System and method for dynamically adjusting traffic load

Abstract

The invention discloses a system and a method for determining dynamic regulation priority of traffic load. The system collects multi-dimensional traffic data of traffic flow, vehicle speed, vehicle type, road condition and weather condition in real time, performs analysis based on the data, predicts future traffic load in combination with an adaptive neural fuzzy inference system, and calculates a dynamic adjustment priority. The data analysis module carries out processing and trend analysis on the collected traffic data, and provides a basis for load prediction. And the traffic load prediction module predicts the future traffic load by using an ANFIS model based on the analysis result, and calculates the regulation and control priority in combination with the Factor1 and the Factor2. According to the calculated priorities, a basis can be provided for traffic management decisions so as to guide traffic signal control and lane distribution. Through the method, real-time and accurate priority judgment can be provided for traffic management, traffic congestion can be effectively relieved, and use of road resources can be optimized.

Description

Technical Field

[0001] The present invention relates to the field of traffic management, and in particular to a system and method for dynamically adjusting traffic load. Background Art

[0002] With the acceleration of urbanization, traditional traffic management methods rely on fixed signal cycles and lane allocations, which are unable to cope with real-time changes in traffic flow, vehicle speed and road conditions, resulting in inefficient traffic and increased congestion.

[0003] To meet this challenge, intelligent transportation systems provide decision support by real-time monitoring and analysis of multi-dimensional traffic data. However, existing methods usually only focus on a single factor and lack a comprehensive dynamic adjustment mechanism. To this end, the present invention proposes a dynamic adjustment method based on multi-dimensional traffic data analysis, which can flexibly adjust traffic signals and lane allocation, thereby improving traffic efficiency and alleviating congestion. Summary of the invention

[0004] To solve the problems raised in the background technology, the present invention provides a system and method for dynamically adjusting traffic load, which is used to determine the regulation priority of traffic flow, so as to optimize traffic signal control, lane allocation and the use of road resources, alleviate traffic congestion and improve the efficiency of traffic flow.

[0005] The present invention provides a system for regulating traffic flow load, the system comprising:

[0006] Data collection unit, used to collect traffic flow data in real time, including traffic volume, number of vehicles, vehicle type, road conditions, and weather conditions;

[0007] Control unit: used to intelligently infer control priority strategies based on collected data and preset algorithms;

[0008] Execution unit: used to execute the decisions of the control unit to balance the traffic flow load.

[0009] Furthermore, the control unit comprises:

[0010] Data analysis module: used to process and analyze the collected traffic data and identify the real-time trend of traffic flow;

[0011] Traffic load prediction module: Based on the data analysis results, the adaptive neuro-fuzzy inference system (ANFIS) is used to predict the future traffic load.

[0012] Traffic load control module: adjusts traffic flow load according to the results of the traffic load prediction module.

[0013] Furthermore, the traffic load prediction module adopts the following mathematical model, which is expressed as follows:

[0014] (1) Factor 1

[0015] Factor1=ANFIS(Flow, Speed, Vehicle Type Index)

[0016] (2) Factor 2

[0017] Factor2=ANFIS(Road Condition Index, Weather Condition Index)

[0018] (3) Regulation priority

[0019]

[0020] in:

[0021] Flow represents traffic flow, Speed ​​represents vehicle speed, and Vehicle Type Index represents the standardized value of vehicle type;

[0022] Priority indicates the control priority;

[0023] The Road Condition Index indicates the road conditions, and the Weather Condition Index indicates the standardized index of weather conditions.

[0024] Furthermore, the traffic load control module adopts the following mathematical model, which is expressed as follows:

[0025] (1) Objective function

[0026]

[0027] (2) Traffic signal control and lane assignment constraints

[0028]

[0029] (3) Lane assignment constraints

[0030] L ij <L max

[0031] in:

[0032] T ij The traffic travel time from intersection i to intersection j.

[0033] N is the number of intersections.

[0034] M is the number of possible destinations.

[0035] L ij The number of lanes from intersection i to intersection j,

[0036] L max The maximum number of lanes for the road.

[0037] C i Traffic signal cycle at intersection i.

[0038] T total The total time specified.

