IVCPS traffic state detection spatial-temporal scale determination method and system

Abstract

The invention relates to an IVCPS traffic state detection space-time scale determination method and system, and belongs to the technical field of traffic state detection. The method comprises the following steps: acquiring space-time distribution data and traffic parameters of vehicles on a road, and preliminarily judging whether the traffic is in a normal running state or not; based on the obtained data, determining the minimum sample collection number in the current traffic state according to a confidence interval and a precision requirement; determining a time scale and a space scale of sampling under the minimum sample collection quantity; whether the change degree of the traffic state in the road exceeds a preset fluctuation range or not is judged, and if yes, the sampling space-time scale is adjusted; and adjusting the minimum sample collection number according to the adjusted sampling space-time scale, and re-determining the sampling space-time scale. According to the invention, the sampling strategy can be adjusted in real time, the data acquisition precision and frequency can be optimized, and the traffic state change on the road can be accurately captured, so that accurate data support is provided for urban traffic scheduling and management.

Description

Technical Field

[0001] The present invention belongs to the technical field of traffic state detection, and relates to a method and system for determining spatiotemporal scales of IVCPS traffic state detection. Background Art

[0002] With the development of electric vehicles, connected cars are increasingly entering our lives. The vehicle's speed, acceleration, operation, location and other information can be provided to the traffic management system through networking, forming an intelligent connected vehicle cyber-physical system (IVCPS), which provides convenience for refined traffic scheduling.

[0003] The state of traffic is affected by changes in the environment and weather, and often switches between free flow, unimpeded flow, congestion and other states. According to the principles of information theory, the frequency of data collection by the system is related to the degree of change of the system state. The higher the frequency of system change, the higher the sampling frequency required, and the more data required to be collected.

[0004] Traffic flow changes are random, and the optimal amount of data collection is determined by the traffic density, the length of the road section (spatial parameter), and the sampling time (temporal parameter). Determining the appropriate spatiotemporal scale method for IVCPS state detection is of great significance to optimizing the information collection granularity of IVCPS. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a method and system for determining the spatiotemporal scale of IVCPS traffic status detection, with the goal of ensuring information credibility and optimizing data scale, to determine the spatiotemporal scale of traffic data acquisition from the perspective of IVCPS, and to facilitate refined traffic scheduling.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] A method for determining the spatiotemporal scale of IVCPS traffic state detection is proposed. The method uses confidence intervals and accuracy requirements to determine the minimum sample collection requirements required for the current traffic state. According to the relationship between traffic flow density, speed, and flow, the required sampling space and time scale are determined under the premise of minimum sample collection.

[0008] Specifically, the method comprises the following steps:

[0009] S1. Obtain the spatiotemporal distribution data and traffic parameters of vehicles on the road, and preliminarily determine whether the traffic is in normal operation;

[0010] S2. Based on the acquired data, determine the minimum number of samples collected under the current traffic conditions according to the confidence interval and accuracy requirements;

[0011] S3. Determine the time scale and spatial scale of sampling under the minimum number of samples collected;

[0012] S4, judging whether the degree of change of the traffic state on the road exceeds the preset fluctuation range, and if so, adjusting the sampling time and space scale;

[0013] S5. Adjust the minimum sample collection quantity according to the adjusted sampling time and space scale, and re-determine the sampling time and space scale.

[0014] On the other hand, the present invention proposes an IVCPS traffic state detection spatiotemporal scale determination system, which comprises:

[0015] The data acquisition module is used to obtain the temporal and spatial distribution data and traffic parameters of vehicles on the road, and preliminarily determine whether the traffic operation status is normal;

[0016] A data extraction module, based on the data acquired by the data acquisition module, extracts parameters for determining the minimum sample collection quantity and parameters for determining the sampling time and space scale;

[0017] A sample quantity determination module is used to determine the minimum number of samples required for collection;

[0018] The sampling scale determination module determines the sampling spatiotemporal scale of traffic state detection based on the minimum sample collection quantity;

[0019] A sampling scale adjustment module, which determines whether the degree of change of the traffic state in the road exceeds a preset fluctuation range according to the data of the data acquisition module, and adjusts the sampling scale based on the judgment result;

[0020] The sample quantity optimization module redefines the minimum sample collection quantity based on the adjusted sampling scale.

