Train operation scheduling methods and computer program products that respond to passenger demand

Abstract

This application provides a train operation scheduling method and computer program product that responds to passenger demand. By pre-calculating passenger demand based on continuously divided time slices at each station of the target urban rail transit system, a time-slice-level passenger demand response mechanism is constructed. By accurately sensing passenger demand and responding to it in the implemented train operation scheduling, proactive prediction and dynamic scheduling of passenger flow are realized, which will significantly reduce passenger waiting time and platform congestion, and improve train capacity utilization and service balance.

Description

Technical Field

[0001] This application relates to the field of urban rail transit technology, specifically to a train operation scheduling method and computer program product that responds to passenger demand. Background Technology

[0002] With the rapid expansion of urban rail transit networks and the increasing complexity of peak passenger flow, existing train operation scheduling schemes largely rely on fixed timetables, i.e., controlling departures and arrivals according to pre-set train operation plans. This type of scheduling method based on static timetables has good controllability and predictability during off-peak hours, but in scenarios such as morning and evening rush hours, emergencies, or holidays, passenger demand exhibits obvious dynamic fluctuations, making it difficult for fixed scheduling plans to effectively match actual passenger flow demand.

[0003] Passenger flow, or passenger demand, is uncertain and disconnected from existing train schedules. In other words, the existing train schedule lacks a passenger demand response mechanism, making it impossible to accurately perceive passenger demand and respond accordingly in the implemented train schedules. Summary of the Invention

[0004] One objective of this application is to construct a passenger demand response mechanism, thereby accurately sensing passenger demand and responding to the implemented train operation scheduling.

[0005] According to one aspect of the embodiments of this application, a train operation scheduling method in response to passenger demand is disclosed, the method comprising:

[0006] For each station of the target city's rail transit system, passenger demand is pre-calculated on consecutive time slices to obtain the required number of trains for each station in different directions of travel and on each time slice, corresponding to the passenger demand.

[0007] Based on the number of trains required for each station in different directions of travel and in each time slot, the consecutively divided time slots are used as waiting time slots. For each direction of travel at the station, a set of trains is determined within the corresponding waiting time slot to carry the passenger demand.

[0008] Based on the set of trains determined for each station in each direction of travel during each waiting time slot, the operation of the trains is scheduled. The scheduled trains run along the corresponding routes and directions of travel, and the arrival times at each station they pass through are matched with the waiting time slots required by the passengers.

[0009] According to one aspect of the embodiments of this application, a computer device is disclosed, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method as described in any of the preceding claims.

[0010] According to one aspect of the embodiments of this application, a computer program product is disclosed, including a computer program that, when executed by a processor, implements the steps of the method as described in any of the preceding claims.

[0011] According to one aspect of the embodiments of this application, a computer-readable storage medium is disclosed having a computer program stored thereon that, when executed by a processor, implements the steps of the method as described in any of the preceding claims.

[0012] This application embodiment constructs a time-slice-level passenger demand response mechanism by pre-calculating passenger demand at each station of the target urban rail transit system based on continuously divided time slices. This mechanism accurately perceives passenger demand and responds to the implemented train operation scheduling, realizing proactive prediction and dynamic scheduling of passenger flow. This will significantly reduce passenger waiting time and platform congestion, and improve train capacity utilization and service balance.

[0013] Specifically, the passenger demand response mechanism constructed in this application embodiment can perform refined modeling of passenger entry and exit demand at each station at different times, and obtain parameter values ​​that reflect the intensity of passenger travel demand. This enables the implementation of operation scheduling to perceive the passenger load change trend of each time slot in advance during the operation plan generation stage. With the help of this pre-calculation result, the passenger demand and train number are matched in each waiting time slot, so that the passenger demand in each waiting time slot at the station is met by the train number arriving in that waiting time slot, achieving precise connection between passenger flow and train number.

[0014] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0015] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this application. Attached Figure Description

[0016] The above and other objectives, features and advantages of this application will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0017] Figure 1 A flowchart of a train operation scheduling method in response to passenger demand according to an embodiment of this application is shown.

[0018] Figure 2 It is based on Figure 1 The flowchart shown in the corresponding embodiment describes the steps of pre-calculating passenger demand for each station of the target urban rail transit system in consecutive time slices to obtain the required number of trains for each station in different travel directions and in each time slice corresponding to passenger demand.

