Bus timetable optimization method and system for time-varying traffic environment

Abstract

The invention relates to the technical field of bus timetable optimization, and relates to a bus timetable optimization method and system for a time-varying traffic environment, and the method comprises the steps: obtaining first information which comprises a bus line set, a station set and a bus travel set; constructing a public transportation network according to the first information; constructing a corresponding topological structure according to the public transportation network to obtain a directed graph which comprises passenger behavior characteristics and the running state of the public transportation vehicle; determining an initial bus timetable according to the directed graph; establishing an optimization model according to the directed graph, and optimizing the initial bus timetable by using the optimization model to obtain an optimized bus timetable, according to the method, the optimization model is established to optimize the bus timetable which does not consider the travel time, the passenger demand and the passenger path selection along with the time in the prior art, and the influence of the actual passenger flow on timetable optimization is further accurately captured.

Description

Technical Field

[0001] The present invention relates to the technical field of bus schedule optimization, and in particular to a bus schedule optimization method and system for a time-varying traffic environment. Background Art

[0002] Most existing studies assume that the travel time between stations is constant, which cannot reflect the dynamic changes in traffic conditions in actual operations, resulting in inaccurate estimates of transfer and boarding waiting times. Secondly, existing methods usually assume that passenger demand is constant, ignoring the dynamic changes in the number and distribution of passengers in different time periods, and cannot accurately capture the impact of actual passenger flow on timetable optimization. In addition, existing optimization models rely on pre-set route selection, ignoring the behavior of passengers who may adjust their travel paths under different timetables, and fail to fully reflect the impact of passenger behavior on timetables. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for optimizing a bus schedule in a time-varying traffic environment to improve the above-mentioned problems.

[0004] In order to achieve the above objectives, the present application provides the following technical solutions: On the one hand, an embodiment of the present application provides a method for optimizing a bus schedule in a time-varying traffic environment, the method comprising: Acquire first information, the first information including a bus route set, a bus station set, and a bus itinerary set; constructing a public transportation network according to the first information; Constructing a corresponding topological structure according to the public transportation network to obtain a directed graph, wherein the directed graph includes passenger behavior characteristics and operation status of public transportation vehicles; Determine an initial bus schedule according to the directed graph; An optimization model is established according to the directed graph, and the initial bus schedule is optimized using the optimization model to obtain an optimized bus schedule.

[0005] In a second aspect, an embodiment of the present application provides a bus schedule optimization system for a time-varying traffic environment, the system comprising: An acquisition module, configured to acquire first information, wherein the first information includes a bus route set, a bus station set, and a bus itinerary set; A first processing module, used for constructing a public transportation network according to the first information; A second processing module is used to construct a corresponding topological structure according to the public transportation network to obtain a directed graph, wherein the directed graph includes passenger behavior characteristics and the operation status of public transportation vehicles; A third processing module, used for determining an initial bus schedule according to the directed graph; The fourth processing module is used to establish an optimization model according to the directed graph, and optimize the initial bus schedule using the optimization model to obtain an optimized bus schedule.

[0006] In a third aspect, an embodiment of the present application provides a bus schedule optimization device for a time-varying traffic environment, the device comprising a memory and a processor. The memory is used to store a computer program; the processor is used to implement the steps of the above-mentioned bus schedule optimization method for a time-varying traffic environment when executing the computer program.

[0007] In a fourth aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned method for optimizing the bus schedule for a time-varying traffic environment are implemented.

[0008] The beneficial effects of the present invention are: The present invention establishes a bus network and constructs a corresponding topological structure based on the bus network to obtain a directed graph, establishes an optimization model based on the directed graph and optimizes the initial bus schedule to obtain an optimized bus schedule. The optimization model in the present invention simultaneously considers the time-dependent travel time, the time-dependent passenger demand and the schedule-dependent passenger path selection, so that the optimized bus schedule is more in line with the actual passenger path selection and behavior pattern, and improves the practicality of the optimized bus schedule.

[0009] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 The figure is a flow chart of a method for optimizing a bus schedule in a time-varying traffic environment according to an embodiment of the present invention.

[0012] Figure 2 It is a schematic diagram of the structure of a bus schedule optimization system for a time-varying traffic environment described in an embodiment of the present invention.

[0013] Figure 3 It is a schematic diagram of the structure of a bus schedule optimization device for a time-varying traffic environment described in an embodiment of the present invention.

