling vehicles, and further improves the accuracy and reliability of demand flow rate evaluation. Description of the Drawings

[0027] Figure 1 is a schematic flowchart of a multi-source fusion traffic demand flow rate evaluation method in an embodiment of the present application; Figure 2 is another schematic flowchart of a multi-source fusion traffic demand flow rate evaluation method in an embodiment of the present application; Figure 3 is a schematic structural diagram of an entity device of a multi-source fusion traffic demand flow rate evaluation system in an embodiment of the present application. Detailed Embodiments

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. As used in the specification of the present application, the singular forms "a", "an", "the above", "the", and "this" are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term " / and" used in the present application refers to any or all possible combinations including one or more of the listed items.

[0029] Hereinafter, the terms "first" and "second" are only used for descriptive purposes, and cannot be construed as implying or indicating relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise stated, the meaning of "a plurality" is two or more.

[0030] The following is a process description of the method provided in this embodiment. Please refer to Figure 1 , which is a schematic flowchart of a multi-source fusion traffic demand flow rate evaluation method in an embodiment of the present application.

[0031] S101. Obtain the data of fixed detectors at intersections, the data of intelligent connected sampling vehicles, and the data of signal control operation. The data of fixed detectors at intersections refers to the traffic flow data collected by fixed detectors installed on the approach lanes of intersections. The data of intelligent connected sampling vehicles refers to the driving data of vehicles equipped with vehicle networking communication devices on the approach lanes of intersections. The data of signal control operation refers to the operation status data of signals controlling the approach lanes of intersections. The signal operation status data includes the signal control cycle, which is used to represent the duration for the signal to complete one cycle of the stage chain. Among them, the fixed detector at the intersection refers to the sensing device installed on the approach lane of the intersection for collecting traffic flow data, such as loop detectors, video detectors, etc. The intelligent connected sampling vehicle refers to a vehicle equipped with a vehicle networking communication device that can upload its driving data such as its position and speed in real time, such as taxis and buses equipped with on-vehicle terminals. The vehicle networking communication device refers to the device installed on the vehicle for realizing vehicle-to-vehicle and vehicle-to-road communication, such as on-board unit (OBU), etc. The data of signal control operation refers to the operation status information of signals controlling the approach lanes of intersections, including signal timing, phase switching, etc. The signal control cycle is used to represent the time required for the signal to complete a complete timing plan, usually several seconds.

[0032] Specifically, the multi-source fusion traffic demand flow rate evaluation system obtains traffic flow data such as traffic volume and vehicle speed from the fixed detectors on the approach lanes of intersections. These traffic flow data can reflect the overall traffic condition of the approach lanes of intersections. At the same time, the multi-source fusion traffic demand flow rate evaluation system obtains detailed data such as its driving trajectory and speed through the intelligent connected sampling vehicles in the approach lanes of intersections. These data can more accurately reflect the operation characteristics of the intelligent connected sampling vehicles. In addition, the multi-source fusion traffic demand flow rate evaluation system also needs to obtain the operation data of signals from the signal control system, including the current timing plan, phase status and other information. These operation data reflect the traffic capacity constraints on the approach lanes of intersections. By synchronously collecting these three types of data, the multi-source fusion traffic demand flow rate evaluation system can comprehensively grasp the traffic operation status of intersections.