[0039] The present invention provides a method for dynamically adjusting traffic load, the method comprising the following steps:

[0040] S1: Real-time monitoring of traffic flow data;

[0041] S2: Based on the standardized index of road conditions, the standardized index of weather conditions, the standardized values ​​of traffic flow, vehicle speed and vehicle type, Factor 1 and Factor 2 are derived respectively, and the priority of regulation is determined by the results of Factor 1 and Factor 2;

[0042] S3: Dynamically adjust according to the result determined by S2 and the traffic flow conditions.

[0043] Beneficial effects:

[0044] The present invention realizes accurate prediction of traffic load and dynamic determination of adjustment priority by combining adaptive neural fuzzy inference system (ANFIS) with multi-dimensional traffic data. Compared with traditional traffic management methods, the present invention can monitor multiple factors such as traffic flow, vehicle speed, vehicle type, road conditions and weather conditions in real time, and conduct effective analysis based on these data, thereby providing a scientific basis for traffic control. By predicting traffic load and calculating control priority, the present invention can dynamically adjust traffic signal cycle and lane allocation according to changes in actual traffic flow, optimize the use of road resources, alleviate traffic congestion, and improve traffic smoothness. At the same time, since the present invention does not involve a specific control scheme, but provides a basis for priority determination, it has good flexibility and can be customized according to the needs of different regions and traffic conditions. In addition, the use of the ANFIS model for load prediction not only improves the accuracy of the prediction, but also effectively copes with complex and uncertain traffic environments, providing strong support for the further development of intelligent transportation systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 for the invention flow chart;

[0046] Figure 2 This is the schematic diagram of the fuzzy rule of Factor1;

[0047] Figure 3 It is the schematic diagram of Factor2 fuzzy rules;

[0048] Figure 4 Derive the Priority rule graph for Factor1 and Factor2. Specific implementation plan

[0049] The following is a specific implementation example to show how the method of the present invention is applied in actual traffic flow. The following implementation examples are only for illustrating the technical concept and features of the invention. The purpose is to enable people familiar with the technology to understand the content of the invention and implement it accordingly. It cannot be used to limit the protection scope of the present invention. Any equivalent or modification made according to the spirit of the present invention should be included in the protection scope of the present invention.

[0050] This embodiment provides a system for dynamic control of traffic flow load, including a data collection unit, a control unit and an execution unit;

[0051] Data collection unit, used to collect traffic flow data in real time, including traffic volume, number of vehicles, vehicle type, road conditions, and weather conditions;

[0052] Control unit: used to intelligently infer control priority strategies based on collected data and preset algorithms;

[0053] Execution unit: used to execute the decisions of the control unit to balance the traffic flow load.

[0054] The data collection unit is mainly used to collect various attributes in traffic flow.

[0055] The data collection frequency is once per minute.

[0056] The collected raw data needs to be preprocessed.

[0057] This embodiment proposes a method for dynamically adjusting traffic load. The specific process is as follows: Figure 1 As shown, the method comprises the following steps:

[0058] S1: Real-time monitoring of traffic flow data;

[0059] S2: Based on the standardized index of road conditions, the standardized index of weather conditions, the standardized values ​​of traffic flow, vehicle speed and vehicle type, Factor 1 and Factor 2 are derived respectively, and the priority of regulation is determined by the results of Factor 1 and Factor 2;

[0060] S3: Dynamically adjust according to the result determined by S2 and the traffic flow conditions.

[0061] In this embodiment, the preprocessing step includes:

[0062] S201: Data filling: To ensure that the data are of the same time scale, missing data are filled.

[0063] S202: Data cleaning: remove outliers and noise to ensure data reliability.

[0064] S203: Data standardization: Convert data of different dimensions into a unified dimension to facilitate subsequent processing.

[0065] S204: Feature extraction: extracting features that have an important impact on traffic flow load regulation from the original data.

[0066] In S201, the present invention has two solutions for dealing with data loss:

[0067] (1) When data at a certain moment is missing, the present invention uses the weighted average of the data at the previous and next moments to fill in the missing data.

[0068] (2) When data for a certain period of time is missing, the present invention uses the Lagrange interpolation method to fill in the missing data.

[0069] In S202, the present invention adopts wavelet transform to remove noise components.

[0070] In S203, the present invention adopts minimum-maximum normalization for standardization.

