Hybrid disaster emergency evacuation path simulation planning method and system based on social distance

Abstract

The invention discloses a mixed disaster emergency evacuation path simulation planning method and system based on social distance, and belongs to the technical field of emergency management. According to the method, a K shortest path capacity planning algorithm with a social distance is provided for a serious infectious disease epidemic situation and natural disaster concurrent scene, the algorithm comprises a K shortest path generation operator with node capacity constraint, a conflict road section recognition operator and a capacity distribution operator with the social distance, an evacuation scheme is rapidly generated under the condition of parameter determination, and the evacuation efficiency is improved. And dynamic balance between evacuation efficiency and infection risk is realized. Furthermore, the operators are integrated into a simulation optimization framework, an alternative scheme library is constructed through random sampling and budget allocation under the condition that parameters are uncertain, and the reliability and robustness of the scheme are improved. According to the invention, a flexible and reliable evacuation strategy can be rapidly formulated in a complex disaster environment, local congestion and scheme failure are avoided, and the multi-disaster cooperative response capability is enhanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of emergency management, in particular to a mixed disaster emergency evacuation path simulation planning method and system based on social distance. BACKGROUND

[0002] Emergency evacuation under mixed disasters is a complex decision-making problem of coordinating infection control and rapid evacuation when an epidemic and a natural disaster occur simultaneously. The superimposed effect of such disasters exacerbates public safety risks, for example, maintaining social distance during floods reduces evacuation efficiency, while overcrowding increases the risk of epidemic spread. Researching this problem has important practical significance for developing emergency strategies that balance dual risks and improving multi-disaster response capabilities, especially in the context of global extreme weather and frequent infectious diseases.

[0003] Mixed disaster evacuation is often modeled as a mixed integer programming (MIP) problem, with path selection, personnel allocation, and social distance decisions as core variables. The objective function minimizes evacuation time and infection risk, with complex factors such as multiple sources, multiple destinations, and multiple periods. Solving methods mainly rely on exact algorithms such as branch and bound, cutting planes, and commercial solvers such as CPLEX, supplemented by dynamic programming to handle multi-period decision-making. Such methods can solve small and medium-sized problems, but have poor adaptability to non-linear constraints and high-dimensional decision variables, and rely on deterministic assumptions, making it difficult to cope with the uncertainty of disaster environments.

[0004] The existing methods face three major challenges: first, the parameters of the evacuation network (such as path capacity and travel time) are difficult to predict due to disasters, and uncertainty leads to a deviation of the model solution from reality, making the mixed disaster emergency evacuation path simulation planning method based on social distance relying on deterministic assumptions ineffective; second, the complexity of the problem increases due to integer variables and non-linear constraints, and the computational cost of traditional algorithms increases exponentially with the size; third, exact algorithms are inefficient in large-scale scenarios, making it difficult to meet the real-time needs of emergency decision-making.

[0005] Therefore, there is an urgent need to design a mixed disaster emergency evacuation path simulation planning method and system based on social distance to solve these problems. SUMMARY

[0006] In view of the complexity and uncertainty of emergency evacuation under mixed disasters, the application provides a mixed disaster emergency evacuation path simulation planning method and system based on social distance. Through efficient and reliable heuristic-simulation optimization integrated algorithm, collaborative optimization is carried out to realize efficient and reliable evacuation decision. First, a simulation optimization framework is proposed, and an efficient heuristic algorithm, K shortest path capacity planning algorithm with social distance, is developed. The algorithm is realized through three operators, i.e. K shortest path generation operator with node capacity constraint, conflict road section identification operator and conflict road section capacity allocation operator with social distance, to quickly generate satisfactory evacuation scheme and determine social distance level under determined parameters. The social distance decision and conflict road section capacity allocation are closely coupled to form a collaborative optimization mechanism, effectively avoiding the increase of infection risk and evacuation delay caused by local path congestion, and dynamically balancing evacuation time and infection risk. Second, the developed K shortest path capacity planning algorithm with social distance is integrated into the simulation optimization framework to form a mixed disaster emergency evacuation path simulation planning method based on social distance. The method builds an alternative scheme library under uncertain parameters to avoid scheme failure caused by extreme path conditions and improve the effectiveness and reliability of path planning decision under complex disaster concurrent conditions.

[0007] To achieve the above object, the application provides the following technical scheme:

[0008] A mixed disaster emergency evacuation path simulation planning method based on social distance, comprising the following steps:

[0009] S1, design a K shortest path generation operator with node capacity constraint to generate the first K feasible evacuation paths for each source node under the constraints of network topology graph, node capacity, arc segment capacity and arc segment travel time, and calculate the maximum flow and evacuation time of each path;

[0010] S2, design a conflict road section identification operator to identify the space-time overlap between paths of different source nodes based on the multi-source path set and the number of evacuees, and generate a conflict road section set and a node priority;

[0011] S3, design a conflict road section capacity allocation operator with social distance to couple different social distance levels with the capacity allocation of conflict road sections, allocate flow to each source node path within a discrete planning period, and output the evacuation scheme under different social distance levels after completing capacity update, and finally select the social distance level with the highest satisfaction score;

[0012] S4, design a simulation optimization framework to integrate the above heuristic operators, perform random sampling and budget allocation under uncertain parameters, generate and screen multiple alternative evacuation schemes, and finally obtain the optimal emergency evacuation path scheme.

