Multi-modal congestion propagation optimization method for internet of vehicles based on niche genetic algorithm

Abstract

The application discloses a multi-modal vehicle networking congestion propagation optimization method based on a niche genetic algorithm, and comprises the following steps: acquiring vehicle networking information; performing mathematical modeling on a vehicle networking congestion propagation influence maximization problem by using the vehicle networking information, and obtaining a congestion propagation dynamic mechanism and a target function of maximizing the number of vehicle networking congestion road sections; and using a genetic algorithm based on a fitness sharing niche technique to maximize the number of vehicle networking congestion road sections, and calculating a plurality of heterogeneous congestion road section combinations capable of maximizing the number of vehicle networking congestion road sections. The application solves the problem that existing methods are limited to generating only a single road section combination capable of maximizing the influence of a road network congestion state, and the genetic algorithm based on the fitness sharing niche technique and the plurality of heterogeneous and excellent road section combinations capable of providing the vehicle networking congestion propagation influence maximization problem in a single evolution process.

Description

Technical Field

[0001] This invention relates to the field of multimodal vehicle network congestion optimization technology, specifically to a multimodal vehicle network congestion propagation optimization method based on niche genetic algorithm. Background Technology

[0002] Existing traffic management systems face numerous challenges. For example, with the number of motor vehicles increasing year by year, traffic volume is growing, while the optimization of traffic infrastructure is a long-term process. This has led to increasingly serious traffic congestion problems in the existing vehicle-to-everything (V2X) network. How to alleviate or avoid V2X congestion is an urgent problem to be solved.

[0003] Due to limited infrastructure costs, optimizing existing road networks is time-consuming and sequential. Therefore, to improve current vehicle-to-everything (V2X) congestion, one can first identify several critical road segments that maximize the spread of congestion and optimize these segments to improve traffic flow. Secondly, policymakers often prefer combinations of such critical road segments to make more informed network optimization decisions, which necessitates solving multimodal V2X congestion optimization problems. However, multimodal V2X congestion optimization is a complex problem, characterized by complex road network structures, abstract dynamic mechanisms for congestion spread, and a multi-peak solution space, making it difficult for traditional optimization algorithms to solve effectively.

[0004] Evolutionary computation combined with niche techniques is frequently used to solve complex multimodal optimization problems and is widely applied across various fields. For the problem of maximizing the impact of congestion propagation in multimodal vehicular networks (V2X), this method can efficiently find peaks in a multi-peak solution space, thus providing multiple distinct but all well-performing solutions. However, the propagation mechanism of road congestion states in V2X is complex, requiring a combination of complex network state propagation and traffic flow modeling. When applying evolutionary computation to solve the problem of maximizing the impact of congestion propagation in V2X, it is necessary to design fitness evaluation metrics that can help the selection mechanism accurately choose the optimal solution. Furthermore, there is currently no research on maximizing the impact of congestion propagation in V2X from a multimodal optimization perspective; therefore, it is necessary to select appropriate niche techniques in this context to more accurately find multiple significant peaks in the solution space. Thus, how to apply evolutionary computation combined with niche techniques to find multiple heterogeneous solutions to the problem of maximizing the impact of congestion propagation in V2X remains an unsolved problem. Summary of the Invention

[0005] To overcome the shortcomings and deficiencies of existing technologies, this invention provides a multimodal vehicle network congestion propagation optimization method based on a niche genetic algorithm. This invention encodes a fixed number of road segment combinations as individuals in the genetic algorithm and designs a fitness function to evaluate the congestion propagation influence of each individual, utilizing the road and traffic flow characteristics in the vehicle network. This function effectively quantifies the propagation influence of each individual. Based on this, a niche technology operator based on fitness sharing is designed and embedded into the classic genetic algorithm. After multiple evolutionary iterations, each niche can occupy different peaks in the solution space of the problem of maximizing the congestion propagation influence in the vehicle network, thus ultimately generating multiple heterogeneous road segment combinations that maximize the congestion propagation influence. This addresses the problem of existing technologies failing to consider solving for road segment combinations that maximize the congestion influence in the vehicle network from a multimodal optimization perspective, thus limiting the problem to generating only a single road segment combination that maximizes the impact of road network congestion.