[0033] The following are data indicators in the three data sources that can be listed: S102. Determine the road section driving speed, the first signal control stop times, and the first actual flow rate based on the data of the intelligent network-connected sampling vehicle, and determine the second signal control stop times, the second actual flow rate, and the queue vehicles at the beginning of the green phase based on the data of the fixed detector at the intersection. The road section driving speed is used to represent the average driving speed of the vehicles on the approach road of the intersection. The first signal control stop times and the second signal control stop times respectively represent the number of stop waits of the vehicles passing through the intersection on the approach road of the intersection due to waiting for the traffic lights, which are collected by the vehicle networking communication device and the fixed detector. The first actual flow rate and the second actual flow rate respectively represent the number of vehicles actually passing through per unit time on the approach road of the intersection, which are collected by the vehicle networking communication device and the fixed detector. The queue vehicles at the beginning of the green phase are used to represent the queue vehicles at the moment when the phase green light starts to light up on the approach road of the intersection. Among them, the road section driving speed refers to the average driving speed of the non-stationary state of the vehicle on the approach road of the intersection, usually in kilometers per hour; the signal control stop times refer to the number of stop waits of the vehicle passing through the intersection on the approach road of the intersection due to waiting for the traffic lights, which reflects the degree of traffic obstruction on the approach road of the intersection; the actual flow rate refers to the number of vehicles actually passing through per unit time on the approach road of the intersection, usually in vehicles per hour; the queue vehicles at the beginning of the green phase refer to the number of queue vehicles on the approach road of the intersection at the moment when the phase green light lights up, which reflects the demand backlog on the approach road of the intersection; the queue vehicles refer to the number of vehicles within the distance from the stop line to the last queue vehicle, expressed in meters.

[0034] Specifically, the steps for the multi-source fusion traffic demand flow rate evaluation system to calculate the road section driving speed, signal control stop times, actual flow rate, and queue vehicles at the beginning of the green phase are as follows: 1. Road section driving speed: It refers to the speed that satisfies the traffic flow density-speed following model, and a relatively regular driving interval in the middle of the approach road of the intersection can be selected. From the perspective of traffic organization, this driving interval should avoid places with channelization, lane splitting and merging, etc. where there are lane-changing impacts; from the perspective of dynamic signal control, this driving interval needs to avoid places where vehicles stop due to non-driving reasons such as signal control queue vehicles or other large boarding and alighting points, so that the vehicle driving speed is only affected by the vehicle density on the road section as much as possible. Take the time when the vehicle speed > 0 m / s in this driving interval as the driving time: Road section driving speed = detection interval length / interval driving time = detection interval length / (interval travel time - interval stop delay time).

[0035] Usually on the road section of traffic organization, the complete turning interval, that is, [from the upstream exit to the line, the exit lane line], can be directly used as the driving interval, and the time when the vehicle speed > 0 m / s during the vehicle passing through the driving interval is taken as the driving time.

[0036] 2. Actual Flow Rate: It refers to the number of vehicles actually passing through the approach of an intersection per unit time, which is one of the most accurate and measurable traffic signal control indicators, with the unit of veh / h. The only drawback is that it cannot represent the demand flow rate under oversaturated conditions. Therefore, it needs to be calibrated in combination with the number of signal-controlled stops to obtain the demand flow rate. There are mainly the following calculation methods for the actual flow rate: (1) The flow rate detected by induction loops or radar-vision per unit time can measure the actual flow rate relatively accurately. Generally, it is detected in units of lanes, and a representative lane can be selected within the turn as the turn-level indicator: Actual Flow Rate 1 = The flow rate detected by induction loops or radar-vision per unit time.

[0037] (2) If there is no traffic detector, the actual flow rate can be expressed by the actual capacity weighted by the number of signal-controlled stops. Among them, the default saturated flow rate = 1600 veh / h, and the saturated headway is 2.25 s. Then there is: Actual Flow Rate 2 = Actual Capacity × min(1, Number of Signal-Controlled Stops / (1 - Green Ratio)) = Green Ratio × Saturated Flow Rate × min(1, Number of Signal-Controlled Stops / (1 - Green Ratio)).

[0038] (3) If there is the ability to accurately detect the second-level queue similar to radar-vision, then the sum of the vehicles in the second-level queue per unit time is the stop delay time of all the vehicles passing through per unit time. There is: Actual Flow Rate 3 = Average Queue Vehicles × Unit Time / Average Delay Time of Sampling Vehicles.

[0039] When the penetration rate of intelligent network-connected sampling vehicles is relatively high and it has the ability to accurately detect vehicle queues, this method can also be used to approximately calculate the actual flow rate.

