CN114723240A - Railway passenger transport comprehensive transportation hub connection mode cooperative scheduling method and system - Google Patents

Abstract

The invention discloses a method and system for coordinated scheduling of connection modes of railway passenger transport integrated transportation hubs. The system includes a collection module, a statistics module and a scheduling module. The collection module collects the operation information of the transportation hub and the transfer information of arriving passengers; the statistics module Count the transfer information of all arriving passengers, and determine the initial sharing rate of each connection mode; the scheduling module, according to the operation information and the initial sharing rate of all connection methods, iteratively solves the double-layer programming model to make the total transfer of arriving passengers. The optimal scheduling parameter with the smallest multiplication time. By adopting the method and system for coordinated scheduling of connection modes of a railway passenger integrated transportation hub of the present invention, it is possible to integrate passengers' connection mode selection behavior, passenger transfer time, timetable and service rate of each connection mode, and realize coordinated scheduling of connection modes. , so as to optimize the allocation of hub connection resources, improve the operation efficiency of the hub, and provide passengers with safe, fast and comfortable transfer services.

Description

Coordinated scheduling method and system for connection mode of railway passenger integrated transportation hub

technical field

The invention relates to the technical field of management optimization of connection modes of transportation hubs, in particular to a method and system for coordinated scheduling of connection modes of railway passenger transport integrated transportation hubs.

Background technique

As the connection point between the modern high-speed rail network and urban transportation, the railway integrated passenger transport hub provides transportation services for urban economic development and citizen travel. It has a variety of internal transportation modes and various passenger flow groups. Evacuation of passenger flow to their respective destinations is the old railway passenger transport. The basic goal of the hub; and the ultimate goal of the railway hub in the new era is to continuously improve the quality of travel services in the hub, improve the quality of travel for the masses, and enhance travel satisfaction of passengers.

Affected by the arrival time of mainline railway trains, the passenger flow of railway arrivals often presents the characteristics of short-term high aggregation, which has a huge impact on various modes of transportation. When the connection methods of the hub cannot match the pulsed arrival passenger flow, passengers will be stranded and missed, which will reduce the transfer efficiency and endanger the safety of passengers in severe cases.

During the transfer process of railway arrival passengers in the hub, the change of time and space presents an unbalanced state. In the hub, there are often queues and crowds of passengers on the platforms of a certain connection method. However, in the platforms of other connection methods, There is a phenomenon of "car waiting for people". Different collecting and distributing capabilities in different directions or uneven distribution of passenger flow cause local congestion and waste of transportation resources, affecting the efficiency of passenger transfer. It is particularly important to coordinate the scheduling of the connection methods of the hub, optimize the departure interval of the connection methods, realize the rapid evacuation of the arriving passenger flow of the railway, and ensure the normal order of various services in the hub.

SUMMARY OF THE INVENTION

Aiming at the deficiencies of the prior art, the present invention proposes a method and system for coordinated scheduling of connection modes of a railway passenger integrated transportation hub, which can coordinately schedule each connection mode of the hub, optimize the departure interval of the connection modes, and realize the rapid evacuation of the arriving passenger flow on the railway. Ensure the normal order of various services in the hub. The specific technical solutions are as follows:

In the first aspect, a coordinated scheduling method for the connection mode of a railway passenger integrated transportation hub is provided, including:

Collect operation information of transportation hubs and transfer information of arriving passengers;

Calculate the transfer information of all arriving passengers, and determine the initial sharing rate of each connection method;

According to the operation information and the initial sharing rate of all connection modes, the optimal scheduling parameters corresponding to different connection modes are obtained by iteratively solving the two-layer programming model;

The upper layer model of the two-layer planning model is a connection time model with the minimum connection time as the objective function, and the lower layer model is a connection selection model.

With reference to the first aspect, in a first possible implementation manner of the first aspect, the iteratively solving the bi-level programming model includes:

Based on the constraints, according to the corresponding initial sharing rate, by solving the connection time model, the optimal scheduling parameters of different connection modes are obtained;

According to the optimized scheduling parameters of different connection methods, the selection probability of arriving passengers for different connection methods is calculated through the connection selection model;

Determine the sharing rate corresponding to different connection methods according to the corresponding selection probability;

After updating the sharing rate of different connection methods, and re-solving the connection time model, calculate the sharing rate corresponding to different connection methods through the connection selection model again;

This is repeated until optimal scheduling parameters corresponding to different connection modes are obtained.

In combination with the first implementable manner of the first aspect, in the second implementable manner of the first aspect, the constraints include: minimum and maximum departure intervals corresponding to buses and rails, and the order of departures of buses and rails. order, the departure time of the connection method is later than the arrival time of the railway train, and the taxi service intensity is optimized.

With reference to the first implementable manner of the first aspect, in a third implementable manner of the first aspect, the connection selection model includes:

Among them, P _in is the selection probability of passenger n for the ith connection mode, α _i is the constant term of connection mode i, β _ik is the calibration coefficient of different characteristic variables corresponding to connection mode i, and x _ikn is the choice of arriving passengers The characteristic variable of the hub connection mode _i , An is the set of each connection mode.

