Emergency resource scheduling method considering network vulnerability

Abstract

The invention is suitable for the technical field of emergency resource scheduling, and provides an emergency resource scheduling method considering network vulnerability. Acquiring first data information of a plurality of disaster-affected stations and second data information of a plurality of supply stations in all stations of the rail transit hub; constructing a multi-target emergency resource scheduling optimization function by taking the shortest emergency scheduling time cost, the minimum additional penalty cost and the minimum emergency resource allocation cost as optimization targets according to the first data information of the plurality of disaster-affected sites and the second data information of the plurality of supply sites; and according to the first data information of the plurality of disaster sites, the second data information of the plurality of supply sites and a preset genetic algorithm, solving the multi-target emergency resource scheduling optimization function under a preset constraint condition to obtain an emergency resource scheduling optimization result, thereby solving the problems of non-uniform resource allocation and low efficiency in an existing scheduling method.

Description

Technical Field

[0001] The present application belongs to the technical field of emergency resource scheduling, and in particular, relates to an emergency resource scheduling method taking network vulnerability into consideration. Background Art

[0002] Since emergency resources are often in short supply in the early stages of sudden disasters, the shortage of emergency resources will cause certain stations in the rail transit hub to be damaged by the disaster, thus seriously affecting the normal operation of the entire rail transit hub. Therefore, it is necessary to adopt appropriate emergency resource scheduling methods to schedule emergency resources for the rail transit hub to ensure the normal operation of the entire rail transit hub.

[0003] At present, existing methods mainly consider the dispatch of emergency resources from the aspects of efficiency, fairness and priority. However, when faced with the dispatch of emergency resources in complex rail transit hubs, these methods lack consideration of the importance of each station, resulting in uneven distribution of rescue resources and low rescue efficiency, thus affecting the normal and stable operation of the entire rail transit hub. Summary of the invention

[0004] The embodiment of the present application provides an emergency resource scheduling method that takes network vulnerability into consideration, which can solve the problem of uneven rescue resource allocation and low rescue efficiency caused by the lack of consideration of the importance of each station in the rail transit hub when facing emergency resource scheduling in a complex rail transit hub in the existing method.

[0005] In a first aspect, an embodiment of the present application provides an emergency resource scheduling method considering network vulnerability, the method comprising:

[0006] When an emergency occurs in any rail transit hub, first data information of multiple disaster-stricken sites and second data information of multiple supply sites among all sites of the rail transit hub are obtained, wherein the first data information is used to indicate the disaster-stricken locations, resource requirements, target time of required resources, and rescue priority coefficients of the multiple disaster-stricken sites; and the second data information is used to indicate the supply locations and resource reserves of the multiple supply sites;

[0007] According to the first data information of the plurality of disaster-affected sites and the second data information of the plurality of supply sites, a multi-objective emergency resource scheduling optimization function is constructed with the shortest emergency scheduling time cost, the minimum additional penalty cost and the minimum emergency resource allocation cost as optimization objectives;

[0008] According to the first data information of the plurality of disaster-stricken sites, the second data information of the plurality of supply sites and a preset genetic algorithm, the multi-objective emergency resource scheduling optimization function is solved under preset constraints to obtain an emergency resource scheduling optimization result.

[0009] In a possible implementation manner of the first aspect, before obtaining first data information of multiple disaster-stricken sites and second data information of multiple supply sites in all sites of the rail transit hub, the method includes:

[0010] According to the collective influence key node identification formula, the collective influence of all the stations in the rail transit hub is calculated to obtain the collective influence value of all the stations, wherein the collective influence is used to characterize the importance of the station in the rail transit hub;

[0011] Normalizing the collective influence values ​​of all the sites to obtain priority coefficients of all the sites;

[0012] The rescue priority coefficients of the plurality of disaster-affected sites are determined from the priority coefficients of all the sites.

[0013] In a possible implementation manner of the first aspect, the collective influence key node identification formula is:

[0014]

[0015] Among them, CI r (a) is the collective influence value of the site, a is the site, k a is the degree of the site a, Ball(a,r) is the set of all sites inside a sphere with a radius of r and the site a as the center. is the set of all sites on the frontier sphere, b is the frontier sphere The site in k b is the degree of the site b.

[0016] In a possible implementation manner of the first aspect, constructing a multi-objective emergency resource scheduling optimization function based on the first data information of the plurality of disaster-stricken sites and the second data information of the plurality of supply sites with the shortest emergency scheduling time cost, the minimum additional penalty cost, and the minimum emergency resource allocation cost as optimization objectives includes:

[0017] A first objective function is constructed according to the disaster locations of the multiple disaster-stricken sites, the supply locations of the multiple supply sites, and the target time for the multiple disaster-stricken sites to demand resources, wherein the first objective function is used to characterize the time cost of emergency dispatch from the multiple supply sites to the multiple disaster-stricken sites;

[0018] A second objective function is constructed according to the rescue priority coefficients of the plurality of disaster-stricken sites, the resource requirements of the plurality of disaster-stricken sites, and the resource reserves of the plurality of supply sites, wherein the second objective function is used to characterize the additional penalty costs of the plurality of supply sites to the plurality of disaster-stricken sites;

[0019] A third objective function is constructed according to the disaster locations of the multiple disaster-stricken sites, the supply locations of the multiple supply sites, and the resource reserves of the multiple supply sites, wherein the third objective function is used to characterize the emergency resource allocation cost from the multiple supply sites to the multiple disaster-stricken sites;

[0020] The multi-objective emergency resource scheduling optimization function is constructed based on the first objective function, the second objective function, and the third objective function.