[0006] The second objective of this invention is to provide a multimodal vehicle-to-everything (V2X) congestion propagation optimization system based on a niche genetic algorithm;

[0007] A third objective of this invention is to provide a computer-readable storage medium;

[0008] A fourth objective of this invention is to provide a computer device.

[0009] To achieve the above objectives, the present invention adopts the following technical solution:

[0010] This invention provides a multimodal vehicle-to-everything (V2X) congestion propagation optimization method based on a niche genetic algorithm, comprising the following steps:

[0011] Obtain vehicle network information;

[0012] Mathematical modeling is used to maximize the impact of vehicle network congestion propagation on vehicle network information, resulting in a dynamic mechanism of congestion propagation and an objective function that maximizes the number of congested road segments in the vehicle network.

[0013] A genetic algorithm based on fitness-sharing niche technology is used to calculate multiple heterogeneous combinations of congested road segments that maximize the number of congested road segments in the vehicle network, with the optimization objective of maximizing the number of congested road segments in the vehicle network.

[0014] As a preferred technical solution, the vehicle network information includes road network structure, road capacity, and vehicle traffic flow data.

[0015] As a preferred technical solution, the genetic algorithm based on fitness sharing niche technology is used to calculate multiple heterogeneous combinations of congested road segments that maximize the number of congested road segments in the vehicle network, with the optimization objective of maximizing the number of congested road segments in the vehicle network. The specific steps include:

[0016] Take all sets containing k vehicle-to-everything (V2X) road segment numbers as individuals, and initialize the database, including decision variables and corresponding fitness values, i.e., the set containing k V2X road segment numbers and the congestion propagation influence, and set the evolution termination condition.

[0017] Select the NP individuals with the best fitness values ​​from the database to form a population, and calculate the congestion propagation influence of each individual in the population based on the congestion propagation influence of the road segment as its fitness value.

[0018] The niche-based fitness sharing method divides the population into n subpopulations as different niches based on the similarity of the combinations of vehicle network road segments contained in the individual within the vehicle network topology.

[0019] Randomly select two niches from the divided niches and apply the sorting semi-crossover operator;

[0020] A small habitat is randomly selected, and a single-point mutation operator is applied to all individuals in the population with a set probability. If the random number corresponding to an individual is greater than its single-point mutation threshold, a road segment that does not belong to that individual is randomly selected from the set of vehicle network road segments to replace any road segment contained in that individual.

[0021] Update the fitness values ​​of all individuals in the population, select the individuals with the highest fitness values ​​from each niche and retain them for the next generation, and clone and breed a population of size NP;

[0022] The process iterates until the evolutionary termination condition is reached, and the individual with the highest fitness in each niche of the population at this point is output as the multimodal optimization solution to the multi-solution optimization problem of the impact of vehicle network congestion propagation.

[0023] As a preferred technical solution, the congestion propagation influence of each individual in the population is calculated based on the congestion propagation influence of road segments as its fitness value. The specific calculation formula is as follows:

[0024]

[0025] in, It is section x i Degree in the vehicle network topology It is section x i Traffic carrying capacity It is section x i The number of lanes, It is section x i The length of L is the average length of lanes occupied by motor vehicles for safe driving.

[0026] The individual congestion propagation influence is:

[0027] As a preferred technical solution, based on the similarity of the combinations of vehicle-to-everything (V2X) road segments contained in an individual within the V2X topology, the population is divided into n subpopulations as different niches, specifically including:

[0028] The community detection algorithm for connected vehicle applications is divided into m Leiden communities;

[0029] For each individual in the population, solve for its vehicle network community affiliation vector, where the m-dimensional community affiliation vector of individual i is... Wherein, the a-th dimension c a This indicates the total number of road segments to which the individual belongs in the vehicle-to-everything (V2X) community j;

[0030] Based on the individual's vehicle-to-everything (V2X) community affiliation vector, a distance metric is defined between individuals, specifically the Euclidean distance between individual i and individual j.

[0031] Using the vehicle network affiliation vector of each individual as a cluster, the clusters with the shortest distance between individuals are merged into one cluster according to the distance metric between individuals, until n clusters are formed. Finally, the population is divided into n subpopulations as different microhabitats.

