Collaborative optimization method and device for time table and time period ticket price of urban rail transit

Abstract

The invention provides an urban rail transit timetable and time period ticket price collaborative optimization method and device. The method comprises the following steps: constructing an initial scheme based on an operation constraint condition; inputting a simulation module of the collaborative optimization model, and determining passenger travel distribution; the carbon emission is distributed and input into a carbon emission calculation module, and the carbon emission is determined; inputting the distribution and the carbon emission into a carbon emission reduction calculation module to determine the carbon emission reduction; inputting the distribution and the carbon emission reduction into an optimization model, and obtaining an optimized scheme based on business constraint conditions and a heuristic algorithm; and inputting the optimization module into the simulation module again, carrying out iteration according to the sequence of the optimization module, the simulation module, the carbon emission calculation module and the carbon emission reduction calculation module, and determining a scheme which has the highest carbon emission reduction and meets the business constraint condition after iteration for a preset number of times as a target optimization result. Therefore, through the constructed collaborative optimization model, the time table and the time period ticket price can be collaboratively optimized according to the passenger travel distribution output by simulation, so that the carbon emission reduction benefit is maximized.

Description

Technical Field

[0001] The present application relates to the field of urban rail transit technology, and in particular to a method and device for collaboratively optimizing urban rail transit timetables and time-period fares. Background Art

[0002] With the continuous development of modern cities, carbon emissions generated by transportation systems are increasing year by year. As a low-carbon, high-capacity, green mode of transportation, urban rail transit should shoulder the responsibility of guiding the public towards green travel. Fares are a key factor influencing passengers' travel mode and time choices. Appropriate price reductions can attract passengers who would otherwise choose other modes to urban rail, thereby reducing carbon emissions across the entire transportation system—a positive externality of carbon reduction. Fares are closely tied to the interests of the government, operating companies, and passengers. The resulting shift in passenger demand also requires operators to adjust urban rail timetables simultaneously. Therefore, optimizing both fares and timetables during specific time periods can enhance the attractiveness and competitiveness of urban rail, balancing transportation costs for operators and passenger wait times while fully leveraging urban rail's carbon reduction potential.

[0003] Existing methods for optimizing urban rail transit timetables or time-period fares are all aimed at maximizing corporate operating efficiency or balancing passenger flow during time periods and improving the utilization rate of train transportation capacity. They ignore the carbon emission reduction benefits brought by passenger flow attracted by ticket prices and lack the coordinated optimization of timetables and time-period fares with the goal of maximizing carbon emission reduction. Summary of the Invention

[0004] In view of this, the embodiments of the present application at least provide a method and device for collaborative optimization of urban rail transit timetables and time period fares. By constructing a collaborative optimization model, the timetable and time period fares can be collaboratively optimized according to the passenger travel distribution output by the simulation to maximize the carbon emission reduction benefits.

[0005] This application mainly includes the following aspects:

[0006] In a first aspect, an embodiment of the present application provides a method for collaboratively optimizing an urban rail transit timetable and time period fares, the method comprising:

[0007] Based on pre-set operational constraints, construct multiple initial plans for train timetables and time-period fares;

[0008] Inputting the multiple initial solutions into a simulation module of a collaborative optimization model to determine the passenger travel distribution corresponding to the multiple initial solutions; the collaborative optimization model also includes a trained carbon emission calculation module, a carbon emission reduction calculation module, and an optimization module;

[0009] Inputting the passenger travel distributions corresponding to the multiple initial plans into the trained carbon emissions calculation module to determine the train operation carbon emissions corresponding to the multiple initial plans;

[0010] Inputting the passenger travel distribution and train operation carbon emissions corresponding to the multiple initial plans into the carbon emission reduction calculation module to determine the carbon emission reductions corresponding to the multiple initial plans;

[0011] Inputting the passenger travel distribution and carbon emission reduction corresponding to the multiple initial plans into the optimization model, and optimizing and adjusting the multiple initial plans based on preset business constraints and a heuristic algorithm with an elite retention strategy to obtain multiple optimized plans;

[0012] The multiple optimized schemes are re-input into the simulation module, and are iterated in the order of optimization module, simulation module, carbon emission calculation module and carbon emission reduction calculation module. The scheme with the highest carbon emission reduction and meeting the preset business constraints among the multiple optimized schemes after a preset number of iterations is determined as the target optimization result of the train timetable and time period fare.

[0013] In a second aspect, an embodiment of the present application further provides a collaborative optimization device for an urban rail transit timetable and time-period fares, the collaborative optimization device for an urban rail transit timetable and time-period fares comprising:

[0014] The initial setting module is used to build multiple initial plans for train timetables and time period fares based on preset operational constraints;

[0015] A passenger flow simulation module is configured to input the multiple initial plans into a simulation module of a collaborative optimization model to determine the passenger travel distribution corresponding to the multiple initial plans; the collaborative optimization model also includes a trained carbon emission calculation module, a carbon emission reduction calculation module, and an optimization module;

[0016] A first calculation module is configured to input the passenger travel distributions corresponding to the multiple initial plans into the trained carbon emissions calculation module to determine the train operation carbon emissions corresponding to the multiple initial plans;

[0017] A second calculation module is configured to input the passenger travel distribution and train operation carbon emissions corresponding to the multiple initial solutions into the carbon emission reduction calculation module to determine the carbon emission reductions corresponding to the multiple initial solutions;

[0018] a scheme optimization module, configured to input the passenger travel distribution and carbon emission reduction corresponding to the multiple initial schemes into the optimization model, and optimize and adjust the multiple initial schemes based on preset business constraints and a heuristic algorithm with an elite retention strategy to obtain multiple optimized schemes;

[0019] The result determination module is used to re-input the multiple optimized schemes into the simulation module, iterate in the order of the optimization module, the simulation module, the carbon emission calculation module and the carbon emission reduction calculation module, and determine the scheme with the highest carbon emission reduction and meeting the preset business constraints among the multiple optimized schemes after a preset number of iterations as the target optimization result of the train timetable and time period fare.

[0020] In a third aspect, an embodiment of the present application further provides an electronic device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to perform the steps of the method for collaborative optimization of urban rail transit timetables and time period fares as described above.

[0021] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for collaborative optimization of urban rail transit timetables and time period fares as described above are executed.