[0040] 3. Number of Signal-Controlled Stops: It refers to the number of times a vehicle stops and waits at the approach of an intersection due to waiting for the signal light. There are mainly the following calculation methods for the number of signal-controlled stops: (1) Approximate the number of signal-controlled stops by the number of times the speed of the sampling vehicle's trajectory point = 0 m / s: Number of Signal-Controlled Stops 1 = Average Number of Stops of Sampling Vehicles.

[0041] (2) By comparing the time when the speed of the sampling vehicle = 0 m / s during the driving interval with the signal control cycle of the approach of the intersection, a more accurate number of signal-controlled stops can be calculated: Number of Signal-Controlled Stops 2 = Average Stop Delay Time of Sampling Vehicles / Signal Control Cycle of the Intersection.

[0042] (3) Use the derived delay time to calculate the number of signal-controlled stops. If there is the ability to accurately detect the second-level queue by radar-vision, the following formula can be used to accurately estimate the average stop delay time: Derived Average Stop Delay Time = Average Queue Vehicles × Unit Time / Actual Flow Rate; The number of signal-controlled parking times 3 = Derived average parking delay time / Intersection signal control cycle.

[0043] When the penetration rate of intelligent connected sampling vehicles is relatively high, they have the ability to accurately detect vehicle queues, and this method can also be used to approximately calculate the number of signal-controlled parking times.

[0044] 4. Queue vehicles at the beginning of green: Refers to the number of queued vehicles on the approach road at the moment when the phase green light starts to illuminate, used to measure the traffic demand on the approach road during the signal control cycle, approximately the maximum queued vehicles: (1) The real-time queue vehicles detected by radar and vision at the second level at the moment when the green light starts to illuminate are a relatively accurate detection caliber: Queue vehicles at the beginning of green 1 = Queue vehicles when turning to the start of the green light.

[0045] If the intelligent connected sampling vehicle supports judging the start time of the green light and the penetration rate of the sampling vehicle is relatively high, the data of the intelligent connected sampling vehicle is also used to calculate the queue vehicles at the beginning of green by this method.

[0046] If the fixed detector does not meet the condition of matching the start time of the green light, the maximum queue length within a period of time is used, and the queue length at the moment when the green light starts to illuminate can also be approximated.

[0047] (2) It can be approximated by the actual flow rate and the number of signal-controlled parking times: Queue vehicles at the beginning of green 2 = (Actual flow rate / (Unit time / Signal control cycle)) × max(number of signal-controlled parking times, 1).

[0048] S103. Determine the first demand flow rate according to the driving speed of the road section, determine the second demand flow rate according to the first number of signal-controlled parking times or the second number of signal-controlled parking times and the first actual flow rate or the second actual flow rate, and determine the third demand flow rate according to the queue vehicles at the beginning of green and the signal control cycle; Among them, the first demand flow rate refers to the traffic demand flow rate evaluated based on the driving speed of the road section, reflecting the influence of the road section passing capacity on the demand flow rate; the second demand flow rate refers to the traffic demand flow rate evaluated based on the number of signal-controlled parking times and the actual flow rate, reflecting the constraint of signal control on the demand flow rate; the third demand flow rate refers to the traffic demand flow rate evaluated based on the queue vehicles at the beginning of green, reflecting the actual accumulated traffic demand.

[0049] Specifically, the steps for the multi-source fusion traffic demand flow rate evaluation system to calculate the first demand flow rate, the second demand flow rate, and the third demand flow rate are as follows: The demand flow rate is the number of vehicles turning at an intersection per unit time and is the main reference index for signal control decision-making. In the case of obvious multiple queues and delays, the demand flow rate is further divided into relative value and absolute value. When there are multiple vehicle queues and delays, the relative value will repeatedly count the queued vehicles, and the relative value can guide the adjustment direction of incremental plus or minus timing. The absolute value only counts the vehicles in multiple queues and delays once, that is, the actual flow rate plus the number of vehicles queued and delayed in the last cycle, which can measure the absolute value of the upper limit of traffic volume. When the statistical time is short (such as a single cycle) or there is no queuing and delay, the relative value and absolute value of the demand flow rate are not much different; when the statistical time is long (such as more than 1 hour) and there is queuing and delay, the relative value will be significantly greater than the absolute value because of the repeated calculation of the queued vehicles. The demand flow rate in this application is all relative values, and its calculation method is as follows: 1. Evaluate the demand flow rate using the road section driving speed: The "flow rate - density - speed" model is the "flow - density - speed" relationship of the road section derived based on the relationship between vehicle driving speed and following distance. Based on the theoretical relationship between indicators, analyzing the law of the detected sample values collected in actual operation can calibrate the parameters of the detected road section, and then the demand flow rate 1 can be calculated through the relationship between vehicle driving distance and vehicle driving speed: Demand flow rate 1 = saturation flow rate × (2 - actual driving speed / saturation flow rate speed) = saturation flow rate × 2 × (1 - actual driving speed / free flow speed).

