A method for optimizing bus route capacity

Abstract

The present invention proposes a method for optimizing the capacity of a bus route, and belongs to the technical field of bus route capacity optimization. It includes: step one, obtaining the operating data of the bus route to be optimized; step two, dividing the operating time periods of the bus route based on passenger demand; step three, configuring the minimum departure interval and generating a timetable plan based on the waiting time of passengers; step four, constructing an optimal vehicle allocation model, taking the minimum departure interval and timetable plan obtained in step three as input, and outputting the optimal scheduling plan. It solves the problem of lack of joint solution that considers the departure frequency, timetable, and vehicle scheduling optimization problems at the same time, and can only output a single problem. The present invention realizes the comprehensive output of the division of bus route operating time periods, the optimal departure interval plan, the timetable generation, and the optimal number of vehicles, comprehensively considers the bus supply-side capacity and demand-side service level factors, and realizes the efficient output of stage indicators and strategy indicators of different departure intervals under different operating periods through step-by-step dynamic planning.

Description

Technical Field

[0001] The invention relates to a method for optimizing the transport capacity of a public transportation line, and belongs to the technical field of optimizing the transport capacity of a public transportation line. Background Art

[0002] The research on bus capacity optimization aims to achieve the maximum benefit and minimum cost of bus operation by scientifically generating bus resource allocation plans, including bus departure frequency optimization, timetable optimization, bus vehicle scheduling optimization and other research directions. Bus departure frequency optimization depends on constraints such as passenger demand and vehicle capacity during the operating period. For example, a more intensive departure frequency is required under the same vehicle type conditions to meet the morning and evening peak commuting needs. It is also a prerequisite for timetable optimization. The optimization results of the two jointly determine the service level and passenger experience of the line. Bus vehicle scheduling optimization reduces the operating costs of bus companies while meeting the timetable by flexibly arranging vehicle resources.

[0003] At present, the research focuses on two aspects: 1) Continuously improve the influencing factors of modeling to expand the applicable scenarios of bus line capacity optimization research, such as commuting, holidays, and traffic congestion scenarios. Common factors include passenger flow characteristics, traffic conditions, vehicle models, operating vehicle restrictions, weather effects and other constraints. However, most of them assume that buses travel at a uniform speed and lack consideration of the spatiotemporal characteristics of buses. 2) Based on the above influencing factors and constraints, single-objective and multi-objective optimization models are established, such as bus operating costs, passenger travel costs, passenger travel comfort and other goals. By converting multi-objectives into single-objectives, traditional optimization theories, heuristic algorithms (such as evolutionary algorithms, simulated annealing algorithms, genetic algorithms, artificial immune algorithms) and other methods are used to solve and output the Pareto solution set under the specified goal. However, when solving non-convex optimization problems of multi-objective models, traditional optimization theories cannot guarantee the acquisition of uniformly distributed Pareto optimal frontier surfaces, and the overall efficiency of heuristic solutions is low. Similarly, the output solution set is not necessarily the global optimal solution. The above studies lack the joint solution of considering the departure frequency, timetable, and vehicle scheduling optimization problems at the same time, and can only output the optimal solution of a single problem and the optimal solution of a non-joint problem. Summary of the invention

[0004] A brief overview of the present invention is provided below in order to provide a basic understanding of certain aspects of the present invention. It should be understood that this overview is not an exhaustive overview of the present invention. It is not intended to identify key or important parts of the present invention, nor is it intended to limit the scope of the present invention. Its purpose is merely to present certain concepts in a simplified form as a prelude to a more detailed description discussed later.

[0005] In view of this, in order to solve the technical problems existing in the prior art, the present invention provides a method for optimizing the transportation capacity of bus routes. The present invention takes into account passenger demand and travel time and space characteristics, that is, the changes in travel volume in different time periods, departure places and destinations, and bus travel time and space characteristics, that is, the changes in the speed of buses between adjacent stations and turnover capacity in different time periods, and combines clustering algorithms, dynamic programming and integer programming models, respectively taking passenger demand, passenger waiting time, and the optimal number of vehicles as the goals, to achieve the joint solution of operating period division, departure interval optimization, timetable generation and vehicle allocation number optimization, output the departure interval, timetable and vehicle scheduling optimal solution set, and provide a variety of configuration solutions and effects for bus operating companies.

