Passenger bus connection method, device and equipment under subway operation interruption

Abstract

The invention relates to the field of bus scheduling and path optimization, and provides a passenger bus connection method, device and equipment under subway operation interruption, and the method comprises the steps: building a passenger transfer demand distribution randomness model based on historical data, the historical data being passenger transfer demand data; determining a passenger evacuation strategy according to the fault station and the passenger transfer demand distribution randomness model; determining a candidate bus route set based on a passenger evacuation strategy; constructing a bus connection model based on the candidate bus route set, and determining an optimization target taking minimization of total delay as the bus connection model; the total delay is determined according to the delay of common passengers, the delay of passengers who do not get on the bus successfully and the delay of detained passengers; and solving the optimization target based on a genetic algorithm, and outputting an optimal solution. According to the invention, the defect of low scheduling efficiency of a traditional single line connection method in the prior art is overcome, the evacuation efficiency is improved, and passenger delay is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of bus dispatching and route optimization, and in particular to a method, device and equipment for connecting passengers to buses when subway operation is interrupted. Background Art

[0002] In recent years, with the acceleration of urbanization, urban public transportation systems have become increasingly complex and have become an indispensable part of citizens' daily travel. As the backbone network of urban public transportation, the subway is favored by passengers for its high efficiency and convenience. However, as the intersection of multiple rail transit lines, the operation status of subway hubs is directly related to the stability and efficiency of the entire urban public transportation network. Unfortunately, frequent emergencies in urban public transportation, especially failures in subway hubs, have had a significant impact on network performance, resulting in a large number of passengers being stranded and difficulty in transferring, further exacerbating traffic pressure.

[0003] In response to the problem of subway hub station interruption, bus connection is widely used in actual operation as an effective evacuation method. At present, the research on bus connection mainly focuses on the optimization of connection after ordinary subway stations and single subway lines fail. These studies effectively alleviate the traffic pressure around the faulty stations by designing connecting bus routes, optimizing passenger allocation, and adjusting bus departure schedules.

[0004] However, in the complex scenario of subway hub station interruption, existing technologies face new challenges. Subway hub station interruption not only causes a large number of passengers to be stranded, but also the passengers' transfer needs are more diverse and complex. Since the hub station connects many lines, the passengers' destinations may be spread all over the city, which makes it difficult for the traditional single-line connection method to meet the needs. Summary of the invention

[0005] The present invention provides a method, device and equipment for connecting passengers to buses when subway operation is interrupted, which solves the defect of low dispatching efficiency of the traditional single-line connecting method in the prior art, improves evacuation efficiency and reduces passenger delays.

[0006] The present invention provides a method for connecting passengers to buses when subway operation is interrupted, comprising the following steps:

[0007] Building a passenger transfer demand distribution stochastic model based on historical data, wherein the historical data is passenger transfer demand data;

[0008] Determining a passenger evacuation strategy based on the fault site and the passenger transfer demand distribution stochastic model;

[0009] Determining a set of candidate bus routes based on the passenger evacuation strategy;

[0010] A bus connection model is constructed based on the candidate bus route set, and minimizing the total delay is determined as the optimization goal of the bus connection model; the total delay is determined based on the delay of ordinary passengers, the delay of passengers who fail to board the bus, and the delay of stranded passengers;

[0011] The optimization objective is solved based on a genetic algorithm, and an optimal solution is output.

[0012] According to a passenger bus connection method under subway operation interruption provided by the present invention, the candidate bus route set is determined based on the passenger evacuation strategy, specifically comprising: determining a connection start station and a connection destination station based on the passenger evacuation strategy; screening out all bus stops within a preset radius of each connection start station and each connection destination station to form a candidate site set for connection; constructing a candidate bus route set based on preset rules and the candidate site set; the preset rule is that when the stops passed by a bus route include both bus stops within a preset radius of the connection start station and bus stops within a preset radius of the connection destination station, the bus route is used as a candidate bus route for connection.

[0013] According to a passenger bus connection method under subway operation interruption provided by the present invention, the bus connection model is constructed based on the candidate bus line set, and minimizing the total delay is determined as the optimization goal of the bus connection model, which specifically includes: determining the bus connection model and its model set, model variables and model parameters based on the candidate bus line set; determining the delay of ordinary passengers, the delay of passengers who failed to board the bus successfully and the delay of stranded passengers according to the model set, model variables and model parameters; determining the total delay according to the delay of ordinary passengers, the delay of passengers who failed to board the bus successfully and the delay of stranded passengers; and minimizing the total delay is used as the optimization goal to obtain the optimization objective function.

