Traffic artery coordination signal timing optimization method, system, equipment and medium

Abstract

The invention provides an arterial traffic coordination signal timing optimization method, system and device and a medium, and belongs to the field of traffic control, and the method comprises the steps: building a dynamic model of traffic signal control through a Markov decision process, obtaining a value function according to the traffic signal control model, and achieving the precise description of signal timing. A value function is introduced into a brightness function and a position updating function of a firefly algorithm, and an adaptive light intensity absorption coefficient and a dynamic random disturbance factor are introduced to improve the firefly algorithm, so that an improved firefly algorithm is obtained, and the global search capability of the firefly algorithm is improved. And performing optimization training on the adaptive neural fuzzy inference system through an improved firefly algorithm to obtain a signal timing optimization model. And outputting the adjustment amount of the signal timing parameter according to the signal timing optimization model, thereby realizing the self-adaptive intelligent control of the traffic signal timing. The method can be applied to a complex and changeable arterial traffic environment, and a signal timing optimization strategy is efficiently and accurately provided for the arterial traffic.

Description

Technical Field

[0001] The present invention belongs to the field of traffic control, and in particular relates to a method, system, equipment and medium for optimizing the timing of coordinated signals on traffic arterial lines. Background Art

[0002] As the backbone of the urban transportation network, arterial roads have large traffic volumes and high traffic density. The optimization of traffic signal control is of great significance to improving overall traffic efficiency. Traditional traffic signal timing methods are mostly based on fixed cycles or simple vehicle sensing, which are difficult to adapt to complex and changing traffic environments, resulting in vehicle delays and increased queue lengths, reducing road capacity. The complexity and dynamics of urban transportation networks make traffic signal control one of the key means to improve road efficiency and alleviate traffic congestion.

[0003] In recent years, intelligent optimization algorithms have received extensive attention in the field of traffic signal control. As an emerging bionic intelligent algorithm, the firefly algorithm has the advantages of strong global search capability and simple parameter adjustment, and has been applied to traffic signal timing optimization. However, when dealing with high-dimensional, nonlinear and multi-objective optimization problems, the standard firefly algorithm is prone to fall into local optimality and converges slowly, which limits its application in complex traffic environments. On the other hand, the Markov decision process (MDP), as a powerful tool for dealing with random dynamic systems, can effectively describe the state transition and decision-making process in traffic signal control. By representing the traffic state as a Markov state, MDP can formulate the optimal signal timing strategy based on the randomness of traffic flow. However, the computational complexity of MDP in high-dimensional state and action space is high, making it difficult to directly apply it to actual traffic systems. Summary of the invention

[0004] In order to solve the problem of optimizing the timing of coordinated signals on traffic arteries under complex traffic environments, the present invention provides a method, system, device and medium for optimizing the timing of coordinated signals on traffic arteries.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] A method for optimizing traffic arterial line coordinated signal timing, comprising the following steps:

[0007] Acquire the coordinated signal timing parameters and traffic flow parameters of the traffic artery, establish a traffic signal control model based on the Markov decision process MDP according to the coordinated signal timing parameters and traffic flow parameters of the traffic artery, and obtain the value function according to the traffic signal control model;

[0008] Introducing an adaptive light intensity absorption coefficient and a dynamic random disturbance factor into the firefly algorithm, and introducing the value function into the brightness function and position update function of the firefly algorithm to form an improved firefly algorithm; training an adaptive neural fuzzy inference system based on the improved firefly algorithm to obtain a signal timing optimization model;

[0009] The real-time traffic arterial data is input into the signal timing optimization model, and the adjustment amount of the signal timing parameters is output.

[0010] Preferably, a traffic signal control model based on a Markov decision process MDP is established according to the traffic artery coordinated signal timing parameters and traffic flow parameters, specifically comprising the following steps:

[0011] Obtain the state space vector S of the traffic artery, which includes the traffic status of each intersection, i.e., queue length and delay time. The state vector formula s t Specifically:

[0012] s t =[L q,1 (t),L q,2 (t),...,L q,N (t)];

[0013] Where t is time; N is the number of intersections on the trunk line; L q,N (t) represents the queue length;

[0014] Get the action space vector A of the traffic trunk line, which includes the signal timing strategy, i.e., the green light time, the red light time and the phase difference. t The specific formula is:

[0015] a t =[G1(t),G2(t),...,G N (t),θ1(t),θ2(t),...,θ N (t)];