[0013] As a preferred technical scheme of the present application, the K shortest path generation operator with node capacity constraint comprises the following sub-steps:

[0014] (1) Convert the multi-terminal problem into a single-terminal problem, introduce a super-terminal in the network, and connect all terminals to the super-terminal through an arc segment with unlimited capacity and zero travel time;

[0015] (2) Initialize the source node counter, path search counter, copy the original network, and set the node capacity and arc segment capacity;

[0016] (3) Find the shortest path from the source node to the super-terminal in the network using Dijkstra's algorithm, and when the path exists, preferentially select the path with the shortest travel time and remaining flow;

[0017] (4) Calculate the maximum flow of the path, which is determined by the minimum node capacity and arc segment capacity on the path; calculate the total travel time of the path, which is the sum of the travel times of all arc segments on the path;

[0018] (5) Update the node capacity and arc segment capacity, and remove them from the network when the capacity is zero;

[0019] (6) Loop until the number of feasible paths of the source node reaches the preset threshold, or there is no feasible path.

[0020] As a preferred technical scheme of the present application, the conflict road segment identification operator comprises the following sub-steps:

[0021] (1) Calculate the potential evacuation time of each source node, and arrange them in descending order of value, giving higher priority to nodes with longer potential evacuation time;

[0022] (2) Traverse the paths of each source node and detect whether there is a coincidence with other paths at a certain arc segment;

[0023] (3) If there is a conflict, mark the arc segment and its path segment to the super-terminal as a conflict road segment;

[0024] (4) Remove and aggregate all conflict road segments to generate a global conflict road segment set, and record their capacity and travel time information.

[0025] As a preferred technical scheme of the present application, the conflict road segment capacity allocation operator with social distance comprises the following sub-steps:

[0026] (1) Input the discrete planning period range, the number of people to be evacuated at each source node, the path set, the maximum flow of the path, the travel time of the path, the conflict road segment set, the social distance level and its corresponding infection risk and capacity loss rate, and the weight;

[0027] (2) In the planning period, the traffic is preferentially allocated according to the node priority order, and the high-priority node preferentially selects the fastest path thereof;

[0028] (3) When the path contains a conflict road section, the smaller value of the available traffic at the current social distance level and the residual capacity of the conflict road section is taken as the allocated traffic;

[0029] (4) When the path does not contain a conflict road section, the available traffic at the current social distance level is directly taken as the allocated traffic;

[0030] (5) After completing a traffic allocation, the conflict road section capacity table is updated until all source nodes are evacuated;

[0031] (6) Corresponding evacuation schemes are generated at multiple social distance levels, and the highest scoring social distance level and the corresponding scheme are selected based on the weighted satisfaction score of evacuation time and infection risk.

[0032] As a preferred technical solution of the application, the social distance level is a plurality of discrete levels, each level corresponds to a capacity reduction ratio and a relative infection risk value, and the method generates evacuation schemes at each level and compares and selects according to the satisfaction score.

[0033] As a preferred technical solution of the application, the simulation optimization framework includes a candidate scheme pre-selection step, specifically:

[0034] Randomly generate parameter samples under a pre-selected budget, run the K-shortest path generation operator with node capacity constraints to generate a plurality of evacuation schemes, and retain high-frequency schemes as a candidate scheme set through frequency statistics.

[0035] As a preferred technical solution of the application, characterized in that the simulation optimization framework includes a sampling optimization step, specifically:

[0036] (1) Assign an initial simulation budget to each candidate scheme, call the conflict road section identification operator and the conflict road section capacity allocation operator with social distance, calculate the initial mean and variance of the scheme satisfaction score, and

[0037] (2) In the sampling process, the posterior distribution information of the scheme is dynamically updated, and the optimal candidate scheme is selected according to the approximate value function result to perform the next round of budget allocation until all simulation budgets are allocated.

[0038] As a preferred technical solution of the application, the simulation optimization framework includes a scheme screening step, specifically:

[0039] After sampling is completed, the candidate schemes are sorted according to the posterior expected performance of the satisfaction score, and the top several best-performing schemes are selected as the final output of the candidate scheme set.

[0040] The application provides a social distance-based mixed disaster emergency evacuation multi-scheme path planning system, comprising:

[0041] A parameter initialization module is configured to input network topology, node capacity, arc segment capacity, arc segment travel time, social distance level, simulation budget and the like.

[0042] A path generation module is configured to generate shortest path information for each source node under the constraint of node capacity.

[0043] An evacuation scheme generation module is configured to perform capacity allocation with social distance based on path information and conflict road segment identification results, and generate an evacuation scheme.

[0044] An alternative pre-generation module is configured to generate a candidate evacuation scheme set under uncertain parameters.

[0045] A multi-scheme selection module is configured to perform dynamic allocation and evaluation on the candidate schemes under the simulation budget, and select the best alternative scheme.

[0046] A social distance level analysis module is configured to simulate the effectiveness of the scheme under different social distance levels and output dynamic suggestions.

[0047] As a preferred technical scheme of the application, the system can be connected with an emergency command platform, and realize real-time generation of evacuation paths, updating of schemes and multi-scheme recommendation under different mixed disaster scenarios.