[0021] Furthermore, under normal traffic operation conditions, the sample quantity determination module determines that the minimum number of sample collections required is:

[0022]

[0023] In the formula, n represents the minimum number of vehicle samples to be collected, represents the critical value of the standard normal distribution corresponding to the confidence level 1-α, α is the credibility, and γ represents the average speed of traffic flow. The relative error, σ v Represents the standard deviation of vehicle speed.

[0024] Under abnormal traffic operation conditions, the sample quantity determination module determines the minimum number of sample collection required as:

[0025]

[0026] Where n j represents the minimum number of vehicle samples required to be collected under abnormal state j, γ j The average speed of traffic flow is The relative error of q 95,j -q 5,j is the quantile difference, which indicates the range of data variation under the jth abnormal state.

[0027] The abnormal traffic operation status includes a light congestion state, a moderate congestion state and a severe congestion state.

[0028] Furthermore, under normal traffic operation conditions, the sampling time scale determined by the sampling scale determination module is:

[0029]

[0030] In the formula, Q represents the traffic flow;

[0031] The determined sampling space scale is:

[0032]

[0033] In the formula, K represents the traffic density;

[0034] Under abnormal traffic operation conditions, the sampling time scale determined by the sampling scale determination module is:

[0035]

[0036] The determined sampling space scale is:

[0037]

[0038] Furthermore, in the sample quantity optimization module, the minimum number of sample collection required is re-determined based on the adjusted sampling time and space scale;

[0039] Establish the minimum number of samples n and the sampling time scale T S and the sampling space scale L S The mathematical relationship is expressed as:

[0040]

[0041] Under normal traffic conditions, the minimum number of samples collected is re-determined as:

[0042]

[0043] Under abnormal traffic conditions, the minimum number of samples collected is re-determined as:

[0044]

[0045] The beneficial effects of the present invention are as follows: the present invention adjusts the sampling time and space scale by detecting the degree of change of traffic conditions, and then adjusts the minimum number of sample collection. Through a closed-loop adjustment process, the cloud server can adjust the sampling strategy in real time, optimize the accuracy and frequency of data collection, and ensure that the traffic management system can accurately capture changes in traffic conditions on the road, thereby providing accurate data support for urban traffic scheduling and management.

[0046] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:

[0048] Figure 1 A schematic diagram of the process of the method proposed in the present invention;

[0049] Figure 2 It is the input and output structure diagram of the sampling scale determination module;

[0050] Figure 3 The figure is a schematic diagram of an application scenario of the method described in the present invention. DETAILED DESCRIPTION

[0051] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0052] In IVCPS, roadside equipment and vehicle-mounted equipment work together to detect traffic conditions on the road in real time, such as Figure 3As shown in the figure, when a vehicle passes through an urban road, the roadside equipment (such as cameras and radars installed on both sides of the road) is responsible for monitoring the dynamic behavior of the vehicle and capturing various traffic parameters of the vehicle, including but not limited to the vehicle speed, traffic density, vehicle spacing, etc. The collected monitoring data is transmitted to the cloud server through the communication network. The cloud server analyzes the data from the roadside equipment and calculates the optimal spatiotemporal scale parameters, which determine the time interval and spatial resolution of subsequent data collection. The calculated spatiotemporal scale parameters are fed back to the roadside equipment through the communication network, so that the roadside equipment can dynamically adjust its monitoring strategy according to the current traffic conditions, such as sampling frequency and monitoring range. When the vehicle is driving on the road, the on-board equipment can also send the real-time data of the vehicle directly to the cloud server through the network. These data are combined with the data collected by the roadside equipment to provide the cloud server with more comprehensive traffic status information. After receiving the real-time data from the vehicle and roadside equipment, the cloud server will conduct a more detailed analysis of the traffic flow and promptly feedback the adjusted spatiotemporal scale parameters to ensure that the system can respond in time when the traffic conditions change.

[0053] Through the above-mentioned closed-loop control process, the cloud server can adjust the sampling strategy in real time, optimize the accuracy and frequency of data collection, and ensure that the traffic management system can accurately capture changes in traffic conditions on the road, thereby providing accurate data support for urban traffic scheduling and management.

[0054] An embodiment of the present invention proposes a method for determining the spatiotemporal scale of IVCPS traffic state detection, with the goal of ensuring information credibility and optimizing data scale, determining the spatiotemporal scale of traffic data acquisition from the perspective of IVCPS, and realizing the above-mentioned closed-loop control process.