[0014] Figure 4 A schematic diagram of a directed graph.

[0015] Labels in the figure: 800, bus schedule optimization device for time-varying traffic environment; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component; 901, acquisition module; 902, first processing module; 903, second processing module; 904, third processing module; 905, fourth processing module. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0017] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0018] Embodiment 1: This embodiment provides a bus schedule optimization method for a time-varying traffic environment. It can be understood that a scenario can be laid out in this embodiment, for example: a scenario of optimizing a bus schedule that fails to simultaneously consider travel time, passenger demand, and passenger route selection that vary with time.

[0019] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3, step S4 and step S5.

[0020] Step S1, obtaining first information, wherein the first information includes a bus route set, a bus station set, and a bus itinerary set; Step S2: constructing a public transportation network according to the first information; In this step, the bus network constructed is , where L represents the bus routes, S represents the bus stations, and V represents the bus itineraries. A series of orderly stations Composition, divide the line into segments, each segment is recorded as ,in, and They correspond to the tail and head stations of the section respectively. A trip is a specific operation instance of a bus traveling on the route according to a scheduled schedule.

[0021] Step S3: construct a corresponding topological structure according to the public transportation network to obtain a directed graph, wherein the directed graph includes passenger behavior characteristics and the operation status of public transportation vehicles; In this step, in order to more intuitively describe the operation of vehicles and the behavior of passengers and to facilitate calculations, an event-activity network, i.e., a directed graph, is constructed to express the corresponding topological structure of the bus network.

[0022] The step S3 also includes step S31, step S32 and step S33, which specifically include: Step S31, obtaining first node information and second node information, wherein the first node information includes arrival events and departure events of public transport vehicles at stations, and the second node information includes the arrival of passenger groups at the departure station or the terminal station; Step S32: Acquire first side information and second side information, wherein the first side information includes the running status of the bus between stations, and the second side information includes the behavioral characteristics of passengers; Step S33: construct a topological structure according to the first node information, the second node information, the first edge information and the second edge information to obtain a directed graph.

[0023] In this embodiment, the directed graph constructed by the first node information and the first edge information describes the operation status and activities of the public transport vehicle, and the directed graph constructed by the second node information and the second edge information describes the behavioral characteristics of the passengers. The two types of directed graphs are combined to obtain the topological structure corresponding to the overall public transport network, as shown in FIG. Figure 4 As shown, Figure 4 middle, Indicates that it is at the station The departure event, Show itinerary At the station The arrival event, Show itinerary From the Station Departure to the station The driving process is recorded as an activity, and the corresponding edge is recorded as an activity edge. It can be understood that the solid line edge is the first edge information used to represent the driving activity of the vehicle between stations; Indicates passenger group At the station It can be understood that the dotted edge is the second edge information used to represent various activities of passengers.

[0024] It should be noted that passengers with the same optional itinerary set are divided into a group according to their optional itineraries, and the transportation demand of each passenger group can be calculated, wherein the specific calculation process is: ; In the above formula, W represents OD pair, Indicates the passenger group under the same OD pair Corresponding traffic needs, Poisson distribution is usually used to represent continuous distribution functions. Indicates the arrival time of the passenger on the previous trip, Indicates the arrival time of passengers on the current trip. Represents all OD pairs included in the trip.

[0025] Step S4, determining an initial bus schedule according to the directed graph; In this step, the bus schedule is a detailed timetable prepared for each trip, which specifies the departure and arrival times of the bus vehicles at each station during the specified period.

[0026] The step S4 also includes step S41, step S42, step S43 and step S44, which specifically include: Step S41, obtaining second information, wherein the second information includes the departure time of the public bus at the departure station; Step S42: Calculate the arrival time of the vehicle at the next station according to the second information and a preset link travel time function; In this step, the specific calculation process of the vehicle's arrival time at the next station is: ; In the above formula, Indicates the arrival time at the next station; Indicates the departure time of the bus at the origin station. represents the link travel time function, which is used to calculate the running time of a bus from the starting station to the next station. Show itinerary All stations included in.

[0027] Step S43, calculating the departure time of the vehicle at the next station according to the arrival time of the vehicle at the next station and the stop time of the vehicle at the station; Step S44: Calculate the arrival time and departure time of each station in turn to determine the initial bus schedule.