[0050] Among them, saturation flow rate speed: refers to the speed rated value when the actual flow rate of the road section is the largest; free flow speed: refers to the speed rated value when the vehicle is not affected by upstream and downstream on the road and can drive unobstructed. By default, the free flow speed is 2 × saturation flow rate speed, and saturation flow rate: refers to the maximum flow rate rated value of the road section.

[0051] 2. Evaluate the demand flow rate using the actual flow rate and the number of signal control stops: Demand flow rate 2 = actual flow rate × compactness calibration coefficient × max (number of signal control stops / number of stops calibration coefficient, 1).

[0052] Among them, compactness calibration coefficient: equal to 1 / 0.85. This compactness calibration coefficient indicates that when the green light time is insufficient, the actual passing traffic flow will queue tightly, and the green light time will be relatively scarce, with a high green light utilization rate. Taking 0.85 as the upper limit of the normal range of green light utilization rate to cope with possible insufficient traffic capacity. Traffic demand flow rate = actual flow rate / 0.85.

[0053] Parking times calibration coefficient: equal to (1 - green ratio). This parking times calibration coefficient indicates that when the traffic flow arrives evenly, the expected value of the parking times is (1 - green ratio). If there are green wave or red wave vehicle platoons formed, there will be a certain deviation in the corresponding relationship between the signal-controlled parking times and the demand flow rate. Therefore, the parking times calibration coefficient of (1 - green ratio) is only applicable to the case of evenly arriving traffic flow. The parking times calibration coefficient defaults to 1 and is applicable to most scenarios.

[0054] 3. Use the vehicles queuing at the beginning of the green phase to evaluate the demand flow rate: Demand flow rate 3 = sum (number of vehicles queuing at the beginning of the cycle per unit time) = average number of vehicles queuing at the beginning of the green phase × (unit time / signal control cycle).

[0055] S104. Determine the confidence level of the demand flow rate according to the first demand flow rate, the second demand flow rate, and the third demand flow rate.

[0056] Among them, the confidence level of the demand flow rate refers to the reliability of the evaluation results of the demand flow rate in each dimension and is used to determine the weights of different evaluation dimensions.

[0057] Specifically, first, the multi-source fusion traffic demand flow rate evaluation system checks whether the characteristic parameters used in each dimension are complete, and reduces the confidence level for the missing or abnormal characteristic parameters accordingly. Then, the multi-source fusion traffic demand flow rate evaluation system evaluates the quality indicators of each data source, including the working status of the detector, the sampling vehicle coverage rate, the timeliness of the signal control data, etc. Next, the multi-source fusion traffic demand flow rate evaluation system calculates the correlation degree of the evaluation results in the three dimensions. The closer the results are, the more reliable the evaluation is. Finally, the multi-source fusion traffic demand flow rate evaluation system synthesizes these factors to determine a confidence level value for each dimension for subsequent weighted fusion calculations.

