Traffic light adaptive control method and system fused with traffic flow prediction

Abstract

The invention discloses a traffic light adaptive control method and system fused with traffic flow prediction, and relates to the technical field of intelligent traffic, and the method comprises the steps: obtaining the real-time traffic flow data of a target intersection; obtaining a current traffic light control strategy of the target intersection; obtaining a traffic flow prediction result; performing change degree evaluation according to the real-time traffic flow data and the traffic flow prediction result to obtain a traffic flow change coefficient, and judging whether the traffic flow change coefficient is greater than or equal to a traffic flow change threshold; and if the traffic flow change coefficient is greater than or equal to the traffic flow change threshold, generating a traffic light adjustment instruction, adjusting a current traffic light control strategy according to a traffic flow prediction result, generating a future traffic light control strategy, and executing traffic light adaptive control of the target intersection. The technical problems of inaccurate traffic flow prediction and inflexible traffic light control strategy in the prior art are solved, and the technical effects of improving traffic passing efficiency, reducing traffic congestion and optimizing traffic light control are achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a traffic light adaptive control method and system integrating traffic flow prediction. Background Art

[0002] With the continuous acceleration of urbanization and the rapid growth of the number of motor vehicles, traffic flow is increasing, resulting in increasingly serious traffic congestion. Especially during peak traffic hours and at key nodes such as intersections, traditional traffic light control methods can no longer effectively cope with complex and changing traffic demands, which in turn affects traffic efficiency and safety. Although there are some traffic light control strategies based on time cycles or flow perception, these traditional methods generally have problems such as low control accuracy, slow response speed, and poor adaptability, making it difficult to effectively alleviate traffic congestion. Summary of the invention

[0003] The present application provides a traffic light adaptive control method and system integrating traffic flow prediction, which is used to solve the technical problems of inaccurate traffic flow prediction and inflexible traffic light control strategy in the prior art.

[0004] In view of the above problems, the present application provides a traffic light adaptive control method and system integrating traffic flow prediction.

[0005] In a first aspect of the present application, a traffic light adaptive control method integrating traffic flow prediction is provided, the method comprising:

[0006] According to the intersection traffic perception module, real-time traffic flow data of the target intersection is obtained; the current traffic light control strategy of the target intersection is obtained; based on the real-time traffic flow data, the traffic flow of the target intersection is predicted according to the future time zone to obtain the traffic flow prediction result; the degree of change is evaluated according to the real-time traffic flow data and the traffic flow prediction result to obtain the traffic flow change coefficient; it is determined whether the traffic flow change coefficient is greater than or equal to the traffic flow change threshold; if the traffic flow change coefficient is greater than or equal to the traffic flow change threshold, a traffic light adjustment instruction is generated; based on the traffic light adjustment instruction, the current traffic light control strategy is adjusted according to the traffic flow prediction result to generate the future traffic light control strategy, and the traffic light adaptive control of the target intersection is executed according to the future traffic light control strategy.

[0007] A second aspect of the present application provides a traffic light adaptive control system integrating traffic flow prediction, the system comprising:

[0008] A real-time traffic flow data acquisition module is used to obtain the real-time traffic flow data of the target intersection according to the intersection traffic perception module; a traffic light control strategy acquisition module is used to obtain the current traffic light control strategy of the target intersection; a traffic flow prediction module is used to predict the traffic flow of the target intersection according to the future time zone based on the real-time traffic flow data to obtain the traffic flow prediction result; a change degree evaluation module is used to evaluate the change degree according to the real-time traffic flow data and the traffic flow prediction result to obtain the traffic flow change coefficient; a judgment module is used to judge whether the traffic flow change coefficient is greater than or equal to the traffic flow change threshold; an adjustment instruction generation module is used to generate a traffic light adjustment instruction if the traffic flow change coefficient is greater than or equal to the traffic flow change threshold; an adaptive control module is used to adjust the current traffic light control strategy according to the traffic flow prediction result based on the traffic light adjustment instruction, generate a future traffic light control strategy, and execute the traffic light adaptive control of the target intersection according to the future traffic light control strategy.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] According to the intersection traffic perception module, the present application obtains the real-time traffic flow data of the target intersection; obtains the current traffic light control strategy of the target intersection; based on the real-time traffic flow data, predicts the traffic flow of the target intersection according to the future time zone to obtain the traffic flow prediction result; evaluates the degree of change according to the real-time traffic flow data and the traffic flow prediction result to obtain the traffic flow change coefficient; determines whether the traffic flow change coefficient is greater than or equal to the traffic flow change threshold; if the traffic flow change coefficient is greater than or equal to the traffic flow change threshold, generates a traffic light adjustment instruction; based on the traffic light adjustment instruction, adjusts the current traffic light control strategy according to the traffic flow prediction result, generates a future traffic light control strategy, and executes the traffic light adaptive control of the target intersection according to the future traffic light control strategy. The present invention solves the technical problems of inaccurate traffic flow prediction and inflexible traffic light control strategy in the prior art, and achieves the technical effects of improving traffic efficiency, reducing traffic congestion, and optimizing traffic light control by combining real-time traffic flow data with traffic flow prediction results and adjusting the traffic light control strategy based on the prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic flow chart of a traffic light adaptive control method integrating traffic flow prediction provided in an embodiment of the present application;

[0013] Figure 2 A schematic diagram of the structure of a traffic light adaptive control system integrating traffic flow prediction provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: real-time traffic flow data acquisition module 11 , traffic light control strategy acquisition module 12 , traffic flow prediction module 13 , change degree evaluation module 14 , judgment module 15 , adjustment instruction generation module 16 , adaptive control module 17 . DETAILED DESCRIPTION

[0015] The present application provides a traffic light adaptive control method and system integrating traffic flow prediction, aiming to solve the technical problems of inaccurate traffic flow prediction and inflexible traffic light control strategy in the prior art. By combining real-time traffic flow data with traffic flow prediction results and adjusting the traffic light control strategy based on the prediction results, the technical effects of improving traffic efficiency, reducing traffic congestion and optimizing traffic light control are achieved.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides a traffic light adaptive control method integrating traffic flow prediction, the method comprising:

[0019] Step S100: obtaining real-time traffic flow data of the target intersection according to the intersection traffic perception module.

[0020] In an embodiment of the present application, traffic data is collected through a perception module to form a real-time traffic perception data set; then, the data set is filtered and denoised to remove environmental interference and generate a traffic perception denoised data set; then, outlier detection is performed to identify abnormal data and obtain perception data outlier detection results; finally, the data is corrected based on the detection results to improve data accuracy and ultimately obtain reliable real-time traffic flow data.

[0021] Furthermore, in the method provided in the embodiment of the application, obtaining real-time traffic flow data of the target intersection according to the intersection traffic perception module also includes:

[0022] According to the intersection traffic perception module, a real-time traffic perception data set of the target intersection is obtained; the real-time traffic perception data set is filtered and denoised to generate a traffic perception denoised data set; outlier detection is performed on the traffic perception denoised data set to obtain a perception data outlier detection result; the traffic perception denoised data set is corrected according to the perception data outlier detection result to obtain the real-time traffic flow data.

[0023] In the embodiment of the present application, firstly, in the data collection stage, the intersection traffic perception module is responsible for real-time monitoring of traffic conditions. The module is composed of video surveillance cameras, millimeter wave radars, geomagnetic sensing devices, infrared sensors, microwave detectors, etc. Different types of sensing devices can respectively sense vehicle passing conditions, vehicle speed, lane occupancy, pedestrian detection and other information. The data collected by these devices are integrated to form a real-time traffic perception data set.

[0024] Then, in the data preprocessing stage, the data is filtered and denoised to reduce sensor errors and environmental noise. For example, the data collected by the video camera may be affected by changes in lighting, and the geomagnetic sensing device may have short-term abnormal readings due to external electromagnetic interference. In order to remove these noises, the real-time traffic perception dataset is smoothed using methods such as Kalman filtering, median filtering or wavelet transform to generate a traffic perception denoised dataset.