[0019] Figure 3 It is based on Figure 2 The corresponding embodiment shows a flowchart describing the steps of aligning historical passenger flow data on stations and time slices for continuously divided time slices after time discretization to obtain historical passenger flow data for each station in each continuously divided time slice.

[0020] Figure 4 It is based on Figure 2 The flowchart shown in the corresponding embodiment describes the steps of splitting historical passenger flow data of each station in each consecutive time segment according to the direction of travel, and calculating the historical passenger flow of each station in each time segment along different directions of travel.

[0021] Figure 5 It is based on Figure 2 The corresponding embodiment shows a flowchart describing the steps of predicting the number of passengers in the corresponding time slot and direction of travel for each station based on the historical passenger flow of each station in the continuous time slots along the direction of travel, and converting it into the required number of trains.

[0022] Figure 6 It is based on Figure 1 The corresponding embodiment shows a flowchart describing the steps of determining the set of trains to meet passenger demand for each direction of travel at a station within the corresponding waiting time slot, based on the required number of trains at the station in different directions of travel and in each time slot, using the continuously divided time slots as waiting time slots. Detailed Implementation

[0023] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided to make the description of this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art. The drawings are merely illustrative of this application and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0024] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more exemplary embodiments. Numerous specific details are provided in the following description to give a full understanding of exemplary embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced with one or more of the specific details omitted, or other methods, components, steps, etc., can be employed. In other instances, well-known structures, methods, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0025] Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0026] This application provides an intelligent scheduling decision system for urban rail transit operations, enabling cities to quickly respond to various problems and resource allocation needs in current rail transit operations by implementing unified constraint modeling and calculations based on it, without relying on experience and manual scheduling. This achieves intelligent scheduling decisions for rail transit operations under complex scheduling structures and the constructed unified constraint system.

[0027] See Figure 1 , Figure 1 A flowchart illustrating a train operation scheduling method in response to passenger demand according to an embodiment of this application is shown. An embodiment of this application provides a train operation scheduling method in response to passenger demand, comprising:

[0028] Step S110: For each station of the target urban rail transit system, pre-calculate the passenger demand in the consecutive time slots to obtain the number of trains required for each station in different directions of travel and in each time slot corresponding to the passenger demand.

[0029] Step S120: Based on the number of trains required for each station in different directions of travel and in each time slot, the consecutively divided time slots are used as waiting time slots. For each direction of travel at the station, a set of trains to meet passenger demand is determined within the corresponding waiting time slot.

[0030] Step S130: Based on the set of trains determined for each station in each direction of travel during each waiting time slot, the operation of the train is scheduled. The scheduled train runs along the corresponding route and direction of travel, and the arrival time of each station it passes through matches the waiting time slots required by the passengers.

[0031] These steps are explained in detail below.

[0032] Passenger demand, as a personalized scheduling requirement, will be embedded in the scheduling optimization, thereby enabling the operation scheduling implemented by the urban rail transit system to meet the passenger flow carrying capacity requirements of each station during each waiting time slot.

[0033] In order to adapt to the passenger demand generated by each train direction in each waiting time slot in the operation scheduling, it is first necessary to perceive and quantify the passenger demand. That is, the passenger demand is pre-calculated by executing step S110 to obtain the required number of trains that represent the passenger demand. In an exemplary embodiment, the required number of trains determined by the station for different train directions in the waiting time slot is used to represent the passenger demand corresponding to each train direction in the waiting time slot of the station.

[0034] This calculation is expected to be performed at each station and within the consecutive time slots at each station. This yields the number of trains required at each station in different directions and time slots. Specifically, it represents the number of trains required at each station in each waiting time slot. The number of trains required at a station within a waiting time slot indicates the passenger demand at that station in the corresponding waiting time slot and direction. For example, for a single train line, the direction of travel often includes both up and down directions, but it is not limited to this. For train lines with extensions, branch lines, turnaround sections, or multiple branch structures, the direction of travel also includes the direction of travel along the extension, branch, or branch section.

[0035] See Figure 2 , Figure 2 It is based on Figure 1 The flowchart shown in the corresponding embodiment describes the steps of pre-calculating passenger demand for each station of the target urban rail transit system in consecutive time slices to obtain the required number of trains for each station in different travel directions and in each time slice corresponding to passenger demand.

