Type 2 fuzzy traffic signal lamp control method and device, medium and product
By using type 2 fuzzy control methods and short -term traffic flow prediction models in the traffic light control system, combined with real -time vehicle flow data and predicting data for fuzzy control, and use the Pelican optimization algorithm optimization model parameters, solving the cross -section road traffic efficiency efficiency The problem of low and traffic congestion has achieved more efficient traffic flow management.
Patent Information
- Application Number
- CN202411480672.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-23
- Publication Date
- 2025-01-21
Smart Images
Figure CN119339564A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a type II fuzzy traffic signal light control method, device, medium and product, belonging to the technical field of intelligent traffic control. Background Art
[0002] Traffic lights, as an important part of urban traffic management, guide vehicles and pedestrians by controlling the time of red, yellow and green lights. Traditional traffic light control often adopts a fixed time difference mode, that is, the lights are switched according to a preset schedule. However, with the continuous increase in urban traffic flow, this fixed control method has been difficult to meet the needs of modern traffic management. In order to improve the efficiency and stability of traffic operation, the control mode of traffic lights has been continuously innovated, and multi-mode control technology has been introduced. Multi-mode control technology analyzes the actual situation of traffic intersections, uses mathematical optimization methods, studies the optimal switching law of traffic signals, and forms a control system mode that integrates the shortest time, minimum waiting, and minimum error. In addition, with the development of information technology, intelligent traffic light control systems have come into being. The system sets sensors at intersections to collect traffic information such as vehicles and pedestrians, and analyzes and processes this information through algorithms to achieve adaptive control of traffic lights. This adaptive control can adjust the timing of traffic lights according to real-time traffic conditions to maximize traffic flow and travel time.
[0003] Although the existing traffic signal control technology has improved the efficiency of traffic management to a certain extent, it still has some significant defects. In particular, in terms of the efficiency of intersection roads, the existing technology is often difficult to achieve the optimal state. Since the traditional traffic signal control system adopts a fixed timing control and cannot be dynamically adjusted according to the real-time traffic conditions, it is easy to cause unnecessary waiting time and traffic jams. Especially in the case of uneven traffic flow, the waiting time of vehicles will be further increased, resulting in low efficiency of signal lights and the inability to fully utilize the road traffic capacity. In addition, congestion is also a major challenge faced by the existing technology. Due to the inflexible control method of traffic lights, it is difficult to effectively deal with traffic congestion. Long-term traffic jams not only have a negative impact on the psychological and physical health of drivers and passengers, but also waste a lot of time and resources. The traffic losses caused by this congestion are not only reflected in the time cost, but may also lead to an increase in traffic accidents and aggravated environmental pollution. Therefore, solving the problems of low traffic efficiency of intersection roads, long waiting time for vehicles, and traffic losses caused by congestion has become a key issue that needs to be solved in the current field of traffic signal control technology.
[0004] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgement or any form of suggestion that the information constitutes the prior art already known to ordinary technicians in this field. Summary of the invention
[0005] The technical problem to be solved by the present invention is: how to improve the traffic efficiency of the intersection road, reduce the waiting time of vehicles, and reduce the traffic losses caused by congestion.
[0006] In order to solve the above technical problems, the present invention is implemented by adopting the following technical solutions.
[0007] In a first aspect, the present invention provides a type II fuzzy traffic signal light control method, comprising:
[0008] Get real-time traffic flow data at the current road intersection;
[0009] The real-time traffic flow data is input into a pre-trained short-term traffic flow prediction model for prediction, and the traffic flow prediction data of the current road intersection within the next 15 minutes is obtained;
[0010] Combining the predicted traffic flow data and the actual traffic flow data of the current road intersection according to a preset ratio to form input data, inputting the data into a type-II fuzzy controller, and outputting a fuzzy variable;
[0011] Based on the fuzzy reasoning mechanism, the fuzzy variables are converted into precise values to control the traffic lights;
[0012] Wherein, the short-term traffic flow prediction model is optimized by utilizing the Pelican optimization algorithm.