[0006] Solution 1: A method for optimizing bus line capacity, comprising:

[0007] Step 1: Obtain the operation data of the bus routes to be optimized;

[0008] Step 2: Divide the bus line operation time periods based on passenger demand;

[0009] Step 3: Configure the minimum departure interval and generate a timetable plan based on the passenger waiting time;

[0010] Step 4: Build an optimal vehicle allocation model, take the minimum departure interval and timetable obtained in step 3 as input, and output the optimal scheduling plan.

[0011] Preferably, step 2 is specifically as follows: generating a passenger demand sequence: reading the actual departure schedule and passenger volume data of the line, and calculating the passenger demand sequence according to the actual departure time AT rs=0 (tb), sum of each shift according to fixed time slices Passenger volume , output time slice passenger demand , output the time slice passenger demand sequence in time slice order; where, Indicates the time when the vehicle leaves the designated point in the direction of travel along the designated route; Indicates the driving direction of the specified route No. sites (used to determine spatial location), when Indicates the departure time of the vehicle at the 0th station, that is, the departure time of the first station;

[0012] Configure the minimum and maximum number of clusters: The minimum number of clusters is 2, and the maximum number is the ratio of the total operating time to the time slice interval rounded down. ;

[0013] Cluster modeling: Optimally split the time-slice passenger demand sequence into kind, , so that the difference between classes is maximized and the difference within a class is minimized; the diameter of the class is used to represent the difference within the class, and the optimal segmentation is achieved by minimizing the loss function. The optimal classification with the minimum loss function is further obtained by step-by-step recursive calculation. ;

[0014] Assume that there are a total of time-slice passenger demand sequences variables, let one class be , ;

[0015] Class diameter : , is the distance from each element in the class to the mean point of all elements in the class, that is, the sum of squares of deviations; where, Represents the mean of all elements in the class;

[0016] Loss Function : , loss function To divide the sequence into specified When there is a class, the sum of the diameters of all classes;

[0017] Clustering solution: With the goal of minimizing the loss function, the time-slice passenger demand sequence is recursively solved to output the optimal operation period segmentation result. .

[0018] Preferably, step three is specifically:

[0019] Step 31: Initialize the dynamic model of departure interval configuration based on the operation period division result;

[0020] Step 32: Generate status information of each operating period based on the departure interval threshold to form a status set;

[0021] Step 33: Combine the states of each stage to form a strategy set;

[0022] Step 3: Calculate the strategy objective function and output the optimal strategy.

[0023] Preferably, the initialization of the dynamic model of departure interval configuration based on the result of operation period division is specifically as follows: constructing an optimal departure interval model: establishing an objective function, specifying the departure interval strategy with the minimum number of trips under the average waiting time index A;

[0024] , ;

[0025] In the formula, Gather for the waiting time; For the The number of departures for each strategy, ; is the set of all strategies, The strategy is composed of the set of departure schedules of all states in the strategy, and is formed by different departure intervals configured in different operating periods. , , ; , represents the set of line departure intervals, is the maximum departure interval, is the minimum departure interval; For the The actual start time of the operation during the operation period, i.e. the last bus of the previous period , To collect according to the operation period , divided into any stage Have the planned operation start time for this phase and end time ; is the initial state, i.e. the start time of the first operation period; For stage The set of all states of ;

[0026] Establish the state transition equation to generate the next state based on the previous state and the selected departure interval;

[0027] ; In the formula, For function , represents the transition rule between the previous and next states, The function input is and .