[0055] Specifically, Figure 1 As shown, the method is as follows:

[0056] 1. Obtain vehicle traffic data in urban road environments and extract the data required to determine the time and space scale from the acquired data

[0057] By obtaining the spatiotemporal distribution data and traffic parameters (including vehicle speed, acceleration, position and other parameters) of vehicles on urban roads, a preliminary judgment can be made as to whether the traffic is in normal operation.

[0058] When traffic is in normal operation, combined with experience and research in the field, vehicle speed generally follows the normal distribution, as shown below:

[0059]

[0060] Through standardization, we can get:

[0061]

[0062] For a confidence interval with a confidence level of 1-α, the interval is expressed as:

[0063]

[0064] in, is the sample mean speed, which represents the average of all sample vehicle speeds; The critical value of the standard normal distribution corresponding to the confidence level 1-α, used to estimate the reliability of the results; σ v is the standard deviation of vehicle speed, indicating the degree of dispersion of sample data.

[0065] Under the same confidence level, the smaller the confidence interval, the higher the accuracy of the estimated value. Half the length of the confidence interval is the acceptable sampling error Δv, so the confidence interval can also be expressed as 2Δv, then:

[0066]

[0067] The requirement for the number of samples can be obtained as follows:

[0068]

[0069] Generally, the error requirement is related to the speed. If the speed of the stable traffic flow is The required relative error is γ, that is, the proportional error between the estimated value and the actual value allowed is:

[0070]

[0071] Then we have:

[0072]

[0073] After the confidence level and relative error are determined, the size of the sample is It is proportional to the square of. Obviously, the larger the speed variation range, the larger the number of samples required.

[0074] When the data of traffic under abnormal operation does not necessarily obey the normal distribution, it may present asymmetric or skewed distribution data. This embodiment adopts the quantile method to determine the sampling scale, and uses the variation range of the data, that is, the quantile difference, to replace the standard deviation. The quantile method does not rely on the assumption of normal distribution. The main idea is to observe the extreme values ​​of the data and use the actual distribution of the sample data (that is, the quantile) to ensure the accuracy of the sampling.

[0075]

[0076] Among them, q 95,j -q 5,jis the quantile difference, which indicates the range of data variation under the jth abnormal state; The coefficient γ for adjusting the confidence level j The allowable relative error determines the tolerance of the error; It is the average speed under abnormal conditions and is used for standardization.

[0077] 2. If Figure 2 As shown, the sampling time and space scale is determined

[0078] (1) Determination of spatial scale

[0079] Assume the length of the sampling section is L S , the number of collected vehicles is n, and the traffic density is K, where:

[0080] n=KL S (9)

[0081] Combining equations (7) and (8), the spatial scale under normal operation is obtained as follows:

[0082]

[0083] The spatial scale under abnormal operation state is obtained as follows:

[0084]

[0085] (2) Determination of time scale

[0086] Assume the sampling time interval is T S , the number of collected vehicles is n, and the traffic flow is Q, where:

[0087] n=QT S (12)

[0088] The time scale under normal operating conditions is:

[0089]

[0090] The time scale in abnormal state is:

[0091]

[0092] 3. Decisions on the adjustment of sampling scale

[0093] Under normal conditions, traffic flow and vehicle speed usually remain in a relatively stable range with small fluctuations. Therefore, in order to reduce unnecessary adjustments, a relatively loose adjustment decision threshold can be set.

[0094] For example, under normal conditions, the fluctuation range of vehicle speed is usually within 5%, and the threshold of vehicle speed fluctuation can be set to ±5%. That is, when the real-time detected vehicle speed changes within this range, the system will consider that the traffic status is still normal and there is no need to adjust the sampling scale. For traffic fluctuations, the threshold is set to ±10%. For example, if the normal traffic flow of a road is 1,000 vehicles per hour, when the real-time detected traffic flow is between 900 and 1,100 vehicles, the system will keep the current sampling scale unchanged.

[0095] When traffic enters an abnormal state, the system needs to capture changes in traffic conditions more finely to provide more accurate data support. At this time, the threshold needs to be set more strictly. Under abnormal conditions, such as minor congestion or accidents, the fluctuation range of vehicle speed will usually increase, but in order to capture abnormal conditions in a timely manner, the threshold can be set to a fluctuation of 1-2%. For example, in a state of minor congestion, if the vehicle speed drops by more than 2% (such as from 60km / h to 58.8km / h), the system's sampling scale adjustment mechanism will be triggered. When traffic suddenly increases or decreases by more than a set threshold (for example, ±5%), this usually indicates that traffic conditions have changed significantly, and the system needs to re-evaluate the sampling frequency and spatial scale to adapt to the new traffic conditions.