[0036] The embodiment of this application provides a step S110 whereby passenger demand is pre-calculated for each station of the target urban rail transit system in consecutively divided time slices to obtain the required number of trains for each station in different travel directions and corresponding to passenger demand in each time slice. This step includes:

[0037] Step S111: For the time slices that have been continuously divided by time discretization, align the historical passenger flow data on the stations and time slices to obtain the historical passenger flow data of each station on each of the continuously divided time slices.

[0038] Step S112: For each station, the historical passenger flow data in each consecutive time segment is divided into passenger flow segments according to the direction of travel, and the historical passenger flow of each station in each time segment along different directions of travel is calculated.

[0039] Step S113: Based on the historical passenger flow of each station along the direction of travel in the consecutive time slots, predict the number of passengers in the corresponding time slot and direction of travel for each station, and convert it into the required number of trains.

[0040] In this exemplary embodiment, historical passenger flow data can come from the turnstiles, that is, the entry data of each station and time stamp is used as historical passenger flow data. In addition, OD data (Origin-Destination Data) will be incorporated to determine the passenger flow of each station in each waiting time slot corresponding to the driving line and driving direction, thereby adapting to the complex scheduling structure under multiple lines and multiple driving directions, and accurately determining the passenger flow generated by each station in each driving direction in each time slot.

[0041] It should be understood that OD data, or OD data combined with arrival data, allows for the determination of passenger flow corresponding to the direction of travel in each waiting time slot at each station. For example, OD data describes passenger travel behavior from the originating station to the destination station. OD data includes at least the arrival station, departure station, arrival time, and departure time. The arrival time can be mapped to a time slot, and the arrival and departure stations are mapped to the travel route and the direction of travel along that route. Therefore, the passenger will be part of the passenger flow at that arrival station in the mapped time slot and direction of travel. Similarly, the historical passenger flow at a station corresponding to the travel route and direction of travel in each waiting time slot can be determined.

[0042] See Figure 3 , Figure 3 It is based on Figure 2 The corresponding embodiment shows a flowchart describing the steps of aligning historical passenger flow data on stations and time slices for continuously divided time slices after time discretization to obtain historical passenger flow data for each station in each continuously divided time slice.

[0043] The embodiment of this application provides a step S111 for aligning historical passenger flow data at stations and time slices for continuously divided time slices after time discretization processing, to obtain historical passenger flow data for each station in each continuously divided time slice, including:

[0044] Step S1111: Adapt to the time slice length applicable to the scheduling and perform time discretization processing to obtain several continuously divided time slices;

[0045] Step S1112: Based on the arrival time and station indicated by the historical passenger flow data, map and align the historical passenger flow data to the corresponding time slots and stations to obtain the historical passenger flow data of each station in each time slot.

[0046] In this exemplary embodiment, it should first be clarified that the time slice length determines the granularity of the implemented operation scheduling in time, and determines the sensitivity of passenger demand perception and response. For example, the time slice length can be 1 minute.

[0047] Historical passenger flow data is mapped and aligned to the defined time slices and stations, meaning that historical passenger flow data for each station in each time slice is obtained. Specifically, historical customer flow data is mapped to the corresponding time slices and stations according to the pre-defined time slice and station dimensions based on the recorded time and station information, forming historical customer data with a unified spatiotemporal granularity, thus achieving spatiotemporal alignment of discretely collected customer records.

[0048] See Figure 4 , Figure 4 It is based on Figure 2 The flowchart shown in the corresponding embodiment describes the steps of splitting historical passenger flow data of each station in each consecutive time segment according to the direction of travel, and calculating the historical passenger flow of each station in each time segment along different directions of travel.

[0049] The embodiment of this application provides a step S112 for calculating the historical passenger flow of each station in each time slot along different driving directions by dividing the historical passenger flow data of each station in each consecutive time slot, including:

[0050] Step S1121: Determine the destination direction based on the exit station indicated in the historical passenger flow data;

[0051] Step S1122: For the historical passenger flow data of the station in each consecutive time segment, classify and statistically analyze the historical passenger flow data according to the determined driving direction to obtain the historical passenger flow of each station in each time segment along the driving direction.