[0032] As a preferred technical solution, two niches are randomly selected from the divided niches and a sorting semi-crossover operator is applied, specifically including:

[0033] From the population, two individuals i and j are randomly selected. Based on the magnitude of the road segment congestion propagation influence value, the road segments contained in individual i are sorted in ascending order, and the road segments contained in individual j are sorted in descending order.

[0034] Exchange the first half of the road segment combination of individuals i and j to form two new individuals i′,j′;

[0035] If there are duplicate road segments in the new individuals i′,j′, then the duplicate road segments are removed, and road segments are randomly selected from the vehicle network road segment set to fill in individuals i′,j′, ensuring that individuals i′,j′ still contain k non-duplicate road segments.

[0036] This invention also provides a multimodal vehicle network congestion propagation optimization system based on niche genetic algorithm, used to implement the above-mentioned multimodal vehicle network congestion propagation optimization method based on niche genetic algorithm. The system includes: a vehicle network information acquisition module, a maximization problem model construction module, and a congestion optimization module.

[0037] The vehicle network information acquisition module is used to acquire vehicle network information;

[0038] The maximization problem model building module is used to mathematically model the problem of maximizing the influence of vehicle network congestion propagation using vehicle network information, and obtains the congestion propagation dynamic mechanism and the objective function of maximizing the number of vehicle network congestion segments respectively.

[0039] The congestion optimization module uses a genetic algorithm based on fitness-sharing niche technology to calculate multiple heterogeneous combinations of congested road segments that maximize the number of congested road segments in the vehicle network, with the optimization objective of maximizing the number of congested road segments in the vehicle network.

[0040] The present invention also provides a computer-readable storage medium storing a program that, when executed by a processor, implements the above-described multimodal vehicle network congestion propagation optimization method based on niche genetic algorithm.

[0041] The present invention also provides a computer device, including a processor and a memory for storing processor-executable programs, wherein when the processor executes the program stored in the memory, it implements the multimodal vehicle network congestion propagation optimization method based on niche genetic algorithm described above.

[0042] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0043] (1) Based on the acquired vehicle network data as a mathematical model for establishing the vehicle network congestion propagation mechanism, this invention quantifies the vehicle network congestion propagation dynamic mechanism, uses road segment combination as a decision variable, takes maximizing the number of congested road segments in the vehicle network as the objective function, and adopts niche technology based on fitness sharing to locate multiple peaks in the solution space of the problem of maximizing the influence of vehicle network congestion, thus solving the problem that the existing technology does not consider the problem of maximizing the influence of vehicle network congestion from the perspective of multimodal optimization.

[0044] (2) This invention uses a community detection algorithm as an aid and takes advantage of the community characteristics presented by the road structure of the Internet of Vehicles to assign Internet of Vehicles community affiliation vectors to all individuals in the genetic algorithm population. It quantifies the differences in the combination of Internet of Vehicles road segments at the community granularity, which solves the problem that the existing technology is difficult to reasonably quantify the degree of difference in the combination of Internet of Vehicles road segments when applying the niche technology based on fitness sharing. Attached Figure Description

[0045] Figure 1 This is a flowchart illustrating the multimodal vehicle-to-everything (V2X) congestion propagation optimization method based on niche genetic algorithm of the present invention.

[0046] Figure 2 This is a schematic diagram of the implementation architecture of the present invention, which obtains the optimal road segment combination based on niche technology and population evolution.

[0047] Figure 3 This is a schematic diagram illustrating the implementation architecture of the population evolution iteration based on the niche technology of fitness value sharing in this invention;

[0048] Figure 4 This is a schematic diagram illustrating the implementation architecture of the niche technology based on fitness value sharing in this invention;

[0049] Figure 5 This is a schematic diagram of the semi-crossing operator for sorting in this invention;

[0050] Figure 6 This is a schematic diagram of the single-point mutation operator for sorting in this invention. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0052] Example 1

[0053] like Figure 1 As shown, this embodiment provides a multimodal vehicle network congestion propagation optimization method based on niche genetic algorithm. The genetic algorithm based on fitness sharing niche technology can provide multiple heterogeneous and high-performing road segment combinations that can maximize the influence of vehicle network congestion propagation in a single evolution process. By utilizing the community characteristics presented by the vehicle network topology, individuals in the genetic algorithm population are assigned vehicle network community affiliation vectors. Through this vector, the differences between the road segment combinations represented by the individuals can be well evaluated. The road segment congestion propagation influence can be constructed by using the key factors that cause vehicle network road segment congestion, which can efficiently induce the algorithm to find higher peaks in the solution space of the vehicle network congestion propagation influence maximization problem.