[0028] In this embodiment, the arrival time and departure time of the bus at each subsequent station can be calculated by the departure time corresponding to the bus at the originating station and the preset link travel time function, thereby determining the initial bus schedule.

[0029] Step S5: establishing an optimization model according to the directed graph, and optimizing the initial bus schedule using the optimization model to obtain an optimized bus schedule.

[0030] The step S5 also includes step S51, step S52, step S53, step S54 and step S55, which specifically include: Step S51: obtaining a first optimization function, where the first optimization function is used to minimize the total travel cost of all passengers; In this step, the first optimization function is specifically: ; In the above formula, represents the total travel cost function, represents the link travel cost, which depends on the departure time and link traffic It can be understood that a path is composed of multiple links on the path, and the path flow of a path is the sum of the link flows included in the path.

[0031] Step S52: establishing an upper-level optimization problem according to the first optimization function; In this step, the upper optimization problem is used to optimize the departure time of the bus trip , in order to minimize the total travel cost of all passengers, the constraints are as follows: ; In the above formula, It represents the feasible domain of departure time. The specific requirements are as follows: the departure time of vehicles must meet the sequentiality, the departure time of the next vehicle is later than the previous one, and it does not exceed the upper limit of the operating time to ensure that the departure time of the trip meets the actual operating requirements; Indicates that at a given departure time The passenger flow set that meets the CUE condition is a balance state when all passengers cannot reduce their personal travel costs by unilaterally changing their travel paths, taking into account the vehicle's passenger capacity limit. Specifically, the maximum cost of all paths in use that have not reached the capacity limit is less than or equal to the minimum cost of other optional paths.

[0032] Step S53: Obtain a second optimization function, where the second optimization function is used to achieve capacity-constrained user balance; In this step, the second optimization function is specifically: ; In the above formula, represents the objective function of passenger allocation, the accumulated travel cost; represents a passenger activity or bus activity in a directed graph, Represents the full set of activities on the entire directed graph; represents the travel cost of an activity; Indicates the link traffic corresponding to the active edge.

[0033] Step S54, establishing a lower-level optimization problem according to the second optimization function; In this step, the lower optimization problem is used to solve the balanced allocation of passengers for a given timetable, that is, to determine the passenger flow for each trip, with the following constraints: ; In the above formula, Indicates link traffic, Represents the feasible domain of the passenger flow pattern.

[0034] Step S55: establishing an optimization model based on the upper-level optimization problem and the lower-level optimization problem.

[0035] In this embodiment, a two-layer optimization framework is adopted. The upper layer is for the public transportation management department to decide the vehicle departure time, and the lower layer simulates the passengers to choose the travel path and departure time according to the given timetable to minimize the personal travel cost. This framework fully considers the response behavior of passengers to the timetable adjustment, making the optimization scheme more in line with the actual path selection and behavior pattern of passengers, and improving the practicality of the optimization model.

[0036] The step S5 also includes step S56, step S57, step S58 and step S59, which specifically include: Step S56, obtaining the initialized bus schedule and lower-layer balanced flow; In this step, the initial bus schedule is initialized to obtain the lower-level equilibrium flow, and the number of initialization iterations is 0 at this time.

[0037] Step S57: During each iteration, the back propagation algorithm is used to calculate the gradient of the first optimization function in the current iteration step to the bus schedule; In this step, the specific process of using the back-propagation algorithm to calculate the gradient of the first optimization function in the current iteration step to the bus schedule is as follows: preset the augmented Lagrange multiplier method (ALM) iteration count and the dual gradient; when the mirror descent algorithm is used in each iteration of the ALM algorithm, the exponential vector gradient and the path flow ratio gradient are updated synchronously; after the ALM algorithm completes the cycle, the dual variable gradient and the equilibrium flow gradient are calculated. The difficulties in gradient calculation can be solved by the back-propagation algorithm. The back-propagation algorithm can calculate the gradient information at the same time in the process of solving the lower-level passenger allocation problem without the need for additional calculations.

[0038] Step S58, using projected gradient descent and Armijo line search to update the initialized bus schedule, calculate vehicle arrival and departure times and passenger group demands, and use augmented Lagrange multiplier method to calculate the passenger equilibrium flow at the new departure time; In this step, projected gradient descent is used to find the descending direction of the objective function value and then project the point after gradient descent to (the feasible domain of departure time), so that the projected solution is the feasible solution closest to the gradient descent point.

