Multi-mode public transit network design optimization method, system and device and storage medium

Abstract

The invention discloses a multi-mode public transit network design optimization method, system and device and a storage medium, and the method comprises the steps: constructing a double-layer Nested Logit model which comprises an upper layer model used for optimizing a bus route structure and bus shift frequency and a lower layer model used for solving a passenger flow distribution result; constructing a multi-mode network including three travel modes of driving, walking and public transportation, determining alternative routes based on a K-shortest circuit algorithm, and screening out effective routes from the alternative routes according to constraint conditions of an upper-layer model to obtain an effective route set; and randomly generating an initial population according to the effective line set, and performing optimization solution on the double-layer Nested Logit model by using a genetic algorithm based on a parallel computing strategy according to the initial population to obtain an optimal bus line structure and the optimal shift frequency of each bus line. The method improves the efficiency and accuracy of public transit network design, and can be applied to the technical field of public transit planning.

Description

Technical Field

[0001] The present invention relates to the technical field of public transportation planning, and in particular to a multi-mode bus line network design optimization method, system, device and storage medium. Background Art

[0002] In many large cities, especially in the city center, public transportation is an important mode of transportation. However, public transportation is facing many internal and external challenges, and the passenger flow of public transportation in many cities has declined significantly. The external factors mainly include the development of other modes of transportation such as online car-hailing, shared bicycles, electric bicycles, and the improvement of residents' travel quality requirements brought about by social and economic development, while the internal factors are mainly the time and space mismatch between public transportation supply and demand. Spatial mismatch means that taking the bus cannot reach the place where the passenger wants to go, while time mismatch means that although the bus can reach the destination, the travel time cannot meet expectations. The mismatch between supply and demand will lead to low passenger flow on the one hand and high empty vehicle rate on the other hand, resulting in a waste of resources.

[0003] The main reason for the mismatch between public transportation supply and demand is the inadequacy of bus network design. The existing bus network design in China mainly relies on manual planning, which is mainly based on subjective experience and supplemented by data indicators. During the design, according to the principle of "laying out one by one and optimizing the network", the route direction is manually planned according to the main passenger flow channels, and the departure frequency and number of vehicles are set for the route based on experience. Manual planning has certain feasibility in small bus networks, but when the number of bus stops and routes increases, manual planning is not only labor-intensive, but also difficult to achieve supply and demand matching for large-scale bus networks because the solution space grows exponentially with the number of stops.

[0004] In existing bus network design problems, it is usually assumed that travel demand is fixed, that is, all demand is for bus travel only. This assumption ignores the choice between multiple modes of transportation that passengers may face when traveling, and does not take into account the impact of factors such as bus travel time on travel mode choice. In reality, the total travel demand is relatively fixed, but the demand for bus travel is elastic and changes with the performance of bus services, such as waiting time and number of transfers. Therefore, the route and frequency of the bus network will affect the choice of user travel mode, and thus affect bus passenger flow. On the one hand, bus routes with direct routes and short waiting times may guide non-bus users, such as private car users, to switch to bus travel. On the other hand, the increase in the number of transfers and waiting time may also cause bus users to switch to other travel modes.

[0005] Theoretical research on existing bus network design usually adopts a two-layer model. The upper problem models the decision variables, objective functions and network constraints. The lower problem is the passenger flow allocation problem, which is used to predict the travel choice behavior of passengers and then calculate the passenger flow of the route. However, when considering multiple modes, the lower problem is not only the bus passenger flow allocation problem, but also the travel mode division and passenger flow allocation problem. When predicting passenger travel, it is necessary to first calculate the probability of choosing different travel modes according to the utility of different travel modes, and then calculate the selection probability of different bus routes according to the utility of different routes, and finally obtain the passenger flow of the route. The Logit model is a commonly used model in existing research on travel mode selection. However, the Logit model calculates the selection probability based on the utility between different options, which implies the assumption that the sample maximum value conforms to the Gumbel distribution. Therefore, when there are multiple accessible bus routes between the same pair of OD stations, that is, the collinear problem, the choice of travel mode and the choice of bus route cannot be calculated by the multinomial Logit model. Because treating different bus routes as options at the same level as driving, walking and other travel modes violates the independence of irrelevant alternatives (IIA) of the Gumbel distribution, this will cause the model to overestimate the probability of choosing bus travel.

[0006] In addition to the collinearity problem, the existing bus network design usually ignores the boarding order constraint when allocating passenger flow. However, due to the capacity constraint of the bus, the travel needs of passengers at the upstream station will be met first, while passengers at the downstream station may not be able to board the bus because the travel demand of the previous station exceeds the capacity constraint. Ignoring the boarding order constraint may cause the bus passenger flow allocation result to be inconsistent with the actual situation, which in turn leads to deviations in the performance evaluation of the bus network scheme. In the existing multi-modal bus network design and frequency setting problems, no research has considered strict capacity constraints, collinearity problems and boarding order constraints at the same time.

[0007] In terms of solution algorithms, they are mainly divided into upper-level problem-solving algorithms and lower-level problem-solving algorithms. Metaheuristic algorithms are the main method for solving upper-level problems in bus network design. According to the comparative analysis of different metaheuristic algorithms on the Mandl standard bus network by Iliopoulou and other scholars, genetic algorithms are one of the algorithms with the best performance. The lower-level problem-solving algorithm is directly related to the factors considered in passenger flow distribution. The more factors considered in the lower-level problem, the higher the algorithm complexity. Existing studies usually ignore factors on the other side while emphasizing one aspect. For example, emphasizing capacity constraints but ignoring collinearity problems, or emphasizing collinearity problems but ignoring boarding order constraints. Considering multiple factors at the same time may greatly increase the complexity of solving the lower-level algorithm, and in the bus network design problem, the lower-level problem needs to be repeatedly executed. Therefore, how to improve the efficiency of the algorithm while ensuring objective constraints is an urgent problem to be solved in the lower-level problem-solving algorithm. Summary of the invention

[0008] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0009] To this end, an object of an embodiment of the present invention is to provide a multimodal bus network design optimization method, which constructs a multimodal network including three travel modes: driving, walking and bus, uses a double-layer NestedLogit model to solve the passenger flow distribution result and optimize the bus line structure and bus departure frequency, and obtains the optimal bus line structure and the optimal departure frequency of each bus line through the genetic algorithm optimization solution considering the parallel computing strategy, thereby improving the efficiency and accuracy of the bus network design.

[0010] Another object of an embodiment of the present invention is to provide a multi-mode bus network design optimization system.