[0054] The method specifically includes the following steps:

[0055] S1: Obtain vehicle network information, including road network structure, road capacity, and vehicle traffic flow data;

[0056] S2: Mathematical modeling is performed on the problem of maximizing the influence of vehicle network congestion propagation using vehicle network information, resulting in the dynamic mechanism of congestion propagation and the objective function of maximizing the number of congested road segments in the vehicle network.

[0057] S3: As Figure 2 As shown, a genetic algorithm based on fitness-sharing niche technology is used to calculate multiple heterogeneous combinations of congested road segments that maximize the number of congested road segments in the vehicle network, with the optimization objective of maximizing the number of congested road segments in the vehicle network.

[0058] like Figure 3 As shown, through niche technology and population evolution, multiple road segment combinations that maximize the propagation of vehicle-to-everything (V2X) congestion are identified. Step S3 specifically includes the following steps:

[0059] S31: Take all sets containing k vehicle-to-everything (V2X) road segment numbers as individuals, and initialize the database, including decision variables and corresponding fitness values, i.e., the set containing k V2X road segment numbers and the congestion propagation influence, and set the evolution termination condition.

[0060] In this embodiment, a random sampling method is used to initialize the database in order to obtain a database that is relatively evenly distributed in the solution space of the problem. Where k represents the number of vehicle-to-everything (V2X) road segments contained in an individual, and each individual represents a potential combination of road segments that can maximize the impact of V2X congestion propagation.

[0061] S32: Select the NP individuals with the best fitness from the database DB to form a population. in, Let $\mathbf$ represent the decision variable. The congestion propagation influence of each individual in the population, i.e., its fitness value, is calculated based on the congestion propagation influence of road segments. The specific calculation formula is as follows:

[0062]

[0063] in, It is section x i Degree in the vehicle network topology It is section x i Traffic carrying capacity It is section x i The number of lanes, It is section x i The length of L is the average length of lanes occupied by motor vehicles for safe driving.

[0064] This leads to the spread of individual congestion influence.

[0065] S33: Apply the niche method based on fitness sharing. According to the similarity of the combination of vehicle network road segments contained in the individual in the vehicle network topology, the population is divided into n subpopulations, i.e. niches, so that each niche occupies a peak in the solution space of the problem of maximizing the influence of vehicle network congestion propagation. Individuals in each niche contain similar vehicle network road segments at the community granularity of the vehicle network topology.

[0066] like Figure 4 As shown, for all individuals in the population, based on the community characteristics presented by the road topology of the vehicle network, a vehicle network community affiliation vector is constructed to quantify the composition of the vehicle network road segment combination represented by the individual, and a difference (or similarity) metric for the vehicle network community affiliation vector is defined, which can effectively evaluate the differences between the road segment combinations represented by the individual. Step S33 specifically includes:

[0067] (1) For the community detection algorithm of vehicle networking application, it is divided into m Leiden communities;

[0068] (2) For each individual in the population, solve for its vehicle network community affiliation vector, i.e., the m-dimensional community affiliation vector of individual i. Wherein, the a-th dimension c a This indicates the total number of road segments to which the individual belongs in the vehicle-to-everything (V2X) community j;

[0069] (3) Based on the individual's vehicle network community affiliation vector, define the distance metric between individuals, namely the Euclidean distance between individual i and individual j.

[0070] (4) Based on the idea of ​​hierarchical clustering, the vehicle network affiliation vector of each individual is used as the cluster. According to the distance metric between individuals, the clusters with the shortest distance are merged into one cluster until n clusters are formed.

[0071] (5) The population is divided into n subpopulations as different microhabitats, thus completing the division of the population's ecological niche.

[0072] S34: To accelerate the location of peaks in the multi-solution space of niches, two niches are randomly selected from the multiple niches divided into units and a sorting semi-crossover operator is applied.