[0039] The step S58 also includes step S581, step S582, step S583, step S584 and step S585, which specifically include: Step S581, obtaining the dual variable of the augmented Lagrangian; In this step, we set the dual variables (multiplier vectors) of the augmented Lagrangian . The number of initial iterations is 0.

[0040] Step S582: At each iteration, the dual variables of the augmented Lagrangian and the bus schedule are processed using the mirror descent algorithm to obtain the equilibrium flow corresponding to the current number of iterations; In this step, the specific processing process of the mirror descent algorithm is as follows: 1. Input the dual variables of the augmented Lagrangian and the bus schedule to set the initial path flow ratio h 0 >0, set the iteration count , the initial relative gap RG = 1000, the step size γ is usually set to 1; 2. When RG < The following steps are iterated in a loop: ① Calculate the shortest path of the passenger group based on the generalized link cost , if the shortest path is not in the path set Pm of the current passenger group, then Add to Pm and set ;② The original cost plus the capacity limit penalty term updates the generalized link cost, then updates the index vector, and finally updates the path traffic ratio according to the preset formula, and then deletes all paths with a traffic ratio less than Path; ③ Calculate the relative gap, if RG< The algorithm terminates. After the algorithm terminates, the corresponding balanced flow can be calculated based on the output path flow ratio, which is specifically, ; In the above formula, represents the link-path association matrix, represents the OD-path association matrix, h is the path flow ratio output by the algorithm, and q is the traffic demand. It should be noted that the link-path association matrix is ​​a A 0-1 matrix, where represents the number of links in the network, represents the number of all feasible paths; the OD-path association matrix is ​​a A 0-1 matrix, where represents the number of OD pairs in the network, Represents the number of all feasible paths.

[0041] It should be noted that the path flow ratio is the ratio of the actual flow on path p to the traffic demand. The generalized link cost is calculated as the sum of the original cost of the link and the capacity limit penalty. When the link flow is far below the capacity, the capacity limit penalty approaches 0; when the link flow is close to or exceeds the capacity, the capacity limit penalty increases significantly, guiding part of the flow to other feasible links.

[0042] Step S583, updating the dual variable pair of the augmented Lagrangian according to the equalization flow corresponding to the current iteration number to obtain the updated dual variable of the augmented Lagrangian; In this step, the update mechanism is that when the flow exceeds the capacity, the multiplier increases; when the flow is lower than the capacity, the multiplier decreases; and a non-negative constraint is set to ensure economic significance.

[0043] Step S584, obtaining a preset second convergence condition and determining whether to stop iteration according to the second convergence condition to obtain a determination result; In this step, the second convergence condition is specifically: ; In the above formula, represents the total number of activities on the entire directed graph, represents the link traffic corresponding to the active edge, represents the vehicle capacity corresponding to the active edge, Represents the preset second convergence threshold. The calculation principle of this formula is to calculate the traffic that exceeds the capacity of each link, square the excess and sum it, normalize it by dividing it by the total number of links, and finally take the square root to obtain the standardized breach metric. means that all capacity constraints are fully satisfied, Indicates that there is a capacity breach, The larger the value, the more serious the default.

[0044] Step S585: When the judgment result is to stop iteration, determine the passenger equilibrium flow at the new departure time.

[0045] Step S59: When the first convergence condition is met, the iteration is terminated to obtain an optimized bus schedule.

[0046] In this step, the first convergence condition is specifically: ; In the above formula, and They represent the bus schedule of the K+1th iteration and the bus schedule of the Kth iteration respectively. ||•|| represents the vector norm, which is used to measure the distance between two solutions. Represents the first convergence threshold. When the first convergence condition is met, the iteration is terminated and the optimized bus schedule is output.

[0047] It can be understood that the main algorithm of the optimization model is to calculate the gradient of the first optimization function to the schedule based on the initialized bus schedule and the balanced flow returned by the lower layer, and use projected gradient descent and Armijo line search to iteratively update the new schedule, so as to obtain the optimized bus schedule.

