Emergency shelter layout optimization method and system based on multi-objective particle swarm optimization

Abstract

The invention relates to the technical field of urban disaster emergency management, in particular to an emergency shelter layout optimization method and system based on a multi-target particle swarm algorithm. Constructing an emergency shelter site selection optimization model taking the minimum evacuation distance, the minimum construction and evacuation cost and the maximum distance away from the disaster hidden danger point as targets and an emergency shelter capacity optimization model taking the maximum emergency shelter capacity as a target; performing joint optimization on the emergency shelter site selection optimization model and the emergency shelter capacity optimization model by using a multi-objective particle swarm algorithm to obtain a Pareto solution set; and acquiring an emergency shelter layout scheme based on the Pareto solution set. According to the invention, the optimal layout scheme of the emergency shelter with different preferences can be formed according to the combination of geographic space characteristics and urban resident evacuation demands, so that the overall emergency efficiency and resource allocation scientificity of the emergency shelter are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban disaster emergency management, and in particular to an emergency shelter layout optimization method and system based on a multi-objective particle swarm algorithm. Background Art

[0002] During natural disasters, emergency shelters, as key infrastructure, play an important role in protecting the lives of urban residents and reducing secondary disasters. However, in the actual planning and management of emergency shelters, problems such as unreasonable site selection, insufficient coverage, and poor accessibility to residents have seriously restricted their functions during disasters. This is mainly reflected in the following aspects: (1) Existing emergency shelter layout planning treats the site selection and capacity configuration of emergency shelters as two isolated issues, lacking systematic linkage. This may lead to a mismatch between capacity allocation and actual shelter needs, resulting in overload or low utilization of emergency shelters, and weakening the disaster emergency response capabilities of emergency shelters; (2) In terms of site selection of emergency shelters, existing technologies only consider the shortest path or single cost minimization, while ignoring the trade-offs between multiple objectives in the facility site selection process, making it difficult to balance fairness and efficiency; (3) In the face of multi-objective conflicts and complex constraints, traditional mathematical programming methods have obvious deficiencies in both solution efficiency and feasible solution quality.

[0003] Based on this, there is an urgent need for an emergency shelter layout optimization method that can meet the supply and demand balance of emergency shelter site selection and capacity, has high solution efficiency, and can improve the overall accessibility, fairness and emergency response efficiency of the shelter system. Summary of the Invention

[0004] The purpose of the present invention is to provide an emergency shelter layout optimization method and system based on a multi-objective particle swarm algorithm to solve the technical problems pointed out in the background technology.

[0005] The present invention is implemented by the following technical solution: an emergency shelter layout optimization method based on a multi-objective particle swarm algorithm comprises the following steps: Obtain geographic information data and construct an emergency shelter site selection optimization model with the goal of minimizing evacuation distance, minimizing construction and evacuation costs, and maximizing distance from disaster risk points; and an emergency shelter capacity optimization model with the goal of maximizing emergency shelter capacity; The multi-objective particle swarm algorithm is used to jointly optimize the emergency shelter site selection optimization model and the emergency shelter capacity optimization model to obtain a Pareto solution set; An emergency shelter layout plan is obtained based on the Pareto solution set.

[0006] According to a preferred embodiment, the geographic information data includes coordinates of settlements, coordinates of shelters, and coordinates of disaster risk points.

[0007] According to a preferred embodiment, the objective function expression of minimizing the evacuation distance is as follows:

[0008] In the above formula, Indicates the The weight of a settlement, Indicates the The coordinates of the emergency shelters, Indicates the The coordinates of the settlements, Indicates emergency shelter and settlements The Euclidean distance of Indicates settlements Evacuate to the nearest emergency shelter , represents a collection of settlements, Indicates an emergency shelter assembly.

[0009] According to a preferred embodiment, the objective function expression for minimizing construction and evacuation costs is as follows:

[0010] In the above formula, Indicates emergency shelter The unit construction cost, Indicates emergency shelter capacity, Indicate whether to build emergency shelters , Indicates settlements To emergency shelter per capita evacuation cost.

[0011] According to a preferred embodiment, the objective function expression of maximizing the distance from the disaster potential point is as follows:

[0012] In the above formula, Indicates potential disaster points The coordinates of Indicates potential disaster points The weight of .