[0073] In this embodiment, step S34 specifically includes:

[0074] (1) From the population, randomly select two individuals i and j. Based on the magnitude of the road segment congestion propagation influence value, sort the road segments contained in individual i in ascending order and sort the road segments contained in individual j in descending order.

[0075] (2) Exchange the first half of the road segment combination of individual i and individual j to form two new individuals i′,j′;

[0076] (3) If there are duplicate road segments in the new individuals i′,j′, the duplicate road segments are removed, and road segments are randomly selected from the vehicle network road segment set to fill in individuals i′,j′, ensuring that individuals i′,j′ still contain k non-duplicate road segments.

[0077] Specifically, this embodiment utilizes the characteristic that each individual is a collection of vehicle-to-everything (V2X) road segments. Based on the influence of road segment congestion propagation, the road segments contained in randomly selected individuals i and j in the population are sorted in ascending and descending order, respectively, and then crossover is performed.

[0078] For example: in In the middle, v i1 The traffic congestion on that section of road had the greatest impact on public awareness. ikTraffic congestion has the least impact on the spread of information, while... In the middle, v j1 The road sections with the least congestion have the least impact on the spread of information. jk Traffic congestion has the greatest impact on public awareness and exchange. and The first half yields new individuals. and The vehicle-to-everything (V2X) road segments that do not belong to this new entity are replaced with road segments that may overlap due to intersections.

[0079] like Figure 5 As shown, this is the semi-crossover operator for sorting in this embodiment. The rectangle with the largest area represents the population, and the rectangle with the smallest area represents the niche obtained by the niche partitioning technique based on fitness sharing. Niches with gradient colors represent randomly selected semi-crossover operators for sorting; the gradient direction indicates the sorting method: a gradient from orange to purple indicates that the set of connected vehicle segments contained in the individual is sorted in ascending order of road segment congestion influence, and a gradient from purple to orange indicates that the set of connected vehicle segments contained in the individual is sorted in descending order of road segment congestion influence. The new niches obtained after crossover are marked with a solid color. All individuals in these two niches undergo semi-crossover, that is, they exchange the first half of the sorted road segments to form two new niches. A pure purple rectangle represents a niche containing road segment combinations with higher congestion influence, and a pure orange rectangle represents a niche containing road segment combinations with lower congestion influence. It is worth mentioning that... Figure 5 The solution for situations where individuals in a new population may contain duplicate road segments due to crossover is not shown. For this problem, duplicate road segments within an individual will be replaced by any road segment from the vehicle-to-everything (V2X) road segment set that does not belong to that individual.

[0080] S35: To increase population diversity, a small habitat is randomly selected, and a single-point mutation operator is applied to all individuals in the population with a certain probability. If the random number corresponding to an individual is greater than its single-point mutation threshold, a road segment that does not belong to that individual is randomly selected from the set of vehicle network road segments to replace any road segment included by that individual.

[0081] In this embodiment, step S35 specifically includes:

[0082] (1) Define the single-point mutation probability threshold p m =0.7, generate random numbers p∈(0,1) for all individuals in the population;

[0083] (2) If the random number p of individual i i >p m If the condition is met, then a road segment that does not belong to individual i is randomly selected from the set of vehicle network road segments and replaced with any road segment in individual i; otherwise, no changes are made.

[0084] like Figure 6 As shown, this is the single-point mutation operator for sorting in this embodiment. The pure orange rectangle represents the initial individual that has not mutated, and the purple-orange gradient rectangle represents the individual that has undergone single-point mutation. All individuals in the population have a certain probability of undergoing single-point mutation. If the randomly generated value exceeds the mutation probability threshold of the individual, then a road segment is randomly selected from the vehicle network road segments included by the individual and replaced by any road segment in the vehicle network road segment set that does not belong to the individual.