[0048] In actual bus operations, there are dynamic factors such as passenger demand fluctuations and traffic congestion, which are difficult to adapt to existing methods. The present invention simultaneously considers travel time, passenger demand, and passenger response behavior under time changes, and can accurately capture the impact of these dynamic factors on the bus schedule. The optimal schedule and equilibrium flow obtained by solving the optimization model can effectively cope with these dynamic changes and improve the actual optimization effect of bus operations, such as reducing passenger waiting time and improving vehicle utilization, providing strong support for the efficient operation of the bus system. In addition, the present invention overcomes the problems of high computational complexity and potential errors caused by discretization processing in existing methods by using continuous functions to describe the dynamic changes of travel time and passenger demand. This innovation enables the model to operate efficiently when dealing with large-scale transportation networks.

[0049] Embodiment 2: like Figure 2As shown, this embodiment provides a bus schedule optimization system for a time-varying traffic environment, the system includes an acquisition module 901, a first processing module 902, a second processing module 903, a third processing module 904 and a fourth processing module 905, which specifically include: An acquisition module, configured to acquire first information, wherein the first information includes a bus route set, a bus station set, and a bus itinerary set; A first processing module, used for constructing a public transportation network according to the first information; A second processing module is used to construct a corresponding topological structure according to the public transportation network to obtain a directed graph, wherein the directed graph includes passenger behavior characteristics and the operation status of public transportation vehicles; A third processing module, used for determining an initial bus schedule according to the directed graph; The fourth processing module is used to establish an optimization model according to the directed graph, and optimize the initial bus schedule using the optimization model to obtain an optimized bus schedule.

[0050] In a specific embodiment of the present disclosure, the second processing module further includes a first acquisition unit, a second acquisition unit and a first processing unit, which specifically include: A first acquisition unit is used to acquire first node information and second node information, wherein the first node information includes arrival events and departure events of public transport vehicles at stations, and the second node information includes the arrival of a passenger group at a departure station or a terminal station; A second acquiring unit, configured to acquire first side information and second side information, wherein the first side information includes the running status of the public transport vehicle between stations, and the second side information includes the behavioral characteristics of the passengers; The first processing unit is configured to construct a topological structure according to the first node information, the second node information, the first edge information, and the second edge information to obtain a directed graph.

[0051] In a specific implementation of the present disclosure, the third processing module further includes a third acquisition unit, a second processing unit, a third processing unit and a fourth processing unit, which specifically include: A third acquisition unit is used to acquire second information, wherein the second information includes a departure time corresponding to a bus at a departure station; a second processing unit, configured to calculate, based on the second information and a preset link travel time function, an arrival time of the vehicle at the next station; A third processing unit is used to calculate the departure time of the vehicle at the next station according to the arrival time of the vehicle at the next station and the stop time of the vehicle at the station; The fourth processing unit is used to calculate the arrival time and departure time of each station in turn to determine the initial bus schedule.

[0052] In a specific implementation of the present disclosure, the fourth processing module further includes a fourth acquisition unit, a fifth processing unit, a fifth acquisition unit, a sixth processing unit and a seventh processing unit, which specifically include: a fourth acquisition unit, configured to acquire a first optimization function, wherein the first optimization function is configured to minimize the total travel cost of all passengers; a fifth processing unit, configured to establish an upper-level optimization problem according to the first optimization function; a fifth acquisition unit, configured to acquire a second optimization function, wherein the second optimization function is used to achieve capacity-constrained user balancing; a sixth processing unit, configured to establish a lower-level optimization problem according to the second optimization function; A seventh processing unit is used to establish an optimization model based on the upper-level optimization problem and the lower-level optimization problem.

[0053] In a specific implementation of the present disclosure, the fourth processing module further includes a sixth acquisition unit, an eighth processing unit, a ninth processing unit and a tenth processing unit, which specifically include: A sixth acquisition unit, used for acquiring an initialized bus schedule and a lower-layer balanced flow; An eighth processing unit, used for calculating the gradient of the first optimization function to the bus schedule in the current iteration step by using a back propagation algorithm during each iteration; The ninth processing unit is used to update the initial bus schedule using projected gradient descent and Armijo line search, calculate vehicle arrival and departure times and passenger group demands, and calculate the passenger equilibrium flow under the new departure time using the augmented Lagrange multiplier method; The tenth processing unit is used to terminate the iteration when the first convergence condition is met to obtain an optimized bus schedule.