[0016] Among them, θ N (t) is the phase difference of the Nth intersection; G N (t) is the effective green light time at the Nth intersection;

[0017] Establish a state transition probability function, which means that in a given state s t and action a t Under the condition that t+1 The probability is:

[0018]

[0019] In statust Take action a t The instant reward obtained is a reward function, which is specifically:

[0020]

[0021] Among them, T d,i (t) represents the delay time of the i-th intersection at time t; L q,i (t) represents the queue length; Q(t) represents the traffic capacity;

[0022] From the state t Initially, the expected value of future cumulative rewards is the value function, which is specifically:

[0023]

[0024] Among them, γ∈(0,1) is the discount factor; E is the expected value;

[0025] The value function V(s t ) is calculated using the Bellman equation, which is:

[0026]

[0027] The value iteration algorithm is used to solve the value function, specifically:

[0028]

[0029] Preferably, it also includes setting an objective function and constraints for the traffic signal control model, wherein the objective function is specifically:

[0030]

[0031] The constraints are specifically constraints on signal period, green-to-signal ratio, phase difference, minimum green light time and saturation, specifically:

[0032]

[0033]

[0034] Among them, g i is the green signal ratio of the i-th intersection; θ i is the phase difference of the i-th intersection; G i is the effective green light time of the i-th intersection; R i is the red light time at the i-th intersection; i (t) represents the saturation of the i-th intersection at time t, α represents the average vehicle length; μ represents the average vehicle speed.

[0035] Preferably, the value function is introduced into the brightness function and position update function of the firefly algorithm, and the adaptive light intensity absorption coefficient and the dynamic random disturbance factor are introduced to form an improved firefly algorithm, specifically through the following steps:

[0036] The value function is introduced into the brightness function, specifically:

[0037]

[0038] Among them, F i is the objective function value of the i-th firefly, is the value function of the corresponding state of the i-th firefly, and ε is the minimum value that avoids division by zero;

[0039] The attraction function in the firefly algorithm is specifically:

[0040]

[0041] Among them, γ ij is the value function of the corresponding state of the i-th firefly; β0 is the initial attractiveness of the firefly; r ij represents the Euclidean distance between the i-th firefly and the j-th firefly;

[0042] The position update function is specifically:

[0043]

[0044] in, is the value of the firefly i in the kth dimension of the lth generation; ε k is a random number that follows a standard normal distribution; α (l) is the dynamic random disturbance factor;

[0045] Set the parameters for adaptive adjustment, where the adaptive light intensity absorption coefficient γ ij The adjustment formula is as follows, the random perturbation factor α (l) The adjustment formula is:

[0046] α (l) =α max ·e -ηl ;

[0047] Where η is the attenuation coefficient;

[0048] When updating the location, take the current state into account and actions The impact on the value function, choose to make the value function Move in the direction of maximum;

[0049] By calculating the partial derivative of the value function with respect to the action and the partial derivative of the action with respect to the decision variable, the value gradient of the value function is obtained, which is:

[0050]

[0051] Based on the value function, the specific formula is as follows:

[0052]

[0053] Among them, λ is the learning rate.

[0054] Preferably, the adaptive neural fuzzy inference system is trained based on the improved firefly algorithm to obtain a signal timing optimization model, which specifically includes the following steps:

[0055] Collect and coordinate intersection traffic data, including queue length L q,i (t), vehicle speed v i (t), saturation λ i (t) and the corresponding optimal green light time adjustment ΔG i (t);

[0056] Randomly initialize the firefly population and obtain the firefly population parameters;

[0057] Input firefly population parameters and calculate the fitness function, which is specifically:

[0058]

[0059] Where M is the sample size; is the actual output; The output predicted by the ANFIS model;

[0060] According to the fitness function value, the position of the fireflies is updated, that is, the parameters of the ANFIS model;

[0061] The model is trained until the convergence condition is met to obtain the signal timing optimization model.

[0062] Preferably, it also includes establishing fuzzy rules in the adaptive neural fuzzy inference system, and the fuzzy rules are specifically: when the length of the vehicle queue is long and the traffic flow is large, the green light time is extended; when the length of the vehicle queue is short and the traffic flow is small, the green light time is shortened.