[0085] S36: Update the fitness values ​​of all individuals in the population, select the individual with the highest fitness value from each niche and keep it for the next generation, and clone it to produce a population of size NP;

[0086] S37: Repeat steps S33, S34 and S35 until the evolution termination condition is reached, that is, the number of evolution iterations reaches the upper limit set by the algorithm;

[0087] S38: Output the individual with the highest fitness in each niche of the population at this time, as the multimodal optimization solution for the multi-solution optimization problem of the influence of vehicle network congestion propagation. Otherwise, if the number of evolution iterations has not yet reached the upper limit set by the algorithm, these individuals are retained in the next generation of evolution, and a new population of size NP is generated with them as the parents.

[0088] This embodiment employs a niche-based fitness value sharing technique. Based on the similarity of the vehicle network topology space, the population is dynamically divided into n niches. Individuals within a niche share high similarity in their vehicle network segment composition, while individuals across different niches share low similarity. This results in each niche occupying a different peak in the solution space for maximizing the impact of vehicle network congestion propagation. Next, a sorting semi-crossover operator is applied to each niche. Then, a single-point mutation operator is applied to all individuals in the population with a certain probability. Finally, the individual with the highest fitness value from each niche is selected and retained for the next generation, serving as the parent to clone NP individuals. If the algorithm reaches the termination condition (i.e., the number of evolution iterations reaches the upper limit set by the algorithm), then these individuals are output as solutions to the problem of maximizing the impact of vehicle network congestion propagation. Conversely, if the number of evolution iterations has not yet reached the upper limit set by the algorithm, these individuals are retained in the next generation of evolution, and a new population of size NP is generated with them as parents to continue evolution. This embodiment can be applied to vehicle networks in different cities. Its goal is to find multiple road segment combinations with different compositions that can maximize the propagation of vehicle network congestion, so that vehicle network optimization decision-makers can select the most suitable road segment combination and carry out optimization at the road engineering level.

[0089] Example 2

[0090] This embodiment provides a multimodal vehicle network congestion propagation optimization system based on niche genetic algorithm, used to implement the multimodal vehicle network congestion propagation optimization method based on niche genetic algorithm in Embodiment 1. The system includes: a vehicle network information acquisition module, a maximization problem model construction module, and a congestion optimization module.

[0091] In this embodiment, the vehicle network information acquisition module is used to acquire vehicle network information;

[0092] In this embodiment, the maximization problem model building module is used to mathematically model the problem of maximizing the influence of vehicle network congestion propagation using vehicle network information, and obtain the congestion propagation dynamic mechanism and the objective function of maximizing the number of vehicle network congested road segments respectively.

[0093] In this embodiment, the congestion optimization module uses a genetic algorithm based on fitness sharing niche technology to calculate multiple heterogeneous combinations of congested road segments that maximize the number of congested road segments in the vehicle network, with the optimization objective of maximizing the number of congested road segments in the vehicle network.

[0094] Example 3

[0095] This embodiment provides a storage medium, which may be a ROM, RAM, disk, optical disk, or other storage medium. The storage medium stores one or more programs. When the programs are executed by the processor, they implement the multimodal vehicle network congestion propagation optimization method based on niche genetic algorithm of Embodiment 1.

[0096] Example 4

[0097] This embodiment provides a computing device, which may be a desktop computer, laptop computer, smartphone, PDA handheld terminal, tablet computer or other terminal device with display function. The computing device includes a processor and a memory. The memory stores one or more programs. When the processor executes the program stored in the memory, it implements the multimodal vehicle network congestion propagation optimization method based on niche genetic algorithm of Embodiment 1.

[0098] The above embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. Any changes, modifications, substitutions, combinations, or simplifications made without departing from the spirit and principle of the present invention shall be considered equivalent substitutions and shall be included within the protection scope of the present invention.