[0028] Preferably, the state information of each operating period based on the departure interval threshold is generated to form a state set specifically as follows:

[0029] State information generation: According to the state transition equation, the state information under different departure interval decisions in each stage is calculated, that is, the departure time of the last train in the previous stage. The formula is:

[0030] ;

[0031] ;

[0032] In the formula, Indicates The stage status is The The number of departure schedules in the departure schedule set is generated by a decision. ;

[0033] Stage indicator information: Define the planned end time for this phase The actual start time of this phase The time difference from the actual start time of this stage +1 starts counting, according to the specified departure interval Departure until the planned end time of this stage Before, the total number of classes sent; Representation stage The planned end time of operations;

[0034] Define the planned end time for this phase The actual start time of this phase The time difference from the actual start time of this stage +1 starts counting, according to the specified departure interval Start until the actual end time of this stage Before, the departure time sequence formed is: ;

[0035] Passenger flow Defined as the state of this stage Start by time interval The sum of all the passengers boarding at all stops along the route is:

[0036] ;

[0037] ;

[0038] ;

[0039] In the formula, Indicates the driving direction of the specified route In site index No. The arrival time of the bus, which is the departure time and the index from the starting station to the station The average travel time is summed up to get; among them, the departure time For stage At the start of actual operation By time interval Departure The departure time of the shuttle bus is ; From the first station to the site index The average travel time is the travel time between bus stops. Calculated;

[0040] The passenger waiting time is defined as the time from the state Start by time interval The sum of the waiting time of all passengers who board the bus at all stops along the route for all departures, where the passenger waiting time is defined as half of the interval between the arrival of the two buses in front and behind. The formula is:

[0041] ;

[0042] Generate state collection: Generate the same stage The different state sets under , .

[0043] Preferably, the states of each stage are combined to form a strategy set as follows:

[0044] Generate strategy: arbitrarily combine the states of each stage and their allowed decision sets to form a strategy , , ;

[0045] Calculate strategic indicators: Strategic indicators include the number of strategic departures, departure schedules, and average waiting time;

[0046] The number of strategic departures is defined as the sum of the number of departures in each stage, and the formula is:

[0047] ;

[0048] The strategic departure schedule is defined as the departure schedule for each stage The union of is:

[0049] ;

[0050] The average waiting time is defined as the ratio of the waiting time at each stage to the total number of people boarding the bus. The formula is:

[0051] .

[0052] Generate a strategy set: Combine the states of each stage and their allowed decision sets to generate a strategy set, denoted as ;

[0053] Preferably, the strategy objective function is calculated and the optimal strategy is output as follows:

[0054] Generate a waiting time set based on the average waiting time of each strategy ; For any waiting time , filter its corresponding strategy set , according to the objective function Output the minimum number of departure intervals .

[0055] Preferably, step 4 is specifically as follows: configure the optimal vehicle number model, use the decision variable to represent the mark of each bus in each direction of the line whether to turn to each bus in the other direction of the line, 0-1 variable, 0 means no, 1 means yes, the formula is:

[0056] ,

[0057] ;

[0058] ,

[0059] ;

[0060] Construct the objective function of the optimal vehicle allocation model and define the objective function as the maximum turnover number:

[0061] ;

[0062] Constraints of the optimal vehicle allocation model: The vehicle turnover of the optimal vehicle allocation model needs to meet both the turnover energy constraint and the turnover time constraint;

[0063] The turnover capacity constraint means that each bus in each direction of the line can only turn around once to a bus in the other direction. The formula is:

[0064] ;

[0065] ;

[0066] The turnaround time constraint means that the departure time of the same vehicle in the next shift must be greater than or equal to the time when the vehicle can be put back into operation after the previous shift ends. The formula is:

[0067] ;

[0068] ;

[0069] In the formula, and Indicates the direction No. Shuttles and Directions No. The time for the shuttle bus to be put back into operation is obtained by summing the historical route station travel time and the minimum turnaround time. The formula is:

[0070] ;

[0071] ;

[0072] ;

[0073] Solve the model and output the optimal scheduling solution.

[0074] Solution 2: An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a bus line capacity optimization method described in Solution 1 are implemented.

[0075] Solution three: A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a bus line capacity optimization method as described in Solution one.