[0025] Then, in the anomaly detection stage, outlier detection is performed on the denoised data to identify unreasonable anomaly data. For example, if the vehicle speed detected by the radar in a certain period of time is far beyond the normal range, or the geomagnetic sensor jumps frequently in a short period of time, these may be abnormal data caused by sensor failure or environmental interference. By using statistical methods (such as Z-Score), outliers are identified and marked to generate perception data outlier detection results.

[0026] Finally, in the data correction stage, based on the outlier detection results of the perception data, the unreasonable data is corrected. For example, if the traffic volume suddenly drops to zero during a period of time, but the camera and other sensors still detect the presence of vehicles, time series interpolation (such as linear interpolation and spline interpolation) is used to correct the data, so as to obtain real-time traffic flow data that is more in line with the actual situation.

[0027] Step S200: Obtain the current traffic light control strategy of the target intersection.

[0028] In an embodiment of the present application, the current traffic light control strategy of the target intersection is obtained by acquiring signal control data from a traffic signal controller or an intelligent traffic management platform, including information such as signal cycle, phase duration, phase sequence arrangement and control mode, and parsing and standardizing the data to form the current traffic light control strategy.

[0029] Step S300: Based on the real-time traffic flow data, traffic flow prediction is performed on the target intersection according to a future time zone to obtain a traffic flow prediction result.

[0030] In the embodiment of the present application, traffic flow prediction is performed based on real-time traffic flow data. First, a traffic flow record set of the target intersection is obtained, and the data is processed in a time series to form a traffic flow combing set. The data set is then used to supervise the long short-term memory neural network (LSTM) to train and optimize the traffic flow prediction model. Finally, the real-time traffic flow data is input into the trained model to output the traffic flow prediction result.

[0031] Furthermore, in the method provided in the embodiment of the application, based on the real-time traffic flow data, traffic flow prediction is performed on the target intersection according to the future time zone to obtain a traffic flow prediction result, and further includes:

[0032] Obtain a traffic flow record set of the target intersection; perform time series processing on the traffic flow record set to obtain a traffic flow combing set; perform supervised learning on a long short-term memory neural network based on the traffic flow combing set to obtain a traffic flow prediction model; input the real-time traffic flow data into the traffic flow prediction model, and output the traffic flow prediction result.

[0033] In an embodiment of the present application, a traffic flow record set of the target intersection is first obtained from a historical traffic database. The data set includes information such as the traffic flow, average speed, lane occupancy, and traffic light status of the target intersection over a historical period of time.

[0034] Next, the traffic flow record set is processed in time series. Since traffic data has time series characteristics, the original data may have problems such as uneven timestamps and inconsistent data granularity. Therefore, by performing time alignment and using the sliding window method, the data is converted into a fixed time interval format to obtain a traffic flow sorting set.

[0035] The traffic flow combing set is then used to supervise the learning of the long short-term memory neural network. During the training process, the traffic flow combing set is divided into a training set, a test set, and a validation set. The Adam optimizer is used to update the parameters, and the prediction effect is evaluated based on the mean square error (MSE) or the mean absolute error (MAE). At the same time, hyperparameter tuning is performed to optimize the number of LSTM layers, the number of neurons, the learning rate, etc. to improve the generalization ability of the model. Through this process, a traffic flow prediction model is obtained.

[0036] Finally, the real-time traffic flow data is input into the trained traffic flow prediction model to generate traffic flow prediction results.

[0037] Furthermore, in the method provided in the embodiment of the application, supervised learning of the long short-term memory neural network is performed according to the traffic flow combing set to obtain a traffic flow prediction model, and the method also includes:

[0038] The traffic flow combing set is divided to obtain a traffic flow training set, a traffic flow test set and a traffic flow verification set; supervised training is performed on a long short-term memory neural network according to the traffic flow training set to obtain a traffic flow prediction network; the traffic flow prediction network is tested according to the traffic flow test set to obtain a traffic flow prediction accuracy; based on the traffic flow prediction accuracy, hyperparameter tuning is performed on the traffic flow prediction network according to the traffic flow verification set to generate the traffic flow prediction model.