[0011] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present invention include:

[0012] On the one hand, an embodiment of the present invention provides a multi-mode bus network design optimization method, comprising the following steps:

[0013] Constructing a two-layer Nested Logit model, the two-layer Nested Logit model includes an upper model for optimizing bus route structure and bus departure frequency and a lower model for solving passenger flow distribution results;

[0014] Construct a multi-modal network including three travel modes: driving, walking and public transportation, determine alternative routes based on the K shortest path algorithm, and select valid routes from the alternative routes according to the constraints of the upper model to obtain a valid route set;

[0015] An initial population is randomly generated according to the effective route set, and the double-layer Nested Logit model is optimized and solved using a genetic algorithm based on a parallel computing strategy according to the initial population to obtain an optimal bus route structure and an optimal departure frequency of each bus route;

[0016] Among them, the upper model includes the objective function of maximizing the bus operation profit, the line station number constraint, the line length constraint, the line first and last station constraint, the line non-linear coefficient constraint, the capacity constraint, the departure frequency constraint, the total number of bus vehicles in the bus network constraint and the total number of bus lines in the bus network constraint; the lower model includes a first functional relationship for solving the bus travel probability and the bus travel demand and a second functional relationship for solving the passenger flow of different bus lines.

[0017] Furthermore, in one embodiment of the present invention, the objective function is:

[0018]

[0019] The line station number constraint is:

[0020]

[0021] The line length constraint is:

[0022]

[0023] The line's first and last station constraints are:

[0024]

[0025] The line non-linear coefficient constraint is:

[0026]

[0027] The capacity constraint is:

[0028]

[0029]

[0030] The frequency constraint is:

[0031]

[0032] The total number of buses in the bus network is constrained as follows:

[0033]

[0034] The total number of bus lines is constrained as follows:

[0035]

[0036] Among them, χ represents the bus operating profit, r represents the route in the bus network, R represents the set of all routes in the bus network, Q r represents the passenger flow of route r, ω represents the bus fare, n r represents the number of buses on route r, λ represents the depreciation cost of a single bus, μ represents the labor cost of a single bus, and f r represents the departure frequency of line r, Indicates the length of line r in the upstream direction, represents the length of line r in the downward direction, τ represents the power cost of the bus per unit mileage, Indicates the number of stations in the upstream direction of line r, Indicates the number of stations in the downstream direction of line r, s max Indicates the maximum number of stations allowed on a single line, s min Indicates the minimum number of stations allowed for a single line, l max Indicates the maximum allowed length of a single line. represents the originating station of line r, represents the terminal station of line r, TS represents the set of first and last stations, ρ r represents the nonlinear coefficient of line r, ρ max Indicates the maximum allowable non-linear coefficient of the line, represents the nonlinear coefficient of the upstream direction of line r, Indicates the nonlinear coefficient of line r in the downstream direction, B ij represents the bus route section from station i to station j, represents the set of uplink intervals of bus route r, represents the set of downlink sections of bus line r, represents the travel distance of route r from station i to the next station j, It represents the travel distance between the first and last stations in the upward direction of line r. Indicates the travel distance between the first and last stations in the down direction of line r, B r represents the set of interval segments of bus route r, represents the cross-sectional passenger flow between adjacent stations i and j on line r, C represents the capacity of a single bus, B od represents the bus route section from station o to station d, represents the passenger flow of route r from station o to station d, h r represents the departure interval of line r, H represents the set of departure intervals that can be set, t r represents the turnaround time of route r, represents the one-way time in the upstream direction of line r, represents the one-way time in the downstream direction of line r, t g Indicates the rest time of the driver between the up and down shifts of the line. represents the bus time between station i and station j, n max Indicates the maximum number of vehicles on the route, N R represents the number of routes in the bus network, Indicates the minimum number of bus lines in the network. Indicates the maximum number of bus lines in the bus network.

[0037] Further, in one embodiment of the present invention, the first functional relationship is:

[0038]

[0039] The second functional relationship is:

[0040]

[0041] in, represents the probability of choosing public transportation from station o to station d, represents the bus travel cost from station o to station d, represents the travel cost of a car from station o to station d, represents the walking travel cost from station o to station d, represents the bus travel demand from station o to station d, D od represents the total travel demand from station o to station d, represents the travel time of a car from station o to station d, vot represents the time-money coefficient, represents the monetary cost of traveling by car from station o to station d, represents the bus travel time from station o to station d, represents the monetary cost of public transportation from station o to station d, represents the walking travel time from station o to station d, m 0 Indicates the starting price of a taxi. represents the travel distance from station o to station d, Indicates the mileage included in the taxi starting price. represents the taxi mileage price, R od represents the set of all feasible routes from site o to site d, represents the bus travel time of route r from station o to station d, represents the waiting time of line r, θ represents the penalty coefficient of waiting time, represents the time on the train of route r from station o to station d, From site o to site d via line r 1 Transfer line 2 The bus travel time, Indicates line r 1 The waiting time, Indicates line r 2 The waiting time, Indicates line r 1 The time on the bus from station o to station k, Indicates line r 2 The time on the bus from station k to station d, represents the transfer time at station k, ψ represents the transfer penalty time, represents the passenger flow of route r boarding at station i, represents the boarding demand of route r at station i, represents the capacity of line r from site i to site j, represents the passenger flow of route r from station i to station k, represents the travel demand of route r from station i to station k.

[0042] Furthermore, in one embodiment of the present invention, the construction of a multi-modal network including three travel modes of driving, walking and public transportation specifically includes:

[0043] Obtain available bus stops and bus terminals in the target area and generate a bus stop table;

[0044] According to the bus stop table, bus stops in the target area are combined in pairs to obtain a plurality of start and end stop pairs;

[0045] Perform driving route planning and walking route planning for the starting and ending station pairs to obtain corresponding driving distance, driving time, and walking time;

[0046] Determine the bus on-board time of the start-end station pair according to the driving distance and the average bus operating speed of the target area;

[0047] Taking the bus stops in the target area as nodes, the paths between the bus stops as edges, and taking the driving time, the walking time, and the bus time as weights of the corresponding edges, a car network, a walking network, and a bus network are obtained;

[0048] The multi-modal network is constructed according to the car network, the pedestrian network and the bus network.

[0049] Further, in one embodiment of the present invention, the determining of candidate routes based on the K shortest path algorithm and selecting valid routes from the candidate routes according to the constraint conditions of the upper model to obtain a valid route set specifically includes:

[0050] Combining the first and last bus stops in the target area in pairs to obtain a plurality of first and last bus stop pairs;

[0051] Determine the alternative routes of each of the first and last station pairs based on the K shortest path algorithm, and determine the number of stations, line length and non-linear coefficient of each of the alternative routes;

[0052] The candidate routes are screened according to the site number constraint, the route length constraint, the route first and last station constraint, and the route non-linear coefficient constraint to obtain a plurality of valid routes;

[0053] The valid line set is constructed according to the valid lines.