[0022] The embodiment of the present application provides a collaborative optimization method and device for urban rail transit timetable and time period fare, which, based on preset operation constraints, constructs multiple initial schemes for train timetable and time period fare; inputs multiple initial schemes into the simulation module of the collaborative optimization model, and determines the passenger travel distribution corresponding to the multiple initial schemes; the collaborative optimization model also includes a trained carbon emission calculation module, a carbon emission reduction calculation module and an optimization module; inputs the passenger travel distribution corresponding to the multiple initial schemes into the trained carbon emission calculation module, and determines the train operation carbon emissions corresponding to the multiple initial schemes; inputs the passenger travel distribution and train operation carbon emissions corresponding to the multiple initial schemes into the carbon reduction module The emission calculation module determines the carbon emission reductions corresponding to multiple initial plans. The passenger travel distribution and carbon emission reductions corresponding to the multiple initial plans are input into the optimization model. Based on preset business constraints and a heuristic algorithm with an elite retention strategy, the multiple initial plans are optimized and adjusted to obtain multiple optimized plans. The multiple optimized plans are re-input into the simulation module and iterated in the order of the optimization module, simulation module, carbon emission calculation module, and carbon emission reduction calculation module. After a preset number of iterations, the plan with the highest carbon emission reduction and meeting the preset business constraints among the multiple optimized plans is determined as the target optimization result for the train timetable and time period ticket price. In this way, through the constructed collaborative optimization model, the timetable and time period ticket price can be collaboratively optimized based on the passenger travel distribution output by the simulation to maximize the carbon emission reduction benefits.

[0023] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 A flow chart showing a method for collaboratively optimizing urban rail transit timetables and time-period fares provided in an embodiment of the present application is shown;

[0026] Figure 2 One of the structural diagrams of the collaborative optimization model in an embodiment of the present application is shown;

[0027] Figure 3 The second structural diagram of the collaborative optimization model in the embodiment of the present application is shown;

[0028] Figure 4 One of the functional module diagrams of a collaborative optimization device for urban rail transit timetables and time-period fares provided in an embodiment of the present application is shown;

[0029] Figure 5 The second functional module diagram of a collaborative optimization device for urban rail transit timetable and time period fare provided by an embodiment of the present application is shown;

[0030] Figure 6 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of this application.

[0032] To facilitate understanding of the present application, the technical solutions provided in the present application are described in detail below in conjunction with specific embodiments.

[0033] The embodiments of the present application provide a method and device for collaborative optimization of urban rail transit timetables and time-period fares. By constructing a collaborative optimization model, the timetable and time-period fares can be collaboratively optimized according to the passenger travel distribution output by simulation to maximize the carbon emission reduction benefits.

[0034] See also Figure 1 , Figure 1 This is a flow chart of a method for collaboratively optimizing urban rail transit timetables and time-period fares provided in an embodiment of the present application. Figure 1 As shown, the collaborative optimization method of urban rail transit timetable and time period fare provided in the embodiment of the present application includes the following steps:

[0035] S101: Based on preset operational constraints, multiple initial plans for train timetables and time-period fares are constructed.

[0036] Here, we first construct multiple initial plans for urban rail transit train schedules and time-of-day fares based on pre-set operational constraints. These constraints include, but are not limited to, minimum and maximum intervals between train departures, and operating hours. Using these constraints, we generate multiple different timetable and time-of-day fare combinations as a starting point for optimization. Urban rail transit refers to urban public passenger transportation systems that operate on dedicated rails, including subway systems, light rail systems, monorail systems, modern trams, maglev systems, automated guided rail systems, and urban rapid rail systems. Time-of-day fares are customized for different operating hours. This fare system can leverage passengers' sensitivity to fare changes and guide them to choose lower-carbon travel options.

[0037] In the embodiment of the present application, the preset operating constraints include:

[0038] The first constraint is:

[0039] Second constraint:

[0040] The third constraint:

[0041] The fourth constraint:

[0042] Fifth constraint:

[0043] Among them, the first and second constraints are the constraints on the number of trains running, T represents the total operating time, h max and hmin Indicates the maximum / minimum departure interval subject to the minimum service level / signal system constraints, The symbol indicates rounding down, y k is a binary 01 variable, indicating whether train k is dispatched. The third and fourth constraints are the constraints on the train departure interval, where h k represents the start time of train k, that is, the time when train k arrives at station 1, t N It represents the time required for the train to run from station 1 to station N. The fifth constraint is the value constraint of the fare rate, where is the upper limit of the fare rate, α t is the fare rate for time period t. The number of initial solutions generated is related to the population size of the heuristic algorithm with the elitist retention strategy. Specifically, based on the preset operational constraints, a population size of chromosomes is randomly generated as the initial population, i.e., multiple initial solutions for train schedules and time period fares. In the genetic algorithm, a chromosome represents a possible solution.

[0044] S102, inputting the multiple initial plans into the simulation module of the collaborative optimization model to determine the passenger travel distribution corresponding to the multiple initial plans; the collaborative optimization model also includes a trained carbon emission calculation module, a carbon emission reduction calculation module and an optimization module.

[0045] Here, see Figure 2 , Figure 2 This is a schematic diagram of the structure of the collaborative optimization model in the embodiment of this application. Figure 2 As shown, the collaborative optimization model 200 includes a simulation module 210, a trained carbon emission calculation module 220, a carbon emission reduction calculation module 230, and an optimization module 240. Multiple initial plans are input into the simulation module 210. In the embodiment of the present application, the simulation module 210 uses a user stochastic equilibrium allocation model to simulate the travel selection behavior of passengers under different plans, thereby determining the passenger travel distribution corresponding to the multiple initial plans, and providing basic data for subsequent carbon emission calculations. Among them, the user stochastic equilibrium allocation model (Stochastic User Equilibrium, SUE) is a model for simulating the travel selection behavior of passengers in a transportation network.

[0046] S103: Inputting the passenger travel distributions corresponding to the multiple initial plans into the trained carbon emission calculation module to determine the train operation carbon emissions corresponding to the multiple initial plans.

[0047] Here, the passenger travel distribution corresponding to the multiple initial schemes is input into the trained carbon emission calculation module 220. In the embodiment of the present application, the carbon emission calculation module 220 uses a variational autoencoder neural network module, which can calculate the train operation carbon emissions of each initial scheme based on the information provided by the passenger travel distribution, providing data support for subsequent optimization. Among them, the variational autoencoder (VAE) is a generative model that combines the concepts of autoencoders and variational inference. By learning the potential probability distribution of the input data, it can generate new data similar to the training data. Compared with traditional autoencoders, VAE uses a Bayesian method for reasoning.