[0039] In an embodiment of the present application, the traffic flow combing set is first divided to obtain a traffic flow training set, a test set, and a validation set. When dividing, the traffic flow combing set is divided according to a ratio of 7:2:1, where the training set accounts for 7 for model learning, the test set accounts for 2 for evaluating the training effect, and the validation set accounts for 1 for hyperparameter optimization. The division method can use a time sliding window, that is, input the data in batches according to the time order, or use random splitting for distribution, and obtain the traffic flow training set, traffic flow test set, and traffic flow validation set through this process.

[0040] Next, the LSTM neural network is supervised and trained using the traffic flow training set to build a traffic flow prediction network. The training process uses the back propagation algorithm, which calculates the prediction error and uses the gradient descent method to continuously adjust the network's weight parameters so that the model's loss function gradually converges. Specifically, the error between the predicted value and the true value is first calculated, and then the gradient descent method is used to update the connection weights of the LSTM network to minimize the error, thereby improving the model's learning ability. After training, the traffic flow prediction network is finally obtained.

[0041] The trained LSTM model is then tested using the traffic flow test set to evaluate the model's prediction accuracy. During the test, the mean square error is used as the evaluation indicator, which calculates the mean of the squared error between the predicted value and the true value and is used to measure the overall error level of the model. The smaller the MSE value, the lower the prediction error of the model and the better the prediction performance. Through the test process, the accuracy of traffic flow prediction is finally obtained.

[0042] Finally, based on the traffic flow prediction accuracy, grid search is used to tune the hyperparameters of the LSTM model to obtain the optimal traffic flow prediction model. Grid search is a method of systematically traversing hyperparameter combinations. By presetting multiple possible hyperparameter combinations, training the models one by one and calculating the MSE on the validation set, the hyperparameter combination with the smallest MSE is finally selected. For example, grid search can be used to adjust parameters such as the number of LSTM layers, the number of hidden units, the learning rate, and the time window length to optimize model performance and improve prediction accuracy. After hyperparameter tuning, a traffic flow prediction model is generated.

[0043] After the above steps, an optimized traffic flow prediction model is finally obtained, which is used to predict the traffic flow change trend in future time zones and provide data support for the optimization of the adaptive control strategy of traffic lights, thereby improving road traffic efficiency and the intelligent level of urban traffic management.

[0044] Step S400: Evaluate the degree of change based on the real-time traffic flow data and the traffic flow prediction result to obtain a traffic flow change coefficient.

[0045] In the embodiment of the present application, by comparing and analyzing the real-time traffic flow data and the traffic flow prediction results, the change trend of the traffic flow is identified, and its rising, falling or stable mode is determined. Subsequently, the degree of fluctuation of the traffic flow is evaluated according to the change trend, and the traffic flow change coefficient is calculated.

[0046] Furthermore, in the method provided in the embodiment of the application, the degree of change is evaluated based on the real-time traffic flow data and the traffic flow prediction result to obtain the traffic flow change coefficient, and further includes:

[0047] The traffic flow prediction result is identified for change trend according to the real-time traffic flow data to obtain the traffic flow change trend; the degree of change is evaluated according to the traffic flow change trend to generate the traffic flow change coefficient.

[0048] In an embodiment of the present application, first, by calculating the difference between real-time traffic flow data and traffic flow prediction results, the changing trend of traffic flow is identified. Specifically, the difference method is used to calculate the flow difference at each time point to determine whether the flow is rising, falling or remaining stable. In order to capture the flow change pattern more accurately, the sliding window method is used. In this method, the data is divided into multiple time periods (such as every 10 minutes), and the difference of each window is analyzed. If the flow difference continues to increase within a certain period of time, it means that the flow is rising; if the difference decreases, it may indicate a decrease in flow. Finally, through the changes in these differences, the trend of traffic flow changes is obtained, which is specifically manifested as the trend of traffic flow changes.

[0049] After identifying the trend of traffic flow, the coefficient of variation is used to quantify the degree of fluctuation of traffic flow. The coefficient of variation is obtained by calculating the ratio of the standard deviation of traffic flow change to the mean. When calculating specifically, the standard deviation of traffic flow difference is first calculated to understand the dispersion of traffic flow change; then the mean of traffic flow difference is calculated. Finally, the standard deviation of traffic flow change is divided by the mean of traffic flow change to obtain the traffic flow variation coefficient.