[0052] In this exemplary embodiment, as previously described, the historical passenger flow data includes OD data, thus enabling the determination of the driving direction to which the historical passenger flow belongs based on the exit station indicated in the OD data.

[0053] Then, based on the historical passenger flow data that has been mapped and aligned to stations and time slices, the historical passenger flow of the station in the direction of travel in this time slice is calculated according to the assigned direction of travel. The historical passenger flow of a station in a direction of travel in a time slice indicates the intensity of passenger flow or passenger demand in that direction of travel within that time slice.

[0054] The historical passenger flow for each station is classified and statistically analyzed for the corresponding driving direction and time slot. The passenger count, and even the net flow, i.e. the number of passengers boarding, are obtained through statistical analysis.

[0055] Historical passenger flow is statistically analyzed for each station according to its corresponding travel direction and time slot. The number of passengers obtained from the statistics, or the net passenger flow obtained through further calculation, is used as the historical passenger flow of the station along the travel direction in the time slot. The net passenger flow is the difference between the number of passengers boarding and alighting at the station within the time slot.

[0056] See Figure 5 , Figure 5 It is based on Figure 2 The corresponding embodiment shows a flowchart describing the steps of predicting the number of passengers in the corresponding time slot and direction of travel for each station based on the historical passenger flow of each station in the continuous time slots along the direction of travel, and converting it into the required number of trains.

[0057] The step S113 provided in this application embodiment, which predicts the number of passengers in the corresponding time slot and direction of travel for each station based on the historical passenger flow of each station in the continuous time slots along the direction of travel, and converts it into the required number of trains, includes:

[0058] Step S1131: For each time slot continuously divided by the station, predict the number of passengers along the corresponding driving direction of the station in this time slot based on the historical passenger flow of each driving direction according to the spatiotemporal characteristics.

[0059] Step S1132: Based on the number of passengers at the station in the corresponding direction of travel during this time slice and the carrying capacity of a single train, the predicted number of passengers is converted into the required number of trains. The carrying capacity of a single train is determined by the target passenger load factor of the target urban rail transit system and the rated passenger capacity of the train.

[0060] In this exemplary embodiment, the spatiotemporal features include temporal features and spatial features. The temporal features include lag windows (past time slices), weekdays / hours / whether it is a holiday, and event identifiers. The spatial features include weather and neighboring station traffic, which will not be listed here.

[0061] The carrying capacity of a single train depends on the operational objectives. It should be understood that the carrying capacity of a single train is determined by the target load factor of the target urban rail transit system and the train's rated passenger capacity; that is, the product of the target load factor and the train's rated passenger capacity. If the operational objective is passenger experience, the carrying capacity of a single train will be reduced by controlling the target load factor, thereby increasing the number of trains. This ensures that passengers do not fill the entire train's capacity while still managing to transport the resulting passenger flow.

[0062] If the operational objective is to reduce operating costs, then the carrying capacity of a single train can be increased by improving the target occupancy rate, thereby ensuring that every train passing through is as full as possible.

[0063] After determining the carrying capacity of a single train in accordance with the operational objectives, the required number of trains can be obtained by calculating the quotient between the number of passengers at the station along the direction of travel in this time slice and the carrying capacity of a single train.

[0064] For a train's stop at a station, this train is the train that passes through that station. In step S120, based on the train's arrival time at the station, the waiting time slot into which the arrival time falls is first determined. Then, based on this, passenger demand and trains are matched in that waiting time slot to determine the trains that meet the passenger demand. By doing so, a set of trains covering the corresponding travel direction for each waiting time slot can be generated for each station.

[0065] This will match and control passenger demand at different times for each station along a specific route and in the direction of travel with the actual arrival of trains, ensuring that the scheduling optimization can meet the service requirements of each station and improve the passenger experience.

[0066] For passenger demand, the continuous and fixed-length time slices divided into operating periods are called waiting time slices. Passenger demand is represented by the waiting time slices and the number of trains needed within each waiting time slice. This allows for the establishment of a matching relationship between passenger demand and train schedules, thereby optimizing the scheduling of trains to meet passenger demand.