[0014] According to a passenger bus connection method under subway operation interruption provided by the present invention, the optimization target is solved based on a genetic algorithm and the optimal solution is output, which specifically includes: defining basic parameters of the genetic algorithm, randomly generating an initial population including multiple individuals, each individual representing a bus scheduling plan; calculating the fitness value of each individual according to the optimization objective function; continuously iterating the current population according to the fitness value to form a new population until a preset iteration termination condition is met; and returning the individual with the highest fitness value as the optimal solution of the bus scheduling plan.

[0015] According to a method for connecting passengers to buses when subway operations are interrupted, the method of continuously iterating the current population according to the fitness value to form a new population specifically includes: selecting individuals with fitness higher than a preset threshold from the current population as parents, performing a crossover operation on the selected parent individuals to generate new child individuals; performing a mutation operation on some of the new child individuals; after the crossover operation and the mutation operation, checking whether the generated individuals meet the constraint conditions; recalculating the fitness value of each individual according to the individuals that meet the constraint conditions; and selecting the individual with the highest fitness value to enter the next generation to form a new population.

[0016] According to a passenger bus connection method under subway operation interruption provided by the present invention, the passenger evacuation strategy is determined based on the fault site and the passenger transfer demand distribution randomness model, specifically including: determining the hub site where the fault occurs in the bus network as the fault site; analyzing the passenger transfer demand of the fault site; and determining the passenger evacuation strategy for multiple destinations based on the passenger transfer demand.

[0017] According to a passenger bus connection method under subway operation interruption provided by the present invention, before building a bus connection model, the connection characteristics of candidate bus lines are analyzed; according to the analysis results, when the vehicles of a bus line are within the dispatching range of two evacuation stations, one of the two evacuation stations is selected as the connection starting station of the bus line according to the actual running distance.

[0018] The present invention also provides a bus connection device based on passenger transfer requirements, comprising the following modules:

[0019] A demand distribution model building module, used to build a passenger transfer demand distribution stochastic model based on historical data, wherein the historical data is passenger transfer demand data;

[0020] A passenger evacuation strategy determination module, used to determine the passenger evacuation strategy according to the fault site and the passenger transfer demand distribution randomness model;

[0021] A bus connection model construction module is used to determine a set of candidate bus routes based on the passenger evacuation strategy; construct a bus connection model based on the candidate bus route set, and determine to minimize the total delay as the optimization goal of the bus connection model; the total delay is determined based on the delay of ordinary passengers, the delay of passengers who failed to board the bus, and the delay of stranded passengers;

[0022] The solution module is used to solve the optimization target based on a genetic algorithm and output an optimal solution.

[0023] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for connecting passengers to a bus when the subway operation is interrupted as described above is implemented.

[0024] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the passenger bus connection method under the interruption of subway operation as described in any of the above methods is implemented.

[0025] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for connecting passengers to buses when subway operation is interrupted.

[0026] The present invention provides a method, device and equipment for connecting passengers to buses under subway operation interruption, including the following beneficial effects: through the passenger transfer demand distribution stochastic model constructed based on historical data, it is possible to more accurately predict and grasp the transfer demand of passengers after the interruption at the subway hub station, so as to formulate a more reasonable evacuation strategy to reduce the waiting time and overall delay of passengers. Through the passenger evacuation strategy, the passenger pressure of the fault station and its adjacent stations is effectively alleviated, and the evacuation efficiency and safety of passengers are improved. At the same time, through the detailed analysis and type classification of candidate bus routes, the existing bus resources can be more reasonably deployed and used to achieve the reduction of connection costs and the improvement of transportation efficiency. With the minimization of the total delay of ordinary passengers and stranded passengers as the optimization goal, a bus connection model is constructed, and it is solved by genetic algorithm to obtain the optimal bus scheduling plan, which can minimize the delay time of passengers and improve the overall efficiency of bus connection services. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 It is a flow chart of a method for connecting passengers to buses when subway operation is interrupted provided by the present invention.

[0029] Figure 2 It is a schematic diagram of the multi-destination evacuation of stranded passengers provided by the present invention.

[0030] Figure 3 It is a schematic diagram of bus connection route type analysis provided by the present invention.