[0050] Step S500: Determine whether the traffic flow change coefficient is greater than or equal to a traffic flow change threshold.

[0051] In the embodiment of the present application, the traffic flow change coefficient calculated above is compared with a preset traffic flow change threshold to determine whether the traffic flow change coefficient is greater than or equal to the traffic flow change threshold. The traffic flow change threshold is preset by technical experts according to needs.

[0052] Step S600: If the traffic flow change coefficient is greater than or equal to the traffic flow change threshold, a traffic light adjustment instruction is generated.

[0053] In an embodiment of the present application, if the traffic flow change coefficient is greater than or equal to the traffic flow change threshold, it is considered that the current traffic flow change exceeds the normal fluctuation range, so a traffic light adjustment instruction is generated, that is, the currently running traffic light control strategy needs to be adjusted.

[0054] Step S700: Based on the traffic light adjustment instruction, the current traffic light control strategy is adjusted according to the traffic flow prediction result, a future traffic light control strategy is generated, and traffic light adaptive control of the target intersection is performed according to the future traffic light control strategy.

[0055] In the embodiment of the present application, based on the traffic light adjustment instruction and the traffic flow prediction results, the current traffic light control strategy is first adjusted to generate multiple traffic light control adjustment schemes. Then, by predicting the traffic efficiency of these schemes, multiple different predicted traffic efficiencies are obtained. Next, based on these prediction results, the control adjustment schemes that can maximize the traffic efficiency are screened out to generate future traffic light control strategies. Finally, the traffic lights at the target intersection are adaptively controlled according to the future traffic light control strategy to ensure that the traffic lights at the intersection can be adjusted in real time under the predicted traffic flow changes, thereby improving overall traffic efficiency, reducing congestion, and ensuring smooth traffic operation.

[0056] Furthermore, in the method provided in the embodiment of the application, based on the traffic light adjustment instruction, the current traffic light control strategy is adjusted according to the traffic flow prediction result to generate a future traffic light control strategy, and further includes:

[0057] Based on the traffic light adjustment instruction, the current traffic light control strategy is adjusted according to the traffic flow prediction result to obtain a traffic light control adjustment scheme set; traffic efficiency is predicted according to the traffic light control adjustment scheme set to obtain multiple predicted traffic efficiencies; traffic efficiency is maximized by screening the traffic light control adjustment scheme set according to the multiple predicted traffic efficiencies to obtain the future traffic light control strategy.

[0058] In the embodiment of the present application, the current traffic light control strategy is first adjusted by the traffic light adjustment instruction and the traffic flow prediction result, and then a series of traffic light control adjustment scheme sets are obtained. This process uses a multi-objective optimization algorithm, such as a particle swarm optimization algorithm, to adjust the parameters of the traffic light control strategy, such as the green light duration, the red light duration, etc., by simulating the behavior of a particle group, to generate multiple possible traffic light control adjustment schemes. These schemes take into account multiple factors, including real-time traffic flow data, predicted traffic flow changes, and historical traffic data. In this process, the particle swarm optimization algorithm is trained to obtain the optimal solution based on historical traffic data and real-time control conditions, thereby forming a set of traffic light adjustment schemes.

[0059] Subsequently, based on the traffic light control adjustment scheme set, a traffic simulation model (such as VISSIM) is used to predict the traffic efficiency. The traffic simulation model simulates the performance of different schemes in a real traffic environment and calculates key traffic indicators such as traffic density, delay time, average speed, etc. Traffic density reflects the density of vehicles on the road per unit time, and is calculated as the number of vehicles per unit road length; delay time is used to measure the waiting time of vehicles under signal control, which can be calculated by tracking the length of vehicle residence through simulation software; average speed measures the degree of traffic flow, and the simulation software calculates the average value by counting the driving speed of each vehicle. In order to quantify the traffic efficiency of each scheme, the normalization method is used to standardize different indicators so that their values ​​are distributed in the range of 0 to 1, and then the predicted traffic efficiency is calculated by weighted summation. When calculating, the traffic density, the difference between 1 and the delay time, and the average speed are multiplied by the corresponding preset weights to obtain the predicted traffic efficiency of the corresponding scheme. Through this process, multiple predicted traffic efficiencies are obtained.