[0063] The present invention also provides a traffic arterial coordinated signal timing optimization system, which specifically includes:

[0064] The coordination control module is used to obtain the coordination signal timing parameters and traffic flow parameters of the traffic artery, establish a traffic signal control model based on the Markov decision process MDP according to the coordination signal timing parameters and traffic flow parameters of the traffic artery, and obtain a value function according to the traffic signal control model.

[0065] A model building module is used to introduce the value function into the brightness function and position update function of the firefly algorithm, and introduce an adaptive light intensity absorption coefficient and a dynamic random disturbance factor to form an improved firefly algorithm; based on the improved firefly algorithm, an adaptive neural fuzzy inference system is trained to obtain a signal timing optimization model.

[0066] The decision output module is used to input real-time traffic arterial data into the signal timing optimization model and output the adjustment amount of the signal timing parameters.

[0067] The present invention also provides a computer device, including a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps described in the method for optimizing the coordinated signal timing of traffic arterial lines.

[0068] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is loaded by a processor, the steps described in the method for optimizing the coordinated signal timing of traffic arterial lines can be executed.

[0069] The traffic arterial coordinated signal timing optimization method provided by the present invention has the following beneficial effects:

[0070] The present invention uses the Markov decision process to establish a dynamic model of traffic signal control and obtains a value function. The value function is introduced into the brightness function and position update function of the firefly algorithm, and the adaptive light intensity absorption coefficient and the dynamic random disturbance factor are introduced to obtain an improved firefly algorithm, thereby improving the global search capability and processing efficiency of the firefly algorithm. The adaptive neural fuzzy inference system is trained according to the improved firefly algorithm to obtain a signal timing optimization model. The signal timing optimization model can dynamically adjust the signal timing of traffic arteries according to real-time traffic conditions, and fully considers the optimization method of dynamic characteristics and uncertainty of traffic flow, thereby improving the intelligence and adaptability of signal timing. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the embodiment of the present invention and its design scheme, the following briefly introduces the drawings required for this embodiment. 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.

[0072] Figure 1 The present invention is a flow chart of a method for optimizing the timing of coordinated traffic signal lines.

[0073] Figure 2 Schematic diagram of the Markov state transition matrix in the embodiment of the present invention.

[0074] Figure 3 This is a diagram of the improved firefly algorithm in an embodiment of the present invention.

[0075] Figure 4 Graph showing the output surface of the adaptive neuro-fuzzy inference system in an embodiment of the present invention.

[0076] Figure 5 This is the optimized traffic flow distribution diagram in the embodiment of the present invention.

[0077] Figure 6 This is a queue length diagram after optimization in an embodiment of the present invention.

[0078] Figure 7 4 is a comparison chart of different algorithms in the embodiments of the present invention.

[0079] Figure 8 This is a heat map of fuzzy rule activation in an embodiment of the present invention.

[0080] Fig. 9 This is a graph showing how queue length changes with the number of iterations in an embodiment of the present invention. DETAILED DESCRIPTION

[0081] In order to enable those skilled in the art to better understand the technical solution of the present invention and implement it, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the scope of protection of the present invention.

[0082] Example

[0083] In view of the problems of insufficient optimization and poor adaptability in current urban traffic signal control, the present invention proposes a method for optimizing coordinated signal timing of traffic arterial lines. A dynamic model of traffic signal control is established using the Markov decision process to provide a mathematical model basis for traffic signal timing optimization. The value function of the Markov decision process is integrated into the firefly algorithm, and the value function information is introduced in the brightness calculation and position update process to overcome the problem that traditional optimization algorithms are prone to fall into local optimality; the parameters, state transition probability, and reward function of the Markov decision process and the improved firefly algorithm are set. The adaptive neural fuzzy inference system is combined with the improved firefly algorithm and the Markov decision process to construct an adaptive signal timing optimization model. By integrating the learning ability of neural networks and the reasoning ability of fuzzy logic, the model's ability to handle nonlinear and uncertain problems is enhanced, such as Figure 1As shown, the specific steps include:

[0084] S1. Establish a traffic signal control model based on Markov decision process (MDP), define system state, action, transition probability and reward function, and represent the traffic state as Markov state, such as Figure 2 As shown in the figure, a multi-objective optimization model is constructed with the goals of minimizing vehicle delay time, queue length and maximizing trunk line capacity.