[0013] According to a preferred embodiment, the method further includes setting constraints for the emergency shelter site selection optimization model, wherein the constraints include: Emergency shelter selection constraints, expressed as , the above formula means that every settlement must be evacuated to the nearest emergency shelter; The constraint on the number of emergency shelters is expressed as , in the above formula, Indicates the number of emergency shelters that can be built.

[0014] According to a preferred embodiment, the objective function expression for maximizing the emergency shelter capacity is as follows:

[0015] In the above formula, is a minimum value, .

[0016] According to a preferred embodiment, the method further includes setting constraints for the emergency shelter capacity optimization model, wherein the constraints include: The supply and demand matching constraint of emergency shelter capacity is expressed as ,The above formula indicates that the capacity of each emergency shelter should meet the needs of surrounding settlements; The supply and demand matching constraint of the total capacity of regional emergency shelters is expressed as , the above formula indicates that the total capacity of emergency shelters should be greater than the total demand in the region .

[0017] According to a preferred embodiment, a multi-objective particle swarm algorithm is used to jointly optimize the emergency shelter site selection optimization model and the emergency shelter capacity optimization model. The solution process is as follows: Encode each particle as a vector , to indicate the coordinates and capacity of emergency shelters; Update the velocity and position of each particle, and after each iteration of the particle group position update, update the coordinates of the emergency shelter. Call the emergency shelter capacity optimization model to optimize the capacity of the emergency shelter ; Through alternate iterations of the emergency shelter site selection optimization model and the emergency shelter capacity optimization model, a Pareto solution set with complementary dominance in the multi-objective space is output.

[0018] The present invention also provides an emergency shelter layout optimization system based on a multi-objective particle swarm algorithm, which is applied to the emergency shelter layout optimization method based on a multi-objective particle swarm algorithm as described above. The system includes: The model building module is used to obtain geographic information data and build an emergency shelter site selection optimization model with the goal of minimizing evacuation distance, minimizing construction and evacuation costs, and maximizing distance from disaster risk points, as well as an emergency shelter capacity optimization model with the goal of maximizing emergency shelter capacity; a joint optimization module, configured to jointly optimize the emergency shelter site selection optimization model and the emergency shelter capacity optimization model using a multi-objective particle swarm algorithm to obtain a Pareto solution set; A solution module is used to obtain an emergency shelter layout plan based on the Pareto solution set.

[0019] The technical solution of the emergency shelter layout optimization method and system based on the multi-objective particle swarm algorithm provided by the present invention has at least the following advantages and beneficial effects: (1) It can form an optimal layout plan of emergency shelters with different preferences based on the combination of geographic spatial characteristics and the evacuation needs of urban residents, so as to improve the overall emergency efficiency and scientific resource allocation of emergency shelters; (2) By constructing and adopting a multi-objective particle swarm algorithm to jointly optimize the emergency shelter site selection optimization model and the emergency shelter capacity optimization model, it provides an efficient and flexible solution to the multi-objective optimization problem of emergency shelter layout, and generates a high-quality Pareto optimal solution set by balancing convergence and diversity, assisting decision makers in making trade-offs under complex constraints; (3) By establishing a dynamic adjustment mechanism of inertia weight, individual learning factor, group learning factor and local learning factor, the convergence efficiency and global search capability of the particle swarm algorithm are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flow chart of an emergency shelter layout optimization method based on a multi-objective particle swarm algorithm provided in Example 1 of the present invention; Figure 2 Flowchart of the multi-objective particle swarm algorithm provided in Example 1 of the present invention; Figure 3 This is a structural block diagram of an emergency shelter layout optimization system based on a multi-objective particle swarm algorithm provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0022] Example 1 This embodiment provides an emergency shelter layout optimization method based on a multi-objective particle swarm optimization algorithm. Figure 1 This is a flow chart of the emergency shelter layout optimization method, see Figure 1 As shown, the emergency shelter layout optimization method includes the following steps: Step S01: Obtain geographic information data and construct an emergency shelter site selection optimization model with the goal of minimizing evacuation distance, minimizing construction and evacuation costs, and maximizing distance from disaster risk points, and an emergency shelter capacity optimization model with the goal of maximizing emergency shelter capacity; Through government public platforms, professional agency databases, remote sensing and mapping technologies, and field research, we collected geographic information data, including the coordinates of settlements, shelters, and disaster risk points. We then constructed emergency shelter site selection optimization models and emergency shelter capacity optimization models based on these geographic information data.