In combination with the third implementable manner of the first aspect, the fourth implementable manner of the first aspect includes:

The characteristic variables of passengers corresponding to different connection modes are collected, and the calibration coefficient β _ik of the characteristic variables corresponding to different connection modes is determined by the maximum likelihood estimation method.

With reference to the third achievable manner of the first aspect, in the fifth achievable manner of the first aspect, the characteristic variables include: the passenger's gender, age, occupation, monthly income, travel distance, travel purpose, and connection time.

In combination with the first achievable manner of the first aspect, in the sixth achievable manner of the first aspect, the sharing rates corresponding to the different connection manners are obtained by performing an aggregate analysis on the selection probabilities of the different connection manners.

With reference to the first aspect, in a seventh implementable manner of the first aspect, the connection time model includes a rail connection time model, a bus connection time model, a taxi connection time model, and a private car connection time model at least one of the.

In combination with the seventh achievable manner of the first aspect, in the eighth achievable manner of the first aspect, in the rail connection time model and the bus connection time model, the probability distribution function obeyed by the passenger walking time is: :

Among them, α, η, γ are distribution parameters.

With reference to the eighth implementation manner of the first aspect, in a ninth implementation manner of the first aspect, the distribution parameters are calibrated by performing maximum likelihood estimation on all the collected passenger transfer information.

In the second aspect, a coordinated scheduling system for the connection mode of a railway passenger integrated transportation hub is provided, including:

The collection module is configured to collect the operation information of the transportation hub and the transfer information of arriving passengers;

Statistics module, configured to count the transfer information of all arriving passengers, and determine the initial sharing rate of each connection mode;

a scheduling module, configured to obtain optimal scheduling parameters corresponding to different connection modes by iteratively solving the two-layer programming model according to the operation information and the initial sharing rate of different connection modes;

The upper layer model of the two-layer planning model is a connection time model with the minimum connection time as the objective function, and the lower layer model is a connection selection model.

With reference to the second aspect, in a first implementable manner of the second aspect, the acquisition module includes:

The retrieval unit is configured to retrieve the operation information of the transportation hub from the railway passenger transportation hub management system;

A positioning unit, configured to locate the movement trajectories of all passengers;

The generating unit is configured to determine the connection method and connection walking time selected by each passenger according to the movement track of each passenger, and generate transfer information of arriving passengers according to the connection method and connection walking time.

With reference to the second aspect, in a second implementation manner of the second aspect, the scheduling module includes:

The optimization solving unit is configured to obtain optimal scheduling parameters of different connection modes by solving the connection time model based on the constraint conditions and the corresponding initial sharing rate;

The selection probability calculation unit is configured to calculate the selection probability of passengers for different connection methods through the connection selection model according to the optimized scheduling parameters of different connection methods;

The sharing rate calculation unit is configured to determine the optimized sharing rate of different connection methods according to the corresponding selection probability;

The optimization solving unit, the selection probability calculating unit and the sharing rate calculating unit successively repeatedly calculate the optimal scheduling parameters, the selection probability and the sharing rate, until the optimal scheduling parameters corresponding to different connection modes are obtained.

In combination with the second achievable manner of the second aspect, in the third achievable manner of the second aspect, the constraints on the configuration of the optimal solution unit include: minimum and maximum departure intervals corresponding to buses and tracks, and . The order of rail departures, the connection mode departure time is later than the railway train arrival time, and the taxi service intensity is optimized.

With reference to the second implementable manner of the second aspect, in a fourth implementable manner of the second aspect, the connection selection model configured by the selection probability calculation unit includes:

Among them, P _in is the selection probability of passenger n for the ith connection mode, α _i is the constant term of connection mode i, β _ik is the calibration coefficient of different characteristic variables corresponding to connection mode i, and x _ikn is the choice of arriving passengers The characteristic variable of the hub connection mode _i , An is the set of each connection mode.

In combination with the fourth achievable manner of the second aspect, the fifth achievable manner of the second aspect further includes a calibration parameter determination module, where the calibration parameter determination module is configured to collect characteristic variables of passengers corresponding to different connection methods , and the calibration coefficient β _ik of various characteristic variables corresponding to different connection modes is determined by the maximum likelihood estimation method.

With reference to the fourth implementable manner of the second aspect, in the sixth implementable manner of the second aspect, the characteristic variables include: the passenger's gender, age, occupation, monthly income, travel distance, travel purpose, and connection time.

In combination with the second achievable manner of the second aspect, in the seventh achievable manner of the second aspect, the sharing rate calculation unit obtains different connections by performing aggregate analysis on the selection probabilities of different connection methods. share rate corresponding to the method.

With reference to the second aspect, in an eighth implementation manner of the second aspect, the connection time model includes a rail connection time model, a bus connection time model, a taxi connection time model, and a private car connection time model at least one of the.

In combination with the eighth implementable manner of the second aspect, in the ninth implementable manner of the second aspect, the probability distribution function obeyed by the passenger walking time in the rail connection time model and the bus connection time model is:

Among them, α, η, γ are distribution parameters.