[0048] Compared with the prior art, the application has the following beneficial effects:

[0049] (1) Multi-scheme reliable decision support under uncertain environment. The existing simulation optimization method mainly depends on fixed sampling strategy or experience parameter setting, and has poor adaptability to dynamic evolution of disasters and parameter uncertainty. The social distance-based mixed disaster emergency evacuation path simulation planning method of the application dynamically evaluates the expected performance of the candidate scheme under the parameter distribution through a Bayesian updating mechanism, preferentially allocates computing resources to potential schemes, and significantly enhances the reliability of the scheme in the dynamic evolution of disasters. The method breaks through the limitation of low efficiency of traditional simulation, and provides a multi-scenario alternative scheme library for decision makers with flexibility and reliability.

[0050] (2) The path generation ability with dynamic node capacity constraint. The traditional path planning algorithm usually only considers the arc segment capacity limit and ignores the influence of node capacity on evacuation efficiency, which is easy to generate a theoretically feasible path but may cause local congestion in practice. The K shortest path generation operator with node capacity constraint based on the mixed disaster emergency evacuation path simulation planning method based on social distance in the application dynamically adjusts the remaining capacity of the node, synchronously reduces the node and arc segment capacity in the path generation stage, ensures that the generated evacuation path not only meets the requirement of shortest time, but also avoids the risk of systematic congestion caused by node overload, and significantly improves the executability of the path in the actual evacuation scene. This step serves as the basis for the heuristic algorithm, and provides a premise for reducing local congestion and improving the robustness of the scheme.

[0051] (3) Efficient analysis mechanism for multi-source path conflict. The existing methods usually use global optimization model to handle path conflict, which has high computational complexity and is difficult to accurately locate the bottleneck area. The conflict road section identification operator of the mixed disaster emergency evacuation path simulation planning method based on social distance in the application accurately quantifies the resource competition relationship between paths by quickly detecting the space-time overlap of multi-source paths at key nodes and arc segments. This step is the key to the heuristic algorithm, which can accurately identify high-load conflict sections, provide spatial dimension decision basis for subsequent dynamic capacity allocation, effectively reduce the computational burden of global optimization, further reduce the possibility of local congestion, and enhance the robustness of the scheme.

[0052] (4) Dynamic balance between infection risk and evacuation efficiency. In view of the complex trade-off problem between path capacity loss and infection risk reduction caused by social distance measures, the conflict road section capacity allocation operator with social distance of the mixed disaster emergency evacuation path simulation planning method based on social distance in the application introduces heuristic rules through close coupling with dynamic adjustment of social distance, efficiently allocates evacuation capacity and comprehensively compares different social distance levels, so as to realize the organic balance between minimum evacuation time and infection risk control. At the same time, this step further reduces local congestion and improves the robustness of the scheme, which is the core link of the realization technology effect of the heuristic algorithm. BRIEF DESCRIPTION OF DRAWINGS

[0053] The drawings accompanying the specification of the application form a part of the application and serve to further understand the application. The schematic embodiments of the application and their descriptions are used to explain the application, and do not constitute a limitation on the application.

[0054] Figure 1 The figure is a multi-scheme emergency evacuation planning framework of the application;

[0055] Figure 2 The figure is the main flow chart of the simulation optimization integrated algorithm of the application;

[0056] Figure 3The performance comparison chart of the method proposed in the application and the OCBASS and EA methods. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the application will be clearly and completely described below Figure 1 It should be apparent that the following described embodiments are only a part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the application. In order to more clearly explain and illustrate the technical solutions and implementation modes of the application, the following introduces specific examples for implementing the technical solutions of the application.

[0058] The social distance-based hybrid disaster emergency evacuation path simulation planning method comprises the following steps:

[0059] A K-shortest path capacity planning algorithm with social distance is designed, which comprises three heuristic operators.

[0060] The first operator is a K-shortest path generation operator with node capacity constraint. Under the node capacity constraint, the first operator generates the first K feasible evacuation paths for each source node and calculates the maximum flow and evacuation time. The operator can effectively avoid local congestion caused by node overload by simultaneously reducing the node and arc segment capacity during the path generation stage.

[0061] The second operator is a conflict road segment identification operator, which identifies the conflict road segments among the multi-source paths to support the subsequent evacuation personnel allocation. The operator accurately identifies the high-load conflict segments by quickly detecting the space-time overlap of the multi-source paths at the key nodes and arc segments, and quantifies the resource competition relationship among the paths, thereby providing accurate spatial dimension decision basis for subsequent capacity allocation and reducing the possibility of local congestion caused by resource competition.

[0062] The third operator is a conflict road segment capacity allocation operator with social distance, which tightly couples the dynamic allocation of conflict segment capacity and social distance decision to realize the collaborative optimization of evacuation time and infection risk. The operator realizes the organic balance between the minimization of evacuation time and the control of infection risk by efficiently allocating evacuation capacity and comprehensively comparing different social distance levels, while avoiding local congestion and improving the robustness of the scheme.

[0063] A simulation optimization framework is designed, and the above heuristic operators are integrated into the framework to form a social distance-based hybrid disaster emergency evacuation path simulation planning method. In the parameter uncertain environment, the method estimates the expected satisfaction score of the evacuation scheme through the simulation method, and then generates a high-reliability multi-alternative evacuation scheme.

[0064] Further, the K shortest path generation operator with node capacity constraint has the following sub-steps:

[0065] Under the constraint of node capacity, the first K feasible evacuation paths are generated for each source node, and the maximum flow and evacuation time are calculated. The specific process includes:

[0066] Input: network topology graph, node capacity, arc segment capacity, arc segment travel time, maximum path number.