[0031] Figure 4 It is a structural schematic diagram of a bus connecting device based on passenger transfer needs provided by the present invention.

[0032] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] Aiming at the interruption scenario of subway hub stations, the present invention proposes a multi-destination bus connection strategy that takes into account the random optimization of passenger transfer demand, and realizes the transfer distribution function of the original station through bus connection. After the subway hub station is interrupted, the distribution of passenger transfer demand is stochastically modeled, and the existing bus routes are classified according to the distance between the bus line stations and the connection points. A "one-stop evacuation in advance" strategy is proposed, and fine-tuning is performed based on the existing bus routes to achieve passenger connection. With the optimization goal of minimizing the total delay of ordinary passengers and stranded passengers, a bus connection and path optimization model for multi-destination transfers is constructed, and the operation adjustment plan of the bus line is solved.

[0035] Combine the following Figure 1-Figure 5 Embodiments of the present invention are described in detail.

[0036] Figure 1 FIG. 1 is one of the flow charts of the method for connecting passengers to buses when subway operation is interrupted provided by the present invention. Figure 1 As shown, the method comprises the following steps:

[0037] S110. Construct a passenger transfer demand distribution stochastic model based on historical data, where the historical data is passenger transfer demand data.

[0038] Specifically, the randomness of the passenger transfer demand distribution is modeled.

[0039] After a failure at a subway hub station, the transfer demand of passengers is uncertain and dynamic, and has certain differences in different periods and dates. Therefore, in the process of model construction, the transfer demand of passengers should be introduced as a random variable. Based on historical data, the distribution characteristics of passenger transfer demand are studied, and the randomness modeling of the distribution of passenger transfer demand is completed, so as to consider the coupling relationship between connecting services and passenger demand under the conditions of random and dynamic passenger demand.

[0040] S120. Determine a passenger evacuation strategy based on a random distribution model of fault stations and passenger transfer demands.

[0041] According to a passenger bus connection method under subway operation interruption provided by the present invention, a passenger evacuation strategy is determined according to a fault site and a random distribution model of passenger transfer demand, specifically including: determining a hub site where a fault occurs in a bus network as a fault site; analyzing the passenger transfer demand at the fault site; and determining a passenger evacuation strategy for multiple destinations according to the passenger transfer demand.

[0042] Specifically, the passenger evacuation strategies mainly include the following two types.

[0043] (1) Passengers were evacuated to multiple destinations.

[0044] Hub stations are responsible for passenger transfers. When the faulty station is a hub station, in addition to considering the large number of passenger flows, the diversity of passenger destinations should also be considered compared to ordinary subway lines. Figure 2 As shown in the figure, the original travel plan of passengers departing from station A2 may be to go to station B5 or transfer to stations B1 to B4 via station B5. Therefore, the multi-destination transfer of passengers needs to be considered in the bus connection model.

[0045] (2) Passengers evacuate one stop in advance.

[0046] When a subway hub fails, not only will a large number of passengers be stranded at the failed station, but also, because of the interruption of the subway line, a large number of passengers will gather at the adjacent stations of the line where the interrupted subway station is located, resulting in a large passenger pressure and certain safety hazards. In order to improve the efficiency of passenger evacuation and reduce the overall delay of passengers, the present invention proposes a "one-station-ahead evacuation" strategy. Figure 2 As shown, the station failure occurred at the transfer hub station B5. Due to the station failure, the lines from B5 to A2, B1, B2, B3, and B4 were all affected, and the subway operation mode was adjusted to interval operation. The passenger transfer direction from A2 station to B1 to B5 station was taken as the research object. A2 station is the starting station for passenger transfer, and there are a large number of stranded passengers. Therefore, it is considered that A1 station is also used as an evacuation station to relieve the passenger pressure of A2 station. In addition, the source of the shuttle vehicle of the present invention is the operating vehicle of the existing bus line. In the process of fine-tuning the line for docking, adding a docking starting station can also make more full use of different types of bus lines, thereby reducing the docking cost and improving the transportation efficiency.

[0047] S130: Determine a set of candidate bus routes based on the passenger evacuation strategy.