[0048] S104: Inputting the passenger travel distribution and train operation carbon emissions corresponding to the multiple initial solutions into the carbon emission reduction calculation module to determine the carbon emission reductions corresponding to the multiple initial solutions.

[0049] Here, the passenger travel distribution and train operation carbon emissions corresponding to multiple initial plans are input into the carbon emission reduction calculation module 230. The carbon emission reduction calculation module 230 comprehensively considers the passenger travel distribution and carbon emissions, calculates the carbon emission reduction of each initial plan, and provides direction for subsequent optimization and adjustment.

[0050] S105: Inputting the passenger travel distribution and carbon emission reduction corresponding to the multiple initial plans into the optimization model, and optimizing and adjusting the multiple initial plans based on preset business constraints and a heuristic algorithm with an elite retention strategy to obtain multiple optimized plans.

[0051] Here, the passenger travel distribution and carbon emission reduction corresponding to the multiple initial solutions are input into the optimization model 240. In the embodiment of the present application, the optimization model 240 uses a heuristic algorithm with an elite retention strategy to optimize and adjust the multiple initial solutions based on the preset business constraints to obtain multiple optimized solutions. Among them, the heuristic algorithm with an elite retention strategy is an improved genetic algorithm that accelerates convergence and improves the optimization effect by retaining excellent individuals. The algorithm combines the basic operations of the genetic algorithm (selection, crossover, mutation) and the elite retention strategy to ensure that excellent genes can be passed on to the next generation, thereby improving the global search ability and convergence speed of the algorithm. The preset business constraints include:

[0052] The sixth constraint:

[0053] Seventh constraint:

[0054] The eighth constraint:

[0055] Among them, the sixth constraint condition indicates that the urban rail ticket revenue will not be reduced due to the coordinated optimization of timetable and time period ticket price, b ij is the base fare for the OD pair with origin i and destination j. The OD pair (Origin-Destination Pair) refers to the path from a specific origin (Origin) to a specific destination (Destination), which is used to describe the distribution of traffic demand and traffic flow. The seventh constraint indicates that the actual passenger flow will not exceed the upper limit of the passenger flow demand. The eighth constraint condition indicates that the train load rate in the interval should not exceed the given load rate threshold. r kv represents the full load rate of train k in interval v. It should be noted that q ijt and r kv The passenger flow and interval load factor are extracted from the passenger travel distribution output by the simulation module 210.

[0056] S106, re-input the multiple optimized schemes into the simulation module, and iterate in the order of optimization module, simulation module, carbon emission calculation module and carbon emission reduction calculation module, and determine the scheme with the highest carbon emission reduction and meeting the preset business constraints among the multiple optimized schemes after a preset number of iterations as the target optimization result of the train timetable and time period fare.

[0057] Here, multiple optimized solutions are re-entered into simulation module 210 for iteration. This simulation process simulates passenger feedback on the optimized solutions, and the output passenger flow distribution is re-passed through carbon emission calculation module 220 and carbon emission reduction calculation module 230. Finally, it is applied to optimization module 240 to find the optimal solution. After a preset number of iterative optimizations, the solution with the highest carbon emission reduction and meeting business constraints is selected as the target optimization result for the train schedule and time period fares. This fully considers carbon emission reduction goals while balancing business operating profits and passenger waiting time, achieving a win-win situation for the government, businesses, and passengers.

[0058] Furthermore, inputting the multiple initial solutions into a simulation module of a collaborative optimization model to determine passenger travel distributions corresponding to the multiple initial solutions includes:

[0059] Step a1, for any initial scheme among the multiple initial schemes, at any iteration number of the simulation, based on the first passenger travel distribution, the departure interval and time period fare rate corresponding to the initial scheme, calculate the passenger generalized travel expenses corresponding to the initial scheme at the iteration number; the first passenger travel distribution is the passenger travel distribution before the iteration.

[0060] Here, before simulation, we must first initialize the simulation data, set the number of simulation iterations Ψ = 0, and the convergence accuracy to ε. And the specific optimization scheme, that is, the departure interval and time fare rate corresponding to the initial scheme, at any iteration of the simulation, calculate the generalized travel cost of the passenger with starting point i and end point j entering the station at time t. Among them, the generalized travel cost of the passenger is composed of the fare cost b ijt , waiting fee ijt and congestion charges ijt The three parties jointly decided:

[0061] b ijt =α t b ij ;

[0062]

[0063] in, represents the departure time of train k at station i, specifically is a 01 variable, indicating whether the passenger entering the station at time t takes train k. is a 01 variable, indicating whether the passenger with starting point i and end point j has passed through interval v. d kv is the interval full load rate, specifically C is the capacity of the train. Introducing μ1 and μ2 as cost conversion coefficients, the generalized cost of a passenger's trip with starting point i and end point j entering the station within time t is:

[0064] C ijt =b ijt +μ1·d ijt +μ2·w ijt .

[0065] Step a2: Calculate the minimum expected travel cost and travel selection probability of the passenger corresponding to the number of iterations based on the passenger's generalized travel cost.

[0066] Here, based on the passenger's generalized travel cost C ijt ; Calculate the minimum expected travel cost for passengers whose starting point is i and whose end point is j and who enter the station during time period t

[0067]

[0068] Among them, θ is the parameter that converts travel cost into utility, and Δt is the travel time adjustment parameter that passengers can accept.

[0069] Calculate the travel choice probability of the elastic passenger flow with starting point i and end point j entering the station within time t and choosing to travel within the time period t1∈[t-Δt,t+Δt] for:

[0070]

[0071] Step a3: Calculate the elastic passenger flow corresponding to the number of iterations based on the minimum expected travel cost and the first passenger travel distribution.

[0072] Here, based on the minimum expected travel cost and first passenger trip distribution Calculate the elastic passenger flow with starting point i and ending point j entering the station within time t

[0073]

[0074] Among them, η ijt is the elastic coefficient of the passenger whose starting point is i and whose end point is j and who enters the station within time t.