[0058] By adopting the above technical solutions, the multi-source fusion traffic demand flow rate evaluation system fuses three types of data sources: the data of fixed detectors at intersections, the data of intelligent network-connected sampling vehicles, and the data of signal control operation. It calculates the demand flow rate from four dimensions: the section driving speed, the signal-controlled parking times, the actual flow rate, and the vehicles queuing at the beginning of the green phase, and determines the confidence level of the demand flow rate, effectively solving the problem of inaccurate evaluation of traffic demand flow rate by a single data source. The fixed detectors at intersections provide traffic flow data at fixed positions on the approach roads of intersections. The intelligent network-connected sampling vehicles provide the driving data of vehicles on the approach roads of intersections. The signal control operation data reflects the traffic capacity constraints on the approach roads of intersections. The three complement each other's advantages. Through this multi-source fusion method, it not only considers the traffic capacity of the section reflected by the section driving speed, but also incorporates the degree of traffic obstruction reflected by the signal-controlled parking times, and also includes the actual demand backlog situation reflected by the vehicles queuing at the beginning of the green phase, so as to be able to comprehensively and accurately evaluate the traffic demand flow rate.

[0059] The following is a further and more specific process description of the method provided in this embodiment. Please refer to Figure 2 , which is another process schematic diagram of the multi-source fusion traffic demand flow rate evaluation method in the embodiment of the present application.

[0060] After step S104, the following steps may also be executed, or may not be executed, which is not limited herein: S201. According to the demand flow rate confidence, perform weighted fusion on the first demand flow rate, the second demand flow rate, and the third demand flow rate to obtain the final demand flow rate; Among them, weighted fusion refers to the process of comprehensively calculating multiple data according to different weights; the weight refers to the value obtained by normalizing the corresponding demand flow rate confidence, which is used to represent the importance degree of each dimension in the fusion; the final demand flow rate refers to the comprehensive evaluation result obtained after fusion, which reflects the actual traffic demand level on the approach lane of the intersection.

[0061] Specifically, first, the multi-source fusion traffic demand flow rate evaluation system normalizes the demand flow rates of the three dimensions to make them comparable; then, the multi-source fusion traffic demand flow rate evaluation system normalizes the demand rate confidence of each dimension to obtain the weight coefficient, and the dimension with a higher demand rate confidence obtains a larger weight coefficient. Next, the multi-source fusion traffic demand flow rate evaluation system performs weighted calculation on the demand flow rates of the three dimensions according to the weight coefficient to obtain the preliminary fusion result. Finally, the multi-source fusion traffic demand flow rate evaluation system calculates the fusion deviation and stability index. If the index is abnormal, the weight coefficient needs to be adjusted and re-fused until a stable and reliable final demand flow rate is obtained.

[0062] S202. Generate traffic organization optimization suggestions according to the final demand flow rate and the preset demand flow rate - traffic suggestion correspondence table.

[0063] Among them, the preset demand flow rate - traffic suggestion correspondence table refers to a list of traffic organization optimization measures corresponding to different demand flow rate intervals; the traffic organization optimization suggestion refers to the specific improvement measures given according to the current demand flow rate.

[0064] Specifically, first, the multi-source fusion traffic demand flow rate evaluation system compares the final demand flow rate with the preset demand flow rate threshold to determine the current traffic state level. Then, the multi-source fusion traffic demand flow rate evaluation system queries the preset demand flow rate - traffic suggestion correspondence table to obtain the list of candidate optimization measures at this traffic state level. Next, the preset demand flow rate - traffic suggestion correspondence table combines the actual conditions of the intersection to conduct a feasibility evaluation on each candidate optimization measure, including checking whether the execution conditions are met and evaluating the implementation effect, etc. Finally, the multi-source fusion traffic demand flow rate evaluation system sorts the feasible candidate optimization measures according to the priority to form traffic organization optimization suggestions including specific implementation steps and expected effects.

[0065] Among them, the key point of traffic organization optimization lies in diagnosing the reduction of the timed passing capacity caused by traffic organization. A typical case is the blocking and overflow phenomenon, that is, there is a situation of channelization, widening, straight-left diversion and blocking in the traffic organization. Specifically, if the left-turn or straight-going vehicles are long enough to block the channelized lane of the other party, resulting in the other party's vehicle being unable to pass through the intersection during its green light period, reducing the passing capacity of the traffic organization, and the actual flow rate << min(demand flow rate, timed passing capacity) occurs, it is considered that there is a risk of passing capacity deadlock in the actual operation of the traffic organization and rectification is required.

