Intelligent edge computing device with adaptive traffic signal control capability and control method

Abstract

The invention relates to the technical field of urban intelligent traffic, in particular to an intelligent edge computing device with adaptive traffic signal control capability and a control method, and the method comprises the following steps: S1, collecting intersection traffic information detected by various traffic information detectors; s2, data preprocessing is carried out on the collected intersection traffic information, preprocessed data comprises a spatial dimension and a time dimension, and the spatial dimension is divided into section data and regional data; the time dimension is divided into real-time data, phase-level statistical data, period-level statistical data, time-period-level statistical data and day-level statistical data; s3, judging whether the data collected by the traffic information detector is seriously abnormal or not, if the data is seriously abnormal, giving an alarm, starting intersection reference signal timing, sending the intersection reference signal timing to a traffic signal controller, and executing by the traffic signal controller; the state of the traffic signal lamp can be detected in real time, and the real-time self-adaptive performability of the traffic signal is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban intelligent transportation, and specifically to an intelligent edge computing device and a control method with adaptive traffic signal control capability. Background Art

[0002] The research on adaptive traffic signal control has been going on for a long time, and there are many related papers and patents. However, the results of actual application are often not satisfactory. The prominent factors include high requirements for perceived traffic flow parameters, complex control algorithms, and non-closed-loop control effects. In addition, the scope of adaptation is mainly concentrated on the timing parameters of traffic signals, while other contents closely related to adaptive control such as channelization and traffic light status are not involved. As a result, adaptive traffic signal control has long been well-received but not popular.

[0003] Invention patent CN116564104A "An adaptive traffic signal control system and method for traffic flow prediction" researched by Pi Jiatian and others from Chongqing Normal University discloses an adaptive traffic signal control system and method for traffic flow prediction; the patent does not involve the detection of traffic light status, cannot ensure that the signal control strategy can be accurately executed, and does not involve traffic channelization, resulting in a limited scope of adaptive control.

[0004] CN115830887A "An adaptive traffic signal control method, system and readable storage medium" studied by Zeng Ke and others from Wuhan Zhian Transportation Technology Co., Ltd. discloses an adaptive traffic signal control method, system and readable storage medium. The patent does not involve the detection of traffic light status and traffic channelization.

[0005] Patent CN111524363A "A Dynamic Adaptive Traffic Signal Control System and Control Method" by Bai Chuandong et al. of Beijing Bonafide Technology Co., Ltd. discloses a dynamic adaptive traffic signal control system and control method. The patent does not involve the detection of traffic light status and traffic channelization. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] In view of the deficiencies in the prior art, the present invention provides an intelligent edge computing device and a control method with adaptive traffic signal control capabilities.

[0008] (II) Technical solution

[0009] To achieve the above object, the present invention provides the following technical solution: a method for controlling the adaptive traffic signal control capability, comprising the following steps:

[0010] S1: Collect intersection traffic information detected by various traffic information detectors;

[0011] S2: preprocessing the collected intersection traffic information. The preprocessed data includes spatial dimension and time dimension. The spatial dimension is divided into cross-sectional data and regional data. The time dimension is divided into real-time data, phase-level statistical data, cycle-level statistical data, time-period-level statistical data and daily-level statistical data.

[0012] S3: Determine whether the data collected by the traffic information detector is seriously abnormal. If the data is seriously abnormal, an alarm is issued, and the intersection reference signal timing is enabled and sent to the traffic signal controller for execution;

[0013] S4: Detect the state of the traffic light and determine the degree of the fault of the traffic light. When the current state of the traffic light does not support adaptive control, enable the intersection reference signal timing and send it to the traffic signal controller for execution;

[0014] S5: When the traffic light is in normal state and the detection data of the traffic detectors in each direction are normal, the traffic signal timing optimization calculation is performed;

[0015] S6: The calculated timing plan is sent to the traffic signal controller, which executes it.

[0016] Furthermore, the present invention is improved in that the data preprocessing method includes missing data completion, time alignment, data missing alarm, multi-source data verification, outlier processing and data normalization.