[0013] Furthermore, before the real-time traffic flow data is input into the pre-trained short-term traffic flow prediction model for prediction, the real-time traffic flow data is also pre-processed, including:
[0014] After adding a placeholder at the position where the real-time traffic flow data is missing, the average value between adjacent data is calculated and scaled to between 0 and 1 to obtain scaled data;
[0015] Normalizing the scaled data using a Min-MaxScaler method to obtain a data sequence;
[0016] The flat vectors in the data sequence are converted into a matrix with nine columns and four rows.
[0017] Furthermore, the short-term traffic flow prediction model includes:
[0018] A multi-layer convolutional neural network (CNN) module is used to perform a sliding window operation on the real-time traffic flow data to extract spatial features of the real-time traffic flow data;
[0019] A bidirectional long short-term memory network BiLstm module is used to capture the long-term dependency between the spatial feature and the real-time traffic flow data of the current road intersection according to each time step of the spatial feature and the forward hidden state and the reverse hidden state, and obtain the feature information of all time steps of the spatial feature;
[0020] The fully connected layer is used to output the traffic flow prediction data of the current road intersection in the future based on the feature information of all time steps of the spatial features and the weighted summation and activation function operation.
[0021] Furthermore, the short-term traffic flow prediction model is optimized using the Pelican optimization algorithm, including:
[0022] The fitness function is used as the loss function of the short-term traffic flow prediction model;
[0023] Determine the hyperparameters that need to be optimized for the short-term traffic flow prediction model, including: the number of CNN convolutional layers, the number of BILSTM units, the learning rate and the regularization parameter;
[0024] In the search space, a group of candidate solutions with uniform distribution are randomly generated as initial hyperparameters of the short-term traffic flow prediction model to form a population;
[0025] Based on the Pelican optimization algorithm and the loss function, minimizing the prediction error is taken as the optimization goal, and the candidate solutions in the population and the fitness of each candidate solution are continuously updated through an iterative process;
[0026] After the iteration is completed, the candidate solution with the highest fitness is obtained as the optimal hyperparameter to configure the short-term traffic flow prediction model.
[0027] Furthermore, based on the Pelican optimization algorithm and the loss function, minimizing the prediction error is taken as the optimization goal, and the candidate solutions in the population and the fitness of each candidate solution are continuously updated through an iterative process, including:
[0028] Repeat the following steps until the preset maximum number of iterations is reached:
[0029] Randomly generate new candidate solutions in the search space, calculate the loss value corresponding to the new candidate solution according to the loss function, and evaluate and record the fitness of the new candidate solution according to the loss value;
[0030] Select new candidate solutions with better fitness to update some or all individuals in the population, and record the candidate solution with the highest fitness in the current population;
[0031] Perform a local search near the candidate solution with the highest fitness in the current population to generate a new candidate solution, calculate a loss value corresponding to the new candidate solution according to the loss function, and evaluate the fitness of the new candidate solution according to the loss value;
[0032] When the fitness of the new candidate solution is better than the fitness of the candidate solution with the highest fitness in the current population, the candidate solution with the highest fitness in the current population is updated.
[0033] Furthermore, based on the fuzzy inference mechanism, the fuzzy variables are converted into precise values to control the traffic lights, including:
[0034] Mapping the fuzzy variables to a series of fuzzy sets, and calculating the membership of the fuzzy variables in each fuzzy set based on a membership function;
[0035] A fuzzy rule base is created based on the natural language rules for controlling traffic lights and the membership of fuzzy variables in various fuzzy sets;
[0036] Based on the fuzzy reasoning mechanism, fuzzy reasoning is performed according to the input fuzzy variables and the rules in the fuzzy rule base, and a fuzzy output set is output. The fuzzy output set is defuzzified to obtain an accurate value, and the traffic light is controlled.
[0037] Furthermore, the membership of the fuzzy variable in each fuzzy set is calculated based on the membership function, wherein the membership function is expressed as:
[0038] (1);
[0039] In the formula, represents a fuzzy set, Represents a set of traffic flow data A traffic flow data in Represents each traffic flow data In fuzzy sets The degree of affiliation in .
[0040] In a second aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the first aspect.
[0041] In a third aspect, the present invention provides a computer-readable storage medium having a computer program / instruction stored thereon, which implements the steps of the method described in the first aspect when the computer program / instruction is executed by a processor.
[0042] In a fourth aspect, the present invention provides a computer program product, comprising a computer program / instruction, which implements the steps of the method described in the first aspect when executed by a processor.
