Bus stop layout and stop control strategy integration optimization method and system based on proxy model

Abstract

The invention provides a bus stop layout and stop control strategy integration optimization method and system based on an agent model, and belongs to the technical field of urban traffic operation services. A bus stop layout model and a bus stop control model are established respectively; determining an objective function of a bus stop layout optimal stop control integration stochastic optimization problem, and constructing and iteratively updating an agent model to estimate and predict an objective function response value corresponding to an unsimulated decision variable; and fitting a simulated solution and a target function of the solution by using the agent model of Gaussian process regression to give a posteriori prediction of a target function response value of a solution which is not simulated yet, and guiding bus stop layout and a stop control strategy. According to the invention, passenger travel costs of different levels are integrated, and the ability of a bus stop layout scheme design result of a planning level to maintain bus service regularity in an operation level is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of urban traffic operation services, and in particular to an agent-based model-based bus stop layout and station control strategy integration optimization method and system. Background Art

[0002] Due to the complexity of the structure of the public transportation system itself and the randomness of the traffic environment, effective system modeling is an important means to understand and characterize the key elements of the public transportation system and their interactions. System modeling can provide in-depth insights into the operating mechanism of the public transportation system, especially in analyzing the association and dynamic relationship between elements. Specifically, the use of system modeling can help identify and characterize the key factors that affect public transportation operation, such as passengers' choice of boarding and alighting platforms, the composition of passengers' travel costs, and the intensity of station control. By modeling these elements, not only can their respective operating characteristics be clearly presented, but also the complex interactive relationship between the elements can be revealed, providing theoretical support for further optimization and regulation. Therefore, public transportation system modeling is of great significance in determining system design solutions and formulating control strategies, and provides a theoretical basis and guidance for building an efficient and reliable public transportation system.

[0003] Adaptive bus stop control is an important technical means to deal with the uncertainty caused by factors such as random traffic conditions and heterogeneous passenger demand. Adaptive bus stop control dynamically determines the bus stop time to improve the line's operating efficiency and service regularity. Adaptive control can respond to changing traffic conditions and known passenger demand in real time, thereby reducing vehicle stringing. Adaptive bus stop control technology relies on monitoring and analysis of line status and operating performance, and adjusts the stop time of the designed control point to ensure a more balanced interval between vehicles and avoid the occurrence or deterioration of stringing. Therefore, adaptive stop control not only improves the overall efficiency of the bus system, but also provides important support for realizing the intelligence and efficiency of the public transportation system.

[0004] The simulation-based optimization method with the help of surrogate models is a technology that uses modern computer simulation technology to establish an optimization method that can replace the actual public transportation system model. Traditional optimization methods have certain limitations when solving random optimization problems of public transportation that consider random scenarios in the operation stage. The challenge is that the dynamic, complex and interactive nature of urban public transportation systems makes it difficult for traditional optimization methods to obtain ideal solutions within limited computing power and computing time. Simulation-based optimization technology can repeatedly evaluate and optimize system performance in a simulation environment. However, directly using high-precision simulation models for simulation also consumes a lot of computing power, especially in integrated random optimization problems with multiple random scenarios and multiple decision variables. Summary of the invention

[0005] The object of the present invention is to provide a method and system for integrating optimization of bus stop layout and bus stop control strategy based on an agent model for determining the number and location of bus stops on a target bus route and bus stop control intensity variables, which can be used for the optimization design and operation regulation of urban public transportation systems, so as to solve at least one technical problem existing in the above-mentioned background technology.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for integrating and optimizing bus stop layout and station control strategy based on an agent model, comprising:

[0008] Based on the systematic analysis of the selection behavior characteristics of bus passengers on boarding and alighting bus stops and the adaptive bus stop control mechanism, a bus stop layout model and a bus stop control model are established respectively.

[0009] Based on the established bus stop layout model and bus stop control model, the objective function of the bus stop layout optimal stop control integrated stochastic optimization problem is determined;

[0010] Construct and iteratively update the proxy model to estimate and predict the objective function response value corresponding to the unsimulated decision variables, fit the Gaussian process regression proxy model to the simulated solution and its objective function to give a posterior prediction of the objective function response value of the solution that has not been simulated, and guide the layout of bus stops and station control strategies.