[0060] Finally, based on the multiple predicted traffic efficiencies obtained, the sorting and screening method is used to maximize the screening of the schemes. This screening process evaluates the traffic efficiency of each scheme and selects the scheme with the highest traffic efficiency. Finally, a future traffic light control strategy that adapts to future traffic flow changes is generated, and the traffic lights at the target intersection are adaptively controlled according to the strategy, thereby achieving efficient traffic flow management.

[0061] Furthermore, the method provided in the application embodiment also includes:

[0062] If the traffic flow change coefficient is less than the traffic flow change threshold, the current traffic light control strategy is mapped to the future time zone, and traffic light adaptive control in the future time zone is performed according to the current traffic light control strategy.

[0063] In the embodiment of the present application, when the traffic flow change coefficient is less than the traffic flow change threshold, it means that the traffic flow change at the target intersection is relatively small, and the traffic flow prediction result in the future time zone does not change much, so there is no need to make significant adjustments to the traffic light control strategy. In this case, by mapping the current traffic light control strategy to the future time zone, it is ensured that the traffic flow will be smoothly transitioned in the future period.

[0064] Specifically, the current traffic light control strategy includes traffic flow management information such as the duration and cycle arrangement of traffic lights in different directions of the target intersection. According to the comparison result of the traffic flow change coefficient and the traffic flow change threshold, if the change coefficient is less than the threshold, it indicates that the trend of traffic flow change is not large, and the current control strategy is sufficient to cope with the traffic demand in the future period.

[0065] Then, by mapping the current traffic light control strategy to the future time zone, the existing traffic light timing and strategy are applied to the next time period without modification. This operation is based on the assumption that the traffic flow will not change much in the future time period and no complex strategy adjustment is required. Through this mapping method, over-adjustment can be avoided.

[0066] Finally, according to the mapped traffic light control strategy, adaptive traffic light control for future time zones is performed. This means that traffic light control at the target intersection will be performed according to the current strategy and automatically adapt to the traffic flow demand in the future time period without additional adjustments. This approach ensures efficient traffic management when traffic flow is relatively stable.

[0067] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0068] According to the intersection traffic perception module, the present application obtains the real-time traffic flow data of the target intersection; obtains the current traffic light control strategy of the target intersection; based on the real-time traffic flow data, predicts the traffic flow of the target intersection according to the future time zone to obtain the traffic flow prediction result; evaluates the degree of change according to the real-time traffic flow data and the traffic flow prediction result to obtain the traffic flow change coefficient; determines whether the traffic flow change coefficient is greater than or equal to the traffic flow change threshold; if the traffic flow change coefficient is greater than or equal to the traffic flow change threshold, generates a traffic light adjustment instruction; based on the traffic light adjustment instruction, adjusts the current traffic light control strategy according to the traffic flow prediction result, generates a future traffic light control strategy, and executes the traffic light adaptive control of the target intersection according to the future traffic light control strategy. The present invention solves the technical problems of inaccurate traffic flow prediction and inflexible traffic light control strategy in the prior art, and achieves the technical effects of improving traffic efficiency, reducing traffic congestion, and optimizing traffic light control by combining real-time traffic flow data with traffic flow prediction results and adjusting the traffic light control strategy based on the prediction results.

[0069] Embodiment 2, based on the same inventive concept as the traffic light adaptive control method integrating traffic flow prediction in the above embodiment, Figure 2 As shown, the present application provides a traffic light adaptive control system integrating traffic flow prediction, and the system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0070] A real-time traffic flow data acquisition module 11 is used to obtain the real-time traffic flow data of the target intersection according to the intersection traffic perception module; a traffic light control strategy acquisition module 12 is used to obtain the current traffic light control strategy of the target intersection; a traffic flow prediction module 13 is used to predict the traffic flow of the target intersection according to the future time zone based on the real-time traffic flow data to obtain the traffic flow prediction result; a change degree evaluation module 14 is used to evaluate the change degree according to the real-time traffic flow data and the traffic flow prediction result to obtain the traffic flow change coefficient; a judgment module 15 is used to judge whether the traffic flow change coefficient is greater than or equal to the traffic flow change threshold; an adjustment instruction generation module 16 is used to generate a traffic light adjustment instruction if the traffic flow change coefficient is greater than or equal to the traffic flow change threshold; an adaptive control module 17 is used to adjust the current traffic light control strategy according to the traffic flow prediction result based on the traffic light adjustment instruction, generate a future traffic light control strategy, and execute the traffic light adaptive control of the target intersection according to the future traffic light control strategy.