[0096] In order to deal with different degrees of traffic anomalies, the abnormal state can be divided into multiple levels, each level corresponds to a different threshold and response strategy. For example, the abnormal state can be divided into "mild congestion", "moderate congestion" and "severe congestion", and the threshold setting for each level is shown in Table 1:

[0097] Table 1

[0098]

[0099] When it is detected that the traffic state changes from a normal state to a certain level of abnormal state, the sampling strategy of the spatiotemporal scale of traffic state detection is immediately adjusted.

[0100] The adjustment has the following characteristics:

[0101] 1) Quick adjustment: When the threshold is triggered, the sampling parameters are adjusted immediately to ensure the timeliness of data collection;

[0102] 2) Feedback: By analyzing the adjusted data, the threshold setting is further optimized to ensure a more accurate response to changes in traffic conditions in the future;

[0103] 3) Multi-level response: Provide different levels of response for different levels of abnormal conditions. For example, in case of mild congestion, only the sampling frequency is adjusted, while in case of severe congestion, both the frequency and spatial resolution are adjusted.

[0104] 4. Based on the extracted data, from a statistical perspective, the number of samples is determined by optimizing the spatiotemporal scale parameters.

[0105] When calculating the minimum sample size, the complexity and accuracy requirements of the traffic detection system are taken into consideration, the time scale and spatial scale are included as constraints, and the sampling number is iteratively optimized to establish a direct mathematical relationship between the sample size and these two parameters. This can enhance the close connection between the sample size and the time and space scales, and help optimize the detection accuracy and resource utilization efficiency of the entire system.

[0106] Among them, the time scale constraint condition is: define the time scale T S and traffic flow Q

[0107] Assume that the time scale is T S The vehicles are sampled for a period, and the number of samples is n. The relationship between the number of samples and the time scale can be described by the following inequality:

[0108]

[0109] Spatial scale constraint: Define the spatial scale L S and traffic density K

[0110] Assume that the spatial scale is L S The vehicles are sampled periodically, and the number of samples is n. The relationship between the number of samples and the spatial scale can be described by the following inequality:

[0111]

[0112] After introducing the above time scale and space scale constraints, the minimum sample number n can be redefined as the function g(T S ,L S ), when traffic is in normal operation:

[0113]

[0114] When traffic is in an abnormal state:

[0115]

[0116] In another embodiment of the present invention, a system for determining spatiotemporal scales of traffic state detection is provided, the system comprising:

[0117] The data acquisition module is used to obtain the temporal and spatial distribution data and traffic parameters of vehicles on urban roads, and preliminarily determine whether the traffic is in a normal operating state;

[0118] A data extraction module is used to screen and determine key data and traffic parameters for determining the spatiotemporal scale of traffic state detection, and to screen and determine parameters for determining the number of sample collection;

[0119] A sample quantity determination module determines the number of samples that need to be collected;

[0120] A sampling scale determination module determines the sampling time scale (sampling frequency) and spatial scale (sampling resolution) based on the determined number of samples;

[0121] The sampling scale adjustment module is used to describe the severity of changes in traffic conditions on urban roads, and determine whether it is necessary to redefine the sampling time and space scale based on a pre-set reasonable fluctuation range, and generate results;

[0122] The sample quantity optimization module re-determines the number of samples according to the adjusted sampling scale.

[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. An IVCPS traffic state detection spatiotemporal scale determination system, characterized by: The system includes: The data acquisition module is used to obtain the temporal and spatial distribution data and traffic parameters of vehicles on the road, and preliminarily determine whether the traffic operation status is normal; A data extraction module, based on the data acquired by the data acquisition module, extracts parameters for determining the minimum sample collection quantity and parameters for determining the sampling time and space scale; A sample quantity determination module is used to determine the minimum number of samples required for collection; The sampling scale determination module determines the sampling spatiotemporal scale of traffic state detection based on the minimum sample collection quantity; a sampling scale adjustment module, which determines whether the degree of change of the traffic state in the road exceeds a preset fluctuation range according to the data of the data acquisition module, and adjusts the sampling scale based on the determination result; and The sample quantity optimization module redefines the minimum sample collection quantity based on the adjusted sampling scale.