[0075] Step a4: Based on the travel selection probability and the elastic passenger flow, the first passenger travel distribution is updated to obtain a second passenger travel distribution; the second passenger travel distribution is the iterated passenger travel distribution.

[0076] Here, based on the travel choice probability and flexible passenger flow Update the first passenger travel distribution to obtain the second passenger travel distribution; the second passenger travel distribution is the iterated passenger travel distribution.

[0077] Specifically, the starting point is i, the end point is j, and the actual passenger flow q entering the station within time t is ijt for:

[0078]

[0079] Set the number of simulation iterations Ψ=Ψ+1, and calculate the passenger flow q according to the formulas in steps a1 and a2. ijt The generalized travel cost C of (Ψ-1) ijt (Ψ) and minimum travel cost Calculate the elastic passenger flow demand q according to the formula in step a3 ijt (Ψ), update the elastic passenger flow demand:

[0080] Get the second passenger travel distribution.

[0081] Step a5: Based on the first passenger travel distribution, the second passenger travel distribution and a preset convergence accuracy, determine whether the passenger travel distribution has converged within the number of iterations.

[0082] Step a6: If not, continue iterating until the passenger travel distribution converges, and determine the corresponding second passenger travel distribution as the passenger travel distribution corresponding to the initial solution.

[0083] Here, here, if The simulation ends and outputs q ijt (Ψ); otherwise, repeat steps a1-a4 until the passenger travel distribution converges at the iteration number, and determine the corresponding second passenger travel distribution as the passenger travel distribution corresponding to the initial solution.

[0084] Furthermore, the trained carbon emissions calculation module includes a preprocessing module and a variational autoencoder module; inputting the passenger travel distributions corresponding to the multiple initial schemes into the trained carbon emissions calculation module to determine the train operation carbon emissions corresponding to the multiple initial schemes includes:

[0085] Step b1: for any initial scheme among the multiple initial schemes, input the passenger travel distribution corresponding to the initial scheme into the preprocessing module to obtain the characteristic variables affecting the carbon emissions of train operation corresponding to the initial scheme.

[0086] Here, see Figure 3 , Figure 3 This is the second structural diagram of the collaborative optimization model in the embodiment of this application. Figure 3 As shown, the carbon emission calculation module 220 includes a preprocessing module 221 and a variational autoencoder module 222. For any of the multiple initial schemes, the passenger travel distribution corresponding to the initial scheme is input into the preprocessing module 221 to obtain the characteristic variables that affect the carbon emissions of the train operation corresponding to the initial scheme. In the embodiment of the present application, the preprocessing module 221 analyzes the passenger travel distribution and extracts characteristic variables related to the carbon emissions of the train operation. Among them, the characteristic variables include at least one of the train load rate, passenger flow, departure interval and time period fare rate. The train load rate indicates the full load of the train in different time periods; the passenger flow indicates the passenger flow of different OD pairs; the departure interval indicates the departure interval of the train; and the time period fare rate indicates the fare rate in different time periods. These characteristic variables will be used as inputs to the variational autoencoder module 222 for subsequent carbon emissions calculations.

[0087] Step b2: input the characteristic variables into the variational autoencoder module to obtain the train operation carbon emissions corresponding to the initial solution.

[0088] Here, the feature variables extracted from preprocessing module 221 are input into variational autoencoder module 222. Variational autoencoder module 222 calculates the train operation carbon emissions for each initial scenario by learning the nonlinear relationship between the input features and carbon emissions. Specifically, variational autoencoder module 222 uses an encoder to encode the feature variables into a distribution in a latent space, and then uses a decoder to generate the corresponding train operation carbon emissions.

[0089] Furthermore, before constructing multiple initial plans for train timetables and time-period fares based on preset operational constraints, the method further includes:

[0090] Step c1: training an initial carbon emissions calculation module based on characteristic variables affecting train operation carbon emissions and corresponding train operation carbon emissions in historical urban rail transit data.

[0091] Here, historical urban rail transit data is collected, including but not limited to train operation data, passenger flow data, timetable data, and fare data. This data specifically includes basic attributes of urban rail transit lines (such as station spacing, line mileage, line horizontal and vertical profiles, and line layout), train attributes (vehicle make and type), the load factor and carbon emissions of each train within each section, and passenger demand data. This data is collected and processed into a standardized format. Feature variables that may affect carbon emissions from train section operations are selected from this collected basic attribute data. A variational autoencoder neural network is used to exploit the nonlinear relationship between train carbon emissions and feature variables, and training is performed for refined carbon emissions calculation. Specifically, a variational autoencoder network is designed, consisting of an input layer, an encoding layer, a hidden layer, a decoding layer, and an output layer. The input layer receives feature variables, the encoding layer encodes the input data into latent variables, the hidden layer extracts the distribution characteristics of the latent variables and the nonlinear relationship between them, the decoding layer decodes the latent variables into carbon emissions, and the output layer outputs the carbon emissions calculated by the neural network.

[0092] Step c2: If the difference between the train operation carbon emissions output by the initial carbon emissions calculation module and the actual train operation carbon emissions meets a preset condition, the training is terminated to obtain a trained carbon emissions calculation module.

[0093] Here, the network is trained using actual train interval operation carbon emission data and corresponding feature variables. During the training process, the network parameters are adjusted to minimize the difference between the output carbon emissions and the actual observed values. The trained model is evaluated using the validation set and the test set to test its calculation accuracy and generalization ability. If the difference between the train operation carbon emissions output by the initial carbon emissions calculation module and the actual train operation carbon emissions meets the preset conditions, the training is terminated and a trained carbon emissions calculation module 220 is obtained. In this way, when it is necessary to calculate the carbon emissions of a new train interval operation, it is only necessary to input the corresponding feature variables into the trained carbon emissions calculation module 220 in the prescribed format to obtain the calculation results.

[0094] Furthermore, characteristic variables affecting train operation carbon emissions in the historical urban rail transit data are determined according to the following steps:

[0095] Step d1 : for each influencing factor in the historical urban rail transit data, evaluating the correlation between the influencing factor and the train operation carbon emissions based on a preset statistical method.

[0096] Here, the collected historical urban rail transit data undergoes preprocessing, including data cleaning, normalization, and missing value filling. Pre-defined statistical methods, such as the Pearson correlation coefficient, Spearman correlation coefficient, or principal component analysis, are used to assess the correlation between various influencing factors and train operation carbon emissions.