In combination with the ninth implementable manner of the second aspect, in the tenth implementable manner of the second aspect, a distribution parameter determination module is further included, and the distribution parameter determination module is configured to perform an operation on all the collected passenger transfer information. The maximum likelihood estimate scales the distribution parameters.

Beneficial effects: By adopting the method and system for coordinated scheduling of connection modes of railway passenger transport integrated transportation hubs of the present invention, it is possible to integrate passenger connection mode selection behavior, passenger transfer time, timetable and service rate of each connection mode, and realize the realization of connection modes. Coordinate scheduling, thereby optimizing the allocation of hub connection resources, improving the operation efficiency of the hub, and providing passengers with safe, fast and comfortable transfer services.

Description of drawings

In order to describe the specific embodiments of the present invention more clearly, the accompanying drawings required for the specific embodiments will be briefly introduced below. In all the drawings, elements or sections are not necessarily drawn to actual scale.

FIG. 1 is a flowchart of a method for coordinated scheduling of a connection mode of a railway passenger integrated transportation hub provided by an embodiment of the present invention;

2 is a flowchart of iteratively solving a two-level programming model provided by an embodiment of the present invention;

FIG. 3 is a system block diagram of a coordinated scheduling system for a connection mode of a railway passenger integrated transportation hub provided by an embodiment of the present invention;

FIG. 4 is a system block diagram of a collection module of a coordinated scheduling system for a connection mode of a railway passenger integrated transportation hub provided by an embodiment of the present invention;

FIG. 5 is a system block diagram of a dispatching module of a coordinated dispatching system for a railway passenger transport integrated transportation hub connection mode provided by an embodiment of the present invention.

Detailed ways

Embodiments of the technical solutions of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only used to more clearly illustrate the technical solutions of the present invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.

As shown in Figure 1, the flow chart of the coordinated scheduling method for the connection mode of the railway passenger integrated transportation hub, the scheduling method includes:

Step 1. Collect the operation information of the transportation hub and the transfer information of arriving passengers;

Step 2. Count the transfer information of all arriving passengers, and determine the initial sharing rate of each connection method;

Step 3. According to the operation information and the initial sharing rate of all connection modes, by iteratively solving the two-layer programming model, the optimal scheduling parameters corresponding to different connection modes are obtained;

The upper layer model of the two-layer planning model is a connection time model with the minimum connection time as the objective function, and the lower layer model is a connection selection model.

Specifically, by establishing a passenger connection selection model and a connection time model, the proportion of arriving passengers who choose different connection methods and the transfer time of various connection methods can be calculated. And the connection selection model is used as the lower model, and the connection time model with the minimum connection time as the objective function is used as the double-layer planning method of the upper model. The minimum optimal scheduling parameters can realize the optimal allocation of hub connection resources, improve the operation efficiency of the hub, and provide passengers with safe, fast and comfortable transfer services.

The scheduling method according to the embodiment of the present invention will be described in detail below with reference to FIG. 1 and FIG. 2 .

In step 1, the operation information of the transportation hub can be collected directly through the railway passenger transportation hub management system, and the operation information includes the infrastructure layout information of the transportation hub, the timetable of arriving trains, and the number of arriving passengers for each train. The existing railway passenger transport hub management system will automatically collect and store this information, so the information can be directly collected through the railway passenger transport hub management system during coordinated scheduling.

For the transfer information of arriving passengers, according to the infrastructure layout information of the transportation hub, the image information of the passengers' transfer can be collected through the cameras arranged at the corresponding positions, and the number of passengers corresponding to different connection methods can be determined through the collected image information. and the connecting walking time to generate transfer information for arriving passengers.

For example, the image at the exit can be collected by a camera installed at the exit of the railway station, and image recognition technology can be used to identify the identity of each outbound passenger and determine the departure time of each passenger. After that, the images at the connection positions are collected by cameras set at different connection positions. For example, the images at the bus station can be collected by the cameras at the bus station, and the identity information and the identity information of each passenger at the bus station can be identified by image recognition technology. The arrival time at the bus station is used to determine the connection method and connection walking time selected by the passenger, and the transfer information of the arriving passenger is generated according to the corresponding connection method and connection walking time.

It should be understood that the embodiment of the present invention only uses image recognition technology to determine the transfer information of arriving passengers, but the present invention is not limited to this, and other methods can also be used to determine the transfer information of arriving passengers, such as mobile phone positioning technology.

In step 2, the transfer information of all outbound and arriving passengers can be counted to determine the number of passengers corresponding to each connection method, and the initial number of passengers corresponding to each connection method can be calculated based on the collected number of arriving passengers share rate.