[0066] The multi-source fusion traffic demand flow rate evaluation system in the embodiment of the present invention application will be described from the perspective of hardware processing. Please refer to Figure 3 , which is a schematic structural diagram of an entity device of the multi-source fusion traffic demand flow rate evaluation system in the embodiment of the present application.

[0067] It should be noted that Figure 3 The structure of the multi-source fusion traffic demand flow rate evaluation system shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.

[0068] As Figure 3 shown, the multi-source fusion traffic demand flow rate evaluation system includes a CPU 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory ROM 302 or the program loaded from the storage section 308 into the random access memory RAM 303, such as executing the method described in the above embodiments. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, ROM 302, and RAM 303 are connected to each other via a bus 304. The I / O interface 305 is also connected to the bus 304.

[0069] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. The drive 310 is also connected to the I / O interface 305 as required. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as required so that the computer program read from it can be installed into the storage section 308 as required.

[0070] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 309, and / or installed from the removable medium 311. When the computer program is executed by the CPU 301, various functions defined in the present invention are executed.

[0071] It should be noted that specific examples of the computer-readable storage medium may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fibers, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings.

[0073] Specifically, the multi-source fusion traffic demand flow rate evaluation system of this embodiment includes a processor and a memory, and a computer program is stored on the memory. When the computer program is executed by the processor, the multi-source fusion traffic demand flow rate evaluation method provided in the above embodiment is implemented.

[0074] As another aspect, the present invention also provides a computer-readable storage medium, which may be included in the multi-source fusion traffic demand flow rate evaluation system described in the above embodiments; or may exist alone without being assembled into the multi-source fusion traffic demand flow rate evaluation system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the multi-source fusion traffic demand flow rate evaluation system, the multi-source fusion traffic demand flow rate evaluation system implements the multi-source fusion traffic demand flow rate evaluation method provided in the above embodiments.

[0075] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present application.

[0076] As used in the above embodiments, depending on the context, the term "when..." can be interpreted to mean "if...", or "after...", or "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if detecting (the stated condition or event)" can be interpreted to mean "if determining...", or "in response to determining...", or "when detecting (the stated condition or event)", or "in response to detecting (the stated condition or event)".

[0077] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware by a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. The foregoing storage medium includes: various media such as ROM or random access memory RAM, magnetic disk, or optical disc that can store program codes.

Claims

1. A multi-source fusion traffic demand flow rate evaluation method, characterized in that: Applied to a multi-source fusion traffic demand flow rate evaluation system, the method includes: Obtaining fixed detector data at the intersection, intelligent network sampling vehicle data, and signal light control operation data, wherein the fixed detector data at the intersection refers to traffic flow data collected by fixed detectors installed on the entrance road of the intersection, the intelligent network sampling vehicle data refers to driving data of vehicles equipped with vehicle networking communication equipment on the entrance road of the intersection, and the signal light control operation data refers to the operation status data of the signal light controlling the entrance road of the intersection, and the signal light operation status data includes a signal control cycle, which is used to indicate the duration of the signal light executing a stage chain; Determine the road section driving speed, the first signal control stop number and the first actual flow rate according to the data of the intelligent network sampling vehicle, determine the second signal control stop number, the second actual flow rate and the green initial queue vehicles according to the data of the fixed detector at the intersection, the road section driving speed is used to represent the average driving speed of vehicles on the entrance road of the intersection, the first signal control stop number and the second signal control stop number respectively represent the number of stops and waits caused by waiting for traffic lights at the entrance road of the intersection collected by the Internet of Vehicles communication equipment and the fixed detector, the first actual flow rate and the second actual flow rate respectively represent the number of flows actually passing through the entrance road of the intersection per unit time collected by the Internet of Vehicles communication equipment and the fixed detector, and the green initial queue vehicles are used to represent the queue length at the entrance road of the intersection when the phase green light is on; Determine a first demand flow rate according to the road section travel speed, determine a second demand flow rate according to the first signal control stop number or the second signal control stop number and the first actual flow rate or the second actual flow rate, and determine a third demand flow rate according to the green initial queue vehicles and the signal control period; A demand flow rate confidence level is determined based on the first demand flow rate, the second demand flow rate, and the third demand flow rate.