[0097] Step d2: determining the influencing factors with correlations greater than a preset correlation threshold as characteristic variables affecting train operation carbon emissions in the historical urban rail transit data.

[0098] Here, a preset correlation threshold is set to screen factors that are highly correlated with carbon emissions, and influencing factors with correlations greater than the preset correlation threshold are determined as characteristic variables that affect train operation carbon emissions in historical urban rail transit data.

[0099] Furthermore, inputting the passenger travel distributions and train operation carbon emissions corresponding to the multiple initial solutions into the carbon emission reduction calculation module to determine the carbon emission reductions corresponding to the multiple initial solutions includes:

[0100] Step e1, for any of the multiple initial plans, based on the passenger travel distribution corresponding to the initial plan, determine the first carbon emissions of the passengers attracted after optimizing the ticket price and timetable who would have originally chosen other modes of transportation.

[0101] Here, for any of the multiple initial plans, based on the passenger travel distribution corresponding to the initial plan, the first carbon emissions of the passengers attracted by the optimized fares and timetable who would have chosen other modes of transportation are determined. Specifically, represents the carbon emissions of passengers who would have chosen other modes of transportation after optimizing fares and timetables, ijt is the optimized passenger flow demand obtained by simulation, specifically the passenger flow departing from station i and arriving at station j at time t, is the known passenger flow distribution before optimization, l ij is the distance between station i and station j, and ζ is the carbon emission factor of other modes of transportation.

[0102] Step e2: Based on the train operation carbon emissions, determine a second carbon emissions change of the train operation carbon emissions after optimizing the ticket price and timetable.

[0103] Here, the second carbon emission of the train operation carbon emission change after optimizing the ticket price and timetable can be expressed as E a -E b ;E b To optimize the carbon emissions of train operations before ticket prices and timetables, E a To optimize the train operation carbon emissions after ticket prices and timetables, E a and E b Calculated by the carbon emission calculation module 220.

[0104] Step e3: Calculate the carbon emission reduction corresponding to the initial solution based on the first carbon emission amount and the second carbon emission amount.

[0105] Here, carbon emission reduction can be expressed as maxE p -(E a -E b ). Among them, the greater the carbon emission reduction, the higher the carbon emission reduction effect brought by attracting passenger flow.

[0106] Furthermore, the passenger travel distribution and carbon emission reduction corresponding to the multiple initial solutions are input into the optimization model, and the multiple initial solutions are optimized and adjusted based on preset business constraints and a heuristic algorithm with an elite retention strategy to obtain multiple optimized solutions, including:

[0107] Step f1, calculating the fitness of the multiple initial solutions based on the preset business constraints, the passenger travel distribution and the carbon emission reduction corresponding to the multiple initial solutions.

[0108] Here, the optimization module 240 is an important component of the collaborative optimization model 200, which is used to optimize and adjust the scheme and generate an optimized scheme. Based on preset business constraints and a heuristic algorithm with an elite retention strategy, this module finally determines the optimal train schedule and time period fare scheme through multiple iterative optimizations. Specifically, according to the passenger travel distribution of the scheme corresponding to the chromosome in the population, it is judged whether the passenger travel distribution meets the preset business constraints. If the constraints are met, the carbon emission reduction under this scheme is used as the fitness of the chromosome. If not, the fitness of the chromosome is set to 0 to calculate the fitness of multiple initial schemes. Among them, population refers to the set of all possible solutions in the genetic algorithm, and each solution is called an individual in the population.

[0109] Step f2: sorting the multiple initial solutions in descending order of fitness, and determining a preset number of initial solutions at the top of the order as elite solutions.

[0110] Here, multiple initial solutions are sorted in descending order of fitness, and the top n solutions are retained. e The high initial solutions are determined as elite solutions and are directly put into the next generation of the genetic algorithm.

[0111] Step f3: Based on the roulette wheel selection algorithm, multiple initial solutions are selected from the initial solutions other than the elite solution as chromosome solutions.

[0112] Here, for the remaining popsize-n e Roulette wheel selection is performed on each individual to select multiple initial solutions as chromosome solutions. Roulette wheel selection is a commonly used genetic algorithm selection strategy used to select the next generation of the population based on the fitness of the individual. The core idea is that individuals with higher fitness have a greater probability of being selected, similar to the probability of the ball landing in roulette based on the size of the sector.

[0113] Step f4: randomly generating multiple genetic variation schemes based on the chromosome scheme, the preset crossover probability and the preset mutation probability.

[0114] Here, the population composed of chromosome schemes obtained by roulette wheel selection is crossover and mutation. Crossover means that the population is crossovered according to the preset crossover probability p. c , the selected individuals are randomly crossovered by the single-point crossover method to re-combine new individuals. Specifically: generate a random number l∈(0,1), if the random number ι is less than or equal to the crossover probability p c, then perform a crossover operation, then generate a random integer κ, the range does not exceed the individual length, take two individuals from κ and cross, and judge whether the new individuals after the crossover meet the preset operation constraints. If not, perform the crossover operation again. Mutation refers to the mutation probability p according to the preset m , perform single-point mutation on the individuals obtained after crossover to obtain new individuals. Specifically: start judging from the first individual, generate a random number belonging to ι∈(0,1), if the random number is less than or equal to the mutation probability p m , then perform a mutation operation, and then generate a random integer κ, the range of which does not exceed the individual length, mutate the gene at the κth position of the individual, and judge whether the mutated new individual meets the preset operation constraints. If not, perform the mutation operation again.

[0115] Step f5: determining the multiple genetic variation schemes and elite schemes as the multiple optimized schemes.

[0116] Here, the population obtained after crossover mutation is combined with the elite population retained from the previous generation to obtain a new population. In other words, multiple genetic mutation schemes and elite schemes are determined as multiple optimized schemes.

[0117] Furthermore, the new population is brought into the simulation module 220, and the passenger travel distribution under different scenarios is recalculated. The distribution passes through the carbon emission calculation module 220 and the carbon emission reduction calculation module 230, respectively. Finally, the optimization module 240 determines whether the preset business constraints are met. If so, the target value under this scenario is calculated as the fitness of the chromosome. If the preset business constraints are not met, the fitness of the chromosome is set to 0. After the iteration is completed, the optimal individual in the population and the optimal fitness are output.