[0054] Furthermore, in one embodiment of the present invention, the initial population is randomly generated according to the effective route set, and the double-layer Nested Logit model is optimized and solved using a genetic algorithm based on a parallel computing strategy according to the initial population to obtain an optimal bus route structure and an optimal departure frequency of each bus route, which specifically includes:

[0055] Constructing the initial population including a plurality of line network individuals, and determining the number of lines of each line network individual, and then randomly extracting a plurality of the valid lines from the valid line set according to the number of lines as the initial lines of the corresponding line network individuals;

[0056] Determine the optimal vehicle allocation schedule for each individual line network, perform multi-modal passenger flow allocation for each individual line network according to the lower-level model, and determine the public transportation operation profit corresponding to each individual line network according to the passenger flow allocation result and the upper-level model;

[0057] Perform crossover and mutation on the current population to obtain a child population, merge the child population with the current population, and determine the public transportation operation profit corresponding to each line network individual in the merged population;

[0058] The probability of each line network individual being selected is determined according to the bus operation profit, and then multiple line network individuals are selected from the merged population as the current population of the next generation, and the step of performing crossover and mutation on the current population to obtain the offspring population is returned until the preset number of population iterations is reached to obtain the target population;

[0059] Determine the optimal line network individual according to the corresponding public transportation operation profit of each line network individual of the target population;

[0060] The optimal bus route structure is determined according to the bus routes included in the optimal line network individual, and the optimal departure frequency of each bus route is determined according to the optimal vehicle allocation and scheduling of the optimal line network individual.

[0061] Further, in one embodiment of the present invention, the crossover and mutation of the current population to obtain the offspring population specifically includes:

[0062] Determine the individuals to be crossed and the individuals to be mutated according to the current population;

[0063] Combining the individuals to be crossed in pairs to obtain a plurality of crossover individual pairs, and then exchanging non-repetitive lines of the crossover individual pairs to obtain crossover offspring individuals;

[0064] Randomly select a number of the valid circuits from the valid circuit set, and randomly replace a number of circuits of the individual to be mutated, to obtain mutated offspring individuals;

[0065] The offspring population is composed according to the crossover offspring individuals and the variant offspring individuals.

[0066] On the other hand, an embodiment of the present invention provides a multi-mode bus network design optimization system, including:

[0067] A model building module, used to build a double-layer Nested Logit model, wherein the double-layer Nested Logit model includes an upper-layer model for optimizing bus route structure and bus departure frequency and a lower-layer model for solving passenger flow distribution results;

[0068] An effective route set determination module is used to construct a multi-modal network including three travel modes: driving, walking and public transportation, determine candidate routes based on the K shortest path algorithm, and select effective routes from the candidate routes according to the constraints of the upper model to obtain an effective route set;

[0069] An optimization solution module, used for randomly generating an initial population according to the effective route set, optimizing and solving the double-layer Nested Logit model according to the initial population using a genetic algorithm based on a parallel computing strategy, and obtaining an optimal bus route structure and an optimal departure frequency of each bus route;

[0070] Among them, the upper model includes the objective function of maximizing the bus operation profit, the line station number constraint, the line length constraint, the line first and last station constraint, the line non-linear coefficient constraint, the capacity constraint, the departure frequency constraint, the total number of bus vehicles in the bus network constraint and the total number of bus lines in the bus network constraint; the lower model includes a first functional relationship for solving the bus travel probability and the bus travel demand and a second functional relationship for solving the passenger flow of different bus lines.

[0071] On the other hand, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, wherein the program, when executed by the processor, realizes the multi-modal bus network design optimization method as described above.

[0072] On the other hand, an embodiment of the present invention further provides a storage medium, which is a computer-readable storage medium used for computer-readable storage, and the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the multi-modal bus network design optimization method as described above.

[0073] The advantages and beneficial effects of the present invention will be partly given in the following description, partly become apparent from the following description, or be understood through the practice of the present invention:

[0074] The embodiment of the present invention constructs a double-layer Nested Logit model, which includes an upper model for optimizing the bus route structure and bus departure frequency and a lower model for solving the passenger flow distribution result, constructs a multi-mode network including three travel modes of driving, walking and bus, determines the alternative routes based on the K shortest path algorithm, and selects effective routes from the alternative routes according to the constraints of the upper model to obtain an effective route set, randomly generates an initial population according to the effective route set, and optimizes and solves the double-layer Nested Logit model based on the initial population using a genetic algorithm based on a parallel computing strategy to obtain the optimal bus route structure and the optimal departure frequency of each bus route. The embodiment of the present invention constructs a multi-mode network including three travel modes of driving, walking and bus, uses a double-layer NestedLogit model to solve the passenger flow distribution result and optimize the bus route structure and bus departure frequency, and optimizes and solves the optimal bus route structure and the optimal departure frequency of each bus route by optimizing and solving the genetic algorithm considering the parallel computing strategy, thereby improving the efficiency and accuracy of bus network design. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the technical solution in the embodiments of the present invention, the following introduction is made to the drawings required for use in the embodiments of the present invention. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solution of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0076] Figure 1A flowchart of the steps of the multi-mode bus network design optimization method provided by an embodiment of the present invention;

[0077] Figure 2 A schematic diagram of a double-layer Nested Logit model provided in an embodiment of the present invention;

[0078] Figure 3 A schematic diagram of a process for optimizing and solving a double-layer NestedLogit model using a genetic algorithm based on a parallel computing strategy provided in an embodiment of the present invention;

[0079] Figure 4 A schematic diagram of the structure of a multi-mode bus network design optimization system provided by an embodiment of the present invention;

[0080] Figure 5 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention;

[0081] Figure 6 A schematic diagram of the structure of a storage medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0082] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limitations on the present application. It should be noted that, although the functional module division is performed in the system schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in a different order from the module division in the system schematic diagram or the flow chart. For the step numbers in the following embodiments, they are only set for the convenience of explanation, and the order between the steps is not limited in any way. The execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0083] In the description of the present invention, the meaning of "a plurality" is two or more. If there is a description of the first or the second, it is only for the purpose of distinguishing the technical features, and it cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features. In addition, unless otherwise defined, all technical and scientific terms used in this document have the same meaning as those commonly understood by technicians in the technical field of this application. The terms used in this document are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0084] The multi-mode bus network design optimization method provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a set-top box, etc.; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the multi-mode bus network design optimization method, etc., but is not limited to the above forms.