[0054] In a specific implementation of the present disclosure, the ninth processing unit further includes a seventh acquisition unit, an eleventh processing unit, a twelfth processing unit, a thirteenth processing unit and a fourteenth processing unit, which specifically include: A seventh acquisition unit, used for acquiring the dual variable of the augmented Lagrangian; An eleventh processing unit is used for processing the dual variables of the augmented Lagrangian and the bus schedule by using a mirror descent algorithm at each iteration to obtain a balanced flow corresponding to the current number of iterations; A twelfth processing unit, configured to update the dual variable pair of the augmented Lagrangian according to the equalization flow corresponding to the current iteration number to obtain the updated dual variable of the augmented Lagrangian; A thirteenth processing unit, used to obtain a preset second convergence condition and determine whether to stop iteration according to the second convergence condition to obtain a determination result; The fourteenth processing unit is used to determine the passenger equilibrium flow at the new departure time when the judgment result is to stop iteration.

[0055] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0056] Embodiment 3: Corresponding to the above method embodiment, this embodiment also provides a bus schedule optimization device for a time-varying traffic environment. The bus schedule optimization device for a time-varying traffic environment described below and the bus schedule optimization method for a time-varying traffic environment described above can refer to each other.

[0057] Figure 3 8 is a block diagram of a bus schedule optimization device 800 for a time-varying traffic environment according to an exemplary embodiment. Figure 3 As shown, the bus schedule optimization device 800 for time-varying traffic environment may include: a processor 801 and a memory 802. The bus schedule optimization device 800 for time-varying traffic environment may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0058] The processor 801 is used to control the overall operation of the bus schedule optimization device 800 for a time-varying traffic environment to complete all or part of the steps in the above-mentioned bus schedule optimization method for a time-varying traffic environment. The memory 802 is used to store various types of data to support the operation of the bus schedule optimization device 800 for a time-varying traffic environment. These data may include, for example, instructions for any application or method operated on the bus schedule optimization device 800 for a time-varying traffic environment, as well as application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be a keyboard, a mouse, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the bus schedule optimization device 800 for time-varying traffic environment and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0059] In an exemplary embodiment, the bus schedule optimization device 800 for time-varying traffic environment can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processing Device, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the above-mentioned bus schedule optimization method for time-varying traffic environment.

[0060] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned bus schedule optimization method for a time-varying traffic environment are implemented. For example, the computer-readable storage medium may be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions may be executed by the processor 801 of the bus schedule optimization device 800 for a time-varying traffic environment to complete the above-mentioned bus schedule optimization method for a time-varying traffic environment.

[0061] Embodiment 4: Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the bus schedule optimization method for a time-varying traffic environment described above can refer to each other.

[0062] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for optimizing a bus schedule for a time-varying traffic environment in the above method embodiment.

[0063] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0064] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0065] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A bus schedule optimization method for time-varying traffic environment, characterized in that: include: Acquire first information, the first information including a bus route set, a bus station set, and a bus itinerary set; constructing a public transportation network according to the first information; Constructing a corresponding topological structure according to the public transportation network to obtain a directed graph, wherein the directed graph includes passenger behavior characteristics and operation status of public transportation vehicles; Determine an initial bus schedule according to the directed graph; An optimization model is established according to the directed graph, and the initial bus schedule is optimized using the optimization model to obtain an optimized bus schedule.

2. The method for optimizing a bus schedule in a time-varying traffic environment according to claim 1, characterized in that: A corresponding topological structure is constructed according to the bus network to obtain a directed graph, including: Acquire first node information and second node information, wherein the first node information includes arrival events and departure events of public transport vehicles at stations, and the second node information includes the arrival of passenger groups at the departure station or the terminal station; Acquire first side information and second side information, wherein the first side information includes the running status of the bus between stations, and the second side information includes the behavioral characteristics of the passengers; A topological structure is constructed according to the first node information, the second node information, the first edge information, and the second edge information to obtain a directed graph.

3. The method for optimizing bus schedule in time-varying traffic environment according to claim 1, characterized in that: Determining an initial bus schedule according to the directed graph includes: Acquire second information, where the second information includes a departure time corresponding to a bus at the departure station; Calculating according to the second information and a preset link travel time function to obtain the arrival time of the vehicle at the next station; Calculate the departure time of the vehicle at the next station based on the arrival time of the vehicle at the next station and the stop time of the vehicle at the station; Calculate the arrival time and departure time of each station in turn to determine the initial bus schedule.