[0118] The embodiment of the present application provides a collaborative optimization method for urban rail transit timetables and time period fares, including constructing multiple initial schemes for train timetables and time period fares based on preset operating constraints; inputting multiple initial schemes into the simulation module of the collaborative optimization model to determine the passenger travel distributions corresponding to the multiple initial schemes; the collaborative optimization model also includes a trained carbon emission calculation module, a carbon emission reduction calculation module and an optimization module; inputting the passenger travel distributions corresponding to the multiple initial schemes into the trained carbon emission calculation module to determine the train operation carbon emissions corresponding to the multiple initial schemes; inputting the passenger travel distributions and train operation carbon emissions corresponding to the multiple initial schemes into the carbon The emission reduction calculation module determines the carbon emission reductions corresponding to multiple initial plans. The passenger travel distribution and carbon emission reductions corresponding to the multiple initial plans are input into the optimization model. Based on preset business constraints and a heuristic algorithm with an elite retention strategy, the multiple initial plans are optimized and adjusted to obtain multiple optimized plans. The multiple optimized plans are re-input into the simulation module and iterated in the order of the optimization module, simulation module, carbon emission calculation module, and carbon emission reduction calculation module. The plan with the highest carbon emission reduction and meeting the preset business constraints after a preset number of iterations is determined as the target optimization result for the train timetable and time period ticket price. In this way, through the constructed collaborative optimization model, the timetable and time period ticket price can be collaboratively optimized based on the passenger travel distribution output by the simulation to maximize the carbon emission reduction benefits.

[0119] Based on the same application concept, the embodiments of the present application also provide a collaborative optimization device for urban rail transit timetables and time period fares corresponding to the collaborative optimization method for urban rail transit timetables and time period fares provided in the above embodiments. Since the principle of solving the problem by the device in the embodiments of the present application is similar to the collaborative optimization method for urban rail transit timetables and time period fares in the above embodiments of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0120] See also Figure 4 , Figure 4 This is one of the functional module diagrams of a collaborative optimization device for urban rail transit timetable and time period fare provided in the embodiment of this application. Figure 4 As shown, the collaborative optimization device 400 for urban rail transit timetable and time period fare includes:

[0121] The initial setting module 410 is used to construct multiple initial plans for train timetables and time period fares based on preset operating constraints.

[0122] The passenger flow simulation module 420 is used to input the multiple initial plans into the simulation module of the collaborative optimization model to determine the passenger travel distribution corresponding to the multiple initial plans; the collaborative optimization model also includes a trained carbon emission calculation module, a carbon emission reduction calculation module and an optimization module.

[0123] The first calculation module 430 is configured to input the passenger travel distributions corresponding to the multiple initial solutions into the trained carbon emissions calculation module to determine the train operation carbon emissions corresponding to the multiple initial solutions.

[0124] The second calculation module 440 is configured to input the passenger travel distribution and train operation carbon emissions corresponding to the multiple initial solutions into the carbon emission reduction calculation module to determine the carbon emission reductions corresponding to the multiple initial solutions.

[0125] The scheme optimization module 450 is used to input the passenger travel distribution and carbon emission reduction corresponding to the multiple initial schemes into the optimization model, and optimize and adjust the multiple initial schemes based on preset business constraints and a heuristic algorithm with an elite retention strategy to obtain multiple optimized schemes.

[0126] The result determination module 460 is used to re-input the multiple optimized schemes into the simulation module, iterate in the order of the optimization module, the simulation module, the carbon emission calculation module and the carbon emission reduction calculation module, and determine the scheme with the highest carbon emission reduction and meeting the preset business constraints among the multiple optimized schemes after a preset number of iterations as the target optimization result of the train timetable and time period fare.

[0127] Furthermore, when the passenger flow simulation module 420 is used to input the multiple initial solutions into the simulation module of the collaborative optimization model and determine the passenger travel distribution corresponding to the multiple initial solutions, the passenger flow simulation module 420 is specifically used to:

[0128] For any of the multiple initial plans, at any iteration number of the simulation, based on a first passenger travel distribution, the departure interval and the time period fare rate corresponding to the initial plan, calculate the passenger generalized travel cost corresponding to the initial plan at the iteration number; the first passenger travel distribution is the passenger travel distribution before the iteration;

[0129] Based on the passenger's generalized travel cost, calculating the passenger's minimum expected travel cost and travel selection probability corresponding to the number of iterations;

[0130] Calculating the elastic passenger flow corresponding to the number of iterations based on the minimum expected travel cost and the first passenger travel distribution;

[0131] Based on the travel selection probability and the elastic passenger flow, the first passenger travel distribution is updated to obtain a second passenger travel distribution; the second passenger travel distribution is the iterated passenger travel distribution;

[0132] Based on the first passenger travel distribution, the second passenger travel distribution, and a preset convergence accuracy, determining whether the passenger travel distribution converges at the number of iterations;

[0133] If not, continue iterating until the passenger travel distribution converges, and determine the corresponding second passenger travel distribution as the passenger travel distribution corresponding to the initial solution.

[0134] Furthermore, the trained carbon emissions calculation module includes a preprocessing module and a variational autoencoder module; when the first calculation module 430 is used to input the passenger travel distribution corresponding to the multiple initial solutions into the trained carbon emissions calculation module and determine the train operation carbon emissions corresponding to the multiple initial solutions, the first calculation module 430 is specifically used to:

[0135] For any of the multiple initial solutions, inputting the passenger travel distribution corresponding to the initial solution into the preprocessing module to obtain characteristic variables affecting train operation carbon emissions corresponding to the initial solution;

[0136] The characteristic variables are input into the variational autoencoder module to obtain the train operation carbon emissions corresponding to the initial solution.

[0137] Further, see Figure 5 , Figure 5 This is the second functional module diagram of a collaborative optimization device for urban rail transit timetable and time period fare provided in the embodiment of this application. Figure 5 As shown, the collaborative optimization device 400 for urban rail transit timetable and time period fare also includes:

[0138] The model training module 470 is used to train the initial carbon emission calculation module based on the characteristic variables affecting train operation carbon emissions and the corresponding train operation carbon emissions in historical urban rail transit data.

[0139] The model determination module 480 is used to terminate the training and obtain a trained carbon emission calculation module if the difference between the train operation carbon emission output by the initial carbon emission calculation module and the actual train operation carbon emission meets a preset condition.