[0011] Furthermore, the establishment of a bus stop layout model includes:

[0012] The bus passengers' perception of the travel costs at different bus stops determines the division of passenger boarding demand at bus stops, as shown below:

[0013]

[0014] In the formula, λ n represents the passenger arrival rate at platform n (unit: person / minute); Λ(x) represents the passenger demand distribution function along the bus line; and They respectively represent the critical position in the forward direction and the critical position in the backward direction of the partition range of the passenger boarding demand at bus stop n;

[0015] The passenger travel cost structure takes into account the passenger walking cost, passenger waiting cost and passenger bus travel cost. Assuming that the travel cost felt by the passenger is directly proportional to the corresponding time, the travel cost of the passenger with (x, y) as the starting and ending point is represented by τ(x, y), and its calculation formula is as follows:

[0016] τ(x, y) = φ 步 ·τ 步 (x,y)+φ 等 ·τ 等 (x,y)+φ 车 ·τ 车 (x, y)

[0017] In the formula, φ 步 ,φ 等 and φ 车 They represent the passenger travel costs caused by the unit passenger walking time, waiting time and in-vehicle travel time (unit: ￥ / minute); τ 步 (x, y), τ 等 (x, y) and τ 车 (x, y) represent the walking time, waiting time and in-vehicle travel time of the passenger's bus trip with (x, y) as the starting and ending points respectively;

[0018] The bus operation state equations are a set of equations that represent the arrival time of buses at bus stops, the time waiting for passengers to board, and the time leaving the platform, as shown below:

[0019] a m，n =d m，n(前) +t m，n(前)

[0020]

[0021] d m，n =a m，n +s m，n +u m，n

[0022] In the formula, a m，n 、s m，n and d m，n They represent the arrival time of bus m at bus stop n, the time waiting for passengers to board the bus, and the time the bus leaves the platform; t m，n(前) represents the time taken by bus m to leave the previous stop of stop n and travel to stop n; β represents the average boarding rate of passengers; u m，n It represents the time when bus m is subject to station control at stop n.

[0023] Furthermore, establishing a bus station control model includes: determining the time when the bus is subject to station control at the stop according to the deviation between the time interval between the arrival of the bus at the platform and the departure time of the preceding bus and the driving plan.

[0024] Furthermore, the calculation of the time that bus m is subject to station control at stop n is as follows:

[0025]

[0026] In the formula, g n It represents the station control intensity set at the bus stop n; H represents the bus service interval of each bus stop in the bus driving plan.

[0027] Furthermore, based on the established bus stop layout model and bus stop control model, the objective function of the bus stop layout and bus stop control integrated stochastic optimization problem is given:

[0028]

[0029] Where p and g are the decision variables of the integrated stochastic optimization problem, representing the bus stop layout plan and the bus stop control intensity plan respectively; t is the random variable in the integrated stochastic optimization problem, representing the travel time of the bus on the road section between bus stops; z 步 (p) represents the total passenger walking time function in the system, which is deterministic and determined only by the decision variable p; z 车 (p, g, t) and z 等 (p, g, t) represent the total passenger travel time functions in the system, which are random and related to the values ​​of decision variables p and g and the sampling of random variable t.

[0030] Furthermore, the objective function of the stochastic optimization problem is integrated into two nested sub-problems:

[0031] q(p, g) = E t [φ 车 ·z 车 (p,g,t)+φ 等 ·z 等 (p, g, t)]

[0032]

[0033] Stop layout optimization sub-problem:

[0034]

[0035] Given a stop layout plan p i , the station intensity optimization sub-problem:

[0036]

[0037] Among them, three types of constraints are considered: constraints on the layout of bus stops and the division of passenger boarding demand, constraints on bus operation and station control mechanism, and constraints on the calculation of passenger travel cost composition.

[0038] In a second aspect, the present invention provides a bus stop layout and station control strategy integration optimization system based on an agent model, comprising:

[0039] A construction module is used to establish a bus stop layout model and a bus stop control model based on the system analysis of bus passengers' selection behavior characteristics of boarding and alighting bus stops and the adaptive bus stop control mechanism;

[0040] A determination module is used to determine the objective function of the bus stop layout optimal bus stop control integrated stochastic optimization problem based on the established bus stop layout model and bus stop control model;

[0041] The prediction module is used to build and iteratively update the proxy model to estimate and predict the objective function response value corresponding to the unsimulated decision variables. The proxy model of Gaussian process regression is fitted to the simulated solution and its objective function to give a posterior prediction of the objective function response value of the solution that has not been simulated, guiding the layout of bus stops and the station control strategy.