[0071] Furthermore, the system is also used to implement the following functions:

[0072] According to the intersection traffic perception module, a real-time traffic perception data set of the target intersection is obtained; the real-time traffic perception data set is filtered and denoised to generate a traffic perception denoised data set; outlier detection is performed on the traffic perception denoised data set to obtain a perception data outlier detection result; the traffic perception denoised data set is corrected according to the perception data outlier detection result to obtain the real-time traffic flow data.

[0073] Furthermore, the system is also used to implement the following functions:

[0074] Obtain a traffic flow record set of the target intersection; perform time series processing on the traffic flow record set to obtain a traffic flow combing set; perform supervised learning on a long short-term memory neural network based on the traffic flow combing set to obtain a traffic flow prediction model; input the real-time traffic flow data into the traffic flow prediction model, and output the traffic flow prediction result.

[0075] Furthermore, the system is also used to implement the following functions:

[0076] The traffic flow combing set is divided to obtain a traffic flow training set, a traffic flow test set and a traffic flow verification set; supervised training is performed on a long short-term memory neural network according to the traffic flow training set to obtain a traffic flow prediction network; the traffic flow prediction network is tested according to the traffic flow test set to obtain a traffic flow prediction accuracy; based on the traffic flow prediction accuracy, hyperparameter tuning is performed on the traffic flow prediction network according to the traffic flow verification set to generate the traffic flow prediction model.

[0077] Furthermore, the system is also used to implement the following functions:

[0078] The traffic flow prediction result is identified for change trend according to the real-time traffic flow data to obtain the traffic flow change trend; the degree of change is evaluated according to the traffic flow change trend to generate the traffic flow change coefficient.

[0079] Furthermore, the system is also used to implement the following functions:

[0080] Based on the traffic light adjustment instruction, the current traffic light control strategy is adjusted according to the traffic flow prediction result to obtain a traffic light control adjustment scheme set; traffic efficiency is predicted according to the traffic light control adjustment scheme set to obtain multiple predicted traffic efficiencies; traffic efficiency is maximized by screening the traffic light control adjustment scheme set according to the multiple predicted traffic efficiencies to obtain the future traffic light control strategy.

[0081] Furthermore, the system is also used to implement the following functions:

[0082] If the traffic flow change coefficient is less than the traffic flow change threshold, the current traffic light control strategy is mapped to the future time zone, and traffic light adaptive control in the future time zone is performed according to the current traffic light control strategy.

[0083] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0084] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0085] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. The traffic light adaptive control method integrating traffic flow prediction is characterized by: The method comprises: According to the intersection traffic perception module, obtain the real-time traffic flow data of the target intersection; Obtaining the current traffic light control strategy of the target intersection; Based on the real-time traffic flow data, predicting the traffic flow at the target intersection according to the future time zone to obtain a traffic flow prediction result; Performing a change degree evaluation based on the real-time traffic flow data and the traffic flow prediction result to obtain a traffic flow change coefficient; Determining whether the traffic flow change coefficient is greater than or equal to a traffic flow change threshold; If the traffic flow change coefficient is greater than or equal to the traffic flow change threshold, generating a traffic light adjustment instruction; Based on the traffic light adjustment instruction, the current traffic light control strategy is adjusted according to the traffic flow prediction result, a future traffic light control strategy is generated, and the traffic light adaptive control of the target intersection is performed according to the future traffic light control strategy.