[0085] S11: define the trunk line coordination signal timing parameters, specifically: N is the number of intersections on the trunk line; C is the signal cycle (seconds), and the trunk line intersection signal cycle is the same in the present invention; G i is the effective green light time of the ith intersection (seconds); R i is the red light time of the i-th intersection (seconds); θ i is the phase difference of the ith intersection (seconds); g i is the green signal ratio of the i-th intersection, is the red signal ratio of the i-th intersection,

[0086] S12: Define traffic flow parameters. The symbols and descriptions are as follows: v i (t) represents the traffic flow (vehicles / hour) of the ith intersection at time t, which is regarded as a random variable in the present invention; s i represents the saturated flow rate of the ith intersection (vehicles / hour); i (t) represents the saturation of the i-th intersection at time t, α represents the average vehicle length (meters), including the headway between vehicles; μ represents the average vehicle speed (meters / second).

[0087] S13: Establish a Markov decision process (MPD) to describe the random process of coordinated traffic signal control on trunk lines. The definition and formula are as follows: First, define the state space S, which mainly includes the traffic state of each intersection, which refers to the queue length and delay time in this invention. The state vector formula is as follows:

[0088] s t =[L q,1 (t),L q,2 (t),...,L q,N (t)];

[0089] Where t is time; N is the number of intersections on the trunk line; L q,N (t) represents the queue length.

[0090] Define the action space A, which mainly includes the signal timing strategy, which refers to the green light time, red light time and phase difference in this invention.t The formula is as follows:

[0091] a t =[G1(t),G2(t),...,G N (t),θ1(t),θ2(t),...,θ N (t)];

[0092] State transition probability P(s t+1 |s t ,a t ), indicating that in a given state s t and action a t Under the condition that t+1 The probability of state transition is as follows:

[0093]

[0094] Set the reward function R(s t ,a t ), indicating that in state s t Take action a t The instant reward obtained, the reward function formula is as follows:

[0095]

[0096] Where: T d,i (t) represents the delay time of the i-th intersection at time t; L q,i (t) represents the queue length; Q(t) represents the traffic capacity.

[0097] In the MDP framework, the value function V(s t ) is used to evaluate the expected cumulative reward that can be obtained by taking a certain action in a specific state. Specifically: Set the value function V(s t ), indicating that from state s t To begin with, the expected value of future cumulative rewards, the specific formula is as follows:

[0098]

[0099] Where: γ∈(0,1) is the discount factor; E is the expected value.

[0100] Value function V(s t ) is calculated using the Bellman equation, which is as follows:

[0101]

[0102] To solve the value function, the value iteration algorithm is used. The specific formula is as follows:

[0103]

[0104] S14: Construct a traffic flow probability density function to describe the randomness of traffic flow. Assuming that traffic flow follows a normal distribution, the formula is as follows:

[0105]

[0106] Where: μ i represents the average traffic volume; Represents variance.

[0107] Taking into account the delay time, queue length and traffic capacity, the goal is to maximize the cumulative reward, that is, to minimize the comprehensive traffic cost. The objective function formula is as follows:

[0108]

[0109] S15: Set constraints, which are signal period constraint, green-to-signal ratio constraint, phase difference constraint, minimum green light time constraint and saturation constraint. The specific formulas are as follows:

[0110] Signal period constraint:

[0111] Green letter ratio constraints:

[0112] Phase difference constraint:

[0113] Minimum green light time constraint:

[0114] Saturation constraint:

[0115] S2. Use the improved firefly algorithm to optimize the trunk coordination signal timing, such as Figure 3 As shown, the improved Firefly Algorithm (IFA) has two main improvements.

[0116] 1) The adaptive light intensity absorption coefficient γ and the dynamic random perturbation factor α are introduced to improve the convergence speed and global search capability of the algorithm.

[0117] 2) Combined with the value function of MDP, the value function V(s t ) is used to evaluate the pros and cons of traffic signal timing strategies, and then guide the optimization process of the improved firefly algorithm (IFA), introducing the information of the value function in brightness calculation and position update.

[0118] S21: Define the algorithm parameters. The symbols and descriptions are as follows: Lmax : Maximum number of iterations; γ: light intensity absorption coefficient, adaptive adjustment; β0: initial attraction of fireflies; α: random perturbation factor, dynamic adjustment.

[0119] S22: Brightness function part, based on the traditional brightness function, combined with the value function of MDP, the brightness function formula is as follows:

[0120]

[0121] Among them: F i is the objective function value of the i-th firefly, containing information about the value function, and ε is the minimum value that avoids division by zero.

[0122] The objective function value formula is as follows:

[0123]

[0124] in: is the value function of the corresponding state of the i-th firefly.