[0042] In a third aspect, the present invention provides a non-transitory computer-readable storage medium, which is used to store computer instructions. When the computer instructions are executed by a processor, the integrated optimization method of bus stop layout and station control strategy based on the agent model as described in the first aspect is implemented.

[0043] In a fourth aspect, the present invention provides a computer device comprising a memory and a processor, wherein the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the integrated optimization method for bus stop layout and station control strategy based on the agent model as described in the first aspect.

[0044] In a fifth aspect, the present invention provides an electronic device, comprising: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes instructions for implementing the integrated optimization method of bus stop layout and station control strategy based on the agent model as described in the first aspect.

[0045] Beneficial effects of the present invention:

[0046] This paper proposes a stochastic optimization method that integrates the bus stop layout plan with the bus stop control intensity plan. The concept of integrated design using the bus stop layout model at the planning level and the bus stop control model at the operation level is introduced. This optimization method integrates the passenger travel costs at different levels and enhances the ability of the bus stop layout design results at the planning level to maintain the regularity of bus service at the operation level.

[0047] The objective function in the integrated optimization problem proposed by the present invention has clear practical significance, which makes it possible to more effectively weigh the travel costs felt by passengers who choose the public transportation mode at different stages in the algorithm optimization process, and to set different weight coefficient combinations for public transportation passengers with different choice behavior modes for targeted reproduction;

[0048] The integrated random optimization framework proposed in the present invention has strong portability and scalability, and can be applied to demand allocation problems at the planning level in other fields and integrated design optimization problems of random scenario problems at the operation level (such as the site selection of centralized shared bicycle delivery points and the integrated optimization of bicycle delivery, etc.). The simulation model and optimization model in the proposed integrated random optimization algorithm can be replaced to enable it to have the ability to solve other types of integrated optimization problems.

[0049] Additional advantages of the present invention will be more clearly given in the following description or learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0051] Figure 1 This is a scenario diagram of the bus stop layout plan and bus travel demand division described in an embodiment of the present invention.

[0052] Figure 2 This is a schematic diagram of the travel cost composition of passengers according to an embodiment of the present invention.

[0053] Figure 3 This is a comparison chart of the effects of the bus stop layout scheme described in the embodiment of the present invention on the bus stringing problem. Figure 3 (a) Design for stops where vehicles are prone to cross-traffic. Figure 3 (b) The layout of stops to prevent vehicles from being stranded. DETAILED DESCRIPTION

[0054] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below by the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.

[0055] It should be understood by those skilled in the art that unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which this invention belongs.

[0056] It should also be understood that terms, such as those defined in commonly used dictionaries, should be understood to have a meaning consistent with that in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless as defined herein.

[0057] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements and / or groups thereof.

[0058] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. Different embodiments or examples described in this specification and features of different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

[0059] To facilitate understanding of the present invention, the present invention is further explained below with reference to specific embodiments in conjunction with the accompanying drawings, and the specific embodiments do not constitute a limitation on the embodiments of the present invention.

[0060] Those skilled in the art should understand that the drawings are merely schematic diagrams of embodiments, and the components in the drawings are not necessarily necessary for implementing the present invention.

[0061] The integrated optimization technology used in the present invention uses modern stochastic optimization methods. In the decision-making of the public transportation system planning and operation stage, the random uncertainty existing in the actual operation scenario of the bus is taken into consideration, so as to obtain a more effective and stable design scheme and control strategy. This integrated stochastic optimization method is a technical method that integrates the bus planning level and the bus operation level, aiming to overcome the limitation that the traditional staged optimization method is often difficult to cope with the dynamic characteristics of the operation level. This method not only improves the effectiveness of decision-making, but also enhances the system's adaptability to real uncertainty, but the difficulty of solving the optimization problem increases significantly. In order to solve this problem, the present invention realizes the integrated stochastic optimization of the bus system based on simulation by means of a proxy model. With the help of the proxy model as an alternative to the original simulation model, the approximate prediction of the performance of the bus system is achieved at a lower computational cost, which improves the efficiency of simulation calculation. The proxy model can effectively reduce the amount of calculation while retaining a high approximation accuracy by approximating the input of the decision variables of the bus system and the output of the objective function, and realizes the effective evaluation of different design schemes and control strategies.