[0043] Compared with the prior art, the present invention has the following beneficial effects:
[0044] 1. The present invention uses a short-term traffic flow prediction model to predict future traffic flow, which can adjust the timing of signal lights in advance, optimize traffic flow, and improve road traffic efficiency. The short-term traffic flow prediction model is optimized using the Pelican optimization algorithm, thereby improving the prediction accuracy and generalization ability of the short-term traffic flow prediction model.
[0045] 2. The present invention obtains the current traffic flow data of the road intersection in real time through the traffic detector, ensures the real-time and accuracy of the traffic light control decision, and effectively avoids the occurrence or deterioration of traffic congestion. The present invention combines the traffic flow prediction data with the current actual traffic flow data in a preset ratio, combines the forward-looking nature of the prediction data with the real-time nature of the actual data, and makes the control strategy more comprehensive and accurate, so as to better adapt to complex traffic conditions.
[0046] 3. The present invention also uses a type II fuzzy controller to process input data and output fuzzy variables. Based on the fuzzy reasoning mechanism, the fuzzy variables are converted into precise values to control the traffic lights. The fuzzy control strategy can be converted into a specific signal light timing plan to achieve precise control and improve the response speed and regulation effect of the traffic lights.
[0047] 4. The present invention optimizes the number of CNN layers, the number of BILSTM units, the learning rate and the regularization parameters of the short-term traffic flow prediction model through the Pelican optimization algorithm, and balances the global search and the local search by simulating the exploration and development stages of pelican hunting, so that the short-term traffic flow prediction model can better adapt to different traffic conditions. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] Figure 1 It is a flow chart of a type II fuzzy traffic signal light control method provided by an embodiment of the present invention;
[0049] Figure 2 It is a schematic diagram of a process for optimization using the Pelican optimization algorithm provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0050] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.
[0051] The term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the related objects are in an "or" relationship.
[0052] Example 1
[0053] like Figure 1 As shown, this embodiment introduces a type II fuzzy traffic signal light control method, including:
[0054] Obtain real-time traffic flow data at the current road intersection based on traffic detectors.
[0055] Traffic detectors such as geomagnetic sensors, cameras, radars, etc. can monitor the flow of vehicles on the road in real time and collect key information such as traffic volume, speed, and vehicle type.
[0056] The present invention obtains the vehicle flow data of the current road intersection in real time through the traffic detector, ensures the real-time and accuracy of the traffic signal light control decision, and effectively avoids the occurrence or deterioration of traffic congestion.
[0057] The real-time traffic flow data is input into a pre-trained short-term traffic flow prediction model for prediction to obtain traffic flow prediction data for the current road intersection in the future.
[0058] The short-term traffic flow prediction model provided by the present invention predicts the changes in traffic flow in the future by analyzing historical traffic flow data and real-time data, providing forward-looking information for traffic management, making the control of traffic lights more flexible and intelligent, and helping to alleviate traffic congestion.
[0059] The vehicle flow prediction data and the actual vehicle flow data of the current road intersection are combined in a preset ratio to form input data, which is input into a type-II fuzzy controller to output fuzzy variables.
[0060] Type II fuzzy controllers are able to handle uncertainty and ambiguity by combining predicted data with actual data to form more comprehensive input information.
[0061] The present invention combines the traffic flow prediction data with the current actual traffic flow data in a preset ratio, combining the forward-looking nature of the prediction data with the real-time nature of the actual data, making the control strategy more comprehensive and accurate, thereby being able to better adapt to complex traffic conditions.
[0062] Based on the fuzzy reasoning mechanism, the fuzzy variables are converted into precise values to control the traffic lights.
[0063] The fuzzy reasoning mechanism can derive accurate traffic light control strategies based on fuzzy variables and preset fuzzy rules.
[0064] The present invention can optimize traffic flow, reduce congestion and waiting time, and improve road traffic efficiency by accurately controlling the red and green light duration of traffic lights.
[0065] Among them, the Pelican optimization algorithm is used to optimize the short-term traffic flow prediction model.
[0066] The present invention is based on the pelican optimization algorithm, and optimizes the short-term traffic flow prediction model by simulating the foraging behavior of pelicans to search for the global optimal solution, thereby further improving the prediction accuracy and stability of the short-term traffic flow prediction model and making the prediction result more reliable.