In step 3, the iterative solution of the two-layer programming model includes:

Step 3-1, based on the constraints, according to the corresponding initial sharing rate, by solving the connection time model, to obtain the optimal scheduling parameters of different connection modes;

Step 3-2, according to the optimized scheduling parameters of different connection methods, calculate the selection probability of passengers for different connection methods through the connection selection model;

Step 3-3: Determine the sharing rate corresponding to different connection modes according to the corresponding selection probability;

Step 3-4, update the sharing rate of different connection methods, re-solve the connection time model, and determine the sharing rate corresponding to different connection methods;

Repeating this, if the optimization range of the connection time in the current and next two iterations is less than the set threshold, it is considered that the optimal scheduling parameters corresponding to different connection modes are obtained.

Specifically, first of all, the initial sharing rate corresponding to each connection method statistically determined in step 2 can be input into the connection time model, and based on the set constraints, the connection time with the minimum connection time as the objective function The model is solved to obtain the optimal scheduling parameters for different connection methods.

minT=min(T _G +T _B +T _C +T _S )

Then, the optimized scheduling parameters are input into the connection selection model, and the selection probabilities of passengers for various connection methods after the scheduling parameters of different connection methods are optimized according to the optimal scheduling parameters are calculated through the connection selection model.

After that, determine the sharing rate of different connection methods according to the selection probabilities corresponding to various connection methods, and update the sharing rate of the input connection time model accordingly, and repeat the above steps 3-1 to 3-4 until each connection method is obtained. The optimal scheduling parameters corresponding to the switching mode.

In this embodiment, optionally, the connection time model is composed of time models corresponding to four connection modes, which are the rail connection time model, the bus connection time model, the taxi connection time model, and the private car connection time model. Distortion time model.

It should be understood that the embodiment of the present invention is only exemplified by four connection modes, but the present invention is not limited thereto, and the connection time model may be determined according to the connection modes actually set by the transportation hub.

Among them, the track connection time model T _G includes:

为赶上就近接驳轨道列车的接驳时间，

为赶不上就近接驳轨道列车的接驳时间，

为就近轨道接驳列车发车时间，

为铁路列车到站时间，δ_G为轨道交通分担率，Q⁽ⁱ⁾为第i列铁路列车的到站旅客数量，f(t)为旅客步行时间所服从的概率分布，

为轨道接驳列车发车时间。in,

In order to catch up with the connection time of the nearest rail train,

In order to catch up with the connection time of the nearest rail train,

For the departure time of the nearest rail connection train,

is the arrival time of the railway train, _δG is the rail traffic sharing rate, Q ⁽ⁱ⁾ is the number of passengers arriving at the station of the i-th railway train, f(t) is the probability distribution obeyed by the walking time of passengers,

It is the departure time of the rail connection train.

The bus connection time model T _B includes:

为赶上就近接驳公交车的接驳时间，

为赶不上就近接驳公交车的接驳时间，

为就近接驳公交发车时间，δ_B为公交车分担率，

为接驳公交发车时间，f(t)为旅客步行时间所服从的随机概率分布，为了更好刻画接驳工具满载以及乘客错过就近接驳工具等待下一趟接驳工具情况，将通常服从正态分布的旅客走行时间分布尾数增大，并调整分布参数使其服从正偏态分布，再利用韦布尔分布表示正偏态分布的情况。in,

In order to catch up with the connecting time of the nearest bus,

In order to be unable to catch up with the connecting time of the nearest bus,

is the departure time of the nearest shuttle bus, _δB is the bus sharing rate,

For the departure time of the shuttle bus, f(t) is the random probability distribution obeyed by the passenger's walking time. In order to better describe the situation that the shuttle is fully loaded and the passengers miss the nearest shuttle and wait for the next shuttle, it will usually obey the normal probability distribution. The mantissa of the passenger travel time distribution of the state distribution increases, and the distribution parameters are adjusted to conform to the positively skewed distribution, and then the Weibull distribution is used to represent the situation of the positively skewed distribution.

其中，α、η、γ为分布参数，可以通过对采集到的换乘信息进行最大似然估计标定所述分布参数。In this embodiment, optionally,

Among them, α, η, and γ are distribution parameters, and the distribution parameters can be calibrated by performing maximum likelihood estimation on the collected transfer information.

The taxi pick-up time model T _C includes:

Among them, W _s is the stay time of passengers at the taxi platform, μ is the taxi service rate, λ is the passenger arrival rate, δ _C is the taxi sharing rate, and t _RC is the walking time required to transfer to a taxi. The taxi service rate can be set manually, and the passenger arrival rate can be based on the historical transfer information, and the relationship between the passenger arrival rate and the number of transfer passengers can be obtained by means of cubic curve fitting. The number of arriving passengers determines the passenger arrival rate.

The private car connection time model T _S includes:

Among them, t _RS is the time required to walk to the private car parking lot, and δ _S is the sharing rate of private cars. The time required for a passenger to walk to a private car parking lot can be determined through the collected transfer information.

In this embodiment, optionally, the constraint conditions include: the minimum and maximum departure intervals corresponding to buses and rail trains, the departure sequence of buses and rail trains, and the departure time of the connecting means later than that of the rail trains. the arrival time of the station, and the optimization range of the taxi service intensity. You can specify the optimization range of taxi service intensity, and then calculate the optimized service intensity and taxi service rate according to the current service intensity and the optimized passenger arrival rate.