[0062] Example 1

[0063] In this embodiment 1, firstly, a bus stop layout and station control strategy integration optimization system based on an agent model is provided, including: a construction module, which is used to establish a bus stop layout model and a bus station control model respectively based on a systematic analysis of the selection behavior characteristics of bus passengers for getting on and off bus stops and the adaptive bus station control mechanism. A determination module, which is used to determine the objective function of the bus stop layout optimization and station control integrated stochastic optimization problem based on the established bus stop layout model and bus station control model. A prediction module, which is used to construct and iteratively update the agent model to estimate and predict the objective function response value corresponding to the decision variables that have not been simulated, fit the agent model of Gaussian process regression to the simulated solution and its objective function to give a posterior prediction of the objective function response value of the solution that has not been simulated, and guide the bus stop layout and station control strategy.

[0064] In this embodiment, the above-mentioned system is used to implement an integrated optimization method for bus stop layout and station control strategy based on an agent model, including: based on a systematic analysis of bus passengers' selection behavior characteristics for getting on and off bus stops and an adaptive bus station control mechanism, a bus stop layout model and a bus station control model are established respectively; based on the established bus stop layout model and bus station control model, the objective function of the integrated stochastic optimization problem of bus stop layout and station control is determined; a proxy model is constructed and iteratively updated to estimate and predict the objective function response value corresponding to the decision variables that have not been simulated, and the proxy model of Gaussian process regression is fitted to the simulated solution and its objective function to give a posterior prediction of the objective function response value of the solution that has not been simulated, so as to guide the bus stop layout and station control strategy.

[0065] Building a bus stop layout model includes:

[0066] The bus passengers' perception of the travel costs at different bus stops determines the division of passenger boarding demand at bus stops, as shown below:

[0067]

[0068] In the formula, λ n represents the passenger arrival rate at platform n (unit: person / minute); Λ(x) represents the passenger demand distribution function along the bus line; and They respectively represent the critical position in the forward direction and the critical position in the backward direction of the partition range of the passenger boarding demand at bus stop n;

[0069] The passenger travel cost structure takes into account the passenger walking cost, passenger waiting cost and passenger bus travel cost. Assuming that the travel cost felt by the passenger is directly proportional to the corresponding time, the travel cost of the passenger with (x, y) as the starting and ending point is represented by τ(x, y), and its calculation formula is as follows:

[0070] τ(x, y) = φ 步 ·τ 步 (x,y)+φ 等 ·τ 等 (x,y)+φ 车 ·τ 车 (x, y)

[0071] In the formula, φ 步 ,φ 等 and φ 车 They represent the passenger travel costs caused by the unit passenger walking time, waiting time and in-vehicle travel time (unit: ￥ / minute); τ 步 (x, y), τ 等 (x, y) and τ 车(x, y) represent the walking time, waiting time and in-vehicle travel time of the passenger's bus trip with (x, y) as the starting and ending points respectively;

[0072] The bus operation state equations are a set of equations that represent the arrival time of buses at bus stops, the time waiting for passengers to board, and the time leaving the platform, as shown below:

[0073] a m，n =d m，n(前) +t m，n(前)

[0074]

[0075] d m，n =a m，n +s m，n +u m，n

[0076] In the formula, a m，n 、s m，n and d m，n They represent the arrival time of bus m at bus stop n, the time waiting for passengers to board the bus, and the time the bus leaves the platform; t m，n(前) represents the time taken by bus m to leave the previous stop of stop n and travel to stop n; β represents the average boarding rate of passengers; u m，n It represents the time when bus m is subject to station control at stop n.

[0077] The establishment of a bus stop control model includes: determining the time that the bus is subject to stop control at the stop according to the time interval between the bus's arrival at the stop and the departure time of the preceding bus and the deviation from the driving plan. The calculation of the time that bus m is subject to stop control at stop n is as follows:

[0078]

[0079] In the formula, g n It represents the station control intensity set at the bus stop n; H represents the bus service interval of each bus stop in the bus driving plan.

[0080] Based on the established bus stop layout model and bus stop control model, the objective function of the bus stop layout and bus stop control integrated stochastic optimization problem is given:

[0081]

[0082] Where p and g are the decision variables of the integrated stochastic optimization problem, representing the bus stop layout plan and the bus stop control intensity plan respectively; t is the random variable in the integrated stochastic optimization problem, representing the travel time of the bus on the road section between bus stops; z 步 (p) represents the total passenger walking time function in the system, which is deterministic and determined only by the decision variable p; z 车 (p, g, t) and z 等 (p, g, t) represent the total passenger travel time functions in the system, which are random and related to the values ​​of decision variables p and g and the sampling of random variable t.