[0067] In one exemplary embodiment, the matching of waiting time slots with train numbers is characterized by the actual arrival of the train at the station within that waiting time slot. On one hand, a matching relationship between the arrival time of a train and the passenger's waiting time slot is introduced to construct the matching between the train number and the waiting time slot. On the other hand, within each waiting time slot, the number of trains required at each station is matched with the number of trains stopping at the station within that waiting time slot, thereby establishing a correspondence between passenger demand and the operating train numbers.

[0068] This approach ensures that the optimized scheduling is precisely matched with passenger demand, avoiding capacity shortages due to insufficient train stops or resource waste due to excessive stops, thereby improving the transportation efficiency and passenger service level of the optimized scheduling.

[0069] See Figure 6 , Figure 6 It is based on Figure 1 The corresponding embodiment shows a flowchart describing the steps of determining the set of trains to meet passenger demand for each direction of travel at a station within the corresponding waiting time slot, based on the required number of trains at the station in different directions of travel and in each time slot, using the continuously divided time slots as waiting time slots.

[0070] The step S120 provided in this application embodiment, which determines the set of trains to meet passenger demand for each direction of travel of a station within the corresponding waiting time slot, based on the required number of trains corresponding to different travel directions and time slots of a station, includes:

[0071] Step S121: Based on the train numbers passing through each station and the waiting time slot to which the train numbers arrive at the station, establish a train arrival variable for the train numbers at that station. The train arrival variable is used to indicate the waiting time slot to which the train numbers arrive at the station under a specific direction of travel.

[0072] Step S122: Match the waiting time slots with the passing trains based on the train arrival variables of the station, assign the passing trains to the waiting time slots to which their arrival times belong, and select the passing trains that match the required number of trains in each direction of travel as the set of trains to carry the passenger demand of the station in the corresponding waiting time slots.

[0073] The following is a detailed explanation of these two steps.

[0074] For example, constructing train number and arrival station variables. By train number and arrival station variable The assignment of values ​​is used to allocate train numbers to waiting time slots, thereby matching train numbers with waiting time slots and determining the train numbers that will meet the passenger demand in the waiting time slots on this travel direction.

[0075] Furthermore, the arrival time of each train can be used as a reference to allocate trains to waiting time slots, thereby assigning values ​​to the corresponding train arrival variables. Each potential train, i.e., a train that may run, has a corresponding arrival time at each station it passes through. Based on the matching between train arrival times and passenger waiting time slots in each direction of travel, the matching between trains passing through each station in that direction of travel and waiting time slots is achieved, thereby determining the trains used to meet passenger demand in that direction of travel during the waiting time slots.

[0076] Therefore, based on the arrival time of each train, the arrival time of each train at the stations it passes through is determined, and the arrival time of the train at each station is established according to the arrival time of the train at each station.

[0077] In other words, based on the constraints of the required number of trains corresponding to the station's direction of travel and time slot, the train arrival variable is adjusted. The resulting train arrival variable indicates the train that arrives at station i in time slot t for the corresponding route and direction of travel. The train arrival variable achieves the matching of pre-calculated passenger demand to train numbers, thus enabling the construction of a system based on the constructed train arrival variable. The indicated train route is lno, the direction of travel is dir, and the train number k departs from the originating station m. Its arrival time at station i will fall into the waiting time slot t, and it will carry passenger flow during the waiting time slot t.

[0078] Therefore, for station i, for each direction of travel dir, the set of trains to accommodate passenger demand is determined within the corresponding waiting time slice t based on the established train arrival variables. For each train k included in this set, its train arrival variable... The value assigned is 1.

[0079] It should be understood that the constraint of pre-calculating the required number of trains refers to the train number and arrival station variable. The system imposes a quantity constraint on the set of train services to limit the number of train services included in the set, thereby ensuring that a sufficient number of trains arrive at station i within the waiting time slice t to meet passenger travel demand.

[0080] Therefore, for station i, all train arrival variables mapped to the train arrival variable with a value of 1 corresponding to the travel direction dir and waiting time slot t form the set of trains determined by the travel direction dir of station i during the waiting time slot t. It should be further noted that the travel route lno, travel direction dir, originating station m, and train number k determine a single train number.

[0081] As a supplementary explanation, the train arrival variables corresponding to the stations are... is a binary variable that takes the value 0 or 1, and represents the arrival time of train (m,k) at station i in the direction of travel dir if and only if the arrival time of train (m,k) is 0 or 1. When the train arrives at station i within time slice t, the arrival time variable is... The value is 1, otherwise it is 0.