[0023] The emergency shelter site selection optimization model aims to minimize the evacuation distance, minimize the construction and evacuation costs, and maximize the distance from the disaster risk point. The expressions of each objective function are as follows: The objective function expression of minimizing the evacuation distance is as follows:

[0024] In the above formula, Indicates the The weight of a settlement, Indicates the The coordinates of the emergency shelters, Indicates the The coordinates of the settlements, Indicates emergency shelter and settlements The Euclidean distance of Indicates settlements Evacuate to the nearest emergency shelter , represents a collection of settlements, Indicates an emergency shelter assembly.

[0025] The objective function expression for minimizing construction and evacuation costs is as follows:

[0026] In the above formula, Indicates emergency shelter The unit construction cost, Indicates emergency shelter capacity, Indicate whether to build emergency shelters , Indicates settlements To emergency shelter per capita evacuation cost.

[0027] The objective function expression of maximizing the distance from the disaster risk point is as follows:

[0028] In the above formula, Indicates potential disaster points The coordinates of Indicates potential disaster points The higher the risk level of the disaster potential point, the The bigger.

[0029] Furthermore, constraints are set for the emergency shelter site selection optimization model, including emergency shelter selection constraints and the number of emergency shelters that can be constructed. The expression of the emergency shelter selection constraint is: , which means that each settlement must be evacuated to the nearest emergency shelter; the expression for the number of emergency shelters that can be built is , is the number of emergency shelters that can be built. This constraint indicates that the number of emergency shelters built should be constrained within the limit.

[0030] The emergency shelter capacity optimization model aims to maximize the emergency shelter capacity, and its objective function is expressed as follows:

[0031] In the above formula, is a minimum value, , to avoid zero errors.

[0032] Furthermore, constraints are set for the emergency shelter capacity optimization model, including the emergency shelter capacity supply and demand matching constraint and the regional emergency shelter total capacity supply and demand matching constraint; wherein, the expression of the emergency shelter capacity supply and demand matching constraint is: , which means that the capacity of each emergency shelter should meet the needs of surrounding settlements; the expression of the regional emergency shelter total capacity supply and demand matching constraint is , which means that the total capacity of emergency shelters should be greater than the total demand in the region. .

[0033] Step S02: using a multi-objective particle swarm algorithm to jointly optimize the emergency shelter site selection optimization model and the emergency shelter capacity optimization model to obtain a Pareto solution set; Specifically, step S02 can be further divided into the following sub-steps: Step S21: Encode each particle as a vector , to indicate the coordinates and capacity of emergency shelters; Step S22: Update the velocity and position of each particle, and update the coordinates of the emergency shelter after each iteration of the particle group position update. Call the emergency shelter capacity optimization model to optimize the emergency shelter capacity ; Among them, the particle update mechanism is as follows: Update the velocity of each particle with the following expression:

[0034] In the above formula, express Moment Particles speed, express Moment Particles speed, represents the inertia weight, represents the individual learning factor, Represents particles The known optimal position of an individual, represents the group learning factor, Represents particles The known global optimal position, represents the local learning factor, Represents particles The known local optimal position, 、 and for A uniform random number in the interval, express Moment Particles location; Among them, the inertia weight and individual learning factors Iteration is performed in a linear decreasing manner, and the expression is as follows:

[0035]

[0036] In the above formula, represents the upper limit of the inertia weight, Indicates the lower limit of the inertia weight, represents the upper limit of the individual learning factor, represents the lower limit of the individual learning factor, represents the number of iterations of the particle swarm algorithm, Indicates the maximum number of iterations of the particle swarm algorithm; It should be noted that in the inertia weight and individual learning factors In the early stages of algorithm iteration, particles are encouraged to fully explore the space and improve the diversity of solutions, while in the later stages of iteration, convergence to the optimal region is accelerated.