[0125] The attractiveness function value formula is as follows:

[0126]

[0127] Where: γ ij is the value function of the corresponding state of the i-th firefly; r ij represents the Euclidean distance between the i-th firefly and the j-th firefly.

[0128] The location update formula is as follows:

[0129]

[0130] in: is the value of the firefly i in the kth dimension of the lth generation; ε k is a random number that follows a standard normal distribution; α (l) is the dynamic random disturbance factor.

[0131] Then set the parameters for adaptive adjustment, random perturbation factor α (l) The adjustment formula is as follows:

[0132] α( l )=α max ·e -ηl ;

[0133] Where: η is the attenuation coefficient.

[0134] To improve the firefly algorithm, we need to combine MDP to update the position. When updating the position, we need to consider the current state. and actions The impact on the value function, choose to make the value function Move in the direction of maximum.

[0135] S23: When calculating the value gradient of the value function, it is necessary to calculate the partial derivative of the value function with respect to the action, and the partial derivative of the action with respect to the decision variable. The specific formula is as follows:

[0136]

[0137] Based on the value function, the specific formula is as follows:

[0138]

[0139] Where: λ is the learning rate.

[0140] S24: The penalty function method is used to penalize the objective function value of the solution that violates the constraint, where the penalty function formula is as follows:

[0141]

[0142] Where: M is the penalty coefficient; M c is the number of constraints.

[0143] S3. To ensure the effectiveness and accuracy of the algorithm, the algorithm parameters, traffic parameters and model parameters are set and initialized in detail. The algorithm parameters and traffic parameters are set as follows:

[0144] Set algorithm parameters for the firefly algorithm: population size n: take the value of 50, that is, optimize 50 candidate solutions at the same time to ensure the diversity of the population and the global search ability of the algorithm; maximum number of iterations L max : Set to 500 to ensure that the algorithm has enough iterations to converge to the optimal solution; Initial attraction β0: The value is 1, indicating the maximum attraction of fireflies in the initial situation; The range of light absorption coefficient γ: Minimum value γ min : Set to 0.1 to ensure that the attraction does not decay too quickly, which is conducive to global search, and the maximum value γ max : Set to 1 to prevent the attraction from being too concentrated and facilitate local search; the maximum value of the random perturbation factor α max : set to 0.5 to increase the initial search diversity; decay coefficient η: set to 0.01, so that α decays exponentially with the number of iterations; learning rate λ: set to 0.1, used for step size control of the value function gradient; penalty coefficient M is set to 10 6 , used for the penalty intensity of the constraint condition.

[0145] For the Markov decision process parameters, set the algorithm parameters as follows: Discount factor λMDP : The value is 0.9, indicating the importance of future rewards; state space S and action space A: discretized according to the actual traffic system, and the discrete granularity is determined according to the computing power and balance effect; time step Δt: set to 15 seconds, corresponding to the minimum unit of the signal cycle.

[0146] The traffic parameters are set as follows:

[0147] Main road parameters: number of intersections N: set to 3, representing 3 consecutive intersections on the main road that need coordinated control; signal cycle C: set to 120 seconds; minimum green light time G min : Set to 10 seconds to ensure the safe passage of pedestrians and vehicles; maximum saturation λ max : Set to 0.9 to avoid traffic collapse caused by oversaturation.

[0148] Traffic flow parameters, traffic flow variance: set according to the fluctuation of historical data Saturation flow i : The value is 1800pcu / h; Average vehicle length α: The value is 7.5m, including the headway; Average vehicle speed μ: Set to 55km / h; Average traffic flow μ: Set the average flow at each intersection based on historical data. The parameters are as follows:

[0149]

[0150] S4. Introduce the Adaptive Neuro-Fuzzy Inference System (ANFIS) and combine it with the improved firefly algorithm to build a signal timing optimization model. This model can adaptively adjust the signal timing strategy in a complex traffic environment, improve the efficiency and stability of trunk traffic, and achieve a deep integration of ANFIS, the improved firefly algorithm and the Markov decision process.

[0151] Adaptive neuro-fuzzy inference system (ANFIS) is a hybrid intelligent system that combines neural network and fuzzy logic, with learning and fuzzy reasoning capabilities. It can automatically generate fuzzy rules by learning input and output data to achieve modeling and control of complex nonlinear systems.