[0082] For the train arrival variable with a value of 1, the corresponding train number realizes the matching of the mapped waiting time slice with the train number, and the matched train number carries the passenger flow generated by this waiting time slice.

[0083] In other words, the train arrival variable at a station maps to a waiting time slice and the train that arrives during that waiting time slice. Therefore, for each station, the waiting time slice and the train can be matched based on the train arrival variable, which has a value of 1.

[0084] In an exemplary embodiment, for the train arrival variable at station i corresponding to the train line lno and the train direction dir on the waiting time slot t, the summation value is constrained to meet the corresponding required number of trains, thereby ensuring that passenger demand can be met by the trains arriving at the waiting time slot.

[0085] For example, this constraint can be achieved using the following formula:

[0086]

[0087] in, It represents the number of trains required at station i during the waiting time slice t. This represents the train number (m, k) that may arrive at station i during waiting time slot t.

[0088] In other words, during the execution of step S120, based on the required number of trains corresponding to the station in the consecutive time slots, a quantity constraint is imposed on the number of trains carrying the passenger demand of the station in the corresponding waiting time slot, so that the number of trains arriving at and stopping at the station in the waiting time slot on a specific line and in the direction of travel is not less than the required number of trains corresponding to the station in the waiting time slot.

[0089] Therefore, by implementing scheduling optimization, the distribution of transport capacity can be effectively controlled, preventing passenger congestion or service level decline due to insufficient train stops, and improving the feasibility and passenger service quality of the urban rail transit scheduling plan obtained from scheduling optimization in actual operation.

[0090] In summary, the number of trains required at a station during a waiting time slot represents the passenger demand at that station during that waiting time slot. This number is calculated pre-calculated based on passenger demand in each direction during the waiting time slot and used as a parameter for scheduling optimization, ensuring that the operated trains meet the existing passenger demand.

[0091] For the set of train services obtained in step S120, operation scheduling will be performed on the included train services to ensure that they meet various legal constraints in actual operation, guaranteeing both rigid safety and flexible requirements in actual train operation. Based on this, the operation scheduling refers to imposing further constraints on the obtained set of train services. These constraints, on the one hand, further determine the decision variables required for scheduling, and on the other hand, reject the scheduling of train services that cannot meet the constraints.

[0092] For the set of train services obtained in step S120, operation scheduling is performed on each train service in the set to ensure that the included train services meet the preset legalization constraints during actual operation, thereby ensuring both the rigid safety requirements and flexible operation needs of the actual operation of the train services.

[0093] Based on this, operation scheduling refers to imposing further scheduling constraints on the existing set of train services. Under these constraints, on the one hand, the scheduling decision variables required for operation scheduling are clearly defined and determined, including but not limited to binary variables indicating whether trains (m,k) on the route lno and the direction dir have arrived at station i. On the other hand, trains or combinations of trains that cannot form a feasible solution under scheduling constraints are identified and their scheduling is rejected, thereby obtaining a feasible operation scheduling scheme that satisfies all constraints.

[0094] Therefore, in an exemplary embodiment, the operation scheduling of step S130 includes:

[0095] Apply a waiting time slice t and an arrival time to each train or combination of trains in the train set. The matching constraints are used to match the waiting time slice t with the train number (m,k) for station i in the time dimension. For example, this can be achieved through the following constraint pair:

[0096] Constraint Pair 1:

[0097]

[0098] in, t is the arrival time of train k departing from station m at station i, where t is the time slot number. It is the departure interval of any originating station on line lno; It is a constraint elimination constant used to control train arrival variables. A value of 0 forces this constraint to be disabled. It is the set of possible time slices for trains (m,k) on line lno and traveling in the direction dir to arrive at station i.

[0099] As a result, the passenger demand during the waiting time t is carried by the subsequent train (m,k) that arrives immediately.

[0100] Corresponding to the first constraint pair constructed above, a second constraint pair will also be constructed to ensure that passenger demand in the first waiting time slot at the station is not carried over to the next waiting time slot, as detailed below:

[0101]

[0102] in, It is a constant.