[0048] According to a passenger bus connection method under subway operation interruption provided by the present invention, a candidate bus route set is determined based on a passenger evacuation strategy, specifically including: determining a connection starting station (referred to as the starting station or starting point) and a connection destination station (referred to as the destination station or destination) based on the passenger evacuation strategy; screening out all bus stops within a preset radius of each connection starting station and each connection destination station to form a candidate site set for connection; constructing a candidate bus route set based on preset rules and the candidate site set; the preset rule is that when a bus route passes through stations including both bus stops within a preset radius of the connection starting station and bus stops within a preset radius of the connection destination station, the bus route is used as a candidate bus route for connection.

[0049] Specifically, bus route type analysis.

[0050] When constructing a candidate bus route set, a radius range r is given and used as the threshold of the detour distance (straight-line distance) that buses can travel when connecting. In this invention, r is set to 2km. All bus stops within 2km of the transfer start and destination subway stations are screened. When a bus route passes through a stop that is included in both the bus stop set around the start station and the bus stop set around the destination station, the route is considered to be a candidate connection route. According to this rule, a candidate bus route set is constructed.

[0051] According to a passenger bus connection method under subway operation interruption provided by the present invention, before building a bus connection model, the connection characteristics of candidate bus lines are analyzed; according to the analysis results, when the vehicles of a bus line are within the dispatching range of two evacuation stations, one of the two evacuation stations is selected as the connection starting station of the bus line according to the actual running distance.

[0052] Specifically, before constructing the connection model, it is necessary to further analyze the characteristics of the candidate bus lines, and analyze their connection characteristics based on the number of connection start stations and connection destination stations that the original bus lines pass through. Considering the evacuation one station in advance, there are two connection start stations and multiple connection destination stations in the present invention. When the vehicles of a line are within the dispatch range of two evacuation stations, one of the two evacuation stations is selected as the connection start station of the line according to the actual operating distance. That is to say, within one operating cycle, a bus will not go to two connection start stations to pick up passengers. The specific types of bus line analysis are as follows: Figure 3 And as shown in Table 1.

[0053] Table 1 Analysis of bus connection route types

[0054]

[0055] The connection rules for different types of lines are as follows:

[0056] When the bus route is type 1, type 2, or type 3, a detour through the starting point must be chosen to enable the route as a connecting route.

[0057] When the bus route is type 2 or type 5, the original route does not pass through the shuttle starting station and a destination station. When the number of destination stations is 1, it means that the destination station is not passed, and the shuttle route vehicle must pass through the destination station after being activated; when the number of destination stations is 2, it means that only one of the destination stations is passed. After the shuttle route vehicle is activated, you can choose whether to detour to another destination station.

[0058] When the bus route is type 1 or type 4, passengers need to select at least one destination for detour.

[0059] After a bus picks up passengers at the transfer starting station, it must send the passengers to the corresponding destination station, that is, passengers need to choose in advance whether to take a detour to the destination station before picking up passengers at the starting station.

[0060] S140: construct a bus connection model based on the candidate bus route set, and determine minimizing the total delay as the optimization goal of the bus connection model.

[0061] The total delay is determined based on the delay for regular passengers, the delay for passengers who failed to board the bus, and the delay for stranded passengers.

[0062] According to a passenger bus connection method under subway operation interruption provided by the present invention, a bus connection model is constructed based on a candidate bus line set, and minimizing the total delay is determined as the optimization goal of the bus connection model, which specifically includes: determining the bus connection model and its model set, model variables and model parameters based on the candidate bus line set; determining the delay of ordinary passengers, the delay of passengers who failed to board the bus and the delay of stranded passengers according to the model set, model variables and model parameters; determining the total delay according to the delay of ordinary passengers, the delay of passengers who failed to board the bus and the delay of stranded passengers; minimizing the total delay is used as the optimization goal to obtain the optimization objective function. The process of building the bus connection model is specifically described below.

[0063] (1) Model assumptions

[0064] The following assumptions are made in the process of constructing the bus connection model: a. Buses give priority to ordinary passengers at the connection starting station; b. The capacity of the connection parking spaces and the delays caused by the simultaneous arrival / stopping of multiple vehicles are not considered; c. When a hub station fails, the stranded passengers will spontaneously go to the corresponding bridge bus area to wait.

[0065] Tables 2.1, 2.2 and 2.3 below respectively show the symbolic representation and definition of the bus connection model set, variables and parameters.