[0071] In S204, the features extracted by the present invention include standardized values ​​of traffic flow, standardized values ​​of vehicle speed, standardized values ​​of vehicle type, standardized values ​​of road conditions, standardized values ​​of weather conditions, standardized values ​​of traffic travel time, number of intersections, number of possible destinations, traffic signal cycle, total specified time, number of lanes, etc. Figure 2 , Figure 3 shown.

[0072] The standardized value of vehicle type is calculated by calculating the proportion of heavy vehicles in the traffic flow. The smaller the proportion of heavy vehicles in the traffic flow, the greater the proportion of small and medium-sized vehicles in the traffic flow. The following formula is used for calculation:

[0073]

[0074] The preprocessed data is stored in the database for historical data analysis and long-term trend prediction.

[0075] In this system, ANFIS (Adaptive Neuro-Fuzzy Inference System) is integrated into the data analysis and prediction module to extract long-term trends from the pre-processed historical data.

[0076] The formula for constructing the traffic load prediction module is as follows:

[0077] (1) Factor 1

[0078] Factor1=ANFIS(Flow, Speed, Vehicle Type Index)

[0079] (2) Factor 2

[0080] Factor2=ANFIS(Road Condition Index, Weather Condition Index)

[0081] (3) Regulation priority

[0082]

[0083] Among them, Flow, Speed ​​and Vehicle Type Index represent the standardized values ​​of traffic flow, vehicle speed and vehicle type, Road Condition Index and Weather Condition Index represent the standardized indexes of road conditions and weather conditions. Priority represents the control priority.

[0084] The purpose of this step is to distinguish the priority of regulation. Factor1 and Factor2 are formulated to derive the regulation priority, which is expressed by Priority.

[0085] Among them, Factor1 is factor 1, which is derived from the standardized value of traffic flow, the standardized value of vehicle speed, and the standardized value of vehicle type; Factor2 is factor 2, which is derived from the standardized value of road conditions and the standardized value of weather conditions.

[0086] After Factor1 and Factor2 are introduced, the regulation priority can be jointly introduced by Factor1 and Factor2.

[0087] The fuzzy rules designed to introduce Factor1 are as follows:

[0088] 1. If the traffic flow normalized value is low, the speed normalized value is low, the vehicle type normalized value is low, and Factor1 is low;

[0089] 2. If the traffic flow normalization value is low, the speed normalization value is high, the vehicle type normalization value is low, and Factor1 is medium;

[0090] 3. If the traffic flow normalization value is low, the vehicle speed normalization value is low, the vehicle type normalization value is high, and Factor1 is medium;

[0091] 4. If the traffic flow normalization value is low, the speed normalization value is high, the vehicle type normalization value is high, and Factor1 is medium;

[0092] 5. If the traffic flow normalized value is high, the speed normalized value is high, the vehicle type normalized value is high, and Factor1 is high;

[0093] 6. If the traffic flow normalization value is high, the speed normalization value is low, the vehicle type normalization value is high, and Factor1 is medium;

[0094] 7. If the traffic flow normalization value is high, the speed normalization value is high, the vehicle type normalization value is low, and Factor1 is medium;

[0095] 8. If the traffic flow normalization value is high, the speed normalization value is low, the vehicle type normalization value is low, and Factor1 is medium;

[0096] Its fuzzy formula is described as follows:

[0097]

[0098] The fuzzy rules designed to introduce Factor2 are as follows:

[0099] 1. If the normalized index of road conditions is low and the normalized index of weather conditions is low, then Factor 2 is low.

[0100] 2. If the normalized index of road conditions is low and the normalized index of weather conditions is medium, then Factor 2 is medium.

[0101] 3. If the normalized index of road conditions is low and the normalized index of weather conditions is medium, then Factor 2 is medium.

[0102] 4. If the normalized index of road conditions is medium and the normalized index of weather conditions is low, then Factor 2 is low.

[0103] 5. If the normalized index of road conditions is medium and the normalized index of weather conditions is medium, then Factor 2 is medium.

[0104] 6. If the normalized index of road conditions is medium and the normalized index of weather conditions is high, then Factor 2 is medium.

[0105] 7. If the normalized index of road conditions is high and the normalized index of weather conditions is high, then Factor 2 is high.

[0106] 8. If the normalized index of road conditions is high and the normalized index of weather conditions is medium, then Factor 2 is medium.