2. The method according to claim 1, characterized in that The first actual flow rate is determined according to the intelligent networked sampling vehicle data, wherein the intelligent networked sampling vehicle data includes the average queue length of the sampling vehicles within the statistical time, the average delay time of the sampling vehicles, and the standard queue distance of the vehicles, specifically including: Input the average queue length of the sampling vehicles, the standard queue distance between vehicles, the statistical duration, and the average delay duration of the sampling vehicles into a preset first actual flow rate calculation formula to obtain the first actual flow rate; The preset first actual flow rate calculation formula is: first actual flow rate = (average queue length of sampling vehicles / standard queue distance between vehicles) × statistical time / average delay time of sampling vehicles.

3. The method according to claim 2, characterized in that Determining a second actual flow rate according to the fixed detector data at the intersection specifically includes: Obtaining the total number of vehicles passing through the fixed detector within the statistical time period; The second actual flow rate is obtained according to the total number of vehicles, the passing interval time, and the number of lanes.

4. The method according to claim 1, characterized in that: The determining of the first required flow rate according to the road section travel speed specifically includes: Input the road section travel speed, saturated flow rate and saturated flow rate speed into a preset first demand flow rate calculation formula to obtain the first demand flow rate, wherein the saturated flow rate is used to represent the maximum flow rate rating on the entrance road of the intersection, and the saturated flow rate speed is used to represent the average travel speed of vehicles passing through the entrance road of the intersection when the saturated flow rate is reached; The preset first required flow rate calculation formula is: first required flow rate=saturated flow rate times×(2-actual driving speed / saturated flow rate speed).

5. The method according to claim 1, characterized in that The determining the second required flow rate according to the first signal-controlled stop number or the second signal-controlled stop number and the first actual flow rate or the second actual flow rate specifically includes: Inputting the first signal-controlled stop number or the second signal-controlled stop number, the first actual flow rate or the second actual flow rate, the compactness calibration coefficient, and the stop number calibration coefficient into a preset second demand flow rate calculation formula to obtain the second demand flow rate, the compactness calibration coefficient is used to represent the driving density of vehicles on the entrance road of the intersection, and the stop number calibration coefficient is used to represent the theoretical minimum stop number under the signal timing scheme; The preset second required flow rate calculation formula is: second required flow rate=actual flow rate×compactness calibration coefficient×max(signal control parking number / parking number calibration coefficient, 1).

6. The method according to claim 1, characterized in that The determining of the third demand flow rate according to the green initial queue vehicles and the signal control period specifically includes: Inputting the green initial queue vehicles and the signal control period into a preset third demand flow rate calculation formula to obtain the third demand flow rate; The preset third demand flow rate calculation formula is: third demand flow rate=green initial queue vehicles×(unit time / signal control cycle).

7. The method according to claim 1, characterized in that After the step of determining the demand flow rate confidence according to the first demand flow rate, the second demand flow rate and the third demand flow rate, the method further includes: According to the demand flow rate confidence, weighted fusion is performed on the first demand flow rate, the second demand flow rate and the third demand flow rate to obtain a final demand flow rate; According to the final demand flow rate and the preset demand flow rate-traffic suggestion correspondence table, a traffic organization optimization suggestion is generated.

8. A multi-source fusion traffic demand flow rate evaluation system, characterized in that: The multi-source fusion traffic demand flow rate assessment system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the multi-source fusion traffic demand flow rate assessment system to execute the method as described in any one of claims 1 to 7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a multi-source fusion traffic demand flow rate evaluation system, the multi-source fusion traffic demand flow rate evaluation system is enabled to execute the method as claimed in any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product runs on a multi-source fusion traffic demand flow rate evaluation system, the multi-source fusion traffic demand flow rate evaluation system is enabled to execute the method according to any one of claims 1 to 7.

Images