[0067] Output: path set of each source node, maximum flow of each path, path travel time.

[0068] Problem transformation, convert the multi-terminal problem into an equivalent single-terminal problem: add a super-terminal in the network, let its capacity be infinite; select all other terminals, respectively add a directed arc pointing to it, and let their travel time be 0, and the arc segment capacity be infinite; add the newly added super-terminal and the related edge to the original network to get the new network; at this point, the original problem is transformed into an equivalent single-terminal problem.

[0069] Algorithm initialization: including initializing the source node counter, initializing the path search counter, copying the network, setting the initial node capacity, and arc segment capacity.

[0070] Path search:

[0071] For each source node, use Dijkstra's algorithm to find the shortest path to the super-terminal in the network, and preferentially select the path with the shortest travel time and remaining flow;

[0072] If the path does not exist, terminate the search for the source node, record the actual number of generated paths, update the source node counter and the path search counter, and go to the path search step of the next source node.

[0073] Path flow and travel time calculation:

[0074] The maximum flow of the path is determined by the minimum node capacity and arc capacity on the path; the total travel time of the path is the sum of the travel times of all arcs on the path.

[0075] Network update:

[0076] Each time a new path is obtained, update the node capacity on the path: for each node passed, subtract the path flow from its current capacity; if the node capacity is 0 at this time, remove it from the network along with all associated arcs;

[0077] Update the arc segment capacity on the path: for each arc segment passed, subtract the path flow from its current capacity; if the arc segment capacity is 0 at this time, remove it from the network;

[0078] When turning to the next source node iteration process, the network is reset to the original network.

[0079] Iteration termination: if the number of paths obtained by the current source node has not reached the threshold, return to the path search step; otherwise, reset the network and turn to the next source node iteration process; when all source nodes complete the path search iteration, the algorithm terminates.

[0080] This step is an important part of the heuristic algorithm. By dynamically adjusting the remaining capacity of the nodes, the capacity of the nodes and arc segments is reduced synchronously in the path generation phase, which can effectively avoid local congestion caused by node overload, lay a foundation for the subsequent steps, and improve the robustness of the entire scheme.

[0081] Further, the conflict road segment identification operator has the following sub-steps:

[0082] Identify the conflict road segments between multi-source paths to support the subsequent allocation of evacuees. The specific process includes:

[0083] Input: number of evacuees at all source nodes, path set, path flow, path travel time.

[0084] Output: conflict road segment set of each path, and non-repeated conflict road segment set.

[0085] Priority sorting:

[0086] Calculate the expected evacuation time of each source node, sort the source nodes in descending order, and give higher priority to nodes with longer expected evacuation time.

[0087] Conflict detection:

[0088] For each path of each source node, traverse each path of other source nodes, and compare to find conflicting arc segments;

[0089] If two paths coincide at an arc segment, mark the road segment composed of the arc segment and all arc segments after it until the super terminal as a conflict road segment of the source node path.

[0090] Conflict road segment aggregation:

[0091] Remove all conflict road segments to generate a global conflict road segment set, and record the capacity and travel time of each conflict road segment.

[0092] This step is a key link of the heuristic algorithm. By quickly detecting the space-time overlap of multi-source paths at key nodes and arc segments, accurately identifying high-load conflict segments, and clearly quantifying the resource competition relationship between paths, it provides accurate spatial dimension decision basis for subsequent capacity allocation, reduces the possibility of local congestion caused by resource competition, and further enhances the robustness of the scheme.

[0093] Further, the social distance conflict road section capacity allocation operator has the following sub-steps:

[0094] Dynamic allocation of conflict section capacity, determine social distance level, balance evacuation time and infection risk, this step is closely coupled with dynamic adjustment of social distance, the specific process includes:

[0095] Input: discrete planning period range, the number of people to be evacuated at each source node, path set, maximum flow of each path, path travel time, conflict road section set, social distance level and its corresponding infection risk and capacity loss rate, weight.

[0096] Output: optimal social distance scheme, optimal evacuation scheme.

[0097] Priority scheduling: process in descending order of source node evacuation time, allocate faster path flow to high priority nodes first.

[0098] Conflict road section capacity allocation: when a path with conflict road section can reach the end point in the current period, the flow allocation value of the path in the period is taken as the smaller value of its available flow under the current social distance level and the current capacity of the conflict section it passes through. Because of different social distance levels, the available flow will change, which will affect the capacity allocation of the conflict road section, and the capacity status of the conflict road section will prompt the reevaluation of the social distance level, forming a coupling relationship.

[0099] Non-conflict path capacity allocation: when a path with no conflict road section can reach the end point in the current period, the flow allocation value of the path in the period is taken as its available flow under the current social distance level.

[0100] Capacity allocation needs to be performed on the current source node for evacuation completion determination: when the allocated flow is greater than the remaining number of people to be evacuated at the current node, take the smaller value of the two as the flow allocation value of the path in the period, and after updating the conflict road section capacity, enter the iteration process of the next source node.

[0101] Conflict road section capacity update: update the remaining capacity of the conflict road section in each period after completing the conflict road section flow once.

[0102] Social distance selection: for each social distance level, obtain the evacuation scheme through the above steps, calculate the multi-objective weighted satisfaction score of evacuation efficiency and risk control, select the highest score as the best social distance, and output the evacuation scheme under the best social distance level.