In this embodiment, optionally, the connection selection model includes:

Among them, P _in is the selection probability of passenger n for the ith connection mode, α _i is the constant term of connection mode i, β _ik is the calibration coefficient of different characteristic variables corresponding to connection mode i, and x _ikn is the choice of arriving passengers The characteristic variables of the hub connection mode _i , An is the set of each connection mode, e in the connection selection model represents a constant, and z is the number of characteristic variables.

In this embodiment, optionally, the characteristic variables include: gender, age, occupation, monthly income, travel distance, travel purpose, and connection time of the passenger. Questionnaires can be issued to passengers through railway passenger transport platforms, such as ticketing platforms, and the corresponding information about these characteristic variables can be collected from passengers by means of questionnaires.

In this embodiment, optionally, the characteristic variables of passengers corresponding to different connection modes can be collected, and the maximum likelihood estimation method is used to determine the calibration coefficient β _ik of various characteristic variables corresponding to different connection modes, so as to construct the The log-likelihood function of the connected model is:

The first derivative of the log-likelihood function is obtained and the derivative is set to 0, and the maximum likelihood estimate of each calibration coefficient is obtained.

In this embodiment, optionally, by calculating the probability set of the selection probabilities of different connection modes, the selection probabilities of all passengers for a certain connection mode are added up and the average value is obtained to obtain the corresponding connection mode. share rate.

As shown in Figure 3, the system block diagram of the coordinated dispatching system for the connection mode of the railway passenger integrated transportation hub, the dispatching system includes:

The collection module is configured to collect the operation information of the transportation hub and the transfer information of arriving passengers;

Statistics module, configured to count the transfer information of all arriving passengers, and determine the initial sharing rate of each connection mode;

a scheduling module, configured to obtain optimal scheduling parameters corresponding to different connection modes by iteratively solving the two-layer programming model according to the operation information and the initial sharing rate of different connection modes;

The upper layer model of the two-layer planning model is a connection time model with the minimum connection time as the objective function, and the lower layer model is a connection selection model.

Specifically, the dispatching system consists of a collection module, a statistics module and a dispatching module, wherein the collection module can collect the operation information of the transportation hub and the transfer information of arriving passengers.

The statistics module can count the number of passengers who choose different connection methods according to the transfer information of each arriving passenger collected by the collection module, and can calculate the initial share of each connection method in combination with the number of arriving passengers on the train. Rate.

The scheduling module can calculate the proportion of arriving passengers choosing different connection methods and the transfer time of various connection methods by establishing passenger connection selection model and connection time model. And the connection selection model is used as the lower model, and the connection time model with the minimum connection time as the objective function is used as the double-layer planning method of the upper model. The minimum optimal scheduling parameters can realize the optimal allocation of hub connection resources, improve the operation efficiency of the hub, and provide passengers with safe, fast and comfortable transfer services.

The scheduling system of the embodiment of the present invention will be described in detail below with reference to FIG. 3 , FIG. 4 , and FIG. 5 .

In this embodiment, optionally, the collection module includes:

The retrieval unit is configured to retrieve the operation information of the transportation hub from the railway passenger transportation hub management system;

A positioning unit, configured to locate the movement trajectories of all passengers;

The generating unit is configured to determine the connection mode and connection walking time selected by all passengers according to the positioning result of the positioning unit.

The acquisition module consists of a retrieval unit, a positioning unit and a generation unit. The retrieval unit is connected to the railway passenger transport hub management system in communication, and tools such as web crawlers can be used to automatically obtain operation information from the railway passenger transport hub management system. Infrastructure layout information, arriving train schedules, and the number of arriving passengers per train.

The positioning unit can collect images of various positions through cameras arranged in the transportation hub, and use image recognition and positioning technology to determine the movement trajectory of each arriving passenger according to the collected images.

Because the basic setting layout information retrieved by the retrieval unit includes the location coordinates of the connection platforms of various connection methods and the location coordinates of the railway train exits, the generation unit can pass the movement trajectory of each arriving passenger. And the infrastructure layout information of the transportation hub retrieved by the retrieval unit, determine the connection method and connection walking time selected by the arriving passengers, and generate the corresponding transfer information according to the connection method and the connection walking time.

For example, the generating unit may determine the position coordinates of the train exit and the position coordinates of the platforms of different connection methods, such as the position coordinates of the bus station, according to the infrastructure layout information. The generating unit can match the position coordinates of the exit of the train and the position coordinates of the platforms of different connection methods with the movement trajectories of the arriving passengers, so as to determine the connection method selected by the arriving passengers and the exit of the arriving passengers. time and the arrival time of the connecting platform, the generating unit can calculate the connecting and walking time of the arriving passengers according to the exit time and the arrival time.