[0066]

[0067]

[0068] Table 2.1 Connection model set and its meaning

[0069] Table 2.2 Connection model variables and their meanings

[0070]

[0071] Table 2.3 Connection model parameters and their meanings

[0072]

[0073] (2) Optimization goal

[0074] The optimization objective function of the bus connection model is defined as follows:

[0075] minT total =min(T ordinary +T fail +σT disrupted )

[0076] The optimization objective function is defined as minimizing the total delay T total , the total delay is the delay of ordinary passengers in the bus T ordinary , Delay of passengers who failed to board the bus T fail (Full load due to carrying stranded passengers) Delay due to stranded passengers T disrupted The delay of ordinary passengers refers to the additional travel time in the bus when following the bus to pick up stranded passengers, the delay of passengers who failed to board the bus refers to the additional waiting time, and the delay of stranded passengers is defined as the time waiting for connecting vehicles at the interruption hub. Among them, σ is a weighting parameter with a value of 0 to 1, which indicates the impact of the delay of stranded passengers.

[0077] Delay for ordinary passengers T ordinary The delay mainly comes from the extra travel time caused by detours. Different types of bus routes will have different delays. For example, there will be no delays for ordinary passengers in type 6 routes. The delays in types 2 and 5 need to be further judged based on the specific circumstances of the route destination. In types 1 and 4, corresponding delays will also occur when different connecting destinations are selected.

[0078]

[0079] Delays for passengers who are unable to board the bus fail The additional waiting time for passengers who are unable to board a fully loaded bus is mainly determined by the train departure interval.

[0080]

[0081] Delays for stranded passengersT disrupted It is the sum of the time that all stranded passengers wait for the connecting vehicle to arrive, that is, the sum of the waiting time from the occurrence of the failure to the time when the passengers are picked up.

[0082]

[0083] (3) Bridge line construction

[0084]

[0085] The generation of the connecting line pair is determined based on the selection of the connecting starting station and the connecting destination station. For example, a bus route of type 1 requires a pair of connecting lines at the starting point, and one or two pairs of connecting lines are generated based on the number of detour destinations, while a bus route of type 2 needs to consider the specific conditions of the route to determine the status of the connecting line, a bus route of type 3 only requires a pair of connecting lines at the destination, and a bus route of type 6 does not require any new connecting line pairs. The connecting line pairs of types 1, 2, and 4 cannot overlap.

[0086] (4) Time constraints

[0087]

[0088] D bj =A bj +δ bj

[0089]

[0090] S150, solving the optimization target based on the genetic algorithm and outputting the optimal solution.

[0091] According to a passenger bus connection method under subway operation interruption provided by the present invention, the optimization target is solved based on a genetic algorithm and the optimal solution is output, which specifically includes: defining basic parameters of the genetic algorithm, randomly generating an initial population including multiple individuals, each individual representing a bus scheduling plan; calculating the fitness value of each individual according to the optimization objective function; continuously iterating the current population according to the fitness value to form a new population until a preset iteration termination condition is met; and returning the individual with the highest fitness value as the optimal solution of the bus scheduling plan.

[0092] According to a passenger bus connection method under subway operation interruption provided by the present invention, a new population is formed by continuously iterating the current population according to the fitness value, specifically comprising: selecting individuals with fitness higher than a preset threshold from the current population as parents, performing a crossover operation on the selected parent individuals to generate new child individuals; performing a mutation operation on some of the new child individuals; after the crossover operation and the mutation operation, checking whether the generated individuals meet the constraint conditions; recalculating the fitness value of each individual according to the individuals that meet the constraint conditions; and selecting the individual with the highest fitness value to enter the next generation to form a new population.

[0093] Specifically, a genetic algorithm is an optimization algorithm that simulates the biological evolution process and is suitable for solving complex optimization problems. The present invention introduces a genetic algorithm for the bus connection problem, which aims to optimize the scheduling and operation of buses to meet passenger demand and improve system efficiency. The goal of this problem is to optimize the connection between multiple bus routes to minimize the total delay of passengers while considering other constraints. This problem is essentially a mixed integer nonlinear programming problem involving multiple interrelated variables.

[0094] (1) Individual representation

[0095] In a genetic algorithm, each individual represents a possible solution. In this problem, the individuals contain the following decision variables:

[0096] x b : Indicates the dispatching status of the b-th vehicle in bus route i.

[0097] u iog and u idg : represent the connection status of the jth station in bus line i (whether to take a detour to pick up stranded passengers). The combination of these variables represents a complete scheduling plan.