[0085] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0086] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with the relevant laws, regulations, and standards of the relevant countries and regions. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0087] like Figure 1 FIG. 1 is a flow chart showing a method for optimizing the design of a multi-mode bus network according to an embodiment of the present invention. Figure 1 The embodiment of the present invention provides a multi-mode bus network design optimization method, which specifically includes the following steps:

[0088] S101, constructing a double-layer Nested Logit model, which includes an upper-layer model for optimizing bus route structure and bus departure frequency and a lower-layer model for solving passenger flow distribution results;

[0089] S102, constructing a multi-modal network including three travel modes of driving, walking and public transportation, determining alternative routes based on the K shortest path algorithm, and selecting effective routes from the alternative routes according to the constraints of the upper model to obtain an effective route set;

[0090] S103, randomly generating an initial population according to the effective route set, optimizing and solving the double-layer Nested Logit model using a genetic algorithm based on a parallel computing strategy according to the initial population, and obtaining an optimal bus route structure and an optimal departure frequency of each bus route;

[0091] Among them, the upper model includes the objective function of maximizing the bus operation profit, the line station number constraint, the line length constraint, the line first and last station constraint, the line non-linear coefficient constraint, the capacity constraint, the departure frequency constraint, the total number of bus vehicles in the bus network constraint and the total number of bus lines in the bus network constraint. The lower model includes the first functional relationship for solving the bus travel probability and the bus travel demand and the second functional relationship for solving the passenger flow of different bus lines.

[0092] Specifically, the embodiment of the present invention adopts a double-layer Nested Logit model to solve the problems of travel mode classification and bus line network selection. The collinearity problem, capacity constraint and boarding order constraint are considered in the bus passenger flow distribution, which more realistically restores the actual travel choice of passengers, and proposes a genetic algorithm considering parallel computing strategy to solve the bus line network design problem.

[0093] First, the double-layer Nested Logit model of the embodiment of the present invention is introduced and explained. The present invention adopts the framework of the double-layer Nested Logit model to model the problem. In the upper-level problem, the optimization goal of the model is to maximize the profit of bus operation, the decision variables are the bus line structure and its departure frequency, and the constraints include line shape constraints, capacity constraints, frequency constraints, vehicle number constraints, line number constraints, etc.; the lower-level problem predicts the travel behavior choices of passengers, including travel mode selection and bus line selection. The model parameter table of the embodiment of the present invention is shown in Table 1 below.

[0094] Table 1

[0095]

[0096]

[0097]

[0098]

[0099]

[0100] In the upper model, the mathematical expression of the objective function and constraints is as follows:

[0101]

[0102] In the above formula, formula (1) is the objective function, where the bus operating profit is obtained by subtracting the bus operating cost from the bus operating income. The bus operating income is the ticket revenue, which is related to the bus passenger flow. The bus operating cost is mainly composed of labor cost, vehicle cost and power cost. Formulas (2) and (3) are the constraints on the number of stations on the line. Formula (4) is the line length constraint. Formulas (5) and (6) are the constraints on the first and last stations of the line. Formulas (7) to (10) are the constraints on the non-linear coefficient of the line. Formulas (11) and (12) are capacity constraints. Formulas (13) to (18) are departure frequency constraints. Formula (19) is the constraint on the total number of vehicles in the bus network. Formula (20) is the constraint on the total number of bus lines in the bus network.

[0103] In the lower level problem, users choose modes and routes based on the travel costs of different travel modes and different bus routes, but are also constrained by capacity and boarding order. Users choose modes and routes based on time cost and money cost, where time cost is converted into money cost through the time value coefficient and used to uniformly calculate utility. The travel costs of cars, buses, and walking are shown in equations (21) to (24).

[0104]

[0105] The travel time of cars and pedestrians is obtained from the time distance matrix in the multimodal network, while the travel time of buses is divided into direct bus travel time and transfer bus travel time. The direct bus travel time consists of the waiting time and the time on the bus, where the waiting time needs to be multiplied by the penalty coefficient. The calculation formula is shown in Equation (25) and (26). The transfer bus travel time consists of the waiting time and the time on the bus and the transfer time of the two bus trips, and the transfer penalty time is added. The calculation formula is shown in Equation (27).

[0106]

[0107] When there are both direct routes and transfer routes between the same station pair, only direct routes are considered. When there are only transfer routes and no direct routes between the station pairs, transfer routes are considered. If there is no bus route between the two station pairs, only car travel and walking travel are considered. The travel time of multiple bus routes under the collinear problem is calculated by the weighted average of the departure frequency, as shown in formula (28).

[0108]

[0109] In order to solve the independence problem of irrelevant options in Gumbel distribution, the present invention adopts a double-layer Nested Logit model to model the passenger travel mode division and bus route selection. Figure 2 As shown in the figure, the Nested Logit model is a hierarchical tree structure, and the options of the same category are at the same level. Therefore, the error terms of different options at the same level are correlated, while the error terms between options at different levels are uncorrelated, which conforms to the independence of irrelevant options of the Gumbel distribution.

[0110] For the choice of travel mode, the calculation formulas for bus travel probability and bus passenger flow are shown in equations (29) and (30). Equations (21) to (30) are the first functional relationship. Due to capacity constraints, the cross-sectional passenger flow of all bus routes should be less than their cross-sectional carrying capacity, as shown in equations (31) and (32). If the bus travel demand is less than the remaining capacity of the bus route, that is, all bus passenger flows can be satisfied, then the selection probability and passenger flow of the three travel modes are calculated based on their travel costs, as shown in equations (33) to (37). If the bus travel demand is greater than the remaining capacity of the bus route, the bus passenger flow is equal to its remaining capacity, and the remaining travel demand is calculated based on the travel costs of cars and walking. The selection probability and passenger flow are shown in equations (38) to (42).

[0111]

[0112] For the selection of bus routes, the selection probability and passenger flow of different routes are also calculated based on travel utility. When allocating passenger flow, the travel demand and capacity constraints of each station are calculated based on the station sequence of the route, starting from the starting station. The calculation formula for the remaining capacity of the route is shown in formula (43).

[0113]

[0114] From this we can get:

[0115]

[0116] That is, if When like like but Equations (43) to (46) are the second functional relationship equations for solving the passenger flow of each bus line.

[0117] In order to solve the above two-layer model, the present invention proposes a multi-modal bus network design solution framework based on genetic algorithm. First, a multi-modal network is constructed by requesting to obtain the time distance matrix of different travel modes. Then, a set of alternative routes is generated based on the K shortest path algorithm, and valid routes are selected according to the model constraints. Finally, a genetic algorithm framework considering parallel computing strategies is used to optimize the route selection and vehicle scheduling of the bus network. Figure 3 The figure is a schematic diagram of a process for optimizing and solving a double-layer Nested Logit model by using a genetic algorithm based on a parallel computing strategy provided by an embodiment of the present invention.

[0118] As an optional implementation, a multi-modal network including driving, walking and public transportation is constructed, which specifically includes:

[0119] Obtain available bus stops and bus terminals in the target area and generate a bus stop table;

[0120] According to the bus stop table, bus stops in the target area are combined in pairs to obtain multiple start and end stop pairs;

[0121] Carry out driving route planning and walking route planning for the starting and ending station pairs to obtain the corresponding driving distance, driving time and walking time;

[0122] Determine the bus on-board time for the start-end station pair based on the driving distance and the average bus operating speed in the target area;

[0123] The bus stops in the target area are taken as nodes, the paths between the bus stops are taken as edges, and the driving time, walking time and bus time are taken as the weights of the corresponding edges to obtain the car network, walking network and bus network.