[0140] Furthermore, the model training module 470 is configured to determine characteristic variables in the historical urban rail transit data that affect train operation carbon emissions according to the following steps:

[0141] For each influencing factor in the historical urban rail transit data, evaluating the correlation between the influencing factor and the train operation carbon emissions based on a preset statistical method;

[0142] The influencing factors with a correlation greater than a preset correlation threshold are determined as characteristic variables that affect train operation carbon emissions in the historical urban rail transit data.

[0143] Furthermore, when the second calculation module 440 is used to input the passenger travel distribution and train operation carbon emissions corresponding to the multiple initial solutions into the carbon emission reduction calculation module to determine the carbon emission reductions corresponding to the multiple initial solutions, the second calculation module 440 is specifically used to:

[0144] For any of the multiple initial plans, based on the passenger travel distribution corresponding to the initial plan, determining the first carbon emissions of passengers attracted by the optimized fares and timetable who would have originally chosen other modes of transportation;

[0145] Based on the train operation carbon emissions, determining a second carbon emissions amount of a change in train operation carbon emissions after optimizing fares and timetables;

[0146] Based on the first carbon emissions and the second carbon emissions, a carbon emission reduction corresponding to the initial solution is calculated.

[0147] Furthermore, when the solution optimization module 450 is used to input the passenger travel distribution and carbon emission reduction corresponding to the multiple initial solutions into the optimization model, and optimize and adjust the multiple initial solutions based on preset business constraints and a heuristic algorithm with an elite retention strategy to obtain multiple optimized solutions, the solution optimization module 450 is specifically used to:

[0148] Calculating the fitness of the multiple initial solutions based on the preset business constraints, passenger travel distributions and carbon emission reductions corresponding to the multiple initial solutions;

[0149] Sorting the multiple initial solutions in descending order of fitness, and determining a preset number of initial solutions ranked first as elite solutions;

[0150] Based on the roulette wheel selection algorithm, multiple initial solutions are selected from other initial solutions except the elite solution as chromosome solutions;

[0151] Randomly generating multiple genetic variation schemes based on the chromosome scheme, the preset crossover probability, and the preset mutation probability;

[0152] The multiple genetic variation schemes and elite schemes are determined as the multiple optimized schemes.

[0153] The embodiment of the present application provides a collaborative optimization device for urban rail transit timetables and time period fares, including: an initial setting module for constructing multiple initial schemes for train timetables and time period fares based on preset operating constraints; a passenger flow simulation module for inputting multiple initial schemes into the simulation module of the collaborative optimization model to determine the passenger travel distribution corresponding to the multiple initial schemes; the collaborative optimization model also includes a trained carbon emission calculation module, a carbon emission reduction calculation module and an optimization module; a first calculation module for inputting the passenger travel distribution corresponding to the multiple initial schemes into the trained carbon emission calculation module to determine the train operation carbon emissions corresponding to the multiple initial schemes; a second calculation module for inputting the passenger travel distribution corresponding to the multiple initial schemes into the trained carbon emission calculation module to determine the train operation carbon emissions corresponding to the multiple initial schemes; The carbon emissions are input into the carbon emission reduction calculation module to determine the carbon emission reductions corresponding to multiple initial solutions. The solution optimization module is used to input the passenger travel distribution and carbon emission reductions corresponding to the multiple initial solutions into the optimization model. Based on the preset business constraints and the heuristic algorithm with the elite retention strategy, the multiple initial solutions are optimized and adjusted to obtain multiple optimized solutions. The result determination module is used to re-input the multiple optimized solutions into the simulation module and iterate in the order of the optimization module, simulation module, carbon emission calculation module, and carbon emission reduction calculation module. After a preset number of iterations, the solution with the highest carbon emission reduction and meeting the preset business constraints among the multiple optimized solutions is determined as the target optimization result for the train timetable and time period fare. In this way, through the constructed collaborative optimization model, the timetable and time period fare can be collaboratively optimized according to the passenger travel distribution output by the simulation to maximize the carbon emission reduction benefits.

[0154] Based on the same application idea, please refer to Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 600 includes a processor 610 , a memory 620 and a bus 630 .

[0155] The memory 620 stores machine-readable instructions executable by the processor 610. When the electronic device 600 is running, the processor 610 communicates with the memory 620 through the bus 630. When the processor 610 is running, the machine-readable instructions execute the steps of the collaborative optimization method of urban rail transit timetable and time period fare provided in the above embodiment. The specific implementation method can be found in the method embodiment and will not be repeated here.

[0156] Based on the same application concept, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the steps of the collaborative optimization method of urban rail transit timetable and time period fare provided in the above embodiment are executed. The specific implementation method can be found in the method embodiment and will not be repeated here.

[0157] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0158] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0159] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0160] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0161] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0162] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0163] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The scope of protection of the present application is not limited thereto. Although the present application has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed in the present application, or make equivalent replacements for some of the technical features thereof. However, these modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A collaborative optimization method for urban rail transit timetable and time period fare, characterized in that: The method comprises: Based on pre-set operational constraints, construct multiple initial plans for train timetables and time-period fares; Inputting the multiple initial solutions into a simulation module of a collaborative optimization model to determine the passenger travel distribution corresponding to the multiple initial solutions; the collaborative optimization model also includes a trained carbon emission calculation module, a carbon emission reduction calculation module, and an optimization module; Inputting the passenger travel distributions corresponding to the multiple initial plans into the trained carbon emissions calculation module to determine the train operation carbon emissions corresponding to the multiple initial plans; Inputting the passenger travel distribution and train operation carbon emissions corresponding to the multiple initial plans into the carbon emission reduction calculation module to determine the carbon emission reductions corresponding to the multiple initial plans; Inputting the passenger travel distribution and carbon emission reduction corresponding to the multiple initial plans into the optimization model, and optimizing and adjusting the multiple initial plans based on preset business constraints and a heuristic algorithm with an elite retention strategy to obtain multiple optimized plans; The multiple optimized schemes are re-input into the simulation module, and are iterated in the order of optimization module, simulation module, carbon emission calculation module and carbon emission reduction calculation module. The scheme with the highest carbon emission reduction and meeting the preset business constraints among the multiple optimized schemes after a preset number of iterations is determined as the target optimization result of the train timetable and time period fare.