[0067] Example 2
[0068] Based on the same inventive concept as that of Example 1, this embodiment introduces a type II fuzzy traffic signal light control method, which specifically includes the following steps:
[0069] Step 1: Obtain real-time traffic flow data at the current road intersection based on the traffic detector.
[0070] Before inputting the real-time traffic flow data into the pre-trained short-term traffic flow prediction model for prediction, the real-time traffic flow data is also pre-processed, including:
[0071] After adding a placeholder at the position where the real-time traffic flow data is missing, the average value between adjacent data is calculated and scaled to between 0 and 1 to obtain scaled data;
[0072] Normalizing the scaled data using a Min-MaxScaler method to obtain a data sequence;
[0073] The flat vectors in the data sequence are converted into a matrix with nine columns and four rows.
[0074] After data preprocessing, the real-time traffic flow data is divided into a training set, a validation set and a test set according to a preset ratio.
[0075] Step 2: Input the real-time traffic flow data into a pre-trained short-term traffic flow prediction model for prediction, and obtain the traffic flow prediction data of the current road intersection within the next 15 minutes.
[0076] The short-term traffic flow prediction model includes:
[0077] A multi-layer convolutional neural network (CNN) module is used to perform a sliding window operation on the real-time traffic flow data to extract spatial features of the real-time traffic flow data;
[0078] A bidirectional long short-term memory network BiLstm module is used to capture the long-term dependency between the spatial feature and the real-time traffic flow data of the current road intersection according to each time step of the spatial feature and the forward hidden state and the reverse hidden state, and obtain the feature information of all time steps of the spatial feature;
[0079] The fully connected layer is used to output the traffic flow prediction data of the current road intersection within the next 15 minutes based on the feature information of all time steps of the spatial features and based on weighted summation and activation function operations.
[0080] Among them, the Pelican optimization algorithm is used to optimize the short-term traffic flow prediction model, including:
[0081] The fitness function is used as the loss function of the short-term traffic flow prediction model;
[0082] Determine the hyperparameters that need to be optimized for the short-term traffic flow prediction model, including: the number of CNN convolutional layers, the number of BILSTM units, the learning rate and the regularization parameter;
[0083] In the search space, a group of candidate solutions with uniform distribution are randomly generated as initial hyperparameters of the short-term traffic flow prediction model to form a population;
[0084] like Figure 2 As shown, based on the Pelican optimization algorithm and the loss function, minimizing the prediction error is taken as the optimization goal, and the candidate solutions in the population and the fitness of each candidate solution are continuously updated through an iterative process, including:
[0085] Repeat the following steps until the preset maximum number of iterations is reached:
[0086] Randomly generate new candidate solutions in the search space, calculate the loss value corresponding to the new candidate solution according to the loss function, and evaluate and record the fitness of the new candidate solution according to the loss value;
[0087] Select new candidate solutions with better fitness to update some or all individuals in the population, and record the candidate solution with the highest fitness in the current population;
[0088] Perform a local search near the candidate solution with the highest fitness in the current population to generate a new candidate solution, calculate a loss value corresponding to the new candidate solution according to the loss function, and evaluate the fitness of the new candidate solution according to the loss value;
[0089] When the fitness of the new candidate solution is better than the fitness of the candidate solution with the highest fitness in the current population, the candidate solution with the highest fitness in the current population is updated.
[0090] After the iteration is completed, the candidate solution with the highest fitness is obtained as the optimal hyperparameter to configure the short-term traffic flow prediction model.
[0091] Based on the training set, the short-term traffic flow prediction model is trained to obtain a trained short-term traffic flow prediction model.
[0092] Based on the validation set, the short-term traffic flow prediction model is verified, and the mean square error MAE, standard error RMSE and mean absolute percentage error MAPE are used as evaluation indicators to evaluate the performance of the short-term traffic flow prediction model, and verify whether the short-term traffic flow prediction model provided by the present invention has advantages in prediction accuracy, stability and relative error. Compared with other prediction models in the prior art, the short-term traffic flow prediction model provided by the present invention shows smaller values in these three indicators, so the short-term traffic flow prediction model provided by the present invention has higher performance in short-term traffic flow prediction.