[0098] (2) Fitness function

[0099] The fitness function is used to evaluate the pros and cons of each individual, which in the present invention is to minimize the total delay of ordinary passengers and stranded passengers.

[0100] (3) Introduction to the overall process of genetic algorithm

[0101] Initialize the population: Randomly generate a certain number of individuals to form the initial population. Each individual represents a possible bus scheduling solution.

[0102] Selection operation: Use Tournament Selection to select excellent individuals from the population to enter the next generation.

[0103] Crossover: Perform a crossover operation on the selected individuals to generate new individuals. The crossover operation simulates gene recombination and generates offspring individuals with the characteristics of both parents by exchanging some genes of the parent individuals.

[0104] Mutation: Perform mutation operations on some individuals to change the value of some of their genes. Mutation operations help maintain the diversity of the population and may explore better solutions.

[0105] Constraint check: After crossover and mutation, check whether the generated individuals meet the constraints of the problem. If not, impose penalties or adjust the individuals to make them meet the constraints.

[0106] Fitness evaluation: Calculate the fitness value of each individual to indicate the quality of its solution.

[0107] Select the next generation: Select the next generation of individuals based on their fitness values, and continue to perform selection, crossover, mutation, and evaluation to form a new population.

[0108] Termination condition: The algorithm ends when a certain termination condition is met, such as after a fixed number of iterations (generations) or when the fitness value reaches a predetermined threshold.

[0109] Output the optimal solution: After the algorithm ends, the individual with the highest fitness value is returned as the optimal solution to the bus scheduling problem.

[0110] (4) Interpretation of the overall algorithm process

[0111] a. Initialization, i.e. setting parameters: defining parameters such as population size (e.g. n_pop), crossover probability (e.g. cxpb), mutation probability (e.g. mutpb) and maximum number of iterations (e.g. NGEN).

[0112] b. Population initialization, that is, generating an initial population: create a population containing multiple individuals (schemes). Each individual is a dictionary containing x b 、u iog and u idg The initial population is randomly generated, that is, the value of each variable is randomly determined within a reasonable range.

[0113] c. Fitness evaluation: Calculate the fitness value of each individual to indicate the quality of the scheduling plan. The fitness value is calculated based on the objective function total passenger delay. The higher the fitness (the lower the corresponding total passenger delay), the better the plan.

[0114] d. Iterative process: In each generation, the algorithm optimizes the population through selection, crossover, mutation, and evaluation, gradually approaching the optimal solution.

[0115] Selection: Select parent individuals from the current population based on fitness values. The method used is Tournament Selection, which randomly selects several individuals from the population and selects the individual with the highest fitness value as the parent. The parent individuals will be used to generate the next generation population.

[0116] Crossover: Perform a crossover operation on the selected parent individuals to generate new individuals (offspring). The goal of the crossover operation is to combine the genes of the two parent individuals (i.e., the variable x b 、u iog and u idg value), producing better offspring individuals. During the crossover process, the variable values ​​of the two parent individuals may be exchanged to form new combinations.

[0117] Mutation: Perform mutation operations on offspring individuals to introduce diversity. The mutation operation is achieved by randomly changing the values ​​of individuals. The probability of mutation is controlled by the set mutation probability value mutpb. For example, if u idg The current value is 0, but it may become 1 after mutation, and vice versa. The mutation operation can help the algorithm jump out of the local optimal solution and explore more solution spaces.

[0118] Constraint check: After crossover and mutation, check whether the generated individuals satisfy the constraints of the problem. For example, check whether u iog and u idg Whether the uniqueness constraint of each site is satisfied, or x b Is the scheduling reasonable? If an individual does not meet the constraints, penalties can be imposed or corrections can be made.

[0119] Fitness evaluation: Calculate the fitness value of each newly generated individual. The fitness value is calculated by the objective function. The new fitness value will be used in the selection process of the next generation.

[0120] Update the population: According to the fitness value, select the individuals with the highest fitness (corresponding to the lowest total delay) to enter the next generation. The population will be continuously optimized to gradually approach the optimal solution. The updated population will continue to select, crossover and mutate in the next generation until the number of iterations is reached or convergence occurs.

[0121] End of iteration: The algorithm ends when the preset termination condition is reached, such as the number of iterations reaches the maximum value NGEN or the fitness value of the population no longer changes significantly (i.e. convergence).