[0103] In another exemplary embodiment, the execution scheduling in step S130 includes:

[0104] Apply trajectory constraints to trains in the train set to ensure that the train arrives at the station and makes an actual stop within the corresponding waiting time slot along the corresponding route and direction of travel.

[0105] For example, the trajectory constraint is to constrain the trains that carry passenger demand during the waiting time slot to stop at the station on a specific route and in the direction of travel.

[0106] For train services that meet passenger demand, the corresponding operating trajectory is constrained to ensure that the train actually stops at the station.

[0107] It should be understood that trains carrying passenger demand must actually stop at their corresponding stations. Therefore, it is necessary to impose operational trajectory constraints on the candidate scheduling framework to ensure that all trains assigned to carry passenger demand at stations have executable stopping arrangements in actual scheduling.

[0108] For example, constructing binary variables By implementing the operational trajectory constraints, the binary variable (m,k) of the train number in the train number set is assigned a value of 1 at station i for subsequent scheduling.

[0109] For line lno, train number (m,k) traveling in the direction dir arrives at station i at all possible time slots, i.e., time slot numbers. Get the corresponding train arrival station variable At this point, a uniqueness constraint will be applied based on the train arrival variables corresponding to all possible time slices, and the actual stop of the train at the current station will also be constrained.

[0110] Furthermore, this can be achieved through the following constraints:

[0111]

[0112] Among them, by analyzing the train (m,k) arriving at station i at time slice t... Perform summation on the corresponding Assigning a value of 1 fulfills the uniqueness constraint, and through... The value of 1 constrains the actual stop of the train (m,k) at station i.

[0113] This effectively prevents situations where trains are logically allocated passenger capacity but their routes do not actually stop at the stations. It achieves physical consistency between train service capacity and passenger flow distribution in scheduling optimization, effectively avoiding situations where capacity is misallocated and passenger flow cannot be fulfilled due to a lack of scheduling constraints.

[0114] The implementation of the method in this application is illustrated below with an exemplary train operation scheduling example. In this example, the implementation of the method is illustrated using the train direction dir of train line lno at station i as an example. The implementations of other train lines and other directions at this station, as well as at other stations, are similar and will not be listed here.

[0115] Perform pre-calculation of passenger demand in the direction of travel dir for time slot t, and obtain the required number of trains for station i in the direction of travel dir and time slot t corresponding to passenger demand. .

[0116] Then determine the required number of trains. Construct a set of train services. This set of train services represents the combination of trains arriving at station i in the direction of travel dir at time slice t, and it represents the required number of trains to meet the quantified passenger demand. .

[0117] By constructing train arrival variables The train arrival time variable is determined by adapting it to the train arrival time and the required number of trains. The assignment of values ​​to the train arrival station variable The train numbers (m,k) with a value of 1 are used to form a set of train numbers.

[0118] At this point, for the set of train services, the feasibility will be further determined through the execution of operation scheduling, and the scheduling decision variables required for operation scheduling will be continuously determined in order to obtain a workable scheduling scheme.

[0119] This implementation method takes station-based passenger demand response as its starting point. By characterizing and constraining passenger demand at each station, it drives the generation of train operation and scheduling decisions. Based on this, the station-level demand response results are extended and coupled to the line and network levels, thereby achieving collaborative operation scheduling and overall scheduling optimization for the entire urban rail transit system.

[0120] In one exemplary embodiment, this application also provides a computer device including a memory, a processor, and a computer program stored in the memory, the processor executing the computer program to implement the steps of the method as described above.

[0121] In one exemplary embodiment, this application also provides a computer program product including a computer program that, when executed by a processor, implements the steps of the method as described above.

[0122] In one exemplary embodiment, this application also provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method as described above.

[0123] Furthermore, although the steps of the method in this application are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0124] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the appended claims.