4. The method for optimizing bus schedule in time-varying traffic environment according to claim 1, characterized in that: Establishing an optimization model according to the directed graph includes: Obtaining a first optimization function, wherein the first optimization function is used to minimize the total travel cost of all passengers; Establishing an upper-level optimization problem according to the first optimization function; Obtaining a second optimization function, where the second optimization function is used to achieve capacity-constrained user balancing; Establishing a lower-level optimization problem according to the second optimization function; An optimization model is established based on the upper-level optimization problem and the lower-level optimization problem.

5. The method for optimizing bus schedule in time-varying traffic environment according to claim 1, characterized in that: Optimizing the initial bus schedule using the optimization model includes: Get the initialized bus schedule and lower-level balanced flow; At each iteration, the back propagation algorithm is used to calculate the gradient of the first optimization function in the current iteration step to the bus schedule; Use projected gradient descent and Armijo line search to update and initialize the bus schedule, calculate vehicle arrival and departure times and passenger group demands, and use the augmented Lagrange multiplier method to calculate the passenger equilibrium flow under the new departure time; When the first convergence condition is met, the iteration is terminated and the optimized bus schedule is obtained.

6. A bus schedule optimization system for time-varying traffic environment, characterized in that: include: An acquisition module, configured to acquire first information, wherein the first information includes a bus route set, a bus station set, and a bus itinerary set; A first processing module, used for constructing a public transportation network according to the first information; A second processing module is used to construct a corresponding topological structure according to the public transportation network to obtain a directed graph, wherein the directed graph includes passenger behavior characteristics and the operation status of public transportation vehicles; A third processing module, used for determining an initial bus schedule according to the directed graph; The fourth processing module is used to establish an optimization model according to the directed graph, and optimize the initial bus schedule using the optimization model to obtain an optimized bus schedule.

7. The bus schedule optimization system for time-varying traffic environment according to claim 6 is characterized in that: The second processing module comprises: A first acquisition unit is used to acquire first node information and second node information, wherein the first node information includes arrival events and departure events of public transport vehicles at stations, and the second node information includes the arrival of a passenger group at a departure station or a terminal station; A second acquiring unit, configured to acquire first side information and second side information, wherein the first side information includes the running status of the public transport vehicle between stations, and the second side information includes the behavioral characteristics of the passengers; The first processing unit is configured to construct a topological structure according to the first node information, the second node information, the first edge information, and the second edge information to obtain a directed graph.

8. The bus schedule optimization system for time-varying traffic environment according to claim 6 is characterized in that: The third processing module comprises: A third acquisition unit is used to acquire second information, wherein the second information includes a departure time corresponding to a bus at a departure station; a second processing unit, configured to calculate, according to the second information and a preset link travel time function, an arrival time of the vehicle at the next station; A third processing unit is used to calculate the departure time of the vehicle at the next station according to the arrival time of the vehicle at the next station and the stop time of the vehicle at the station; The fourth processing unit is used to calculate the arrival time and departure time of each station in turn to determine the initial bus schedule.

9. The bus schedule optimization system for time-varying traffic environment according to claim 6, characterized in that: The fourth processing module comprises: a fourth acquisition unit, configured to acquire a first optimization function, wherein the first optimization function is configured to minimize the total travel cost of all passengers; a fifth processing unit, configured to establish an upper-level optimization problem according to the first optimization function; a fifth acquisition unit, configured to acquire a second optimization function, wherein the second optimization function is used to achieve capacity-constrained user balancing; a sixth processing unit, configured to establish a lower-level optimization problem according to the second optimization function; A seventh processing unit is used to establish an optimization model based on the upper-level optimization problem and the lower-level optimization problem.

10. The bus schedule optimization system for time-varying traffic environment according to claim 6, characterized in that: The fourth processing module further includes: A sixth acquisition unit, used for acquiring an initialized bus schedule and a lower-layer balanced flow; An eighth processing unit, used for calculating the gradient of the first optimization function to the bus schedule in the current iteration step by using a back propagation algorithm during each iteration; The ninth processing unit is used to update the initial bus schedule using projected gradient descent and Armijo line search, calculate vehicle arrival and departure times and passenger group demands, and calculate the passenger equilibrium flow under the new departure time using the augmented Lagrange multiplier method; The tenth processing unit is used to terminate the iteration when the first convergence condition is met to obtain an optimized bus schedule.

Images