Claims

1. A multimodal vehicle-to-everything (V2X) congestion propagation optimization method based on niche genetic algorithm, characterized in that, Includes the following steps: Acquire vehicle-to-everything (V2X) information, including road network structure, road capacity, and vehicle traffic flow data; Mathematical modeling is used to maximize the impact of vehicle network congestion propagation on vehicle network information, resulting in a dynamic mechanism of congestion propagation and an objective function that maximizes the number of congested road segments in the vehicle network. A genetic algorithm based on fitness-sharing niche technology is used to calculate multiple heterogeneous combinations of congested road segments that maximize the number of congested road segments in the vehicle network, with the optimization objective of maximizing the number of congested road segments in the vehicle network. The specific steps include: Take all sets containing k vehicle-to-everything (V2X) road segment numbers as individuals, and initialize the database, including decision variables and corresponding fitness values, i.e., the set containing k V2X road segment numbers and the congestion propagation influence, and set the evolution termination condition. The population is formed by selecting NP individuals with the best fitness values ​​from the database. The congestion propagation influence of each individual in the population is calculated based on the congestion propagation influence of road segments as its fitness value. The specific calculation formula is as follows: in, It is section x i Degree in the vehicle network topology It is section x i Traffic carrying capacity It is section x i The number of lanes, It is section x i The length of L is the average length of lanes occupied by motor vehicles for safe driving. The individual congestion propagation influence is: The niche-based fitness-sharing approach divides the population into n subpopulations as different niches based on the similarity of the combinations of vehicle-to-everything (V2X) road segments contained in an individual within the V2X topology. These subpopulations specifically include: The community detection algorithm for connected vehicle applications is divided into m Leiden communities; For each individual in the population, solve for its vehicle network community affiliation vector, where the m-dimensional community affiliation vector of individual i is... Wherein, the a-th dimension c a This indicates the total number of road segments to which the individual belongs in the vehicle-to-everything (V2X) community j; Based on the individual's vehicle-to-everything (V2X) community affiliation vector, a distance metric is defined between individuals, specifically the Euclidean distance between individual i and individual j. Using the vehicle network affiliation vector of each individual as a cluster, the clusters with the shortest distance are merged into one cluster according to the distance metric between individuals, until n clusters are formed. Finally, the population is divided into n subpopulations as different microhabitats. From the defined multiple niches, two niches are randomly selected and a sorting semi-crossover operator is applied, specifically including: From the population, two individuals i and j are randomly selected. Based on the magnitude of the road segment congestion propagation influence value, the road segments contained in individual i are sorted in ascending order, and the road segments contained in individual j are sorted in descending order. Exchange the first half of the road segment combination of individuals i and j to form two new individuals i′,j′; If there are duplicate road segments in the new individuals i′,j′, then the duplicate road segments are removed, and road segments are randomly selected from the vehicle network road segment set to fill in individuals i′,j′, ensuring that individuals i′,j′ still contain k non-duplicate road segments. A small habitat is randomly selected, and a single-point mutation operator is applied to all individuals in the population with a set probability. If the random number corresponding to an individual is greater than its single-point mutation threshold, a road segment that does not belong to that individual is randomly selected from the set of vehicle network road segments to replace any road segment contained in that individual. Update the fitness values ​​of all individuals in the population, select the individuals with the highest fitness values ​​from each niche and retain them for the next generation, and clone and breed a population of size NP; The process iterates until the evolutionary termination condition is reached, and the individual with the highest fitness in each niche of the population at this point is output as the multimodal optimization solution to the multi-solution optimization problem of the impact of vehicle network congestion propagation.

2. A multimodal vehicle-to-everything (V2X) congestion propagation optimization system based on niche genetic algorithm, characterized in that, To implement the multimodal vehicle-to-everything (V2X) congestion propagation optimization method based on niche genetic algorithm as described in claim 1, the system includes: a V2X information acquisition module, a maximization problem model construction module, and a congestion optimization module; The vehicle network information acquisition module is used to acquire vehicle network information; The maximization problem model building module is used to mathematically model the problem of maximizing the influence of vehicle network congestion propagation using vehicle network information, and obtains the congestion propagation dynamic mechanism and the objective function of maximizing the number of vehicle network congestion segments respectively. The congestion optimization module uses a genetic algorithm based on fitness-sharing niche technology to calculate multiple heterogeneous combinations of congested road segments that maximize the number of congested road segments in the vehicle network, with the optimization objective of maximizing the number of congested road segments in the vehicle network.

3. A computer-readable storage medium storing a program, characterized in that, When the program is executed by the processor, it implements the multimodal vehicle network congestion propagation optimization method based on niche genetic algorithm as described in claim 1.

4. A computer device, comprising a processor and a memory for storing a processor-executable program, characterized in that, When the processor executes the program stored in the memory, it implements the multimodal vehicle network congestion propagation optimization method based on niche genetic algorithm as described in claim 1.

Images