[0083] Integrate the objective function of the stochastic optimization problem as two nested subproblems:

[0084] q(p, g) = E t [φ 车 ·z 车 (p,g,t)+φ 等 ·z 等 (p, g, t)]

[0085]

[0086] Stop layout optimization sub-problem:

[0087]

[0088] Given a stop layout plan p i , the station intensity optimization sub-problem:

[0089]

[0090] Among them, three types of constraints are considered: constraints on the layout of bus stops and the division of passenger boarding demand, constraints on bus operation and station control mechanism, and constraints on the calculation of passenger travel cost composition.

[0091] Example 2

[0092] The purpose of this embodiment is to address the inapplicability of the existing stage-by-stage bus system design method. By integrating the bus stop layout problem at the planning level and the bus station control at the operation level, a bus system integrated stochastic optimization method based on an agent model is proposed for the first time. This method uses random simulation to reproduce the complexity of the occurrence and evolution of bus stringing in a random traffic environment, and establishes a Gaussian process agent model to capture the relationship between the bus stop layout plan and the station control intensity strategy and the objective function response value. Compared with the traditional stage-by-stage bus system optimization process, the integrated stochastic optimization framework of this embodiment enhances the integrity of bus system design, is more helpful to weigh the performance of the bus system at different levels, and helps to obtain an integrated design plan and control strategy that is closer to the global optimal. This embodiment uses an agent model for simulation-based optimization, which provides technology and methods for integrating the trade-offs of passenger travel costs at different levels in the bus system and the optimization of the station control strategy, and has significant scientific value, practical significance and application prospects.

[0093] Firstly, this method establishes a bus stop layout model and a bus stop control model. Secondly, this method gives an integrated optimization problem that integrates the bus stop layout optimization problem and the bus stop control stochastic optimization problem. Finally, this method designs a simulation-based optimization algorithm framework using a surrogate model of Gaussian process regression.

[0094] According to the above ideas, the implementation steps of this embodiment are as follows:

[0095] Step 1: Establish the bus stop layout model and bus stop control model.

[0096] In this embodiment, based on the systematic analysis of the selection behavior characteristics of bus passengers for boarding and alighting bus stops and the adaptive bus stop control mechanism, a bus stop layout model and a bus stop control model are established respectively. The specific model formula is as follows:

[0097] (1) Passenger boarding demand classification

[0098] The passenger boarding demand at a bus stop is expressed as the passenger arrival rate (in persons / minute) at a given bus stop. The passenger demand at a given bus stop on a bus route depends on the choice behavior of bus passengers along the route. The bus passengers' perception of the travel cost at different bus stops determines the division of passenger boarding demand at bus stops, as shown below.

[0099]

[0100] In the formula, λ nrepresents the passenger arrival rate at platform n (unit: person / minute); Λ(x) represents the passenger demand distribution function along the bus line (unit: person / minute / km); and They respectively represent the forward critical position and the backward critical position of the passenger boarding demand division range of bus stop n (unit: km).

[0101] (2) Composition of passenger travel costs

[0102] The passenger travel cost structure takes into account the passenger walking cost, the passenger waiting cost and the passenger bus travel cost. Assuming that the travel cost felt by the passenger is proportional to the corresponding time, the travel cost of the passenger with (x, y) as the starting and ending point is represented by τ(x, y) (unit: ￥), and its calculation formula is as follows.

[0103] τ(x, y) = φ 步 ·τ 步 (x,y)+φ 等 ·τ 等 (x,y)+φ 车 ·τ 车 (x, y) (2)

[0104] In the formula, φ 步 ,φ 等 and φ 车 They represent the passenger travel costs caused by the unit passenger walking time, waiting time and in-vehicle travel time (unit: ￥ / minute); τ 步 (x, y), τ 等 (x, y) and τ 车 (x, y) represent the walking time, waiting time and in-vehicle travel time (unit: minutes) of the passenger's bus trip with (x, y) as the starting and ending points.

[0105] (3) Bus operation state equation

[0106] The bus operation state equations are a set of equations that represent the arrival time of buses at bus stops, the time they wait for passengers to board, and the time they leave the bus stop, as shown below.

[0107] a m， n=d m，n(前) +t m，n(前) (3a)

[0108]

[0109] d m，n =a m，n +s m，n +u m，n (3c)

[0110] In the formula, a m，n 、s m，n and d m，n They represent the arrival time of bus m at bus stop n, the time waiting for passengers to board the bus, and the time the bus leaves the platform (in minutes); t m，n(前) represents the time (in minutes) taken by bus m to travel from the previous stop of stop n to stop n; β represents the average passenger boarding rate (in persons / minute); u m，n It represents the time (in minutes) that bus m is subject to station control at stop n.