[0122] e. Output the optimal solution: After the algorithm is finished, the individual with the highest fitness value is returned as the optimal solution to the bus scheduling problem. This individual contains the optimal x b 、u iog and u idg The combined solution can minimize the total delay time for passengers.

[0123] (5) The genetic algorithm optimizes the bus connection plan through continuous iterative selection, crossover and mutation. The core of the algorithm lies in the design of appropriate individual representation, reasonable fitness function and effective constraint processing mechanism. Through these steps, the algorithm can find an optimal bus scheduling plan that minimizes the total passenger delay.

[0124] Through the subway hub station interruption shuttle bus scheduling and path optimization strategy proposed in the present invention, by constructing a passenger transfer demand stochastic model and combining genetic algorithm to optimize bus scheduling, the passenger evacuation efficiency is effectively improved, the total delay of ordinary passengers and stranded passengers is reduced, and the emergency response capability and resilience of the urban public transportation system are enhanced.

[0125] The bus connecting device based on the passenger transfer demand provided by the present invention is described below. The bus connecting device based on the passenger transfer demand described below and the passenger bus connecting method under the subway operation interruption described above can be referred to each other.

[0126] like Figure 4 The present invention shows a bus connection device based on passenger transfer demand, including: a demand distribution model building module 410, used to build a passenger transfer demand distribution randomness model based on historical data, wherein the historical data is passenger transfer demand data; a passenger evacuation strategy determination module 420, used to determine a passenger evacuation strategy according to a fault site and the passenger transfer demand distribution randomness model; a bus connection model building module 430, used to determine a candidate bus route set based on the passenger evacuation strategy; a bus connection model is built based on the candidate bus route set, and minimizing the total delay is determined as the optimization goal of the bus connection model; the total delay is determined based on the delay of ordinary passengers, the delay of passengers who have not successfully boarded the bus, and the delay of stranded passengers; a solution module 440, used to solve the optimization goal based on a genetic algorithm and output an optimal solution.

[0127] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute a passenger bus connection method under subway operation interruption, the method comprising: constructing a passenger transfer demand distribution randomness model based on historical data, the historical data being passenger transfer demand data; determining a passenger evacuation strategy based on the fault station and the passenger transfer demand distribution randomness model; determining a candidate bus line set based on the passenger evacuation strategy; constructing a bus connection model based on the candidate bus line set, determining to minimize the total delay as the optimization goal of the bus connection model; the total delay is determined based on the delay of ordinary passengers, the delay of passengers who have not successfully boarded the bus and the delay of stranded passengers; solving the optimization goal based on a genetic algorithm and outputting an optimal solution.

[0128] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, 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, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0129] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the passenger bus connection method under subway operation interruption provided by the above methods, the method including: constructing a passenger transfer demand distribution randomness model based on historical data, the historical data being passenger transfer demand data; determining a passenger evacuation strategy based on fault sites and the passenger transfer demand distribution randomness model; determining a candidate bus route set based on the passenger evacuation strategy; constructing a bus connection model based on the candidate bus route set, and determining to minimize the total delay as the optimization goal of the bus connection model; the total delay is determined based on the delay of ordinary passengers, the delay of passengers who failed to board the bus successfully, and the delay of stranded passengers; solving the optimization goal based on a genetic algorithm and outputting the optimal solution.

[0130] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the passenger bus connection method under subway operation interruption provided by the above-mentioned methods, the method comprising: constructing a passenger transfer demand distribution randomness model based on historical data, the historical data being passenger transfer demand data; determining a passenger evacuation strategy according to the fault site and the passenger transfer demand distribution randomness model; determining a candidate bus route set based on the passenger evacuation strategy; constructing a bus connection model based on the candidate bus route set, and determining to minimize the total delay as the optimization goal of the bus connection model; the total delay is determined based on the delay of ordinary passengers, the delay of passengers who have not successfully boarded the bus, and the delay of stranded passengers; solving the optimization goal based on a genetic algorithm, and outputting the optimal solution.

[0131] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0132] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for connecting passengers to buses when subway operation is interrupted, characterized in that: include: Building a passenger transfer demand distribution stochastic model based on historical data, wherein the historical data is passenger transfer demand data; Determining a passenger evacuation strategy based on the fault site and the passenger transfer demand distribution stochastic model; Determining a set of candidate bus routes based on the passenger evacuation strategy; Building a bus connection model based on the candidate bus route set, and determining minimizing total delay as the optimization goal of the bus connection model; The total delay is determined based on the delay of ordinary passengers, the delay of passengers who failed to board the bus, and the delay of stranded passengers; The optimization objective is solved based on a genetic algorithm, and an optimal solution is output.