[0076] The beneficial effects of the present invention are as follows: The present invention realizes the comprehensive output of the division of bus line operation periods, the optimal departure interval plan, the timetable generation, and the optimal number of vehicles, and comprehensively considers the factors of the bus supply-side capacity and the demand-side service level, such as passenger boarding and alighting needs, bus driving characteristics, passenger waiting time, vehicle turnover capacity and other constraints. Through step-by-step dynamic planning, efficient output of stage indicators and strategy indicators for different departure intervals under different operating periods is achieved. It supports the output of the optimal departure interval under different waiting times, and provides a variety of configuration solutions for bus companies. It supports the output of the evolution process of waiting time and the optimal number of vehicles under different timetables, and provides data support with diverse influences for the formulation of departure intervals and timetables of bus operating companies. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0078] Figure 1 It is a flow chart of a bus line capacity optimization method;

[0079] Figure 2 Schematic diagram of different decision combinations;

[0080] Figure 3 To provide a schematic diagram of the changing trend of passenger service effects under different flight configuration plans;

[0081] Figure 4 Schematic diagram of the changing trend of passenger service effects under different vehicle configuration schemes.

[0082] Figure 5 In order to determine the departure interval and timetable, a schematic diagram of service data that comprehensively considers the supply side and demand side is provided, where a represents the demand side and b represents the supply side. DETAILED DESCRIPTION

[0083] In order to make the technical solutions and advantages of the embodiments of the present invention more clearly understood, the exemplary embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than an exhaustive list of all the embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0084] Example 1: Reference Figure 1-Figure 5 This embodiment describes a method for optimizing bus line capacity, including:

[0085] Step 1: Obtain the operation data of the bus routes to be optimized;

[0086] Operational data includes bus route information, historical bus arrival records, bus passenger boarding and alighting flow, maximum departure interval, minimum departure interval and minimum turnaround interval;

[0087] Step 2: Divide the bus line operation time periods based on passenger demand;

[0088] Generate passenger demand sequence: read the actual departure timetable and passenger volume data of the line, and generate the passenger demand sequence according to the actual departure time AT rs =0(tb), count and sum each shift according to fixed time slices (such as 1min / 5min / 15min) Passenger volume , output time slice passenger demand , output the time slice passenger demand sequence in the order of time slices; where AT represents the time when the vehicle leaves the designated point in the direction of the designated route; rs represents the sth station in the direction of the designated route r (used to determine the spatial position), when rs=0, it means the departure time of the vehicle at the 0th station, that is, the departure time of the starting station;

[0089] Configure the minimum and maximum number of clusters: The minimum number of clusters is 2, and the maximum number is the ratio of the total operating time to the time slice interval rounded down. ;

[0090] Cluster modeling: Optimally split the time-slice passenger demand sequence into kind, , so that the difference between classes is maximized and the difference within a class is minimized; the diameter of the class is used to represent the difference within the class, and the optimal segmentation is achieved by minimizing the loss function. The optimal classification with the minimum loss function is further obtained by step-by-step recursive calculation. ;

[0091] Assume that there are a total of time-slice passenger demand sequences variables, let one class be , ;

[0092] Class diameter : , is the distance from each element in the class to the mean point of all elements in the class, that is, the sum of squares of deviations; where, Represents the mean of all elements in the class;

[0093] Loss Function : , loss function To divide the sequence into specified When there is a class, the sum of the diameters of all classes;

[0094] Clustering solution: With the goal of minimizing the loss function, the time-slice passenger demand sequence is recursively solved to output the optimal operation period segmentation result. .

[0095] Step 3: Configure the minimum departure interval and generate a timetable plan based on the passenger waiting time;

[0096] Step 31: Initialize the dynamic model of departure interval configuration based on the operation period division result;

[0097] Construct the optimal departure interval model: establish the objective function, specify the average waiting time index A, and provide the departure planning interval with the least number of trips;

[0098] ;

[0099] In the formula, Gather for the waiting time; For the The number of departures for each strategy, ; is the set of all strategies, The strategy is composed of the set of departure schedules of all states in the strategy, and is formed by different departure intervals configured in different operating periods. , , ; , represents the set of line departure intervals, is the maximum departure interval, is the minimum departure interval; For the The actual start time of the operation during the operation period, i.e. the last bus of the previous period , To collect according to the operation period , divided into any stage Have the planned operation start time for this phase and end time ; is the initial state, i.e. the start time of the first operation period; For stage The set of all states of ;

[0100] Establish the state transition equation to generate the next state based on the previous state and the selected departure interval;

[0101] ;

[0102] In the formula, For function , represents the transition rule between the previous and next states, The function input is and .