[0103] This step is the core of the heuristic algorithm, which efficiently allocates evacuation capacity and compares different social distance levels by coupling with dynamic adjustment of social distance, realizes the organic balance of minimum evacuation time and infection risk control, and avoids local congestion and improves the robustness of the scheme.

[0104] Further, the simulation optimization framework integrated with heuristic operators has the following sub-steps:

[0105] Under the environment of parameter uncertainty, the expected satisfaction score of the evacuation scheme is estimated by the simulation method, and then a high-reliability multi-alternative evacuation scheme is generated.

[0106] Input: network parameter distribution information, pre-selection budget, simulation budget, initial budget, pre-selection scheme number, best alternative scheme number.

[0107] Output: best alternative scheme set, scheme expected satisfaction score estimate.

[0108] Preselection of candidate schemes: randomly generate parameter samples under the pre-selection budget, generate a number of path schemes by running the K shortest path generation operator with node capacity constraints, and reserve high-frequency schemes as the candidate scheme set through frequency statistics.

[0109] Sampling optimization:

[0110] Initialization: allocate an initial simulation budget to each candidate scheme, calculate the initial mean and variance of the satisfaction score by the conflict road segment identification operator and the conflict road segment capacity allocation operator with social distance.

[0111] Dynamic sampling: after each round of sampling, update the posterior distribution information, and dynamically select the next sampling scheme according to the approximate value function until all simulation budgets are allocated.

[0112] Scheme screening: after the simulation is completed, arrange the schemes in descending order according to the posterior performance of the expected satisfaction score, and select the best performance of a number of schemes as the final output and include them in the alternative scheme library.

[0113] Further, the present application provides a mixed disaster emergency evacuation multi-scheme path planning system based on social distance, comprising:

[0114] Parameter initialization module, used for initializing algorithm parameters, including network topology graph, node capacity, edge capacity and travel time, social distance level, simulation budget, etc.

[0115] Path generation module, used for generating the shortest path information of each source node according to the given or simulated network information scenario.

[0116] The evacuation scheme generation module is configured to identify conflict road sections and dynamically allocate traffic according to the path information, and generate an optimal social distance level and evacuation planning scheme.

[0117] The alternative pre-generation module is configured to dynamically generate a plurality of candidate evacuation path planning schemes according to known uncertain parameter information.

[0118] The multi-scheme selection module is configured to perform budget allocation, evaluation and sorting on the pre-generated alternative schemes, and finally select an optimal alternative scheme to be included in the scheme library.

[0119] The social distance level analysis module is configured to simulate the selection of a social distance level under different scenarios and the influence on the effectiveness of the evacuation scheme, and give a dynamic suggestion of an optimal social distance level.

[0120] Embodiment I

[0121] As shown in Figure 1 , the embodiment discloses a K-shortest path capacity planning algorithm with social distance, which is an important part of the mixed disaster emergency evacuation path simulation planning method based on social distance proposed by the present application, and includes the following steps:

[0122] S1: providing a K-shortest path generation operator with node capacity constraints, generating a feasible evacuation path for each source node and calculating the maximum flow and evacuation time under given network path information and node capacity constraints;

[0123] S2: providing a conflict road section identification operator to identify potential conflict road sections between different paths of different source nodes;

[0124] S3: providing a conflict road section capacity allocation operator with social distance, selecting an optimal social distance level and generating an evacuation scheme based on path and conflict road section information and dynamic adjustment of social distance;

[0125] Next, a K-shortest path capacity planning algorithm with social distance disclosed by the embodiment will be described in detail.

[0126] In S1, based on the K-shortest path generation operator with node capacity constraints, the shortest path of each source node is obtained, and the maximum flow and evacuation time are calculated. Given the input network , and node capacity , arc capacity and arc travel time .

[0127] S101: converting the multi-destination network problem into a single-destination network problem:

[0128] S1011: introducing a virtual destination node​ ;

[0129] S1012: Direct each node in the original destination set with a new one-way arc , and set the arc travel time as 0 and the capacity as infinite; ;

[0130] S1013: Generate a new network, i.e. a new single-destination network problem. ;

[0131] S102: For each source node, obtain its shortest paths, calculate its maximum flow and evacuation time, and update the network. The detailed procedure for obtaining each shortest path of each source node is as follows: ;

[0132] S1021: For the first shortest path of the source node to the terminal , obtain it in the network using Dijkstra algorithm. If there is no shortest path, let the actually available shortest path of the source node be , then let and go to the next node ; ; ;

[0133] S1022: Calculate the maximum flow of the path : the minimum value of the flow of all arcs and the capacity of all passed nodes, and let the residual of the passed nodes and arcs minus ; ;

[0134] S1023: Calculate the travel time of the path : the sum of the travel times of all arcs on ; ;

[0135] S1024: Update the nodes in the network: for the nodes with residual capacity of 0, remove them and the arcs directly connected to them from the network; ;

[0136] S1025: Update the arcs in the network: for the arcs with residual capacity of 0, remove them from the network; ;

[0137] S1026: Path loop and termination: if at this time , let the actually available shortest path of the source node be , then let , go to the next node , and let the network ; if , let , update the network as new , go to the next path of the node;

[0138] S1027: node loop and termination: when , and or there is no shortest path, the algorithm terminates.

[0139] S103: algorithm output: the shortest paths of each source node, and its maximum flow and evacuation time .