[0017] Furthermore, the present invention is improved in that the traffic signal timing optimization calculation includes:

[0018] The intersection traffic law calculation method is mainly responsible for analyzing the traffic operation law of the intersection based on the intersection traffic information, such as the traffic law on weekdays, the traffic law on winter and summer vacations, and the traffic law on major holidays. The laws to be analyzed include the benchmark traffic flow on each date, the benchmark traffic congestion situation, and the division suggestions of signal timing periods;

[0019] Traffic channelization optimization calculation method, whose main calculation basis is the matching of the benchmark traffic flow data of each flow direction calculated by the intersection traffic law calculation method and the intersection channelization capacity, and the output result is the lane configuration suggestion for a certain direction;

[0020] The core logic of the benchmark traffic signal timing calculation method is that, based on the benchmark traffic volume at the intersection, the algorithm will determine 16 benchmark traffic signal timing parameters according to different traffic conditions at the intersection; at the same time, the algorithm will select a set of schemes that best suits the current control strategy from the 16 schemes based on the parameters of the previous three cycles of the current intersection. At the same time, for the current signal phase, the algorithm will determine the fine-tuning parameters for each phase scheme of the current intersection based on the real-time detection of traffic parameters;

[0021] The real-time adaptive calculation method of traffic signals can quickly calculate a signal timing plan suitable for the current traffic conditions based on the currently detected traffic flow and other relevant parameters in a short period of time. It can automatically adjust the signal timing according to changes in traffic flow to respond to sudden traffic incidents or changes in daily traffic flow, thereby improving traffic efficiency and reducing congestion.

[0022] Furthermore, the present invention has the following improvements: when the data collected by the traffic information detectors are normal, the timing scheme calculated by the real-time adaptive traffic signal calculation method has a higher priority than the timing scheme calculated by the reference traffic signal timing calculation method.

[0023] Furthermore, the present invention is improved in that the traffic signal timing optimization calculation also includes a real-time intersection operation evaluation method, which evaluates the actual operation effect of the intersection, and the evaluation scope includes phase-level evaluation, cycle-level evaluation and scheme-level evaluation, and the evaluation indicators include vacancy rate, flow and congestion;

[0024] Furthermore, the present invention has the following improvements: the real-time intersection operation evaluation method feeds back the phase-level and cycle-level evaluation results to the real-time adaptive traffic signal calculation method to determine whether it is necessary to further make a quasi-real-time optimization plan; and feeds back the plan-level evaluation results to the benchmark traffic signal timing calculation method to determine whether it is necessary to adjust the benchmark traffic timing parameters.

[0025] An intelligent edge computing device with adaptive traffic signal control capability of the present invention includes a metering module: receiving input from a traffic signal light and converting it into a structured data format;

[0026] GPU: used to process data from various traffic detectors;

[0027] CPU: runs the steps of a control method for adaptive traffic signal control capability as described in any one of claims 1 to 7, and outputs calculation results to the traffic signal controller and the traffic signal platform.

[0028] Further, the present invention is improved in that the CPU comprises:

[0029] Traffic information collection and preprocessing unit: used to receive traffic information from the detector and preprocess it;

[0030] Traffic light status detection unit: used to receive detection data of the status of the traffic light and determine the degree of fault of the traffic light;

[0031] Signal timing logic calculation unit, including:

[0032] Calculation method of intersection traffic rules: Determine the traffic operation rules of the intersection based on the collected data;

[0033] Traffic channelization optimization calculation method: provide lane configuration suggestions based on traffic law calculation results;

[0034] Benchmark traffic signal timing method: Determine multiple benchmark traffic signal timing parameters based on the benchmark traffic volume at the intersection and select the most appropriate solution;

[0035] Traffic signal real-time adaptive calculation method: The timing scheme is calculated based on real-time traffic parameters and is used first when the detection data is normal;

[0036] Intersection benchmark signal timing: When there are serious anomalies in the detection data or the signal light status does not support adaptive control, the benchmark signal timing is enabled to ensure basic traffic control functions;

[0037] Real-time adaptive signal timing at intersections: The timing scheme calculated by the real-time adaptive calculation method of traffic signals is sent to the traffic signal controller through the network port for execution;

[0038] Real-time evaluation method for intersection operation: used to evaluate the execution effect of control scheme.