[0103] Step 32: Generate status information of each operating period based on the departure interval threshold to form a status set;

[0104] State information generation: According to the state transition equation, the state information under different departure interval decisions in each stage is calculated, that is, the departure time of the last train in the previous stage. The formula is:

[0105] ;

[0106] ;

[0107] In the formula, Indicates The stage status is The The number of departure schedules in the departure schedule set is generated by a decision. ;

[0108] Stage indicator information:

[0109] Define the planned end time for this phase The actual start time of this phase The time difference from the actual start time of this stage +1 starts counting, according to the specified departure interval Departure until the planned end time of this stage Before, the total number of classes sent; Representation stage The planned end time of operations;

[0110] Define the planned end time for this phase The actual start time of this phase The time difference from the actual start time of this stage +1 starts counting, according to the specified departure interval Start until the actual end time of this stage Before, the departure time sequence formed is: ;

[0111] Passenger flow Defined as the state of this stage Start by time interval The sum of all the passengers boarding at all stops along the route is:

[0112] ;

[0113] ;

[0114] ;

[0115] In the formula, Indicates the driving direction of the specified route In site index No. The arrival time of the bus, which is the departure time and the index from the starting station to the station The average travel time is summed up to get; among them, the departure time For stage At the start of actual operation By time interval Departure The departure time of the shuttle bus is ; From the first station to the site index The average travel time is the travel time between bus stops. Calculated;

[0116] The passenger waiting time is defined as the time from the state Start by time interval The sum of the waiting time of all passengers who board the bus at all stops along the route for all departures, where the passenger waiting time is defined as half of the interval between the arrival of the two buses in front and behind. The formula is:

[0117] .

[0118] Generate state collection: Generate the same stage The different state sets under , ;

[0119] Step 33: Combine the states of each stage to form a strategy set;

[0120] Generate strategy: arbitrarily combine the states of each stage and their allowed decision sets to form a strategy .

[0121] Calculate strategic indicators: Strategic indicators include the number of strategic departures, departure schedules, and average waiting time;

[0122] The number of strategic departures is defined as the sum of the number of departures in each stage, and the formula is:

[0123] ;

[0124] The strategic departure schedule is defined as the departure schedule for each stage The union of is:

[0125] ;

[0126] The average waiting time is defined as the ratio of the waiting time at each stage to the total number of people boarding the bus. The formula is:

[0127] .

[0128] Generate a strategy set: Combine the states of each stage and their allowed decision sets to generate a strategy set, denoted as .

[0129] Step 34: Calculate the strategy objective function and output the optimal strategy;

[0130] Generate a waiting time set based on the average waiting time of each strategy ; For any waiting time , filter its corresponding strategy set , according to the objective function Output the minimum number of departure intervals .

[0131] Step 4: Build an optimal vehicle allocation model, take the minimum departure interval and timetable obtained in step 3 as input, and output the optimal dispatching plan;

[0132] The optimal vehicle number model is configured, and the decision variable is used to represent the mark of each bus in each direction of the line whether to turn to each bus in the other direction of the line. It is a 0-1 variable, 0 means no, 1 means yes, and the formula is:

[0133] ,

[0134] ;

[0135] ,

[0136] ;

[0137] Construct the objective function of the optimal vehicle allocation model and define the objective function as the maximum turnover number:

[0138] ;

[0139] Constraints of the optimal vehicle allocation model: The vehicle turnover of the optimal vehicle allocation model needs to meet both the turnover energy constraint and the turnover time constraint;

[0140] The turnover capacity constraint means that each bus in each direction of the line can only turn around once to a bus in the other direction. The formula is:

[0141] ;

[0142] ;

[0143] The turnaround time constraint means that the departure time of the same vehicle in the next shift must be greater than or equal to the time when the vehicle can be put back into operation after the previous shift ends. The formula is:

[0144] ;

[0145] ;

[0146] In the formula, and Indicates the direction No. Shuttles and Directions No. The time for the shuttle bus to be put back into operation is obtained by summing the historical route station travel time and the minimum turnaround time. The formula is:

[0147] ;

[0148] ;

[0149] ;

[0150] Solve the model and output the optimal scheduling solution.