[0107] 9. If the normalized index of road conditions is high and the normalized index of weather conditions is low, Factor 2 is low.

[0108] Its fuzzy formula is described as follows:

[0109]

[0110] The inferred Factor1 and Factor2, when both Factor1 and Factor2 are low, it means that the traffic flow load is in a low state and needs to be adjusted first, otherwise it does not need to be adjusted first. The rules for deriving the control priority of Factor1 and Factor2 are as follows Figure 4 The specific rules are as follows:

[0111] 1. If Factor1 is low and Factor2 is low, the priority is high.

[0112] 2. If Factor1 is low and Factor2 is medium, the priority is medium.

[0113] 3. If Factor1 is low and Factor2 is high, the priority is medium.

[0114] 4. If Factor1 is medium and Factor2 is low, the priority is medium.

[0115] 5. If Factor1 is medium and Factor2 is medium, then the priority is medium.

[0116] 6. If Factor1 is medium and Factor2 is high, the priority is medium.

[0117] 7. If Factor1 is high and Factor2 is low, the priority is medium.

[0118] 8. If Factor1 is high and Factor2 is medium, the priority is medium.

[0119] 9. If Factor1 is high and Factor2 is high, the priority is low.

[0120] This step is to determine the priority order of dynamic regulation of traffic flow load.

[0121] After obtaining the control priority, the road traffic load control module is used.

[0122] The mathematical model used by the traffic load control module is as follows:

[0123] (1) Objective function

[0124]

[0125] (2) Traffic signal control and lane assignment constraints

[0126]

[0127] (3) Lane assignment constraints

[0128] L ij <L max

[0129] Among them, T ij is the traffic travel time from intersection i to intersection j, N is the number of intersections. M is the number of possible destinations. L ij is the number of lanes from intersection i to intersection j, L max is the maximum number of lanes on the road. C i is the traffic signal cycle of intersection i. total is the total time specified.

[0130] The objective function is to minimize the total congestion time and achieve load balance among multiple intersections; the constraint condition is that each intersection has a traffic signal cycle, and the sum of the cycles of each intersection should be equal to the total time of the specified time; the constraint of lane allocation is that the number of lanes must meet a certain limit, and the lane allocation of each intersection needs to consider the balance of load. Only when the constraints are met and implemented according to the objective function can the dynamic balance control of traffic load be achieved.

[0131] The execution unit is used to execute the decisions of the control unit and regulate traffic flow. The system execution unit consists of multiple subsystems, mainly including:

[0132] 1. Traffic signal control interface: responsible for receiving control instructions and adjusting the cycle and timing of traffic lights.

[0133] 2. Lane allocation control interface: responsible for receiving control instructions and adjusting lane usage.

[0134] 3. Traffic monitoring interface: responsible for receiving control instructions and adjusting the configuration of the traffic monitoring system.

[0135] 4. Road information release interface: responsible for receiving control instructions and publishing real-time road condition information.

[0136] The execution unit has the following steps

[0137] S301: Control instruction analysis

[0138] The execution unit first parses the instructions from the control unit to clarify the operation requirements of each subsystem, including traffic signal cycle adjustment, lane allocation, traffic monitoring settings, etc. The execution unit generates specific operation steps based on these instructions.

[0139] S302: Device control logic

[0140] Develop detailed control logic for each subsystem to ensure that each device can accurately perform operations according to control instructions. The control logic includes operations such as starting and stopping traffic lights, cycle adjustment, lane switches, and activation and deactivation of monitoring equipment.

[0141] S303: Execution process synchronization

[0142] Coordinate the operation process of different equipment to ensure that the control instructions of traffic signals, lane allocation and monitoring systems can be executed synchronously. Through this step, the smoothness of traffic flow and the efficient coordination of the system are ensured.

[0143] S304: Real-time data feedback

[0144] During the execution process, the equipment's operating data, including traffic signal cycles, lane allocation, and the operating status of the monitoring system, are collected in real time and fed back to the control unit. The feedback information is used to optimize the traffic management strategy in real time.

[0145] S305: Anomaly detection and processing

[0146] The execution unit has the ability to detect anomalies. When the equipment's operating status is abnormal or inconsistent with the control instructions, it can promptly identify and take emergency measures, such as automatically adjusting traffic lights, adjusting lane configurations, or activating backup monitoring equipment.