[0093] Step 3: Combine the predicted traffic flow data and the actual traffic flow data of the current road intersection according to a preset ratio to form input data, input the data into a type-II fuzzy controller, and output fuzzy variables.
[0094] Step 4: Based on the fuzzy reasoning mechanism, the fuzzy variables are converted into precise values to control the traffic lights, including:
[0095] Mapping the fuzzy variables to a series of fuzzy sets, and calculating the membership of the fuzzy variables in each fuzzy set based on a membership function;
[0096] A fuzzy rule base is created based on the natural language rules for controlling traffic lights and the membership of fuzzy variables in various fuzzy sets;
[0097] Wherein, the membership function is expressed as:
[0098] (1);
[0099] In the formula, represents a fuzzy set, Represents a set of traffic flow data A traffic flow data in Represents each traffic flow data In fuzzy sets The degree of affiliation in .
[0100] Based on the fuzzy reasoning mechanism, fuzzy reasoning is performed according to the input fuzzy variables and the rules in the fuzzy rule base, and a fuzzy output set is output. The fuzzy output set is defuzzified to obtain an accurate value, and the traffic light is controlled.
[0101] The performance of the precise value is evaluated using the average vehicle delay and the average vehicle queue length as evaluation indicators. Compared with other prediction models in the prior art, the average vehicle delay value and the average vehicle queue length value under the traffic light control strategy obtained by the method provided in this embodiment are smaller than those of other prediction models in the prior art.
[0102] Example 3
[0103] Based on the same inventive concept as other embodiments, this embodiment introduces a computer device, including a memory, a processor, and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the steps of the method described in Embodiment 1 or 2.
[0104] Example 4
[0105] Based on the same inventive concept as other embodiments, this embodiment introduces a computer-readable storage medium on which a computer program / instruction is stored, characterized in that the computer program / instruction implements the steps of the method described in Embodiment 1 or 2 when executed by a processor.
[0106] Example 5
[0107] Based on the same inventive concept as other embodiments, this embodiment introduces a computer program product, including a computer program / instruction, characterized in that the computer program / instruction implements the steps of the method described in Embodiment 1 or 2 when executed by a processor.
[0108] In summary, the present invention uses a short-term traffic flow prediction model to predict the traffic flow in the next 15 minutes, which can adjust the timing of signal lights in advance, optimize traffic flow, and improve road traffic efficiency. The short-term traffic flow prediction model is optimized using the Pelican optimization algorithm, which improves the prediction accuracy and generalization ability of the short-term traffic flow prediction model.
[0109] The present invention obtains the current traffic flow data of the road intersection in real time through the traffic detector, ensures the real-time and accuracy of the traffic signal control decision, and effectively avoids the occurrence or deterioration of traffic congestion. The present invention combines the traffic flow prediction data with the current actual traffic flow data in a preset ratio, combines the forward-looking nature of the prediction data with the real-time nature of the actual data, makes the control strategy more comprehensive and accurate, and can better adapt to complex traffic conditions.
[0110] The present invention also adopts a type-II fuzzy controller to process input data, output fuzzy variables, and based on the fuzzy reasoning mechanism, converts the fuzzy variables into precise values to control the traffic lights. It can convert the fuzzy control strategy into a specific traffic light timing plan, achieve precise control, and improve the response speed and regulation effect of the traffic lights.
[0111] The present invention optimizes the number of CNN layers, the number of BILSTM units, the learning rate and the regularization parameters of the short-term traffic flow prediction model through the Pelican optimization algorithm. By simulating the exploration and development stages of pelican hunting, the global search and the local search are balanced, so that the short-term traffic flow prediction model can better adapt to different traffic conditions.
[0112] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0113] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0114] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0116] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.
Claims
1. A type II fuzzy traffic signal light control method, characterized in that: include: Get real-time traffic flow data at the current road intersection; Inputting the real-time traffic flow data into a pre-trained short-term traffic flow prediction model for prediction to obtain traffic flow prediction data for the current road intersection in the future; Combining the predicted traffic flow data and the actual traffic flow data of the current road intersection according to a preset ratio to form input data, inputting the data into a type-II fuzzy controller, and outputting a fuzzy variable; Based on the fuzzy reasoning mechanism, the fuzzy variables are converted into precise values to control the traffic lights; Among them, the short-term traffic flow prediction model is optimized by the Pelican optimization algorithm.