In this embodiment, optionally, the scheduling module includes:

The optimization solving unit is configured to obtain optimal scheduling parameters of different connection modes by solving the connection time model based on the constraint conditions and the corresponding initial sharing rate;

The selection probability calculation unit is configured to calculate the selection probability of passengers for different connection methods through the connection selection model according to the optimized scheduling parameters of different connection methods;

The sharing rate calculation unit is configured to determine the optimized sharing rate for different connection methods according to the corresponding selection probability;

The optimization solving unit, the selection probability calculating unit and the sharing rate calculating unit successively repeatedly calculate the optimal scheduling parameters, the selection probability and the sharing rate, until the optimal scheduling parameters corresponding to different connection modes are obtained.

Specifically, the optimization solving unit can input the initial sharing rate corresponding to different connection methods calculated by the statistical module into the connection time model, and based on the set constraints, through the connection with the minimum connection time as the objective function The time model is solved to obtain the optimal scheduling parameters for different connection methods.

The selection probability calculation unit can input the optimized scheduling parameters obtained by the optimization solving unit into the connection selection model. Choose a probability.

The sharing rate calculation unit may calculate the sharing rate of different connection modes according to the selection probabilities corresponding to various connection modes calculated by the selection probability calculation unit.

The optimization solving unit can update the input sharing rate according to the sharing rate calculated by the sharing rate, and optimize and solve the connection time model again according to the updated sharing rate to obtain new optimal scheduling parameters. The selection probability calculation unit then calculates the new selection probability of passengers for various connection modes according to the new optimized scheduling parameters. The sharing rate calculation unit finally calculates the sharing rate of different connection modes again according to the new selection probability, and updates the sharing rate input by the optimization solving unit. This is repeated until the optimization solution unit determines that the connection time optimization range in the two iterations before and after is smaller than a certain threshold, then it is considered that the optimal scheduling parameters corresponding to different connection methods are obtained.

In this embodiment, optionally, the connection time model adopted by the optimization solving unit is composed of time models corresponding to 4 connection modes, namely, the rail connection time model, the bus connection time model, and the taxi connection time model. Time model and private car connection time model.

It should be understood that the embodiment of the present invention is only exemplified by four connection modes, but the present invention is not limited thereto, and the connection time model may be determined according to the connection modes actually set by the transportation hub.

Among them, the track connection time model T _G includes:

为赶上就近接驳轨道列车的接驳时间，

为赶不上就近接驳轨道列车的接驳时间，

为就近轨道接驳列车发车时间，

为铁路列车到站时间，δ_G为轨道交通分担率，Q⁽ⁱ⁾为第i列铁路列车的到站旅客数量，f(t)为旅客步行时间所服从的概率分布，

为轨道接驳列车发车时间。in,

In order to catch up with the connection time of the nearest rail train,

In order to catch up with the connection time of the nearest rail train,

For the departure time of the nearest rail connection train,

is the arrival time of the railway train, _δG is the rail traffic sharing rate, Q ⁽ⁱ⁾ is the number of passengers arriving at the station of the i-th railway train, f(t) is the probability distribution obeyed by the walking time of passengers,

It is the departure time of the rail connection train.

The bus connection time model T _B includes:

为赶上就近接驳公交车的接驳时间，

为赶不上就近接驳公交车的接驳时间，

为就近接驳公交发车时间，δ_B为公交车分担率，

为接驳公交发车时间，f(t)为旅客步行时间所服从的随机概率分布，为了更好刻画接驳工具满载以及乘客错过就近接驳工具等待下一趟接驳工具情况，将通常服从正态分布的旅客走行时间分布尾数增大，并调整分布参数使其服从正偏态分布，再利用韦布尔分布表示正偏态分布的情况。in,

In order to catch up with the connecting time of the nearest bus,

In order to be unable to catch up with the connecting time of the nearest bus,

is the departure time of the nearest shuttle bus, _δB is the bus sharing rate,

For the departure time of the shuttle bus, f(t) is the random probability distribution obeyed by the passenger's walking time. In order to better describe the situation that the shuttle is fully loaded and the passengers miss the nearest shuttle and wait for the next shuttle, it will usually obey the normal probability distribution. The mantissa of the passenger travel time distribution of the state distribution increases, and the distribution parameters are adjusted to conform to the positively skewed distribution, and then the Weibull distribution is used to represent the situation of the positively skewed distribution.

In this embodiment, optionally, in the track connection time model and the bus connection time model, the probability distribution function obeyed by the passenger's walking time is:

其中，α、η、γ为分布参数。

Among them, α, η, γ are distribution parameters.

The dispatching system further includes a distribution parameter determination module, which can calibrate the distribution parameters by performing maximum likelihood estimation on the collected transfer information of all arriving passengers. Specifically, the distribution parameter determination module can substitute the transfer travel time sample data of arriving passengers in the collected transfer information into the probability distribution function, and obtain the likelihood function by summing the logarithms, and then calculating the distribution function for the likelihood function. The partial derivatives of α, η and γ are obtained to obtain the likelihood equation and solved, and the maximum likelihood estimation of α, η and γ is obtained.