[0039] (III) Beneficial effects

[0040] Compared with the prior art, the present invention provides an intelligent edge computing device and control method with adaptive traffic signal control capability, which has the following beneficial effects: the intelligent edge computing device of the present invention can detect the state of traffic lights in real time, thereby improving the feasibility of real-time adaptive traffic signals;

[0041] The intelligent edge computing device involved in the present invention can perform refined analysis on multi-source traffic flow detection data, involving cross-sectional data and regional data, and can be used in a comprehensive manner, thereby improving the adaptability of traffic data use;

[0042] The intelligent edge computing device of the present invention can analyze traffic flow detection data from multiple sources according to different date attributes and granularity, so as to provide different calculation methods for calling, thereby improving the efficiency of data utilization;

[0043] The control method of the intelligent edge computing device involved in the present invention involves real-time adaptive control at the cycle level and the phase level, and also covers adaptive adjustment of the benchmark scheme, thereby improving the control range and control effect of traffic signal adaptation;

[0044] The real-time intersection operation evaluation method of the intelligent edge computing device of the present invention can detect the effect of signal timing in real time and realize quantitative closed-loop feedback, thereby changing the drawbacks of previous signal timing schemes that rely on manual experience and making the timing schemes more accurate.

[0045] The optimization method of the intelligent edge computing device involved in the present invention combines the optimization of intersection traffic channelization, so that the influencing factors of the optimization are considered more completely, changing the traditional practice of adaptive control that only optimizes signal timing parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a flow chart of a control method for adaptive traffic signal control capability of the present invention;

[0047] Figure 2 It is a schematic diagram of the structure of an intelligent edge computing device with adaptive traffic signal control capability. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] See also Figure 1-Figure 2 The intelligent edge computing device involved in the present invention realizes an adaptive control method for traffic signal control by comprehensively utilizing the detection information of various traffic detectors at the intersection and comprehensively considering the fault state of the traffic light and traffic channelization. The specific logic is as follows:

[0050] Step 1: Various traffic information detectors transmit the detected information to the intelligent edge computing device. The collected information includes two categories: the detected location information and the traffic flow information. The detected location information mainly includes the detection direction, the detection area (section or area), and the distance between the detection location and the stop line; the detected traffic flow information mainly includes the flow rate, occupancy rate, vehicle head data, speed, the length of the green light end queue, the length of the green light initial queue, etc.

[0051] Step 2: Traffic information detected by various traffic detectors is sent to the traffic information collection and preprocessing unit of the intelligent edge computing device through the network port;

[0052] Step 3: The traffic information collection and preprocessing unit of the intelligent edge computing device preprocesses the collected intersection traffic information. The preprocessing methods include missing data completion, time alignment, data missing alarm, multi-source data verification, outlier processing, data normalization, etc.

[0053] Step 4: The data preprocessed by the traffic information collection and preprocessing unit of the intelligent edge computing device will contain two dimensions: one is the spatial dimension, which can be divided into cross-sectional data and regional data; the other is the temporal dimension, which can be divided into real-time data, phase-level statistical data, cycle-level statistical data, time-period-level statistical data and daily-level statistical data;

[0054] Step 5: The traffic information collection and preprocessing unit of the intelligent edge computing device is responsible for determining whether the data collected by the detector has serious anomalies (including data missing, data anomalies), etc. If data is missing, a data failure alarm is issued;

[0055] Step 6: When the data is valid, the intersection reference signal timing of the intelligent edge computing device is enabled and sent to the traffic signal controller for execution;

[0056] Step 7: The traffic light status detection unit of the intelligent edge computing device is responsible for receiving the detection data of the traffic light status and determining the degree of failure of the traffic light;

[0057] Step 8: When the traffic light state detection unit of the intelligent edge computing device determines that the current state of the traffic light does not support adaptive control, the intersection reference signal timing of the intelligent edge computing device is enabled and sent to the traffic signal controller for execution by the traffic signal controller;

[0058] Step 9: When the traffic light is in normal state and the detection data of the traffic detectors in each direction are normal, the signal timing logic calculation unit is enabled to perform optimization calculation of the traffic signal timing;