2. The system according to claim 1, characterized in that: Under normal traffic operation conditions, the sample quantity determination module determines the minimum number of sample collections required as: In the formula, n represents the minimum number of vehicle samples to be collected, represents the critical value of the standard normal distribution corresponding to the confidence level 1-α, α is the credibility, and γ represents the average speed of traffic flow. The relative error, σ v Represents the standard deviation of vehicle speed. Under abnormal traffic operation conditions, the sample quantity determination module determines the minimum number of sample collection required as: Where n j represents the minimum number of vehicle samples required to be collected under abnormal state j, γ j The average speed of traffic flow is The relative error of q 95,j -q 5,j is the quantile difference, which indicates the range of data variation under the jth abnormal state.

3. The system according to claim 2, characterized in that: The abnormal traffic operation state includes a light congestion state, a moderate congestion state and a severe congestion state.

4. The system according to claim 1, characterized in that: Under normal traffic operation conditions, the sampling time scale determined by the sampling scale determination module is: In the formula, Q represents the traffic flow; The determined sampling space scale is: In the formula, K represents the traffic density; Under abnormal traffic operation conditions, the sampling time scale determined by the sampling scale determination module is: The determined sampling space scale is:

5. The system according to claim 1, characterized in that: In the sample quantity optimization module, the minimum number of sample collection required is re-determined based on the adjusted sampling time and space scale; Establish the minimum number of samples n and the sampling time scale T S and the sampling space scale L S The mathematical relationship is expressed as: Under normal traffic conditions, the minimum number of samples collected is re-determined as: Under abnormal traffic conditions, the minimum number of samples collected is re-determined as:

6. A method for determining the spatiotemporal scale of IVCPS traffic state detection, characterized by: Obtain the spatiotemporal distribution data and traffic parameters of vehicles on the road, and make a preliminary judgment on whether the traffic is in normal operation; Based on the acquired data, determine the minimum number of samples collected under the current traffic conditions according to the confidence interval and accuracy requirements; Determine the temporal and spatial scales of sampling with the minimum number of samples collected; Determine whether the degree of change in the traffic status on the road exceeds the preset fluctuation range, and adjust the sampling time and space scale based on the judgment result; The minimum number of samples collected is adjusted according to the adjusted sampling time and space scale, and the sampling time and space scale is re-determined.

7. The method according to claim 6, characterized in that: The minimum sample collection quantity is determined as follows: 1) Under normal traffic conditions, the speed of vehicles on the road follows a normal distribution; for a confidence interval with a confidence level of 1-α, the interval is expressed as: In the formula, represents the sample mean speed, which is the average of all sample vehicle speeds; The critical value of the standard normal distribution corresponding to the confidence level 1-α is used to estimate the reliability of the results; σ v It represents the standard deviation of vehicle speed and the degree of discreteness of sample data. Under the same confidence level α, the smaller the confidence interval, the higher the accuracy of the estimated value. Half the length of the confidence interval is the acceptable sampling error Δv. Therefore, the confidence interval is expressed as 2Δv, and then: The requirement for the number of samples is: The error requirement is related to the speed. If the speed of the stable traffic flow is The required relative error is γ, that is, the proportional error between the estimated value and the actual value allowed is: The minimum number of samples collected is: 2) Under abnormal traffic conditions, vehicle speeds present an asymmetric or skewed distribution. Therefore, the quantile method is used to determine the minimum number of sample collections. The data variation range, i.e., the quantile difference, is used to replace the standard deviation. The minimum number of sample collections is expressed as: In the formula, q 95,j -q 5,j is the quantile difference, which indicates the range of data variation under the jth abnormal state; The coefficient γ for adjusting the confidence level j The allowable relative error determines the tolerance of the error; It is the average speed under abnormal conditions and is used for standardization.

8. The method according to claim 6, characterized in that: Based on the minimum number of samples collected under normal traffic operation conditions, the sampling time scale is determined as: In the formula, Q represents the traffic flow; the sampling space scale is determined as: In the formula, K represents the traffic density; Based on the minimum number of samples collected under abnormal traffic conditions, the sampling time scale is determined as: Determine the sampling space scale as:

9. The method according to claim 6, characterized in that: Under normal traffic conditions, after adjusting the sampling scale, the minimum number of samples collected is adjusted to: Under abnormal traffic conditions, the minimum number of samples collected is adjusted as follows:

Images