[0124] A multimodal network is constructed based on the car network, pedestrian network and bus network.

[0125] Specifically, in order to ensure the feasibility of the generated route and the accuracy of the time distance matrix between sites, the present invention adopts a path planning API interface provided by a navigation software or map service company to construct a multi-mode network, including the following steps:

[0126] 1) Calculate and extract the available bus stops and bus terminals in the study area and generate a bus stop table.

[0127] 2) Arrange and combine each bus stop in the study area in pairs, using them as the departure point and destination respectively.

[0128] 3) The longitude and latitude coordinates corresponding to each pair of bus stops are converted into the coordinate system required by the map navigation API, combined with the APIKey and other request parameters, and the driving and walking route planning between the stations is requested through http and other forms.

[0129] 4) Parse the request results returned by the map navigation API and extract the walking time Driving distance Driving time

[0130] 5) Based on driving distance from the map navigation API The data is combined with the average bus operating speed in the study area to calculate the bus on-board time between bus stops.

[0131] 6) A multi-modal network is constructed with all bus stops in the study area as nodes and paths between stops as edges. The weighted construction with driving time as edges is the car network, the weighted construction with walking time as edges is the walking network, and the weighted construction with bus on-board time as edges is the bus network. The networks of the three travel modes constitute a multi-modal network.

[0132] As an optional implementation method, the candidate routes are determined based on the K shortest path algorithm, and valid routes are selected from the candidate routes according to the constraints of the upper model to obtain a valid route set, which specifically includes:

[0133] Combine the first and last bus stops in the target area in pairs to obtain multiple first and last bus stop pairs;

[0134] Determine the alternative routes for each pair of first and last stations based on the K shortest path algorithm, and determine the number of stations, line length and non-linear coefficient of each alternative route;

[0135] The candidate routes are screened according to the number of stations, the line length, the first and last station, and the line non-linear coefficient to obtain multiple valid routes;

[0136] Construct a valid line set based on valid lines.

[0137] Specifically, the first and last stations in the study area are combined in pairs to construct a bus first and last station combination table. Based on the K shortest path algorithm, a set of alternative routes between any two first and last stations is obtained. For each generated alternative route, the number of stations, route length, and non-linear coefficient are calculated, and the alternative routes that meet the constraints (2) to (10) in the upper-level problem are selected as valid routes. The valid routes generated by all combinations of first and last stations are merged to construct a valid route set.

[0138] As an optional implementation method, an initial population is randomly generated according to the effective route set, and a genetic algorithm based on a parallel computing strategy is used to optimize and solve the double-layer Nested Logit model according to the initial population to obtain the optimal bus route structure and the optimal departure frequency of each bus route, which specifically includes:

[0139] An initial population including a plurality of line network individuals is constructed, and the number of lines of each line network individual is determined, and then a plurality of valid lines are randomly selected from a valid line set according to the number of lines as the initial lines of the corresponding line network individual;

[0140] Determine the optimal vehicle allocation schedule for each line network, perform multi-modal passenger flow allocation for each line network according to the lower-level model, and determine the corresponding bus operation profit for each line network according to the passenger flow allocation results and the upper-level model;

[0141] Perform crossover and mutation on the current population to obtain a child population, merge the child population with the current population, and determine the bus operation profit corresponding to each line network individual in the merged population;

[0142] The probability of each line network individual being selected is determined according to the bus operation profit, and then multiple line network individuals are selected from the merged population as the current population of the next generation, and the step of performing crossover and mutation on the current population to obtain the offspring population is returned until the preset number of population iterations is reached to obtain the target population;

[0143] Determine the optimal line network individual according to the corresponding bus operation profit of each line network individual of the target population;

[0144] The optimal bus route structure is determined based on the bus routes included in the optimal line network individual, and the optimal departure frequency of each bus route is determined based on the optimal vehicle allocation and scheduling of the optimal line network individual.

[0145] As an optional implementation, crossover and mutation are performed on the current population to obtain a progeny population, which specifically includes:

[0146] Determine the individuals to be crossed and the individuals to be mutated according to the current population;

[0147] The crossover individuals are combined in pairs to obtain multiple crossover individual pairs, and then the non-repeating lines of the crossover individual pairs are exchanged to obtain crossover offspring individuals;

[0148] Randomly select several valid circuits from the valid circuit set, and randomly replace several circuits of the individuals to be mutated to obtain mutant offspring individuals;

[0149] The offspring population is composed of crossover offspring individuals and mutation offspring individuals.

[0150] Specifically, the genetic algorithm framework considering parallel computing strategies includes the main contents of initial population generation, individual fitness evaluation, and offspring population generation. First, in the genetic algorithm, the present invention regards a line as a chromosome, a bus network as an individual, and multiple bus networks as a population. The number of populations can be set according to the scale of the network and computing resources. The specific algorithm process is as follows:

[0151] 1) Initial population generation. For each individual line network, a random integer is generated between the maximum and minimum line numbers. As the number of lines for the individual, and then randomly select from the pool of candidate lines The line is used as the initial line of the individual. Thus, the population is initialized.

[0152] 2) Individual fitness evaluation. For each individual line network, fitness evaluation is required, that is, the objective function is calculated. Before calculating the objective function, it is necessary to schedule the line network individuals, calculate the optimal schedule under the line network structure, and then perform multi-modal passenger flow allocation. Finally, based on the allocation results, the operating cost and income of the individual line network are calculated to obtain the bus operation profit.

[0153] When the line structure is determined, the line departure interval determines the number of vehicles assigned to the line. The total number of vehicles assigned to the line network is limited, so the goal of vehicle scheduling is to allocate the limited number of vehicles to each line network to maximize the efficiency. According to formula (16), the turnover time t of each line in the line network is calculated. r , and then set the minimum number of vehicles required for the route according to the maximum departure interval in the set H of departure intervals allowed to be set; perform multi-modal passenger flow allocation for each departure interval in the departure interval set H for the line network individuals, calculate the number of vehicles that need to be increased under different departure intervals compared with the maximum departure interval, and the change value of the objective function; calculate the change value of the objective function corresponding to the increase in the number of single vehicles under different departure intervals through the ratio of the two, that is, the vehicle addition benefit; select the departure interval with the highest vehicle addition benefit for each route, and allocate half of the remaining number of vehicles from high to low according to the vehicle addition benefit; repeat the above steps until all vehicles are allocated or all routes reach the minimum departure interval.

[0154] The specific process of multi-modal passenger flow allocation is as follows:

[0155] According to the network structure and station relationships, a table of accessible routes between station pairs in the study area is constructed, including direct routes and transfer routes.