[0147] S306: User interface interaction

[0148] Provide a user interface so that operators can monitor the operating status of the execution unit, manually input instructions or intervene in the automatic control process. The interface should have functions such as data visualization, operation log recording, and alarm prompts to facilitate real-time adjustment and management by operators.

[0149] S307: Safety and reliability design

[0150] Ensure the safety and reliability of the execution unit, including equipment redundancy design, automatic fault switching and system self-checking mechanisms to improve the fault tolerance and stability of the system. All control equipment and systems should have fault tolerance to ensure uninterrupted traffic control.

[0151] S308: Execution effect evaluation

[0152] Regularly evaluate the operational effects of the execution units, including indicators such as traffic flow, signal response time, and lane utilization efficiency, to ensure that the system execution meets the expected goals. The evaluation results are used to optimize subsequent control strategies and execution logic.

[0153] S309: Execution Records and Audits

[0154] Record all operation history of the execution unit, including control instructions, equipment response and operation data, etc., to facilitate operation audit and problem tracking. These data provide support for subsequent optimization adjustment and problem analysis.

[0155] Establish a comprehensive feedback system that can monitor and record key indicators of traffic flow management in real time, including traffic flow, signal light cycle, lane allocation, monitoring system status, and changes in road traffic. The collected data is deeply analyzed and processed to extract useful information for regulation.

[0156] Establish a real-time feedback loop to ensure that the system can respond quickly to changes in traffic conditions. When traffic flow data deviates from expectations, the system automatically adjusts the control strategy to ensure the optimal operation of traffic flow. Regularly update the optimization strategy to adapt to changes in factors such as traffic flow, weather conditions, and emergencies. Use historical data and forecasting models to predict long-term trends in traffic flow, thereby better providing decision support for traffic management.

Claims

1. A system for dynamic regulation of traffic load, characterized in that: The system comprises: Data collection unit: used to monitor traffic data such as traffic flow, vehicle speed, vehicle type, road conditions, and weather conditions in real time. Control unit: used to decide traffic flow control strategies based on collected data and algorithms. Execution unit: used to execute the decisions of the control unit and regulate the traffic flow load.

2. A system for dynamic regulation of traffic load according to claim 1, characterized in that: The control unit comprises: Data analysis module: used to process and analyze the collected traffic data and identify the real-time trend of traffic flow; Traffic load prediction module: Based on the data analysis results, the adaptive neuro-fuzzy inference system ANFIS is used to predict future traffic loads. Traffic load control module: adjusts traffic flow load according to the results of the traffic load prediction module.

3. The system for dynamic regulation of traffic load according to claim 2, characterized in that: The traffic load prediction module adopts the following mathematical model, which is expressed as follows: (1) Factor 1 Factor1=ANFIS(Flow, Speed, Vehicle Type Index) (2) Factor 2 Factor2=ANFIS(Road Condition Index, Weather ConditionIndex) (3) Regulation priority in: Flow represents traffic flow, Speed ​​represents vehicle speed, and Vehicle Type Index represents the standardized value of vehicle type; Priority indicates the control priority; The Road Condition Index indicates the road conditions, and the Weather Condition Index indicates the standardized index of weather conditions.

4. The system for dynamic regulation of traffic load according to claim 2, characterized in that: The traffic load control module adopts the following mathematical model, which is expressed as follows: (1) Objective function (2) Traffic signal control and lane assignment constraints (3) Lane assignment constraints L ij <L max ; in: T ij The traffic travel time from intersection i to intersection j; N is the number of intersections; M is the number of possible destinations; L ij The number of lanes from intersection i to intersection j; L max The maximum number of lanes on the road; C i Traffic signal cycle at intersection i; T total The total time specified.

5. A method for dynamic adjustment of traffic load, implemented based on the system according to any one of claims 1 to 4, characterized in that: The method comprises the following steps: S1: Real-time monitoring of traffic flow data; S2: Based on the standardized index of road conditions, the standardized index of weather conditions, the standardized values ​​of traffic flow, vehicle speed and vehicle type, Factor 1 and Factor 2 are derived respectively, and the priority of regulation is determined by the results of Factor 1 and Factor 2; S3: Dynamically adjust according to the result determined by S2 and the traffic flow conditions.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for dynamically adjusting the traffic load as described in claim 5.

Images