2. The type II fuzzy traffic signal light control method according to claim 1, characterized in that: Before inputting the real-time traffic flow data into the pre-trained short-term traffic flow prediction model for prediction, the real-time traffic flow data is also pre-processed, including: After adding a placeholder at the position where the real-time traffic flow data is missing, the average value between adjacent data is calculated and scaled to between 0 and 1 to obtain scaled data; Normalizing the scaled data using a Min-MaxScaler method to obtain a data sequence; The flat vectors in the data sequence are converted into a matrix with nine columns and four rows.
3. The type II fuzzy traffic signal light control method according to claim 1, characterized in that: The short-term traffic flow prediction model includes: A multi-layer convolutional neural network (CNN) module is used to perform a sliding window operation on the real-time traffic flow data to extract spatial features of the real-time traffic flow data; A bidirectional long short-term memory network BiLstm module is used to capture the long-term dependency between the spatial feature and the real-time traffic flow data of the current road intersection according to each time step of the spatial feature and the forward hidden state and the reverse hidden state, and obtain the feature information of all time steps of the spatial feature; The fully connected layer is used to output the traffic flow prediction data of the current road intersection in the future based on the feature information of all time steps of the spatial features and the weighted summation and activation function operation.
4. The type II fuzzy traffic signal light control method according to claim 1, characterized in that: The short-term traffic flow prediction model is optimized using the Pelican optimization algorithm, including: The fitness function is used as the loss function of the short-term traffic flow prediction model; Determine the hyperparameters that need to be optimized for the short-term traffic flow prediction model, including: the number of CNN convolutional layers, the number of BILSTM units, the learning rate and the regularization parameter; In the search space, a group of candidate solutions with uniform distribution are randomly generated as initial hyperparameters of the short-term traffic flow prediction model to form a population; Based on the Pelican optimization algorithm and the loss function, minimizing the prediction error is taken as the optimization goal, and the candidate solutions in the population and the fitness of each candidate solution are continuously updated through an iterative process; After the iteration is completed, the candidate solution with the highest fitness is obtained as the optimal hyperparameter to configure the short-term traffic flow prediction model.
5. The type II fuzzy traffic signal light control method according to claim 4, characterized in that: Based on the Pelican optimization algorithm and the loss function, minimizing the prediction error is taken as the optimization goal, and the candidate solutions in the population and the fitness of each candidate solution are continuously updated through an iterative process, including: Repeat the following steps until the preset maximum number of iterations is reached: Randomly generate new candidate solutions in the search space, calculate the loss value corresponding to the new candidate solution according to the loss function, and evaluate and record the fitness of the new candidate solution according to the loss value; Select new candidate solutions with better fitness to update some or all individuals in the population, and record the candidate solution with the highest fitness in the current population; Perform a local search near the candidate solution with the highest fitness in the current population to generate a new candidate solution, calculate a loss value corresponding to the new candidate solution according to the loss function, and evaluate the fitness of the new candidate solution according to the loss value; When the fitness of the new candidate solution is better than the fitness of the candidate solution with the highest fitness in the current population, the candidate solution with the highest fitness in the current population is updated.
6. The type II fuzzy traffic signal light control method according to claim 1, characterized in that: The method of converting the fuzzy variables into precise values to control the traffic lights based on the fuzzy inference mechanism includes: Mapping the fuzzy variables to a series of fuzzy sets, and calculating the membership of the fuzzy variables in each fuzzy set based on a membership function; A fuzzy rule base is created based on the natural language rules for controlling traffic lights and the membership of fuzzy variables in various fuzzy sets; Based on the fuzzy reasoning mechanism, fuzzy reasoning is performed according to the input fuzzy variables and the rules in the fuzzy rule base, and a fuzzy output set is output. The fuzzy output set is defuzzified to obtain an accurate value, and the traffic light is controlled.
7. The type II fuzzy traffic signal light control method according to claim 6, characterized in that: The membership of the fuzzy variable in each fuzzy set is calculated based on the membership function, wherein the membership function is expressed as: （1）； In the formula, represents a fuzzy set, Represents a set of traffic flow data A traffic flow data in Represents each traffic flow data In fuzzy sets The degree of affiliation in .
8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.
9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.