[0151] Embodiment 2: The computer device of the present invention may be a device including a processor and a memory, such as a single chip microcomputer including a central processing unit, etc. Moreover, the processor is used to implement the steps of the above-mentioned bus line capacity optimization method when executing the computer program stored in the memory.

[0152] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0153] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0154] Embodiment 3: Computer readable storage medium embodiment.

[0155] The computer-readable storage medium of the present invention can be any form of storage medium that can be read by the processor of a computer device, including but not limited to non-volatile memory, volatile memory, ferroelectric memory, etc. The computer-readable storage medium stores a computer program. When the processor of the computer device reads and executes the computer program stored in the memory, the steps of the above-mentioned bus line capacity optimization method can be implemented.

[0156] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer readable media do not include electric carrier signals and telecommunication signals.

[0157] Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is selected primarily for readability and teaching purposes, rather than for explaining or defining the subject matter of the present invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is illustrative, not restrictive, with respect to the scope of the present invention, which is defined by the appended claims.

Claims

1. A method for optimizing bus route capacity, characterized in that: include: Step 1: Obtain the operation data of the bus routes to be optimized; Step 2: Divide the bus line operation time periods based on passenger demand; Step 3: Configure the minimum departure interval and generate a timetable plan based on the passenger waiting time; Step 4: Build an optimal vehicle allocation model, take the minimum departure interval and timetable obtained in step 3 as input, and output the optimal dispatching plan; Step three is as follows: Step 31: Initialize the dynamic model of departure interval configuration based on the operation period division result; Step 32: Generate a state set based on the state information of each operating period of the departure interval threshold; Step 33: Combine the states of each stage to form a strategy set; Step 34: Calculate the strategy objective function and output the optimal strategy; The dynamic model initialization of the departure interval configuration based on the operation period division results is as follows: Construct the optimal departure interval model: establish the objective function and provide the departure interval strategy with the minimum number of trips under the specified average waiting time index; A is any waiting time; In the formula, AWT is the waiting time set; is the number of departures of the st-th strategy, st∈ST; ST is the set of all strategies, st is the strategy solution composed of the set of departures of all states in the strategy, and is formed by different departure intervals configured under different operating periods D k = Set(h min ,h min +1,…,h max ), represents the set of line departure intervals, h max is the maximum departure interval, h min is the minimum departure interval; T k is the actual operation start time of the kth operation period, i.e., the last bus of the previous stage, and K is the set of operation periods P = (p1, p2, ..., p K ), divided into K stages, any stage k has the planned operation start time p of this stage k and the end time p k+1 ; T1 is the initial state, i.e. the start time of the first operation period; C k is the set of all states in stage k; Establish the state transition equation to generate the next state based on the previous state and the selected departure interval; Indicates the transition rule between the previous and next states. The FT function input is T k and d; Based on the status information of each operating period of the departure interval threshold, the generated status set is specifically: State information generation: According to the state transition equation, the state information under different departure interval decisions in each stage is calculated, that is, the departure time of the last train in the previous stage. The formula is: Stage indicator information: Define the planned end time p for this stage k+1 The actual start time of this stage is T k Within the time difference, from the actual start time of this stage T k +1 starts counting, and the trains start at the specified departure interval d until the planned end time p of this stage k+1 Before, the total number of flights sent; p k+1 represents the planned operation end time of stage k; Define the planned end time p for this stage k+1 The actual start time of this stage is T k Within the time difference, from the actual start time of this stage T k +1 starts counting, and the trains start at the specified departure interval d until the actual end time of this stage T k+1 Before, the departure time sequence formed is: Passenger flow Defined as the state T in this stage k The sum of all the boarding numbers at all stops along the route for all the trips that start at time intervals d is: t l (T)=rt(rs=l,T∈[T+δt)) In the formula, It indicates the arrival time of the i-th bus at the station index s in the driving direction r of the specified route. The arrival time is obtained by summing the departure time and the average travel time from the starting station to the station index s. is the actual operation start time T of stage k k The departure time of the i-th bus that departs at time interval d is The average travel time from the starting station to the station index s is calculated by the bus line station travel time rt(rs,T); The passenger waiting time is defined as the time from state T k The sum of the waiting time of all passengers boarding at all stops along the route for all buses that start to depart at time intervals d is: Generate state sets: Generate different state sets at the same stage k, denoted as C k , Combining the states of each stage to form a strategy set is as follows: Generate strategy: arbitrarily combine the states of each stage and their allowed decision sets to form a strategy; Calculate strategic indicators: Strategic indicators include the number of strategic departures, departure schedules, and average waiting time; The number of strategic departures is defined as the sum of the number of departures in each stage, and the formula is: The strategic departure schedule is defined as the departure schedule for each stage The union of is: The average waiting time is defined as the ratio of the waiting time at each stage to the total number of people boarding the bus. The formula is: Generate strategy set: Combine the states of each stage and their allowed decision sets to generate a strategy set, denoted as ST; Calculate the strategy objective function and output the optimal strategy as follows: Based on the average waiting time of each strategy, generate the waiting time set AWT; filter its corresponding strategy set ST A , according to the objective function Output the minimum number of departure intervals Step 4 is as follows: configure the optimal vehicle number model, use decision variables to represent the mark of each bus in each direction of the line whether to turn to each bus in the other direction of the line, 0-1 variable, 0 means no, 1 means yes, the formula is: Construct the objective function of the optimal vehicle allocation model and define the objective function as the maximum turnover number: Constraints of the optimal vehicle allocation model: The vehicle turnover of the optimal vehicle allocation model needs to meet both the turnover energy constraint and the turnover time constraint; The turnover capacity constraint means that each bus in each direction of the line can only turn around once to a bus in the other direction. The formula is: The turnaround time constraint means that the departure time of the same vehicle in the next shift must be greater than or equal to the time when the vehicle can be put back into operation after the previous shift ends. The formula is: In the formula, and Denotes the re-entry time of the ith bus in direction ab and the jth bus in direction ba, respectively, which is obtained by summing the historical inter-station travel time and the minimum turnaround time of the line. The formula is: t l (T)=rt(rs=l,T∈[T+δt)) Solve the model and output the optimal scheduling solution.