2. The traffic light adaptive control method integrating traffic flow prediction as claimed in claim 1 is characterized in that: According to the intersection traffic perception module, the real-time traffic flow data of the target intersection is obtained, including: According to the intersection traffic perception module, obtaining a real-time traffic perception data set of the target intersection; Filtering and denoising the real-time traffic perception data set to generate a traffic perception denoised data set; Performing outlier detection on the traffic perception denoising data set to obtain a perception data outlier detection result; The traffic perception denoising data set is corrected according to the perception data outlier detection result to obtain the real-time traffic flow data.

3. The traffic light adaptive control method integrating traffic flow prediction as claimed in claim 1 is characterized in that: Based on the real-time traffic flow data, traffic flow prediction is performed on the target intersection according to the future time zone to obtain a traffic flow prediction result, including: Obtaining a traffic flow record set of the target intersection; Performing time series processing on the traffic flow record set to obtain a traffic flow sorting set; Performing supervised learning on a long short-term memory neural network according to the traffic flow combing set to obtain a traffic flow prediction model; The real-time traffic flow data is input into the traffic flow prediction model, and the traffic flow prediction result is output.

4. The traffic light adaptive control method integrating traffic flow prediction as claimed in claim 3 is characterized in that: According to the traffic flow combing set, supervised learning is performed on the long short-term memory neural network to obtain a traffic flow prediction model, including: Dividing the traffic flow combing set to obtain a traffic flow training set, a traffic flow test set and a traffic flow verification set; Performing supervised training on a long short-term memory neural network according to the traffic flow training set to obtain a traffic flow prediction network; Testing the traffic flow prediction network according to the traffic flow test set to obtain the traffic flow prediction accuracy; Based on the traffic flow prediction accuracy, the traffic flow prediction network is hyper-parameter tuned according to the traffic flow verification set to generate the traffic flow prediction model.

5. The traffic light adaptive control method integrating traffic flow prediction as claimed in claim 1 is characterized in that: The change degree is evaluated according to the real-time traffic flow data and the traffic flow prediction result to obtain the traffic flow change coefficient, including: Identify the change trend of the traffic flow prediction result according to the real-time traffic flow data to obtain the traffic flow change trend; The degree of change is evaluated according to the traffic flow change trend to generate the traffic flow change coefficient.

6. The traffic light adaptive control method integrating traffic flow prediction as claimed in claim 1, characterized in that: Based on the traffic light adjustment instruction, the current traffic light control strategy is adjusted according to the traffic flow prediction result to generate a future traffic light control strategy, including: Based on the traffic light adjustment instruction, adjusting the current traffic light control strategy according to the traffic flow prediction result to obtain a traffic light control adjustment scheme set; Performing traffic efficiency prediction according to the traffic light control adjustment scheme set to obtain multiple predicted traffic efficiencies; The traffic light control adjustment scheme set is screened for maximizing traffic efficiency according to the multiple predicted traffic efficiencies to obtain the future traffic light control strategy.

7. The traffic light adaptive control method integrating traffic flow prediction as claimed in claim 1, characterized in that: If the traffic flow change coefficient is less than the traffic flow change threshold, the current traffic light control strategy is mapped to the future time zone, and traffic light adaptive control in the future time zone is performed according to the current traffic light control strategy.

8. Traffic light adaptive control system integrating traffic flow prediction, characterized by: The system comprises: A real-time traffic flow data acquisition module is used to obtain real-time traffic flow data of a target intersection based on the intersection traffic perception module; A traffic light control strategy acquisition module, used to obtain the current traffic light control strategy of the target intersection; A traffic flow prediction module is used to predict the traffic flow of the target intersection according to the future time zone based on the real-time traffic flow data to obtain a traffic flow prediction result; A change degree evaluation module, used to evaluate the change degree according to the real-time traffic flow data and the traffic flow prediction result, and obtain a traffic flow change coefficient; A judgment module, used to judge whether the traffic flow change coefficient is greater than or equal to a traffic flow change threshold; An adjustment instruction generating module, used for generating a traffic light adjustment instruction if the traffic flow change coefficient is greater than or equal to the traffic flow change threshold; The adaptive control module is used to adjust the current traffic light control strategy based on the traffic light adjustment instruction and the traffic flow prediction result, generate a future traffic light control strategy, and perform traffic light adaptive control at the target intersection according to the future traffic light control strategy.

Images