[0111] (4) Adaptive bus station control

[0112] Adaptive bus stop control is an important bus stop control method. It determines the time that the bus is subject to stop control at the stop according to the deviation between the time interval between the arrival of the bus at the platform and the departure time of the preceding bus and the driving plan. The time (unit: minute) that bus m is subject to stop control at stop n is calculated as follows.

[0113]

[0114] In the formula, g n It represents the station control intensity set at the bus stop n; H represents the bus service interval of each bus stop in the bus driving plan.

[0115] Step 2: Bus stop layout and optimal station control integrate stochastic optimization problem.

[0116] Based on the bus stop layout model and bus stop control model established in step 1, the objective function of the bus stop layout and bus stop control integrated stochastic optimization problem is given as follows.

[0117]

[0118] Where p and g are the decision variables of the integrated stochastic optimization problem, representing the bus stop layout plan and the bus stop control intensity plan respectively; t is the random variable in the integrated stochastic optimization problem, representing the travel time of the bus on the road section between bus stops; z 步 (p) represents the total passenger walking time function in the system, which is deterministic and determined only by the decision variable p; z 车 (p, g, t) and z 等 (p, g, t) represent the total passenger travel time functions in the system, which are random and related to the values ​​of decision variables p and g and the sampling of random variable t.

[0119] In particular, the objective function of the integrated stochastic optimization problem (Formula 5) can be written as two nested sub-problems as shown below.

[0120] q(p, g) = E t [φ 车 ·z 车 (p,g,t)+φ 等 ·z 等 (p, g, t)] (6a)

[0121]

[0122] Stop layout optimization sub-problem (P1):

[0123]

[0124] Given a stop layout plan p i , the station intensity optimization sub-problem (P2):

[0125]

[0126] In the proposed integrated optimization problem, three types of constraints are considered: a. constraints on the layout of bus stops and the division of passenger boarding demand; b. constraints on bus operation and station control mechanism; c. constraints on the calculation of passenger travel cost components.

[0127] Step 3: Optimization algorithm framework based on simulation fitting of Gaussian process regression surrogate model

[0128] In this embodiment, a simulation-based optimization framework is proposed, which constructs and iteratively updates a proxy model to estimate and predict the objective function response value corresponding to the decision variables that have not been simulated, thereby guiding the optimization of the integrated stochastic optimization problem. This algorithm is proposed to solve the integrated stochastic optimization problem proposed in step 2. In the algorithm, the proxy model of Gaussian process regression is fitted to the simulated solution and its objective function to give a posterior prediction of the objective function response value of the solution that has not been simulated, thereby guiding the allocation of simulation resources.

[0129] The main steps of the integrated stochastic optimization algorithm based on the surrogate model are as follows:

[0130] Step 1: Initialize simulation parameters, set the number of iterations k = 1, preset simulation computing power budget C, convergence ratio threshold α0, random scene scale R0, random scene scale growth coefficient gr and other parameters.

[0131] Step 2: Generate an initial set of bus stop layout plans using Latin Hypercube Design (LHD)

[0132] Step 3: For the collection The layout plan of each bus stop in If p i If it is the first access, execute Step 3a-Step 4a; otherwise, execute Step 3b-Step 4b.

[0133] Step 3a: Set up bus stop layout plan i The convergence ratio threshold α under k (p i )=α0, random scene scale R (k) (p i )=R0, use Simple Random Sampling (SRS) to generate a set of random scenarios under the bus stop layout plan

[0134] Step 3b: Update the convergence ratio threshold Random scene scale R (k) (p i )=R (k-1) (p i ) gr. Use SRS to generate (R (k) (p i )-R (k-1) (p i )) Random scenes added to the collection middle.

[0135] Step 4a: Use LHD to generate bus stop layout plan i A collection of bus stop layout plans by The Zhang Cheng space is used as the simulation space to perform simulation operations.

[0136] Step 4b: The Zhang Cheng space is used as the simulation space to perform simulation operations.

[0137] Step 5: Construct a given bus stop layout plan p i Agent model for optimizing station intensity under And used to solve the bus stop layout plan p i The optimal station intensity scheme under

[0138] Step 6: Check the optimal station intensity solution Whether the termination condition of the station intensity optimization is met. If the termination condition is not met, update And return to Step 3b.