The taxi pick-up time model T _C includes:

Among them, W _s is the stay time of passengers at the taxi platform, μ is the taxi service rate, λ is the passenger arrival rate, δ _C is the taxi sharing rate, and t _RC is the walking time required to transfer to a taxi. Taxi service rate can be set manually, passenger arrival rate

The private car connection time model T _S includes:

Among them, t _RS is the time required to walk to the private car parking lot, and δ _S is the sharing rate of private cars. The time required for a passenger to walk to a private car parking lot can be determined through the collected transfer information.

In this embodiment, optionally, the constraints on the configuration of the optimization solving unit include: the minimum and maximum departure intervals corresponding to buses and rails, the sequence of departures of buses and rails, and the departure time of the connection mode is later than that of the railway. Train arrival time, taxi service intensity optimization range.

In this embodiment, optionally, the connection selection model configured by the selection probability calculation unit includes:

Among them, P _in is the selection probability of passenger n for the ith connection mode, α _i is the constant term of connection mode i, β _ik is the calibration coefficient of different characteristic variables corresponding to connection mode i, and x _ikn is the choice of arriving passengers The characteristic variable of the hub connection mode _i , An is the set of connection modes.

In this embodiment, optionally, a calibration parameter determination module is further included, and the calibration parameter determination module is configured to collect characteristic variables of passengers corresponding to different connection modes, and determine the parameters corresponding to different connection modes through a maximum likelihood estimation method. Calibration coefficients β _ik for various characteristic variables.

The coordination system also includes a calibration parameter determination module. The calibration parameter determination module can collect the characteristic variable information of the arriving passengers through the collection module, and use the maximum likelihood estimation method to determine the corresponding connection methods according to the characteristic variable information of each passenger. Calibration coefficients for various characteristic variables.

In this embodiment, the characteristic variables extracted by the calibration parameter determination module include the passenger's gender, age, occupation, monthly income, travel distance, travel purpose, and connection time. The collection module can issue questionnaires to passengers taking railway trains through the railway passenger transport platform, and obtain the information of these characteristic variables by means of questionnaires.

In this embodiment, optionally, the sharing rate calculation unit obtains the sharing rates corresponding to different connection methods by performing aggregate analysis on the selection probabilities of different connection methods.

The above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that the foregoing embodiments can still be used for The recorded technical solutions are modified, or some or all of the technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and should be included in the The invention is within the scope of the claims and description.

Claims (21)

1. A method for cooperatively dispatching a railway passenger transport integrated transportation hub in a connection mode is characterized by comprising the following steps:

collecting operation information of a traffic hub and transfer information of passengers arriving at a station;

counting transfer information of all arriving passengers, and determining the initial sharing rate of each connection mode;

according to the operation information and the initial sharing rate of all the connection modes, carrying out iterative solution on the double-layer planning model to obtain optimal scheduling parameters corresponding to different connection modes;

the upper layer model of the double-layer planning model is a connection time model taking the minimum connection time as a target function, and the lower layer model is a connection selection model.

2. The method for joint connection type collaborative scheduling of the railway passenger transport integrated transportation hub according to claim 1, wherein the iterative solution through the double-layer planning model comprises:

based on constraint conditions, solving the connection time model according to corresponding initial sharing rate to obtain optimized scheduling parameters of different connection modes;

according to the optimized scheduling parameters of different docking modes, calculating the selection probability of the arriving passengers for different docking modes through a docking selection model;

determining the sharing rate corresponding to different connection modes according to the corresponding selection probability;

updating the sharing rates of different connection modes, solving the connection time model again, and calculating the corresponding sharing rates of the different connection modes through the connection selection model again;

and repeating the steps until the optimal scheduling parameters corresponding to different connection modes are obtained.

3. The method for cooperatively dispatching the integrated transportation hub connection mode for passenger train according to claim 2, wherein the constraint condition comprises: the minimum departure interval and the maximum departure interval corresponding to the bus and the rail train, the departure sequence of the bus and the rail train, the departure time of the connection tool is later than the arrival time of the rail train, and the service intensity of the taxi is optimized.

4. The method for joint connection type collaborative scheduling of the railway passenger transport integrated transportation hub according to claim 2, wherein the connection selection model comprises:

wherein, P_inFor the selection probability, alpha, of the inbound passenger n for the ith mode of docking_iConstant term, β, for the docking mode i_ikCalibration coefficients, x, for different characteristic variables corresponding to the docking mode i_iknSelecting characteristic variable of hub connection mode i for passengers arriving at station, A_nIs the set of each connection mode.

5. The method for cooperatively dispatching the connection mode of the railway passenger transport integrated transportation hub according to claim 4, comprising the following steps: collecting characteristic variables of passengers corresponding to different connection modes, and determining calibration coefficients beta of the characteristic variables corresponding to the different connection modes by adopting a maximum likelihood estimation method_ik。

6. The method for the joint connection type collaborative scheduling of the railway passenger transportation integrated transportation hub according to claim 4, wherein the characteristic variables comprise: gender, age, occupation, monthly income, distance traveled, purpose of travel, and docking time of the arriving passenger.