2. A method for optimizing bus line capacity according to claim 1, characterized in that: Step 2 is as follows: Generate passenger demand sequence: read the actual departure timetable and passenger volume data of the route, and generate passenger demand sequence according to the actual departure time AT rs＝0 (tb), calculate the passenger volume FL of each trip tb according to fixed time slice statistics tb , output time slice passenger demand FL T , output the time slice passenger demand sequence in the order of time slices; where AT represents the time when the vehicle leaves the designated point in the direction of the designated route; rs represents the sth station in the direction of the designated route r, rs is used to determine the spatial position, when rs = 0, it means the departure time of the vehicle at the 0th station, that is, the departure time of the starting station; Configure the minimum and maximum number of clusters: The minimum number of clusters is 2, and the maximum number is the ratio of the total operating time to the time slice interval rounded down to n; Clustering modeling: optimally divide the time-slice passenger demand sequence into n* classes, n*∈[2,n], so that the difference between classes is maximized and the difference within a class is minimized; the diameter of the class is used to represent the difference within the class, and the optimal segmentation is achieved by minimizing the loss function. The optimal classification n* with the minimum loss function is further obtained through step-by-step recursive calculation; Assume that the time slice passenger demand sequence has a total of N variables, and assume that one of the categories is {FL i ,FL i+1 ,…,FL j }, 1≤i≤j≤N; The diameter of the class A(i,j): A(i,j) is the distance between each element in the class and the mean point of all elements in the class, that is, the sum of squared deviations; where, Represents the mean of all elements in the class; Loss function e K,N :e K,N =∑ k＝[1,K] A(i k ,i k+1 -1), loss function e K,N The sum of the diameters of all classes when dividing the sequence into specified K classes; Clustering solution: With the goal of minimizing the loss function, the time-slice passenger demand sequence is recursively solved to output the optimal operation period segmentation result.

3. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of a bus line capacity optimization method as claimed in claim 1 or 2 when executing the computer program.

4. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, a bus line capacity optimization method as claimed in claim 1 or 2 is implemented.

Images