2. The collaborative optimization method for urban rail transit timetable and time period fare according to claim 1 is characterized in that: Inputting the multiple initial solutions into a simulation module of a collaborative optimization model to determine passenger travel distributions corresponding to the multiple initial solutions includes: For any of the multiple initial plans, at any iteration number of the simulation, based on a first passenger travel distribution, the departure interval and the time period fare rate corresponding to the initial plan, calculate the passenger generalized travel cost corresponding to the initial plan at the iteration number; the first passenger travel distribution is the passenger travel distribution before the iteration; Based on the passenger's generalized travel cost, calculating the passenger's minimum expected travel cost and travel selection probability corresponding to the number of iterations; Calculating the elastic passenger flow corresponding to the number of iterations based on the minimum expected travel cost and the first passenger travel distribution; Based on the travel selection probability and the elastic passenger flow, the first passenger travel distribution is updated to obtain a second passenger travel distribution; the second passenger travel distribution is the iterated passenger travel distribution; Based on the first passenger travel distribution, the second passenger travel distribution, and a preset convergence accuracy, determining whether the passenger travel distribution converges at the number of iterations; If not, continue iterating until the passenger travel distribution converges, and determine the corresponding second passenger travel distribution as the passenger travel distribution corresponding to the initial solution.

3. The collaborative optimization method for urban rail transit timetable and time period fare according to claim 1 is characterized in that: The trained carbon emission calculation module includes a preprocessing module and a variational autoencoder module; inputting the passenger travel distribution corresponding to the multiple initial schemes into the trained carbon emission calculation module to determine the train operation carbon emissions corresponding to the multiple initial schemes includes: For any of the multiple initial solutions, inputting the passenger travel distribution corresponding to the initial solution into the preprocessing module to obtain characteristic variables affecting train operation carbon emissions corresponding to the initial solution; The characteristic variables are input into the variational autoencoder module to obtain the train operation carbon emissions corresponding to the initial solution.

4. The collaborative optimization method for urban rail transit timetable and time period fare according to claim 3 is characterized in that: Before constructing multiple initial plans for train timetables and time-period fares based on preset operational constraints, the method further includes: The initial carbon emissions calculation module is trained based on the characteristic variables that affect train operation carbon emissions and the corresponding train operation carbon emissions in historical urban rail transit data; If the difference between the train operation carbon emissions output by the initial carbon emissions calculation module and the actual train operation carbon emissions meets a preset condition, the training is terminated to obtain a trained carbon emissions calculation module.

5. The collaborative optimization method for urban rail transit timetable and time period fare according to claim 4 is characterized in that: Determine the characteristic variables that affect train operation carbon emissions in the historical urban rail transit data according to the following steps: For each influencing factor in the historical urban rail transit data, evaluating the correlation between the influencing factor and the train operation carbon emissions based on a preset statistical method; The influencing factors with a correlation greater than a preset correlation threshold are determined as characteristic variables that affect train operation carbon emissions in the historical urban rail transit data.

6. The collaborative optimization method for urban rail transit timetable and time period fare according to claim 1 is characterized in that: Inputting the passenger travel distributions and train operation carbon emissions corresponding to the multiple initial solutions into the carbon emission reduction calculation module to determine the carbon emission reductions corresponding to the multiple initial solutions includes: For any of the multiple initial plans, based on the passenger travel distribution corresponding to the initial plan, determining the first carbon emissions of passengers attracted by the optimized fares and timetable who would have originally chosen other modes of transportation; Based on the train operation carbon emissions, determining a second carbon emissions amount of a change in train operation carbon emissions after optimizing fares and timetables; Based on the first carbon emissions and the second carbon emissions, a carbon emission reduction corresponding to the initial solution is calculated.

7. The collaborative optimization method for urban rail transit timetable and time period fare according to claim 1 is characterized in that: The passenger travel distribution and carbon emission reduction corresponding to the multiple initial solutions are input into the optimization model, and the multiple initial solutions are optimized and adjusted based on preset business constraints and a heuristic algorithm with an elite retention strategy to obtain multiple optimized solutions, including: Calculating the fitness of the multiple initial solutions based on the preset business constraints, passenger travel distributions and carbon emission reductions corresponding to the multiple initial solutions; Sorting the multiple initial solutions in descending order of fitness, and determining a preset number of initial solutions ranked first as elite solutions; Based on the roulette wheel selection algorithm, multiple initial solutions are selected from other initial solutions except the elite solution as chromosome solutions; Randomly generating multiple genetic variation schemes based on the chromosome scheme, the preset crossover probability, and the preset mutation probability; The multiple genetic variation schemes and elite schemes are determined as the multiple optimized schemes.

8. A collaborative optimization device for urban rail transit timetable and time period fare, characterized in that: The collaborative optimization device for urban rail transit timetable and time period fare includes: The initial setting module is used to build multiple initial plans for train timetables and time period fares based on preset operational constraints; A passenger flow simulation module is configured to input the multiple initial plans into a simulation module of a collaborative optimization model to determine the passenger travel distribution corresponding to the multiple initial plans; the collaborative optimization model also includes a trained carbon emission calculation module, a carbon emission reduction calculation module, and an optimization module; A first calculation module is configured to input the passenger travel distributions corresponding to the multiple initial plans into the trained carbon emissions calculation module to determine the train operation carbon emissions corresponding to the multiple initial plans; A second calculation module is configured to input the passenger travel distribution and train operation carbon emissions corresponding to the multiple initial solutions into the carbon emission reduction calculation module to determine the carbon emission reductions corresponding to the multiple initial solutions; a scheme optimization module, configured to input the passenger travel distribution and carbon emission reduction corresponding to the multiple initial schemes into the optimization model, and optimize and adjust the multiple initial schemes based on preset business constraints and a heuristic algorithm with an elite retention strategy to obtain multiple optimized schemes; The result determination module is used to re-input the multiple optimized schemes into the simulation module, iterate in the order of the optimization module, the simulation module, the carbon emission calculation module and the carbon emission reduction calculation module, and determine the scheme with the highest carbon emission reduction and meeting the preset business constraints among the multiple optimized schemes after a preset number of iterations as the target optimization result of the train timetable and time period fare.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus. When the processor is running, the machine-readable instructions execute the steps of the method for collaborative optimization of urban rail transit timetables and time period fares as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the method for collaboratively optimizing urban rail transit timetables and time period fares as claimed in any one of claims 1 to 7.

Images