[0152] According to the characteristics of traffic flow, fuzzy rules between input and output are established, such as Figure 8 The following is a heat map of fuzzy rule activation. The two rules are as follows:

[0153] Rule 1: If the queue length is long and the traffic volume is heavy, extend the green light time.

[0154] Rule 2: If the queue length is short and the traffic volume is light, shorten the green light time.

[0155] The input variables x1, x2, and x3 are the lengths of the vehicle queues L q,i (t), vehicle speed v i (t), the time saturation of the intersection λ i (t), the output variable y is the green light time adjustment ΔG i (t), such as Figure 4 The ANFIS model is integrated with the improved firefly algorithm, and the improved firefly algorithm is used to optimize the parameters of the ANFIS model, including the membership function parameter c i ,σ i And the rule output function parameter p ki ,r k , and carry out integrated optimization, which specifically includes the following steps:

[0156] S41: Data collection collects and coordinates intersection traffic data, including L q,i (t), v i (t), λ i (t) and the corresponding optimal green light time adjustment ΔG i (t).

[0157] S42: Initialize the firefly population, randomly initialize the firefly population, and each firefly represents a parameter set of the ANFIS model.

[0158] S43: Calculate the fitness function. The formula is as follows:

[0159]

[0160] Where: M is the sample size; is the actual output; is the output predicted by the ANFIS model.

[0161] S44: Update the position of the fireflies, use the improved firefly algorithm, and update the position of the fireflies according to the brightness (fitness function value), that is, the parameters of the ANFIS model.

[0162] S45: Train the ANFIS model, repeat S43 and S44 until the convergence condition is met, that is, the maximum number of iterations is 1000, and then perform model optimization and signal timing adjustment. Fig. 9 Shown is a graph showing the queue length in a traffic artery changing with the number of iterations.

[0163] Adjust the green time ΔG according to the output of the ANFIS model i (t), green light time adjustment ΔG i(t) represents the green light time that needs to be increased or decreased for each intersection i under the current traffic conditions. The green light update time formula is as follows:

[0164] G i (t+1)=G i (t)+ΔG i (t);

[0165] Under the new green light time, calculate other signal timing parameters to ensure that the constraints are met: red light time R i (t+1)=CG i (t+1).

[0166] Phase difference adjustment, according to the Markov decision process, combined with the current traffic status, adjust the phase difference θ i (t+1). The adjusted phase difference is integrated with the Markov decision process, and at each decision time t i Green light time adjustment ΔG predicted by ANFIS model i (t), update the system state st. The state transition probability P(s t+1 |s t ,a t ) is determined by the output of the ANFIS model. The specific composition of the system state includes a variety of key indicators that reflect the current status of the traffic system, including: traffic flow, vehicle queue length, saturation and signal timing parameters.

[0167] Among them, the input variables and output variables of the ANFIS model are derived from the trunk coordination model to ensure data consistency between models. The traffic signal control model provides macroscopic traffic status information, which, combined with the improved firefly algorithm, provides a basis for the training and prediction of the ANFIS model. The improved firefly algorithm is not only used to optimize signal timing parameters, but also to optimize the parameters of the ANFIS model, achieving the unification and coordination of the algorithm and handling different optimization objectives under the same algorithm framework. The parameter setting module provides the initial algorithm parameters, traffic parameters and model parameters, laying the foundation for the training of the ANFIS model and the operation of the improved firefly algorithm.

[0168] The innovation of the present invention lies in (1) using the Markov decision process (MDP) to establish a dynamic model of traffic signal control. By expressing the traffic state as a Markov state, the description of traffic signal timing is realized. (2) An improved firefly algorithm is proposed and applied to traffic signal optimization, and an improved firefly algorithm (IFA) with an adaptive light intensity absorption coefficient is designed. The value function of the Markov decision process is integrated into the algorithm, and the value function information is introduced in the brightness calculation and position update to improve the global search ability of the algorithm. (3) The adaptive neural fuzzy inference system is combined with the improved firefly algorithm and the Markov decision process. The ANFIS model parameters are optimized by the improved firefly algorithm to realize adaptive intelligent control of traffic signal timing. The learning ability of the neural network and the reasoning ability of fuzzy logic are integrated to enhance the model's ability to handle nonlinear and uncertain problems. The traffic flow, queue length and comparison with different algorithms after optimization by the present invention correspond to: Figure 5 , Figure 6 and Figure 7 .