[0140] In S2, the potential conflict path between different paths of different source nodes is identified based on the conflict path identification operator. The input is: the number of people to be evacuated , shortest paths of each source node, and its maximum flow and evacuation time .

[0141] S201: get the priority of the source node:

[0142] S2011: calculate the potential evacuation time of each node using the following formula :

[0143] ;

[0144] S2012: according to the potential evacuation time, arrange in descending order to get a new order , the larger the source node has higher priority.

[0145] S202: start from the fastest path of the source node with high priority, get the conflict path table of each path of each source node :

[0146] S2021: compare with any path of any node (including itself), whether there is path conflict;

[0147] S2022: if there is conflict, record it as , write it into .

[0148] S203: summarize all , and put the non-repeated conflict path into a new set .

[0149] S204: Output: Set of conflict road segments without repetition , node priority order , potential evacuation time , all conflict path table .

[0150] In S3, based on the conflict road segment capacity allocation operator with social distance, combined with dynamic adjustment of social distance, the evacuees are allocated to each path within the planning period range, and the social distance level is determined. The input is: Set of conflict road segments without repetition , node priority order , potential evacuation time , all conflict path table , the number of people to be evacuated at each source node , shortest path , and its maximum flow evacuation time , the capacity reduction coefficient corresponding to the social distance and the infection risk coefficient , the upper and lower limits of evacuation time , the upper and lower limits of relative infection risk , weight .

[0151] S301: Initialize conflict path capacity table . For each social distance level, initialize its evacuation scheme and conflict road segment capacity table , where the capacity reduction due to social distance is deducted.

[0152] S302: Obtain the evacuation planning scheme under each social distance level.

[0153] S303: Assign all source nodes in priority order in turn, complete one node and then calculate the next node:

[0154] S3031: For a source node at a certain time , in turn, determine whether the path can reach the destination at this time, if it cannot reach the destination, the next path is determined, if it can reach the destination, capacity allocation is performed;

[0155] S3032: Capacity allocation: first allocate the maximum flow after deducting the capacity reduction to it directly, write Then, it is determined whether any conflict road section is passed. If no conflict exists, the evacuation completion is determined. If a conflict exists, the conflict capacity is calculated.

[0156] S3033: Conflict capacity calculation: the path Allocated capacity is compared with the capacity of the conflict road section corresponding to the current time, and the minimum value is selected. Then, the evacuation completion is determined.

[0157] S3034: Evacuation completion determination: if the current remaining number of untransferred people is not reached, only the conflict road section capacity table needs to be updated , and the calculation of the next path is continued. If the current remaining number of untransferred people is exceeded, the minimum value of the two is taken as the evacuation personnel allocation , the conflict road section capacity table is updated , and the calculation of the current source node is terminated, and the next source node is entered.

[0158] S3035: Update conflict road section capacity table: the capacity of all conflict paths related to the current time is deducted .

[0159] S3036: When all source node calculations are completed, the evacuation scheme under the social distance level is obtained, and the evacuation completion time is obtained. .

[0160] S304: After completing the evacuation planning under all social distance levels, the best satisfaction score is calculated according to the following formula , and the best social distance level is selected:

[0161]

[0162] S305: Output: best satisfaction score , best social distance level , best evacuation scheme , and best evacuation time .

[0163] In order to prove the effectiveness of the scheme described in the embodiment, the following specific examples are combined to verify the related experiments:

[0164] A 62-node evacuation network is set up, including 12 source nodes and 3 destination nodes. First, add a super terminal to convert the problem into a single-destination problem. Set three social distance levels: no limit, at least one meter, and at least two meters, respectively denoted as , the relative infection risk is 1.0, 0.4, and 0.3, respectively, and the capacity loss ratio is 0, 0.2, and 0.5, respectively. It is assumed that the capacity of the arc and the capacity of the node are known. Solve the problem, which only needs to use S1, S2, S3 three steps to obtain the accurate satisfactory solution. Experimental results show that the optimal social distance level is one meter ( ), the total evacuation time is 22 minutes, and the final satisfaction score is . After repeated experiments, the average running time of the algorithm is 0.0660 seconds, which reflects the high efficiency of the calculation.

[0165] Example two

[0166] S4: Provide a hybrid disaster emergency evacuation path simulation planning method based on social distance, which integrates the three heuristic operators of the K shortest path capacity planning algorithm with social distance, quickly and efficiently generates multiple alternative solutions under uncertain conditions, and includes them in the solution library;

[0167] In S4, as shown in Figure 2 , in a simulation optimization framework, multiple alternative solutions are generated under uncertain conditions by integrating the above heuristic operators, and the top best alternative solutions are obtained according to the expected value of the solution satisfaction score , which are included in the solution library. Input: parameter information set , solution pre-selection budget , pre-selected solution number , total simulation budget , initial simulation budget of solution , final number of alternative solutions .

[0168] S401: Under the condition of containing uncertain parameter distribution information , randomly sample the uncertain parameters times, each time use step S1 to obtain a set of evacuation path planning solutions and count them. If it appears repeatedly, let its count increase by 1. After the iteration is completed, arrange the solutions in descending order according to the number of occurrences, and keep the top solutions as the pre-selection result. Obtain the prior expectation and variance of the satisfaction score of each solution , assuming that the expectation is unknown and the variance is known .