[0139] Step 7: Build a proxy model for the bus stop placement problem And with the help of Solve the optimal stop layout plan p *(k) .

[0140] Step 8: Check the currently optimal stop layout plan p *(k) Whether the termination condition of the optimization of the layout and intensity of the stop is met. If the termination condition is not met, the number of iterations is updated k = k + 1, And return to Step 3.

[0141] In this embodiment, the optimization algorithm framework based on the proxy model is shown in Table 1.

[0142] Table 1 Description of the optimization algorithm framework based on the proxy model

[0143]

[0144] Example 3

[0145] This embodiment 3 provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the above-mentioned agent-based bus stop layout and station control strategy integration optimization method is implemented. The method includes:

[0146] Based on the systematic analysis of the selection behavior characteristics of bus passengers on boarding and alighting bus stops and the adaptive bus stop control mechanism, a bus stop layout model and a bus stop control model are established respectively.

[0147] Based on the established bus stop layout model and bus stop control model, the objective function of the bus stop layout optimal stop control integrated stochastic optimization problem is determined;

[0148] Construct and iteratively update the proxy model to estimate and predict the objective function response value corresponding to the unsimulated decision variables, fit the Gaussian process regression proxy model to the simulated solution and its objective function to give a posterior prediction of the objective function response value of the solution that has not been simulated, and guide the layout of bus stops and station control strategies.

[0149] Example 4

[0150] This embodiment 4 provides a computer device, including a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the above-mentioned agent-based bus stop layout and station control strategy integration optimization method, the method comprising:

[0151] Based on the systematic analysis of the selection behavior characteristics of bus passengers on boarding and alighting bus stops and the adaptive bus stop control mechanism, a bus stop layout model and a bus stop control model are established respectively.

[0152] Based on the established bus stop layout model and bus stop control model, the objective function of the bus stop layout optimal stop control integrated stochastic optimization problem is determined;

[0153] Construct and iteratively update the proxy model to estimate and predict the objective function response value corresponding to the unsimulated decision variables, fit the Gaussian process regression proxy model to the simulated solution and its objective function to give a posterior prediction of the objective function response value of the solution that has not been simulated, and guide the layout of bus stops and station control strategies.

[0154] Example 5

[0155] This embodiment 5 provides an electronic device, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes instructions for implementing the above-mentioned agent-based bus stop layout and station control strategy integrated optimization method, the method comprising:

[0156] Based on the systematic analysis of the selection behavior characteristics of bus passengers on boarding and alighting bus stops and the adaptive bus stop control mechanism, a bus stop layout model and a bus stop control model are established respectively.

[0157] Based on the established bus stop layout model and bus stop control model, the objective function of the bus stop layout optimal stop control integrated stochastic optimization problem is determined;

[0158] Construct and iteratively update the proxy model to estimate and predict the objective function response value corresponding to the unsimulated decision variables, fit the Gaussian process regression proxy model to the simulated solution and its objective function to give a posterior prediction of the objective function response value of the solution that has not been simulated, and guide the layout of bus stops and station control strategies.

[0159] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0160] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0161] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0162] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0163] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative work on the basis of the technical solution disclosed in the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for integrating bus stop layout and station control strategy based on agent model, characterized in that: include: Based on the systematic analysis of the selection behavior characteristics of bus passengers on boarding and alighting bus stops and the adaptive bus stop control mechanism, a bus stop layout model and a bus stop control model are established respectively. Based on the established bus stop layout model and bus stop control model, the objective function of the bus stop layout optimal stop control integrated stochastic optimization problem is determined; Construct and iteratively update the proxy model to estimate and predict the objective function response value corresponding to the unsimulated decision variables, fit the Gaussian process regression proxy model to the simulated solution and its objective function to give a posterior prediction of the objective function response value of the solution that has not been simulated, and guide the layout of bus stops and station control strategies.