[0156] The bus travel time for direct routes and transfer routes is calculated according to equations (25) to (27); if there are multiple accessible routes between a station pair, the bus travel time weighted by route frequency is calculated according to equation (28).

[0157] The travel time and distance of different travel modes between station pairs are obtained from the time distance matrix in the multimodal network. The travel costs of car, bus and walking travel modes are calculated according to equations (21) to (24). Then, the bus travel demand is calculated according to equations (29) and (30) to construct the bus travel demand table.

[0158] Construct a line section passenger flow table to record the passenger flow between adjacent stations on all lines and initialize the passenger flow to 0.

[0159] The bus travel demand table and the section passenger flow table are combined through the station relationship and sorted according to the station sequence of the line. For the same section passenger flow, the station with the earlier station sequence is given priority.

[0160] The cumulative bus travel demand is calculated for all sections of each line, and the remaining capacity of all sections is obtained by subtracting the cumulative bus travel demand from the line capacity.

[0161] Compare the remaining capacity of all sections of each line with the bus travel demand. If the remaining capacity of the section is zero, all bus travel demands starting from the station cannot be met, that is, the bus passenger flow is zero; if the remaining capacity of the section is greater than the bus travel demand, all bus travel demands starting from the station can be met, and the bus passenger flow is equal to the bus travel demand; if the remaining capacity of the section is between zero and the bus travel demand, the bus demand starting from the station is partially met, that is, the bus passenger flow is equal to the remaining capacity of the section. The proportion of satisfied demand is equal to the proportion of bus travel demands starting from the station but with different alighting stations.

[0162] The difference between the total travel demand between stations and the bus passenger flow is calculated to obtain the sum of the passenger flow of cars and pedestrians, and the passenger flow of cars and pedestrians is calculated according to equations (39) to (42).

[0163] The bus operating profit of the individual line network is calculated according to formula (1).

[0164] 3) Generation of offspring population. The offspring population is mainly generated by crossover operator and mutation operator. S1: Randomly generate an even number between 1 and the population size as the number of individuals N for the crossover operation C . S2: Randomly select N from all populations C Individuals perform crossover operations to generate N C crossover offspring individuals. S3: Perform mutation operator operation on the remaining individuals to generate mutant offspring individuals. S4: Combine crossover offspring individuals and mutant offspring individuals into offspring population.

[0165] 4) Crossover operator. S1: randomly pair the wire mesh individuals to be cross-operated. S2: remove the same wires in the two wire mesh individuals, and take the smaller value of the remaining wires as the swappable wire. S3: If Then a random number between 1 and Integer between And execute the subsequent steps; otherwise, end the crossover operation. S4: Randomly extract from the two wire mesh individuals Non-repetitive lines are exchanged with each other to form new line network entities.

[0166] 5) Mutation operator. S1: For the network individual to be mutated, the number of lines is N. R . S2: Randomly generate a number between 1 and N R Integer between S3: Randomly select from the candidate line pool Lines, replace the randomly selected ones in the line network Lines form new network entities.

[0167] 6) Offspring selection. After the offspring population is generated, it will be merged with the parent population to select the next generation population. S1: The objective function value X of each individual after the merger i Perform the maximum and minimum scaling normalization process to obtain S2: According to Calculate the probability of each individual being selected. The higher the objective function value, the greater the probability of being selected. S3: According to the selection probability P i Randomly select N from the combined population P The line network individuals serve as the next generation population.

[0168] 7) Parallel computing strategy. Population evaluation includes vehicle scheduling and multi-mode passenger flow distribution, which is the most computationally complex part of the entire solution process. Therefore, the present invention adds a parallel computing strategy to the solution algorithm, decouples the input and output of each line network individual, and the evaluation of each line network individual is performed by an independent thread. The number of cores used by the algorithm can be set according to the set population size and computing resources.

[0169] After the target population is obtained after a preset number of iterations, the optimal line network individual is determined according to the corresponding bus operating profit of each line network individual of the target population, the optimal bus route structure is determined according to the bus routes included in the optimal line network individual, and the optimal departure frequency of each bus route is determined according to the optimal vehicle allocation and scheduling of the optimal line network individual.

[0170] It can be understood that the embodiment of the present invention constructs a multimodal network that includes three travel modes: driving, walking and public transportation. A double-layer Nested Logit model is used to solve the passenger flow distribution results and optimize the bus line structure and bus departure frequency. The optimal bus line structure and the optimal departure frequency of each bus line are obtained by optimizing the genetic algorithm with parallel computing strategy, thereby improving the efficiency and accuracy of bus network design.

[0171] Compared with the prior art, the embodiments of the present invention also have the following advantages:

[0172] (1) Comprehensive consideration of factors and reasonable modeling process. The more comprehensive the factors considered in the bus network design problem, the closer it is to the actual situation, and the more the solution can conform to the actual situation, and the more reference value it has. However, at the same time, more factors may bring higher model complexity. Considering multiple factors at the same time requires the introduction of more complex modeling ideas and derivation processes to avoid conflicts and ensure the rationality of logic. In terms of the upper-level problem, the present invention considers many factors that conform to the actual situation in the objective function, decision variables, and constraints. For example, the objective function considers the specific bus operating costs, including labor costs, vehicle costs, and power costs; the decision variables consider both the network structure and the frequency of departure; and the constraints consider the line shape constraints, capacity constraints, frequency constraints, vehicle number constraints, and line number constraints. In terms of the lower-level problem, the present invention introduces a multi-mode passenger flow distribution problem, transforms the bus travel demand from the traditional fixed demand to the elastic demand, and allows passengers to choose among different travel modes according to the travel cost. At the same time, in order to solve the independence problem of irrelevant options in the multinomial Logit model, the present invention constructs a two-layer Nested Logit model to select travel modes and bus routes respectively. In addition, the present invention introduces the co-linear problem and boarding order constraints in multi-modal passenger flow distribution, so that the passenger flow distribution results are more in line with the actual situation, further improving the accuracy of passenger flow prediction, thereby improving the rationality of bus network design and frequency setting results.

[0173] (2) The algorithm framework is complete and the solution process is efficient. The present invention not only comprehensively and reasonably models the multi-modal bus network design and frequency setting problems, but also proposes a corresponding algorithm framework to efficiently solve the model. First, in the network construction, this study uses the path planning API of the network map instead of the offline topological road network to build the multi-modal network. This construction method takes into account the impact of road traffic rules and congestion, ensures the accuracy of the planned route and travel time, and has obvious advantages in the design of large-scale bus networks. Secondly, the present invention proposes an efficient solution algorithm for vehicle allocation and scheduling. By initializing the maximum departure interval and calculating the vehicle addition benefits of different routes, the limited vehicle resources are efficiently allocated to the most efficient routes. Then, the present invention proposes a solution algorithm for multi-modal passenger flow distribution, which realizes the solution of travel mode division and bus route selection model, capacity constraints, collinear problems, boarding order constraints and other problems considered in the modeling process. Finally, the present invention proposes a genetic algorithm framework that considers parallel computing strategies. Through a specific encoding method, the bus network iteration process is embedded in the genetic algorithm. At the same time, in the population evaluation part, the input and output of each individual line network are decoupled, and each individual line network evaluation is executed by an independent thread. The most time-consuming part of the solution process is calculated in parallel, which greatly improves the calculation efficiency.