2. The method for connecting passengers to buses when subway operation is interrupted according to claim 1, characterized in that: The step of determining a candidate bus route set based on the passenger evacuation strategy specifically includes: Determine the connecting starting station and the connecting destination station based on the passenger evacuation strategy; Filter out all bus stops within a preset radius of each connecting starting station and each connecting destination station to form a set of candidate connecting stations; A candidate bus route set is constructed based on preset rules and the candidate site set; the preset rule is that when a bus route passes through a bus station that includes both a bus station within a preset radius of the connecting start station and a bus station within a preset radius of the connecting destination station, the bus route is used as a candidate bus route for connection.

3. The method for connecting passengers to buses when subway operation is interrupted according to claim 1, characterized in that: The step of constructing a bus connection model based on the candidate bus route set and determining minimizing total delay as the optimization goal of the bus connection model specifically includes: Determine a bus connection model and its model set, model variables and model parameters based on the candidate bus route set; Determining the delay of ordinary passengers, the delay of passengers who failed to board the bus, and the delay of stranded passengers according to the model set, model variables, and model parameters; Determine the total delay based on the delay for regular passengers, the delay for passengers who failed to board, and the delay for stranded passengers; Taking minimizing the total delay as the optimization goal, the optimization objective function is obtained.

4. The method for connecting passengers to buses when subway operation is interrupted according to claim 1, characterized in that: Solving the optimization objective based on a genetic algorithm and outputting an optimal solution specifically includes: Define the basic parameters of the genetic algorithm and randomly generate an initial population consisting of multiple individuals, each of which represents a bus scheduling solution; Calculate the fitness value of each individual according to the optimization objective function; The current population is continuously iterated to form a new population according to the fitness value until the preset iteration termination condition is met; The individual with the highest fitness value is returned as the optimal solution for the bus scheduling plan.

5. The method for connecting passengers to buses when subway operation is interrupted according to claim 4, characterized in that: The step of continuously iterating the current population according to the fitness value to form a new population specifically includes: Select individuals with fitness higher than the preset threshold from the current population as parents, perform crossover operations on the selected parent individuals, and generate new offspring individuals; Perform mutation operations on some of the new offspring individuals; After the crossover and mutation operations, check whether the generated individuals meet the constraints; Recalculate the fitness value of each individual according to the individuals that meet the constraint conditions; The individuals with the highest fitness values ​​are selected to enter the next generation and form a new population.

6. The method for connecting passengers to buses when subway operation is interrupted according to claim 1, characterized in that: The determining of the passenger evacuation strategy according to the fault site and the passenger transfer demand distribution stochastic model specifically includes: Determine the hub station where the bus network fails as the failure station; Analyzing the passenger transfer demand at the faulty station; A passenger evacuation strategy for multiple destinations is determined according to the passenger transfer demand.

7. The method for connecting passengers to buses when subway operation is interrupted according to claim 1, characterized in that: Before constructing the bus connection model, the method further includes: Analyze the connection characteristics of candidate bus routes; According to the analysis result, when the vehicles of a bus line are within the dispatching range of two evacuation stations, one of the two evacuation stations is selected as the connecting starting station of the bus line according to the actual running distance.

8. A passenger bus connection device when subway operation is interrupted, characterized in that: include: A demand distribution model building module, used to build a passenger transfer demand distribution stochastic model based on historical data, wherein the historical data is passenger transfer demand data; A passenger evacuation strategy determination module, used to determine the passenger evacuation strategy according to the fault site and the passenger transfer demand distribution randomness model; A bus connection model building module, used to determine a set of candidate bus routes based on the passenger evacuation strategy; Building a bus connection model based on the candidate bus route set, and determining minimizing total delay as the optimization goal of the bus connection model; The total delay is determined based on the delay of ordinary passengers, the delay of passengers who failed to board the bus, and the delay of stranded passengers; The solution module is used to solve the optimization target based on a genetic algorithm and output an optimal solution.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the passenger bus connection method under subway operation interruption as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for connecting passengers to buses when subway operation is interrupted as described in any one of claims 1 to 7 is implemented.

Images