[0059] Step 10: The signal timing logic calculation unit includes a calculation method for intersection traffic rules, which is mainly responsible for analyzing the rules of intersection traffic operation based on the data collected by the traffic information collection and preprocessing unit, such as weekday traffic rules, summer and winter vacation traffic rules, major holiday traffic rules (including 2 days before and after), etc. The rules include the benchmark traffic flow under each date, the benchmark traffic congestion situation (occurrence time period, duration, congestion degree), and the division suggestions of signal timing time periods, etc.;

[0060] Step 11: The signal timing logic calculation unit includes a traffic channelization optimization calculation method, the main calculation basis of which is the matching of the benchmark traffic flow data of each direction calculated by the intersection traffic law calculation method and the intersection channelization capacity, and the output result is a lane configuration suggestion for a certain direction;

[0061] Step 12: The signal timing logic calculation unit includes a benchmark traffic signal timing calculation method, and its core logic is that according to the benchmark flow of the intersection, the algorithm will determine 16 benchmark traffic signal timing parameters according to different traffic conditions at the intersection; at the same time, the algorithm will select a set of the most suitable schemes for the current control strategy (including the maximum flow per unit time at the intersection, the least empty traffic at the intersection, and ensuring that there is no congestion in the key direction) from the 16 schemes according to the parameters of the previous three cycles of the current intersection. At the same time, for the current signal phase, the algorithm will determine the fine-tuning parameters of each phase scheme of the current intersection according to the real-time detection traffic parameters;

[0062] Step 13: The timing scheme calculated by the traffic signal real-time adaptive calculation method in the signal timing logic calculation unit can be sent to the traffic signal controller through the network port and executed by the traffic signal controller;

[0063] Step 14: When the traffic information collection and preprocessing unit of the intelligent edge computing device is responsible for determining that the data collected by the detector is normal, the timing scheme calculated by the real-time adaptive calculation method of the traffic signal has a higher priority than the timing scheme calculated by the reference traffic signal timing calculation method;

[0064] Step 15: For the issued control scheme, the real-time intersection operation evaluation method of the intelligent edge computing device will evaluate the actual operation effect of the intersection. The scope of the evaluation includes phase-level evaluation, cycle-level evaluation and scheme-level evaluation. The evaluation indicators include vacancy rate, flow rate and congestion.

[0065] Step 16: The real-time intersection operation evaluation method of the intelligent edge computing device feeds back the phase-level and cycle-level evaluation results to the real-time adaptive calculation method of the traffic signal to determine whether a quasi-real-time optimization plan needs to be further made; the plan-level evaluation results are fed back to the benchmark traffic signal timing calculation method to determine whether the benchmark traffic timing parameters need to be adjusted;

[0066] Step 17: The above steps are repeated repeatedly to realize adaptive control of traffic signal timing at intersections by the intelligent edge computing device, while comprehensively considering the fault status of traffic lights and traffic channelization.

[0067] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for controlling adaptive traffic signal control capability, characterized in that: The following steps are involved: S1: Collect intersection traffic information detected by various traffic information detectors; S2: preprocessing the collected intersection traffic information. The preprocessed data includes spatial dimension and time dimension. The spatial dimension is divided into cross-sectional data and regional data. The time dimension is divided into real-time data, phase-level statistical data, cycle-level statistical data, time-period-level statistical data and daily-level statistical data. S3: Determine whether the data collected by the traffic information detector is seriously abnormal. If the data is seriously abnormal, an alarm is issued, and the intersection reference signal timing is enabled and sent to the traffic signal controller for execution; S4: Detect the state of the traffic light and determine the degree of the fault of the traffic light. When the current state of the traffic light does not support adaptive control, enable the intersection reference signal timing and send it to the traffic signal controller for execution; S5: When the traffic light is in normal state and the detection data of the traffic detectors in each direction are normal, the traffic signal timing optimization calculation is performed; S6: The calculated timing plan is sent to the traffic signal controller, which executes it.

2. A method for controlling adaptive traffic signal control capability according to claim 1, characterized in that: The data preprocessing method includes missing data completion, time alignment, data missing alarm, multi-source data verification, outlier processing and data normalization.