[0174] like Figure 4 FIG. 1 is a schematic diagram of a multi-mode bus network design optimization system according to an embodiment of the present invention. Figure 4 The embodiment of the present invention provides a multi-mode bus network design optimization system, including:

[0175] Model building module, used to build a double-layer Nested Logit model, which includes an upper-layer model for optimizing bus route structure and bus departure frequency and a lower-layer model for solving passenger flow distribution results;

[0176] The effective route set determination module is used to build a multi-modal network that includes three travel modes: driving, walking, and public transportation. It determines the candidate routes based on the K shortest path algorithm, and selects the effective routes from the candidate routes according to the constraints of the upper model to obtain the effective route set.

[0177] The optimization solution module is used to randomly generate an initial population based on the effective route set, and optimize the double-layer Nested Logit model based on the initial population using a genetic algorithm based on a parallel computing strategy to obtain the optimal bus route structure and the optimal departure frequency of each bus route;

[0178] Among them, the upper model includes the objective function of maximizing the bus operation profit, the line station number constraint, the line length constraint, the line first and last station constraint, the line non-linear coefficient constraint, the capacity constraint, the departure frequency constraint, the total number of bus vehicles in the bus network constraint and the total number of bus lines in the bus network constraint. The lower model includes the first functional relationship for solving the bus travel probability and the bus travel demand and the second functional relationship for solving the passenger flow of different bus lines.

[0179] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0180] The embodiment of the present invention also provides an electronic device, which includes: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the above-mentioned multi-mode bus network design optimization method. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0181] like Figure 5 FIG. 1 is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention, referring to FIG. Figure 5 , an embodiment of the present invention provides an electronic device, including:

[0182] The processor 501 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention;

[0183] The memory 502 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 502 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 502, and the processor 501 calls and executes the multi-mode bus network design optimization method of the embodiment of the present invention;

[0184] Input / output interface 503, used to implement information input and output;

[0185] Communication interface 504, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0186] A bus 505 that transmits information between the various components of the device (e.g., the processor 501, the memory 502, the input / output interface 503, and the communication interface 504);

[0187] The processor 501 , the memory 502 , the input / output interface 503 and the communication interface 504 are connected to each other in communication within the device via the bus 505 .

[0188] like Figure 6 FIG. 1 is a schematic diagram of a storage medium according to an embodiment of the present invention. Figure 6 The embodiment of the present invention further provides a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more programs 601, and the one or more programs 601 can be executed by one or more processors to implement the above-mentioned multi-mode bus network design optimization method.

[0189] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0190] The embodiment of the present invention also discloses a computer program product or a computer program, wherein the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes Figure 1 The method shown.

[0191] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the above-mentioned boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0192] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified to the contrary, one or more of the above-mentioned functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0193] If the above 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 invention, 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, including several 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 above 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.

[0194] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0195] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the above-mentioned program is printed, since the above-mentioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or processing in other suitable ways as necessary, and then stored in a computer memory.

[0196] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0197] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0198] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0199] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A multi-mode bus network design optimization method, characterized in that: The following steps are involved: Constructing a two-layer Nested Logit model, the two-layer Nested Logit model includes an upper model for optimizing bus route structure and bus departure frequency and a lower model for solving passenger flow distribution results; Construct a multi-modal network including three travel modes: driving, walking and public transportation, determine alternative routes based on the K shortest path algorithm, and select valid routes from the alternative routes according to the constraints of the upper model to obtain a valid route set; An initial population is randomly generated according to the effective route set, and the double-layer Nested Logit model is optimized and solved using a genetic algorithm based on a parallel computing strategy according to the initial population to obtain an optimal bus route structure and an optimal departure frequency of each bus route; Among them, the upper model includes the objective function of maximizing the bus operation profit, the line station number constraint, the line length constraint, the line first and last station constraint, the line non-linear coefficient constraint, the capacity constraint, the departure frequency constraint, the total number of bus vehicles in the bus network constraint and the total number of bus lines in the bus network constraint; the lower model includes a first functional relationship for solving the bus travel probability and the bus travel demand and a second functional relationship for solving the passenger flow of different bus lines.

2. A multi-mode bus network design optimization method according to claim 1, characterized in that: The objective function is: The line station number constraint is: The line length constraint is: The line's first and last station constraints are: The line non-linear coefficient constraint is: The capacity constraint is: The frequency constraint is: The total number of buses in the bus network is constrained as follows: The total number of bus lines in the bus network is constrained as follows: Among them, χ represents the bus operating profit, r represents the route in the bus network, R represents the set of all routes in the bus network, Q r represents the passenger flow of route r, ω represents the bus fare, n r represents the number of buses on route r, λ represents the depreciation cost of a single bus, μ represents the labor cost of a single bus, and f r represents the departure frequency of line r, represents the length of line r in the upstream direction, represents the length of line r in the downward direction, τ represents the power cost of the bus per unit mileage, Indicates the number of stations in the upstream direction of line r, Indicates the number of stations in the downstream direction of line r, s max Indicates the maximum number of stations allowed on a single line, s min Indicates the minimum number of stations allowed for a single line, l max Indicates the maximum allowed length of a single line. represents the originating station of line r, represents the terminal station of line r, TS represents the set of first and last stations, ρ r represents the nonlinear coefficient of line r, ρ max Indicates the maximum allowable non-linear coefficient of the line, represents the nonlinear coefficient of the upstream direction of line r, Indicates the nonlinear coefficient of line r in the downstream direction, B ij represents the bus route section from station i to station j, represents the set of uplink intervals of bus route r, represents the set of downlink sections of bus line r, represents the travel distance of route r from station i to the next station j, It represents the travel distance between the first and last stations in the upward direction of line r. Indicates the travel distance between the first and last stations in the down direction of line r, B r represents the set of interval segments of bus route r, represents the cross-sectional passenger flow between adjacent stations i and j on line r, C represents the capacity of a single bus, B od represents the bus route section from station o to station d, represents the passenger flow of route r from station o to station d, h r represents the departure interval of line r, H represents the set of departure intervals that can be set, t r represents the turnaround time of route r, represents the one-way time in the upstream direction of line r, represents the one-way time in the downstream direction of line r, t g Indicates the rest time of the driver between the up and down shifts of the line. represents the bus time between station i and station j, n max Indicates the maximum number of vehicles on the route, N R represents the number of routes in the bus network, Indicates the minimum number of bus lines in the network. Indicates the maximum number of bus lines in the bus network.