[0169] The present invention also provides a traffic arterial coordinated signal timing optimization system, which specifically includes:

[0170] The coordination control module is used to obtain the coordinated signal timing parameters and traffic flow parameters of the traffic artery, establish a traffic signal control model based on the Markov decision process MDP according to the coordinated signal timing parameters and traffic flow parameters of the traffic artery, and obtain the value function according to the traffic signal control model.

[0171] The model building module is used to introduce the value function into the brightness function and position update function of the firefly algorithm, and introduce the adaptive light intensity absorption coefficient and the dynamic random disturbance factor to form an improved firefly algorithm; based on the improved firefly algorithm, the adaptive neural fuzzy inference system is trained to obtain the signal timing optimization model.

[0172] The decision output module is used to input real-time traffic arterial data into the signal timing optimization model and output the adjustment amount of the signal timing parameters.

[0173] Each module in the above-mentioned traffic artery coordinated signal timing optimization system can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module above.

[0174] The present invention also provides a computer device, including a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps in an embodiment of a method for optimizing the coordinated signal timing of a traffic artery. The specific implementation method can be found in the method embodiment, which will not be described in detail here.

[0175] Furthermore, the present invention also provides a non-temporary computer-readable storage medium containing instructions, and a computer program is stored on the storage medium. For example, a memory containing instructions, the above instructions can be executed by a processor of a computer device to complete the above method. For example, a non-temporary computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device. When the computer program is executed by the processor, it can implement the steps in an embodiment of a method for optimizing the coordinated signal timing of a traffic artery. The specific implementation method can be found in the method embodiment, which will not be repeated here.

[0176] It will be appreciated by those skilled in the art that embodiments of the present invention may provide 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. Moreover, 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.

[0177] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (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 a 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.

[0178] 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.

[0179] 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.

[0180] It should be pointed out that the specific implementation methods described above can enable those skilled in the art to understand the invention more comprehensively, but do not limit the invention in any way. Therefore, although the invention has been described in detail in this specification and embodiments, those skilled in the art should understand that the invention can still be modified or replaced by equivalents; and all technical solutions and improvements that do not deviate from the spirit and scope of the invention are included in the protection scope of the patent for the invention. Any figure mark in the claims should not be regarded as limiting the claims involved. Any simple change or equivalent replacement of the technical solution that can be obviously obtained by any technician familiar with the field within the technical scope disclosed in the present invention belongs to the protection scope of the present invention.

Claims

1. A traffic artery coordinated signal timing optimization method, characterized in that: The following steps are involved: Acquire the coordinated signal timing parameters and traffic flow parameters of the traffic artery, establish a traffic signal control model based on the Markov decision process MDP according to the coordinated signal timing parameters and traffic flow parameters of the traffic artery, and obtain the value function according to the traffic signal control model; The value function is introduced into the brightness function and position update function of the firefly algorithm, and the adaptive light intensity absorption coefficient and the dynamic random disturbance factor are introduced to form an improved firefly algorithm; based on the improved firefly algorithm, an adaptive neural fuzzy inference system is trained to obtain a signal timing optimization model; The real-time traffic arterial data is input into the signal timing optimization model, and the adjustment amount of the signal timing parameters is output.

2. A traffic artery coordinated signal timing optimization method according to claim 1, characterized in that: A traffic signal control model based on the Markov decision process MDP is established according to the traffic artery coordinated signal timing parameters and traffic flow parameters, which specifically includes the following steps: Obtain the state space vector S of the traffic artery, which includes the traffic status of each intersection, i.e., queue length and delay time. The state vector formula s t Specifically: s t =[L q,1 (t),L q,2 (t),...,L q,N (t)]; Where t is time; N is the number of intersections on the trunk line; L q,N (t) represents the queue length; Get the action space vector A of the traffic trunk line, which includes the signal timing strategy, i.e., the green light time, the red light time and the phase difference. t The specific formula is: a t =[G1(t),G2(t),...,G N (t),θ1(t),θ2(t),...,θ N (t)]; Among them, θ N (t) is the phase difference of the Nth intersection; G N (t) is the effective green light time at the Nth intersection; Establish a state transition probability function, which means that in a given state s t and action a t Under the condition that t+1 The probability is: In status t Take action a t The instant reward obtained is a reward function, which is specifically: Among them, T d,i (t) represents the delay time of the i-th intersection at time t; L q,i (t) represents the queue length; Q(t) represents the traffic capacity; From the state t Initially, the expected value of future cumulative rewards is the value function, which is specifically: Among them, γ∈(0,1) is the discount factor; E is the expected value; The value function V(s t ) is calculated using the Bellman equation, which is: The value iteration algorithm is used to solve the value function, specifically:

3. A traffic artery coordinated signal timing optimization method according to claim 2, characterized in that: It also includes setting an objective function and constraints for the traffic signal control model, wherein the objective function is specifically: The constraints are specifically constraints on signal period, green-to-signal ratio, phase difference, minimum green light time and saturation, specifically: Among them, g i is the green signal ratio of the i-th intersection; θ i is the phase difference of the i-th intersection; G i is the effective green light time of the i-th intersection; R i is the red light time at the i-th intersection; i (t) represents the saturation of the i-th intersection at time t, α represents the average vehicle length; μ represents the average vehicle speed.

4. A traffic artery coordinated signal timing optimization method according to claim 1, characterized in that: The value function is introduced into the brightness function and position update function of the firefly algorithm, and the adaptive light intensity absorption coefficient and the dynamic random disturbance factor are introduced to form an improved firefly algorithm, which is specifically implemented by the following steps: The value function is introduced into the brightness function, specifically: Among them, F i is the objective function value of the i-th firefly, is the value function of the corresponding state of the i-th firefly, and ε is the minimum value that avoids division by zero; The attraction function in the firefly algorithm is specifically: Among them, γ ij is the value function of the corresponding state of the i-th firefly; β0 is the initial attractiveness of the firefly; r ij represents the Euclidean distance between the i-th firefly and the j-th firefly; The position update function is specifically: in, is the value of the firefly i in the kth dimension of the lth generation; ε k is a random number that follows a standard normal distribution; α( l ) is the dynamic random disturbance factor; Set the parameters for adaptive adjustment, where the adaptive light intensity absorption coefficient γ ij The adjustment formula is as follows, the random perturbation factor α (l) The adjustment formula is: Where η is the attenuation coefficient; When updating the location, take the current state into account and actions The impact on the value function, choose to make the value function Move in the direction of maximum; By calculating the partial derivative of the value function with respect to the action and the partial derivative of the action with respect to the decision variable, the value gradient of the value function is obtained, which is: Based on the value function, the specific formula is as follows: Among them, λ is the learning rate.

5. A traffic artery coordinated signal timing optimization method according to claim 1, characterized in that: Based on the improved firefly algorithm, the adaptive neural fuzzy inference system is trained to obtain a signal timing optimization model, which specifically includes the following steps: Collect and coordinate intersection traffic data, including queue length L q,i (t), vehicle speed v i (t), saturation λ i (t) and the corresponding optimal green light time adjustment ΔG i (t); Randomly initialize the firefly population and obtain the firefly population parameters; Input firefly population parameters and calculate the fitness function, which is specifically: Where M is the sample size; is the actual output; The output predicted by the adaptive neuro-fuzzy inference system ANFIS model; According to the fitness function value, the position of the fireflies is updated, that is, the parameters of the ANFIS model; The model is trained until the convergence condition is met to obtain the signal timing optimization model.

6. A traffic artery coordinated signal timing optimization method according to claim 1, characterized in that: It also includes establishing fuzzy rules in the adaptive neural fuzzy inference system, wherein the fuzzy rules are as follows: when the length of the vehicle queue is long and the traffic flow is large, the green light time is extended; when the length of the vehicle queue is short and the traffic flow is small, the green light time is shortened.

7. A traffic artery coordinated signal timing optimization system, characterized in that: include: A coordination control module, used for obtaining the coordination signal timing parameters and traffic flow parameters of the traffic artery, establishing a traffic signal control model based on the Markov decision process MDP according to the coordination signal timing parameters and traffic flow parameters of the traffic artery, and obtaining a value function according to the traffic signal control model; A model building module is used to introduce the value function into the brightness function and position update function of the firefly algorithm, and introduce an adaptive light intensity absorption coefficient and a dynamic random disturbance factor to form an improved firefly algorithm; based on the improved firefly algorithm, an adaptive neural fuzzy inference system is trained to obtain a signal timing optimization model; The decision output module is used to input real-time traffic arterial data into the signal timing optimization model and output the adjustment amount of the signal timing parameters.

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 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is loaded into a processor, it can execute the steps of the method according to any one of claims 1 to 6.

Images