7. The method for the connection mode cooperative scheduling of the railway passenger transport integrated transportation hub according to claim 2, wherein the sharing rate corresponding to different connection modes is obtained by performing centralized analysis on the selection probabilities of the different connection modes.

8. The method for collaborative scheduling of junction connection modes of the railway passenger transport integrated transportation junction according to claim 1, wherein the junction time model comprises at least one of a rail junction time model, a bus junction time model, a taxi junction time model and a private car junction time model.

9. The method for cooperatively dispatching the connection mode of the railway passenger transport integrated transportation hub according to claim 8, wherein in the rail connection time model and the bus connection time model, the probability distribution function obeyed by the walking time of the passenger is as follows:

wherein, alpha, eta and gamma are distribution parameters.

10. The method according to claim 9, wherein the distribution parameters are calibrated by performing maximum likelihood estimation on the collected passenger transfer information.

11. A railway passenger transport comprehensive transportation hub connection mode cooperative dispatching system is characterized by comprising:

the acquisition module is configured to acquire operation information of a transportation junction and transfer information of passengers arriving at the station;

the statistical module is configured to count transfer information of all arriving passengers and determine the initial sharing rate of each connection mode;

the scheduling module is configured to obtain optimal scheduling parameters corresponding to different connection modes by performing iterative solution on the double-layer planning model according to the operation information and the initial sharing rates of the different connection modes;

the upper layer model of the double-layer planning model is a connection time model taking the minimum connection time as a target function, and the lower layer model is a connection selection model.

12. The integrated transportation hub connection type cooperative dispatching system for passenger trains according to claim 11, wherein the collecting module comprises:

the calling unit is configured to call the operation information of the transportation junction from the railway passenger transportation junction management system;

the positioning unit is configured to position the moving tracks of all passengers;

and the generating unit is configured to determine the connection mode and the connection walking time selected by each passenger according to the moving track of each passenger, and generate transfer information of the passengers arriving at the station according to the connection mode and the connection walking time.

13. The integrated transportation hub connection type cooperative dispatching system for passenger trains according to claim 11, wherein the dispatching module comprises:

the optimization solving unit is configured to solve the connection time model according to the corresponding initial sharing rate based on the constraint conditions to obtain the optimized scheduling parameters of different connection modes;

the selection probability calculation unit is configured to calculate the selection probability of the arriving passenger for different connection modes through the connection selection model according to the optimized scheduling parameters of the different connection modes;

the sharing rate calculation unit is configured to determine the sharing rate after optimization of different connection modes according to the corresponding selection probability;

and the optimization solving unit, the selection probability calculating unit and the sharing rate calculating unit sequentially and repeatedly calculate the optimized scheduling parameters, the selection probability and the sharing rate until the optimal scheduling parameters corresponding to different connection modes are obtained.

14. The system for joint connection type cooperative dispatching of the integrated transportation hub for passenger train according to claim 13, wherein the constraint conditions configured by the optimization solution unit comprise: the minimum departure interval and the maximum departure interval corresponding to the bus and the rail train, the departure sequence of the bus and the rail train, the departure time of the connection tool is later than the arrival time of the rail train, and the service intensity of the taxi is optimized.

15. The system for collaborative dispatching of connection modes of integrated transportation hubs for passenger trains according to claim 13, wherein the connection selection model configured by the selection probability calculation unit comprises:

wherein, P_inFor the probability of selection of passenger n for the ith mode of docking, α_iConstant term, β, for the docking mode i_ikCalibration coefficients, x, for different characteristic variables corresponding to the docking mode i_iknSelecting characteristic variable of hub connection mode i for arriving passengers, A_nIs the set of each connection mode.

16. The transportation junction connection mode cooperative scheduling system of claim 15, further comprising a calibration parameter determination module, wherein the calibration parameter determination module is configured to collect characteristic variables of passengers corresponding to different connection modes, and determine the calibration coefficients β of the characteristic variables corresponding to different connection modes by using a maximum likelihood estimation method_ik。

17. The connection type cooperative dispatching system of the railway passenger transportation integrated transportation junction according to claim 15, wherein the characteristic variables comprise: gender, age, occupation, monthly income, distance traveled, purpose of travel, and docking time of the arriving passenger.

18. The connection mode cooperative scheduling system of the railway passenger transport integrated transportation hub according to claim 13, wherein the sharing rate calculating unit obtains the sharing rates corresponding to different connection modes by performing centralized analysis on the selection probabilities of the different connection modes.

19. The transportation junction docking mode collaborative scheduling system of claim 11, wherein the docking time model includes at least one of a track docking time model, a bus docking time model, a taxi docking time model, and a private car docking time model.

20. The transportation junction connection mode cooperative scheduling system of claim 19, wherein in the rail connection time model and the bus connection time model, the probability distribution function obeyed by the walking time of the arriving passenger is as follows:

wherein, alpha, eta and gamma are distribution parameters.

21. The integrated transportation hub docking mode coordinated scheduling system of passenger train according to claim 20, further comprising a distribution parameter determination module configured to calibrate said distribution parameter by performing maximum likelihood estimation on all collected passenger transfer information.

Images