3. A multi-mode bus network design optimization method according to claim 2, characterized in that: The first functional relationship is: The second functional relationship is: in, represents the probability of choosing public transportation from station o to station d, represents the bus travel cost from station o to station d, represents the travel cost of a car from station o to station d, represents the walking travel cost from station o to station d, represents the bus travel demand from station o to station d, D od represents the total travel demand from station o to station d, represents the travel time of a car from station o to station d, vot represents the time-money coefficient, represents the monetary cost of traveling by car from station o to station d, represents the bus travel time from station o to station d, represents the monetary cost of public transportation from station o to station d, represents the walking travel time from station o to station d, m0 represents the starting price of a taxi, represents the travel distance from station o to station d, Indicates the mileage included in the taxi starting price. represents the taxi mileage price, R od represents the set of all feasible routes from site o to site d, represents the bus travel time of route r from station o to station d, represents the waiting time of line r, θ represents the penalty coefficient of waiting time, represents the time on the train of route r from station o to station d, represents the bus travel time from station o to station d via line r1 and then transfer to line r2, represents the waiting time of line r1, represents the waiting time for line r2, represents the time on the train of route r1 from station o to station k, represents the time on board of route r2 from station k to station d, represents the transfer time at station k, ψ represents the transfer penalty time, represents the passenger flow of route r boarding at station i, represents the boarding demand of route r at station i, represents the capacity of line r from site i to site j, represents the passenger flow of route r from station i to station k, represents the travel demand of route r from station i to station k.

4. A multi-mode bus network design optimization method according to claim 1, characterized in that: The construction of a multi-modal network including three modes of travel: driving, walking and public transportation, specifically includes: Obtain available bus stops and bus terminals in the target area and generate a bus stop table; According to the bus stop table, bus stops in the target area are combined in pairs to obtain a plurality of start and end stop pairs; Perform driving route planning and walking route planning for the starting and ending station pairs to obtain corresponding driving distance, driving time, and walking time; Determine the bus on-board time of the start-end station pair according to the driving distance and the average bus operating speed of the target area; Taking the bus stops in the target area as nodes, the paths between the bus stops as edges, and taking the driving time, the walking time, and the bus time as weights of the corresponding edges, a car network, a walking network, and a bus network are obtained; The multi-modal network is constructed according to the car network, the pedestrian network and the bus network.

5. A multi-mode bus network design optimization method according to claim 4, characterized in that: The method of determining candidate routes based on the K shortest path algorithm and selecting valid routes from the candidate routes according to the constraint conditions of the upper model to obtain a valid route set specifically includes: Combining the first and last bus stops in the target area in pairs to obtain a plurality of first and last bus stop pairs; Determine the alternative routes of each of the first and last station pairs based on the K shortest path algorithm, and determine the number of stations, line length and non-linear coefficient of each of the alternative routes; The candidate routes are screened according to the site number constraint, the route length constraint, the route first and last station constraint, and the route non-linear coefficient constraint to obtain a plurality of valid routes; The valid line set is constructed according to the valid lines.

6. A multi-mode bus network design optimization method according to claim 1, characterized in that: The method of randomly generating an initial population according to the effective route set and optimizing and solving the double-layer Nested Logit model by using a genetic algorithm based on a parallel computing strategy according to the initial population to obtain an optimal bus route structure and an optimal departure frequency of each bus route specifically includes: Constructing the initial population including a plurality of line network individuals, and determining the number of lines of each line network individual, and then randomly extracting a plurality of the valid lines from the valid line set according to the number of lines as the initial lines of the corresponding line network individuals; Determine the optimal vehicle allocation schedule for each individual line network, perform multi-modal passenger flow allocation for each individual line network according to the lower-level model, and determine the public transportation operation profit corresponding to each individual line network according to the passenger flow allocation result and the upper-level model; Perform crossover and mutation on the current population to obtain a child population, merge the child population with the current population, and determine the public transportation operation profit corresponding to each line network individual in the merged population; The probability of each line network individual being selected is determined according to the bus operation profit, and then multiple line network individuals are selected from the merged population as the current population of the next generation, and the step of performing crossover and mutation on the current population to obtain the offspring population is returned until the preset number of population iterations is reached to obtain the target population; Determine the optimal line network individual according to the corresponding public transportation operation profit of each line network individual of the target population; The optimal bus route structure is determined according to the bus routes included in the optimal line network individual, and the optimal departure frequency of each bus route is determined according to the optimal vehicle allocation and scheduling of the optimal line network individual.

7. A multi-mode bus network design optimization method according to claim 6, characterized in that: The crossover and mutation of the current population to obtain the offspring population specifically includes: Determine the individuals to be crossed and the individuals to be mutated according to the current population; Combining the individuals to be crossed in pairs to obtain a plurality of crossover individual pairs, and then exchanging non-repetitive lines of the crossover individual pairs to obtain crossover offspring individuals; Randomly select a number of the valid circuits from the valid circuit set, and randomly replace a number of circuits of the individual to be mutated, to obtain mutated offspring individuals; The offspring population is composed according to the crossover offspring individuals and the variant offspring individuals.

8. A multi-mode bus network design optimization system, characterized in that: include: A model building module, used to build a double-layer Nested Logit model, wherein the double-layer Nested Logit model includes an upper-layer model for optimizing bus route structure and bus departure frequency and a lower-layer model for solving passenger flow distribution results; An effective route set determination module is used to construct a multi-modal network including three travel modes: driving, walking and public transportation, determine candidate routes based on the K shortest path algorithm, and select effective routes from the candidate routes according to the constraints of the upper model to obtain an effective route set; An optimization solution module, used for randomly generating an initial population according to the effective route set, optimizing and solving the double-layer Nested Logit model according to the initial population using a genetic algorithm based on a parallel computing strategy, and obtaining an optimal bus route structure and an optimal departure frequency of each bus route; Among them, the upper model includes the objective function of maximizing the bus operation profit, the line station number constraint, the line length constraint, the line first and last station constraint, the line non-linear coefficient constraint, the capacity constraint, the departure frequency constraint, the total number of bus vehicles in the bus network constraint and the total number of bus lines in the bus network constraint; the lower model includes a first functional relationship for solving the bus travel probability and the bus travel demand and a second functional relationship for solving the passenger flow of different bus lines.

9. An electronic device, characterized in that: The electronic device includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory. When the program is executed by the processor, the steps of the multi-modal bus network design optimization method as described in any one of claims 1 to 7 are realized.

10. A storage medium, the storage medium being a computer-readable storage medium, used for computer-readable storage, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the multi-modal bus network design optimization method as described in any one of claims 1 to 7.

Images