2. The integrated optimization method for bus stop layout and station control strategy based on agent model according to claim 1 is characterized in that: Building a bus stop layout model includes: The bus passengers' perception of the travel costs at different bus stops determines the division of passenger boarding demand at bus stops, as shown below: In the formula, λ n represents the passenger arrival rate at platform n (unit: person / minute); Λ(x) represents the passenger demand distribution function along the bus line; and They respectively represent the critical position in the forward direction and the critical position in the backward direction of the partition range of the passenger boarding demand at bus stop n; The passenger travel cost structure takes into account the passenger walking cost, the passenger waiting cost and the passenger bus travel cost. Assuming that the travel cost felt by the passenger is directly proportional to the corresponding time, the travel cost of the passenger with (x, y) as the starting and ending point is represented by τ(x, y), and its calculation formula is as follows: τ(x,y)=φ 步 ·t 步 (x,y)+φ 等 ·t 等 (x,y)+φ 车 ·t 车 (x,y) In the formula, φ 步 ,φ 等 and φ 车 They represent the passenger travel costs caused by the unit passenger walking time, waiting time and in-vehicle travel time (unit: ￥ / minute); τ 步 (x,y),τ 等 (x,y) and τ 车 (x, y) represent the walking time, waiting time and in-vehicle travel time of the passenger's bus trip with (d, y) as the starting and ending points respectively; The bus operation state equations are a set of equations that represent the arrival time of buses at bus stops, the time waiting for passengers to board, and the time leaving the platform, as shown below: a m,n =d m,n(前) +t m,n(前) d m,n =a m,n +s m,n +u m,n In the formula, a m,n 、s m,n and d m,n They represent the arrival time of bus m at bus stop n, the time waiting for passengers to board the bus, and the time the bus leaves the platform; t m,n(前) represents the time taken by bus m to leave the previous stop of stop n and travel to stop n; β represents the average boarding rate of passengers; u m,n It represents the time when bus m is subject to station control at stop n.

3. The integrated optimization method for bus stop layout and station control strategy based on agent model according to claim 2 is characterized in that: The establishment of a bus station control model includes: determining the time when the bus is subject to station control at the stop according to the deviation between the time interval between the arrival of the bus at the platform and the departure time of the preceding bus and the driving plan.

4. The integrated optimization method for bus stop layout and station control strategy based on agent model according to claim 3 is characterized in that: The calculation of the time that bus m is subject to station control at stop n is as follows: In the formula, g n It represents the station control intensity set at the bus stop n; H represents the bus service interval of each bus stop in the bus driving plan.

5. The integrated optimization method for bus stop layout and station control strategy based on agent model according to claim 1 is characterized in that: Based on the established bus stop layout model and bus stop control model, the objective function of the bus stop layout and bus stop control integrated stochastic optimization problem is given: Where p and g are the decision variables of the integrated stochastic optimization problem, representing the bus stop layout plan and the bus stop control intensity plan respectively; t is the random variable in the integrated stochastic optimization problem, representing the travel time of the bus on the road section between bus stops; z 步 (p) represents the total passenger walking time function in the system, which is deterministic and determined only by the decision variable p; z 车 (p,g,t) and z 等 (p, g, t) represent the total passenger travel time functions in the system, which are random and related to the values ​​of decision variables p and g and the sampling of random variable t.

6. The integrated optimization method for bus stop layout and station control strategy based on agent model according to claim 5 is characterized in that: Integrate the objective function of the stochastic optimization problem as two nested subproblems: q(p,g)=E t [φ 车 ·z 车 (p,g,t)+φ 等 ·z 等 (p,g,t)] Stop layout optimization sub-problem: Given a stop layout plan p i , the station intensity optimization sub-problem: Among them, three types of constraints are considered: constraints on the layout of bus stops and the division of passenger boarding demand, constraints on bus operation and station control mechanism, and constraints on the calculation of passenger travel cost composition.

7. An agent-based bus stop layout and station control strategy integration optimization system, characterized in that: include: A construction module is used to establish a bus stop layout model and a bus stop control model based on the system analysis of bus passengers' selection behavior characteristics of boarding and alighting bus stops and the adaptive bus stop control mechanism; A determination module is used to determine the objective function of the bus stop layout optimal bus stop control integrated stochastic optimization problem based on the established bus stop layout model and bus stop control model; The prediction module is used to build and iteratively update the proxy model to estimate and predict the objective function response value corresponding to the unsimulated decision variables. The proxy model of Gaussian process regression is fitted to the simulated solution and its objective function to give a posterior prediction of the objective function response value of the solution that has not been simulated, guiding the layout of bus stops and the station control strategy.

8. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the agent-based bus stop layout and station control strategy integration optimization method as described in any one of claims 1-6 is implemented.

9. A computer device, characterized in that: It includes a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the integrated optimization method for bus stop layout and station control strategy based on the agent model as described in any one of claims 1-6.

10. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes instructions for implementing the integrated optimization method of bus stop layout and station control strategy based on the agent model as described in any one of claims 1-6.

Images