[0037] Group learning factor Iteration is performed in a linear increasing manner, so that particles can explore the global optimal solution in the later stage of iteration, increase the weighted convergence speed and improve the quality of the solution. The expression is as follows:

[0038] In the above formula, represents the upper limit of the group learning factor, Indicates the lower limit of the group learning factor.

[0039] Local learning factor Using fixed values ​​for iteration helps prevent particles from falling into local optimality, thereby improving the stability of the particle global search.

[0040] It should be noted that this embodiment improves the convergence efficiency and global search capability of the particle swarm algorithm by establishing a dynamic adjustment mechanism of the inertia weight, individual learning factor, group learning factor and local learning factor.

[0041] Furthermore, the position of each particle is updated, and the expression is as follows:

[0042] Step S23: Output a Pareto solution set of complementary dominance in the multi-objective space by alternately iterating the emergency shelter site selection optimization model and the emergency shelter capacity optimization model.

[0043] Specifically, after each iteration of the particle swarm position update, the coordinates of the emergency shelter are Call the emergency shelter capacity optimization model to optimize the capacity of the emergency shelter ; Through alternating iterations of the emergency shelter site selection optimization model and the emergency shelter capacity optimization model, a Pareto solution set with complementary dominance in the multi-objective space is output.

[0044] See also Figure 2 As shown, this embodiment constructs and adopts a multi-objective particle swarm algorithm to jointly optimize the emergency shelter site selection optimization model and the emergency shelter capacity optimization model, providing an efficient and flexible solution to the multi-objective optimization problem of emergency shelter layout. By balancing convergence and diversity, a high-quality Pareto optimal solution set is generated to assist decision makers in making trade-offs under complex constraints.

[0045] In some implementations of this embodiment, a Pareto solution set is generated according to a non-dominated sorting mechanism, as follows: During the solution process, each solution in the particle swarm According to the dominant relationship Perform non-dominated sorting, where Indicates the The objective function, Represents the solution Dominant solution .

[0046] After multiple iterations, a Pareto solution set is generated ,satisfy , Represents the set of all generated solutions during the particle swarm iteration process, including candidate solutions generated by each iteration generation. To distinguish Different solutions.

[0047] Step S03: Based on the Pareto solution set, obtain an emergency shelter layout plan.

[0048] In summary, the technical solution provided in this embodiment can form an optimal layout plan for emergency shelters with different preferences based on the combination of geographic spatial characteristics and the evacuation needs of urban residents, so as to improve the overall emergency efficiency and scientific resource allocation of emergency shelters.

[0049] Example 2 This embodiment provides an emergency shelter layout optimization system based on a multi-objective particle swarm algorithm based on the technical solution provided in Example 1. The system is applied to the emergency shelter layout optimization method based on a multi-objective particle swarm algorithm as described in Example 1. Figure 3 As shown, the system includes: The model building module is used to obtain geographic information data and build an emergency shelter site selection optimization model with the goal of minimizing evacuation distance, minimizing construction and evacuation costs, and maximizing distance from disaster risk points, as well as an emergency shelter capacity optimization model with the goal of maximizing emergency shelter capacity; a joint optimization module, configured to jointly optimize the emergency shelter site selection optimization model and the emergency shelter capacity optimization model using a multi-objective particle swarm algorithm to obtain a Pareto solution set; A solution module is used to obtain an emergency shelter layout plan based on the Pareto solution set.

[0050] The functions of each module of the emergency shelter layout optimization system based on a multi-objective particle swarm algorithm in this embodiment are the same as those explained in the embodiment of the emergency shelter layout optimization method based on a multi-objective particle swarm algorithm and have the same technical effects, so they will not be repeated here.

[0051] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. An emergency shelter layout optimization method based on a multi-objective particle swarm optimization algorithm is characterized by: The steps include: Obtain geographic information data and construct an emergency shelter site selection optimization model with the goal of minimizing evacuation distance, minimizing construction and evacuation costs, and maximizing distance from disaster risk points; and an emergency shelter capacity optimization model with the goal of maximizing emergency shelter capacity; The multi-objective particle swarm algorithm is used to jointly optimize the emergency shelter site selection optimization model and the emergency shelter capacity optimization model to obtain a Pareto solution set; An emergency shelter layout plan is obtained based on the Pareto solution set.