3. The method for controlling the adaptive traffic signal control capability according to claim 1, characterized in that: The traffic signal timing optimization calculation includes: The intersection traffic law calculation method is mainly responsible for analyzing the traffic operation law of the intersection based on the intersection traffic information, such as the traffic law on weekdays, the traffic law on winter and summer vacations, and the traffic law on major holidays. The laws to be analyzed include the benchmark traffic flow on each date, the benchmark traffic congestion situation, and the division suggestions of signal timing periods; Traffic channelization optimization calculation method, whose main calculation basis is the matching of the benchmark traffic flow data of each flow direction calculated by the intersection traffic law calculation method and the intersection channelization capacity, and the output result is the lane configuration suggestion for a certain direction; The core logic of the benchmark traffic signal timing calculation method is that, based on the benchmark traffic volume at the intersection, the algorithm will determine 16 benchmark traffic signal timing parameters according to different traffic conditions at the intersection; at the same time, the algorithm will select a set of schemes that best suits the current control strategy from the 16 schemes based on the parameters of the previous three cycles of the current intersection. At the same time, for the current signal phase, the algorithm will determine the fine-tuning parameters for each phase scheme of the current intersection based on the real-time detection of traffic parameters; The real-time adaptive calculation method of traffic signals can quickly calculate a signal timing plan suitable for the current traffic conditions based on the currently detected traffic flow and other relevant parameters in a short period of time. It can automatically adjust the signal timing according to changes in traffic flow to respond to sudden traffic incidents or changes in daily traffic flow, thereby improving traffic efficiency and reducing congestion.

4. The method for controlling the adaptive traffic signal control capability according to claim 3, characterized in that: When the data collected by the traffic information detectors are normal, the timing scheme calculated by the real-time adaptive traffic signal calculation method has a higher priority than the timing scheme calculated by the reference traffic signal timing calculation method.

5. The method for controlling the adaptive traffic signal control capability according to claim 3, characterized in that: The traffic signal timing optimization calculation also includes a real-time intersection operation evaluation method, which evaluates the actual operation effect of the intersection. The evaluation scope includes phase-level evaluation, cycle-level evaluation and scheme-level evaluation. The evaluation indicators include vacancy rate, flow rate and congestion.

6. A method for controlling adaptive traffic signal control capability according to claim 5, characterized in that: The real-time intersection operation evaluation method feeds back the phase-level and cycle-level evaluation results to the real-time adaptive calculation method of traffic signals to determine whether a quasi-real-time optimization plan is needed; and feeds back the plan-level evaluation results to the benchmark traffic signal timing calculation method to determine whether the benchmark traffic timing parameters need to be adjusted.

7. An intelligent edge computing device with adaptive traffic signal control capability, characterized in that: Includes metering module: receives input from traffic lights and converts it into a structured data format; GPU: used to process data from various traffic detectors; CPU: runs the steps of a control method for adaptive traffic signal control capability as described in any one of claims 1 to 7, and outputs calculation results to the traffic signal controller and the traffic signal platform.

8. An intelligent edge computing device with adaptive traffic signal control capability, characterized in that: The CPU comprises: Traffic information collection and preprocessing unit: used to receive traffic information from the detector and preprocess it; Traffic light status detection unit: used to receive detection data of the status of the traffic light and determine the degree of fault of the traffic light; Signal timing logic calculation unit, including: Calculation method of intersection traffic rules: Determine the traffic operation rules of the intersection based on the collected data; Traffic channelization optimization calculation method: provide lane configuration suggestions based on traffic law calculation results; Benchmark traffic signal timing method: Determine multiple benchmark traffic signal timing parameters based on the benchmark traffic volume at the intersection and select the most appropriate solution; Traffic signal real-time adaptive calculation method: The timing scheme is calculated based on real-time traffic parameters and is used first when the detection data is normal; Intersection benchmark signal timing: When there are serious anomalies in the detection data or the signal light status does not support adaptive control, the benchmark signal timing is enabled to ensure basic traffic control functions; Real-time adaptive signal timing at intersections: The timing scheme calculated by the real-time adaptive calculation method of traffic signals is sent to the traffic signal controller through the network port for execution; Real-time evaluation method for intersection operation: used to evaluate the execution effect of control scheme.

Images