Claims

1. A train operation scheduling method in response to passenger demand, characterized in that, The method includes: For each station of the target city's rail transit system, passenger demand is pre-calculated on consecutive time slices to obtain the required number of trains for each station in different directions of travel and on each time slice, corresponding to the passenger demand. Based on the required number of trains for each station in different travel directions and time slots, the consecutively divided time slots are designated as waiting time slots. For each travel direction of the station, a set of trains is determined within the corresponding waiting time slot to accommodate passenger demand. The steps for determining the set of trains include: establishing a train arrival variable for each passing train at the station based on the passing trains and the waiting time slot to which their arrival time at the station belongs; matching the waiting time slots with the passing trains based on the train arrival variable; assigning the passing trains to the waiting time slots to which their arrival time belongs; and selecting passing trains that match the required number of trains in each travel direction as the set of trains to accommodate passenger demand at the station within the corresponding waiting time slot. Based on the set of trains determined for each station in each direction of travel during each waiting time slot, the operation of the trains is scheduled. The scheduled trains run along the corresponding routes and directions of travel, and the arrival times at each station they pass through are matched with the waiting time slots required by the passengers.

2. The method according to claim 1, characterized in that, The number of trains required by the station for different directions of travel within the waiting time slot is used to characterize the passenger demand of the station for each direction of travel within the waiting time slot.

3. The method according to claim 1, characterized in that, For each station of the target urban rail transit system, passenger demand is pre-calculated in consecutive time slots to obtain the required number of trains for each station in different travel directions and in each time slot corresponding to the passenger demand, including: For the time slices that are continuously divided by time discretization, historical passenger flow data is aligned on the station and time slice to obtain the historical passenger flow data of each station on each of the continuously divided time slices. For each station's historical passenger flow data in each consecutive time segment, the passenger flow is split according to the direction of travel, and the historical passenger flow of each station in each time segment along different directions of travel is calculated. Based on the historical passenger flow of each station along the direction of travel in the consecutive time slots, predict the number of passengers in the corresponding time slot and direction of travel for each station, and convert it into the required number of trains.

4. The method according to claim 3, characterized in that, The process involves aligning historical passenger flow data across stations and time slices for each consecutively divided time slice after time discretization, thereby obtaining historical passenger flow data for each station in each consecutively divided time slice, including: Adapt to the time slice length applicable to the scheduling, and perform time discretization processing to obtain several continuously divided time slices; Based on the arrival time and station indicated by the historical passenger flow data, the historical passenger flow data is mapped and aligned to the corresponding time slots and stations to obtain the historical passenger flow data of each station in each time slot.

5. The method according to claim 3, characterized in that, The historical passenger flow data of each station in each consecutive time slot is divided into passenger flow segments according to the direction of travel, and the historical passenger flow of each station in each time slot along different directions of travel is calculated, including: The destination direction is determined based on the exit station indicated in the historical passenger flow data. For the historical passenger flow data of the station in each consecutive time segment, the historical passenger flow data is classified and statistically analyzed according to the determined driving direction to obtain the historical passenger flow of each station in each time segment along each driving direction.

6. The method according to claim 3, characterized in that, The process of predicting the number of passengers at each station in the corresponding time slot and in the direction of travel based on the historical passenger flow of each station in the continuous time slots along the travel direction, and converting this prediction into the required number of trains, includes: For each time slot continuously divided by the station, the historical passenger flow in each direction of travel is used to predict the number of passengers at the station in the corresponding direction of travel in that time slot based on spatiotemporal characteristics; The predicted number of passengers is converted into the required number of trains by using the number of passengers at the station along the corresponding direction of travel in the time slice and the carrying capacity of a single train. The carrying capacity of a single train is determined by the target passenger load factor of the target urban rail transit system and the rated passenger capacity of the train.

7. The method according to claim 1, characterized in that, The step of determining the set of trains to meet passenger demand for each train direction within the corresponding waiting time slot, based on the required number of trains at the station in different travel directions and at each time slot, further includes: Based on the required number of trains corresponding to a station in a consecutive time slot, a quantity constraint is imposed on the number of trains that carry the passenger demand of the station in the corresponding waiting time slot, so that the number of trains arriving at and stopping at the station in a specific line and direction of travel is not less than the required number of trains corresponding to the station in the waiting time slot.

8. The method according to claim 7, characterized in that, The method of scheduling train services based on the set of train services determined for each station and each direction of travel in each waiting time slot, wherein the scheduled train services run along the corresponding routes and directions of travel, and the arrival times at each station along the route are matched with the waiting time slots required by passengers, further includes: Apply trajectory constraints to the trains in the set of train numbers, so that the trains arrive at the station and make actual stops within the corresponding waiting time slots along the corresponding driving route and driving direction.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-8.

Images