2. The emergency shelter layout optimization method based on multi-objective particle swarm optimization according to claim 1, characterized in that: The geographic information data includes coordinates of settlements, shelters, and disaster risk points.

3. The emergency shelter layout optimization method based on multi-objective particle swarm optimization according to claim 2, characterized in that: The objective function expression of minimizing the evacuation distance is as follows: In the above formula, Indicates the The weight of a settlement, Indicates the The coordinates of the emergency shelters, Indicates the The coordinates of the settlements, Indicates emergency shelter and settlements The Euclidean distance of Indicates settlements Evacuate to the nearest emergency shelter , represents a collection of settlements, Indicates an emergency shelter assembly.

4. The emergency shelter layout optimization method based on multi-objective particle swarm optimization according to claim 3, characterized in that: The objective function expression of minimizing construction and evacuation costs is as follows: In the above formula, Indicates emergency shelter The unit construction cost, Indicates emergency shelter capacity, Indicate whether to build emergency shelters , Indicates settlements To emergency shelter per capita evacuation cost.

5. The emergency shelter layout optimization method based on multi-objective particle swarm optimization according to claim 4, characterized in that: The objective function expression of maximizing the distance from the disaster potential point is as follows: In the above formula, Indicates potential disaster points The coordinates of Indicates potential disaster points The weight of Represents a set of disaster risk points.

6. The emergency shelter layout optimization method based on multi-objective particle swarm optimization according to claim 5, characterized in that: The method further includes setting constraints for the emergency shelter site selection optimization model, wherein the constraints include: Emergency shelter selection constraints, expressed as , the above formula means that every settlement must be evacuated to the nearest emergency shelter; The constraint on the number of emergency shelters is expressed as , in the above formula, Indicates the number of emergency shelters that can be built.

7. The emergency shelter layout optimization method based on a multi-objective particle swarm optimization algorithm according to any one of claims 2 to 6, characterized in that: The objective function expression for maximizing the emergency shelter capacity is as follows: In the above formula, is a minimum value, .

8. The emergency shelter layout optimization method based on multi-objective particle swarm optimization according to claim 7, characterized in that: The method further includes setting constraints for the emergency shelter capacity optimization model, wherein the constraints include: The supply and demand matching constraint of emergency shelter capacity is expressed as ,The above formula indicates that the capacity of each emergency shelter should meet the needs of surrounding settlements; The supply and demand matching constraint of the total capacity of regional emergency shelters is expressed as , the above formula indicates that the total capacity of emergency shelters should be greater than the total demand in the region .

9. The emergency shelter layout optimization method based on multi-objective particle swarm optimization according to claim 8, characterized in that: The multi-objective particle swarm optimization algorithm is used to jointly optimize the emergency shelter site selection optimization model and the emergency shelter capacity optimization model. The solution process is as follows: Encode each particle as a vector , to indicate the coordinates and capacity of emergency shelters; Update the velocity and position of each particle, and after each iteration of the particle group position update, update the coordinates of the emergency shelter. Call the emergency shelter capacity optimization model to optimize the capacity of the emergency shelter ; Through alternate iterations of the emergency shelter site selection optimization model and the emergency shelter capacity optimization model, a Pareto solution set with complementary dominance in the multi-objective space is output.

10. Emergency shelter layout optimization system based on multi-objective particle swarm optimization algorithm, characterized by: Applied to the emergency shelter layout optimization method based on a multi-objective particle swarm algorithm according to any one of claims 1 to 9, the system comprises: The model building module is used to obtain geographic information data and build an emergency shelter site selection optimization model with the goal of minimizing evacuation distance, minimizing construction and evacuation costs, and maximizing distance from disaster risk points, as well as an emergency shelter capacity optimization model with the goal of maximizing emergency shelter capacity; a joint optimization module, configured to jointly optimize the emergency shelter site selection optimization model and the emergency shelter capacity optimization model using a multi-objective particle swarm algorithm to obtain a Pareto solution set; A solution module is used to obtain an emergency shelter layout plan based on the Pareto solution set.

Images