[0169] S402: Solution initialization: pre-allocate A simulation budget is used to obtain initial observations;

[0170] S403: Simulation Budget Allocation

[0171] S4031: Calculate the posterior performance of each option using the following formula:

[0172]

[0173] in, The solution in this iteration The posterior mean and variance of satisfaction scores. For the plan The number of simulation budgets already allocated, This represents the average of the observed satisfaction scores under the simulation budget.

[0174] S4032: Calculate the approximate value function using the following formula:

[0175]

[0176] S4033: Select the alternative with the highest approximate value function value. Assign a simulation budget to it: incorporating information on the distribution of uncertain parameters Next, perform one random sampling of the uncertain parameters, and then for the alternative schemes... The planning scheme uses steps S2 and S3 to obtain a satisfaction score. Then, the posterior expected value is recalculated, thus completing one simulation.

[0177] S4034: Termination judgment: If at this time If there is still a remaining simulation budget, then return to step S4031 to continue the algorithm; if at this time... If the simulation budget is fully allocated, the loop exits and the result is output.

[0178] S404: Sort the alternatives in descending order based on the posterior expected value of their satisfaction scores, starting with the top three options. The selected option is the optimal alternative. Output: Expected satisfaction score for all alternative options. Best alternative solutions .

[0179] To demonstrate the effectiveness of the solution described in this embodiment, relevant experiments were conducted in conjunction with specific embodiments:

[0180] Based on the evacuation network in the previous specific embodiment, the capacity and travel time of the arcs and the capacity of the nodes are uncertain, but the mean and variance of their normal distribution are known, denoted as the parameter information set. . In the uncertain condition, step S4 is used to seek multiple optimal candidate solutions. Let the solution pre-selection budget , the pre-selected solution number , the total simulation budget , the initial simulation budget of the solution , the final candidate solution number . Experimental results show that among the five pre-selected candidate solutions , , , , the first, third and fourth solutions are the optimal candidate solutions.

[0181] To verify the accuracy of the solution, 10000 simulations are independently performed for each candidate solution, and the average score is taken as the expected performance, which is 0.5517, 0.5490, 0.5518, 0.5517, 0.5491, indicating that the first, third and fourth solutions have higher actual expected performance, proving the accuracy of the algorithm. In addition, after repeated experiments, the average running time of the algorithm is 188.8696 seconds, and accurate results can be obtained, which reflects the high efficiency and reliability of the calculation.

[0182] To further verify the superiority of the proposed method, the social distance-based hybrid disaster emergency evacuation path simulation planning method proposed in the application is compared with the EA and OCBASS methods, and the experimental settings are as follows. Based on the five pre-selected candidate solutions obtained in the embodiment, the simulation budget is gradually increased to . Let in each iteration, the social distance-based hybrid disaster emergency evacuation path simulation planning method, the EA and the OCBASS are independently executed 10000 times, and the number of times of correctly selecting the optimal candidate solution is counted to obtain the correct selection probability PCS of each method. As shown in Figure 3 , the correct selection probability of the social distance-based hybrid disaster emergency evacuation path simulation planning method is significantly higher than that of the EA and the OCBASS under the same simulation budget, which reflects the advancement and high efficiency of the application.

[0183] Embodiment three

[0184] The application provides a social distance-based hybrid disaster emergency evacuation multi-solution path planning system, which comprises:

[0185] A parameter initialization module is used to initialize algorithm parameters, including network topology, node capacity, edge capacity and travel time, social distance level, simulation budget, etc.

[0186] A path generation module is used to generate the shortest path information of each source node according to the given or simulated network information scenario.

[0187] a dispersing scheme generation module, configured to identify conflict road segments and dynamically allocate traffic according to the path information, and generate a best social distance level and a dispersing scheme;

[0188] an alternative pre-generation module, configured to dynamically generate a plurality of candidate dispersing scheme planning schemes according to known uncertain parameter information.

[0189] a multi-scheme selection module, configured to perform budget allocation, evaluation and sorting on the pre-generated alternative schemes, and finally select a best-performing alternative scheme to be included in the scheme library.

[0190] a social distance level analysis module, configured to simulate social distance level selection in different scenarios and the influence on the effectiveness of the dispersing scheme, and give a dynamic suggestion of the best social distance level.

[0191] The modules involved in the second embodiment correspond to those in the first embodiment, and the specific implementation can be referred to the relevant description in the first embodiment.

[0192] The contents not described in detail in the description belong to the prior art known to those skilled in the art. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features, as long as they are within the spirit and principles of the present application. Any modification, equivalent replacement, improvement, etc. shall be included in the protection scope of the present application.

Claims

1. A simulation planning method for emergency evacuation routes in hybrid disasters based on social distancing, characterized in that, Includes the following steps: S1. Design a K-shortest path generation operator with node capacity constraints. Under the constraints of network topology, node capacity, arc capacity and arc travel time, generate the first K feasible evacuation paths for each source node, and calculate the maximum flow and evacuation time of each path. S2. Design a conflict segment identification operator. Based on the multi-source path set and the number of evacuees, identify the spatiotemporal overlap between different source node paths and generate a conflict segment set and node priority. S3. Design a capacity allocation operator for conflict road segments with social distancing, couple different social distancing levels with capacity allocation of conflict road segments, allocate traffic to each source node path during the discrete planning period, and output evacuation schemes under different social distancing levels after completing capacity update, and finally select the social distancing level with the highest satisfaction score. S4. Design a simulation optimization framework that integrates the above heuristic operators. Under the condition of parameter uncertainty, perform random sampling and budget allocation to generate and screen multiple alternative evacuation schemes, and finally obtain the optimal emergency evacuation route scheme.

2. The simulation planning method for emergency evacuation routes in hybrid disasters based on social distancing as described in claim 1, characterized in that, The K-shortest path generation operator with node capacity constraints includes the following sub-steps: (1) Transform the multi-terminal problem into a single-terminal problem, introduce a super-terminal in the network, and connect all the terminals to the super-terminal through arcs with infinite capacity and zero travel time; (2) Initialize the source node counter and path search counter, copy the original network, and set the node capacity and arc capacity; (3) Use Dijkstra's algorithm to find the shortest path from the source node to the super endpoint in the network. When a path exists, prioritize the path with the shortest travel time and remaining flow. (4) Calculate the maximum flow of the path, which is determined by the minimum node capacity and arc capacity on the path; calculate the total travel time of the path, which is the sum of the travel times of all arcs on the path; (5) Update node capacity and arc capacity, and remove the node from the network when the capacity is zero; (6) Repeat until the number of feasible paths to the source node reaches the preset threshold, or until there are no feasible paths.

3. The simulation planning method for emergency evacuation routes in hybrid disasters based on social distancing as described in claim 1, characterized in that, The conflict segment identification operator includes the following sub-steps: (1) Calculate the potential evacuation time of each source node and sort them in descending order of value, giving higher priority to nodes with longer potential evacuation times; (2) Traverse the path of each source node and check if there is any overlap with other paths at a certain arc segment; (3) If a conflict exists, mark the arc segment and its path segment to the super endpoint as a conflict segment; (4) Deduplicatize and aggregate all conflicting road segments to generate a global conflicting road segment set, and record its capacity and travel time information.

4. The simulation planning method for emergency evacuation routes in hybrid disasters based on social distancing as described in claim 1, characterized in that, The conflict segment capacity allocation operator with social distancing includes the following sub-steps: (1) Input the discrete programming time period, the number of people to be evacuated from each source node, the path set, the maximum flow of the path, the path travel time, the set of conflict road segments, the social distancing level and its corresponding infection risk and capacity loss rate, and the weights; (2) During the planning period, traffic is allocated according to the priority of nodes, and high-priority nodes are given priority to select their fastest path; (3) When the path contains conflicting segments, the smaller value between the available flow at the current social distancing level and the remaining capacity of the conflicting segments shall be used as the allocated flow. (4) When the path does not contain conflicting road segments, the available traffic under the current social distancing level is directly taken as the allocated traffic; (5) After completing one flow allocation, update the conflict section capacity table until all source nodes are evacuated; (6) Generate corresponding evacuation plans under multiple social distancing levels, and select the social distancing level with the highest score and its corresponding plan based on the weighted satisfaction score of evacuation time and infection risk.

5. The simulation planning method for emergency evacuation routes in hybrid disasters based on social distancing as described in claim 1, characterized in that, The social distancing level is divided into multiple discrete levels, each level corresponding to a capacity reduction ratio and a relative infection risk value. The method generates evacuation plans at each level and compares and selects them based on satisfaction scores.

6. The simulation planning method for emergency evacuation routes in hybrid disasters based on social distancing as described in claim 1, characterized in that, The simulation optimization framework includes a candidate solution pre-selection step, specifically: Parameter samples are randomly generated under a pre-selected budget. A K-shortest path generation operator with node capacity constraints is run to generate several evacuation schemes. High-frequency schemes are retained as a candidate scheme set by frequency statistics.

7. The simulation planning method for emergency evacuation routes in hybrid disasters based on social distancing as described in claim 1, characterized in that, The simulation optimization framework includes a sampling optimization step, specifically: (1) Allocate an initial simulation budget for each candidate scheme, call the conflict segment identification operator and the conflict segment capacity allocation operator with social distance, and calculate the initial mean and variance of the scheme satisfaction score; (2) During the sampling process, the posterior distribution information of the scheme is dynamically updated, and the optimal candidate scheme is selected for the next round of budget allocation based on the approximate value function results until all simulation budget allocations are completed.

8. The simulation planning method for emergency evacuation routes in hybrid disasters based on social distancing as described in claim 1, characterized in that, The simulation optimization framework includes a scheme selection step, specifically: After sampling, the candidate solutions are ranked according to their posterior expected performance based on their satisfaction scores, and the top few best-performing solutions are selected as the final set of candidate solutions.

9. A multi-path planning system for emergency evacuation in hybrid disasters based on social distancing, characterized in that, include: Parameter initialization module: used to input parameters such as network topology, node capacity, arc capacity, arc travel time, social distance level, and simulation budget; Path generation module: Used to generate shortest path information for each source node under node capacity constraints; Evacuation plan generation module: Used to generate evacuation plans by allocating capacity with social distancing based on route information and conflict segment identification results; Alternative pre-generation module: used to generate a set of candidate evacuation schemes under uncertain parameter conditions; Multi-option selection module: used to dynamically allocate and evaluate candidate options under simulation budget, and select the best performing alternative. Social distancing level analysis module: used to simulate the effectiveness of solutions under different social distancing levels and output dynamic suggestions.

10. The system as described in claim 9, characterized in that, The system can interface with the emergency command platform to enable real-time generation, updating, and recommendation of evacuation routes under different mixed disaster scenarios.

Images