[0021] In a possible implementation manner of the first aspect, the first objective function is:

[0022]

[0023] The second objective function is:

[0024]

[0025] The third objective function is:

[0026]

[0027] Wherein, Z1 is the first objective function, which is used to represent the emergency dispatch time cost; Z2 is the second objective function, which is used to represent the additional penalty cost; Z3 is the third objective function, which is used to represent the emergency resource allocation cost; let the supply site be G i , where i is a natural number, used to represent the location of the supply site, i∈{1,…,m}; the affected site is Q j , where j is a natural number, used to represent the location of the disaster site, j∈{1,…,n}; T1 is the supply site G i Go to the disaster site Q j T2 is the sum of the rescue time from the supply site to the disaster site beyond the standard rescue time; x ij is the scheduling result, which is used to indicate whether the supply site provides resources for the disaster site. i To the affected site Q j When providing resources, x ij =1, when the supply site G i No disaster site Q j When providing resources, xij =0; t cost is the unit time conversion cost coefficient for emergency dispatch; l ij The supply site G i Go to the disaster site Q j distance; p is the penalty coefficient for being late; v is the target speed of the rescue vehicle on the road; t j The affected site Q j The target time for resource demand; s is the affected site Q j The unit penalty cost when resources are not satisfied; f j The affected site Q j The rescue priority coefficient of ij The affected site Q j The resource demand of ij The supply site G i To the affected site Q j The supply of resources provided; ij The supply site G i To the affected site Q j The unit cost of the resource provided.

[0028] In a possible implementation manner of the first aspect, constructing the multi-objective emergency resource scheduling optimization function according to the first objective function, the second objective function, and the third objective function includes:

[0029] Multiplying the first objective function by a first cost weight corresponding to the first objective function to obtain a first optimization objective function corresponding to the first objective function;

[0030] Multiplying the second objective function by a second cost weight corresponding to the second objective function to obtain a second optimization objective function corresponding to the second objective function;

[0031] Multiplying the third objective function by a third cost weight corresponding to the third objective function to obtain a third optimization objective function corresponding to the third objective function;

[0032] The first optimization objective function, the second optimization objective function and the third optimization objective function are added together to obtain the multi-objective emergency resource scheduling optimization function.

[0033] In a possible implementation manner of the first aspect, before solving the multi-objective emergency resource scheduling optimization function under preset constraints according to the first data information of the plurality of disaster-stricken sites, the second data information of the plurality of supply sites, and a preset genetic algorithm to obtain an emergency resource scheduling optimization result, the method includes:

[0034] Setting the preset constraint condition for the multi-objective emergency resource scheduling optimization function;

[0035] Among them, the preset constraints include a first preset constraint, a second preset constraint, a third preset constraint, a fourth preset constraint and a fifth preset constraint; the first preset constraint is used to indicate that the amount of resources obtained by the disaster-stricken site does not exceed the resource demand of the disaster-stricken site; the second preset constraint is used to indicate that the amount of resources provided by the supply site does not exceed the resource reserve of the supply site; the third preset constraint is used to indicate that the resource scheduling transportation volume is non-negative; the fourth preset constraint is used to indicate an integer state constraint on whether the supply site provides resources for the disaster-stricken site; the fifth preset constraint is used to characterize that each of the disaster-stricken sites has resources provided by the supply site.

[0036] In a possible implementation manner of the first aspect, the first preset constraint condition is:

[0037] The second preset constraint condition is:

[0038] The third preset constraint condition is: ij ≥0,y ij is an integer;

[0039] The fourth preset constraint condition is:

[0040] The fifth preset constraint condition is:

[0041] Wherein, suppose the supply site is G i , where i is a natural number, used to represent the location of the supply site, i∈{1,…,m}; the affected site is Q j , where j is a natural number, used to represent the location of the disaster site, j∈{1,…,n}; x ij is the scheduling result, which is used to indicate whether the supply site provides resources for the disaster site. i To the affected site Q j When providing resources, x ij =1, when the supply site G i No disaster site Q j When providing resources, x ij =0;y ij The supply site G i To the affected site Q j The amount of resource supply provided; qj The affected site Q j The resource demand of i The supply site G i of the resource reserves.

[0042] In a possible implementation manner of the first aspect, according to the first data information of the plurality of disaster-stricken sites, the second data information of the plurality of supply sites, and a preset genetic algorithm, the multi-objective emergency resource scheduling optimization function is solved under preset constraints to obtain an emergency resource scheduling optimization result, including:

[0043] According to the first data information of the plurality of disaster-affected sites and the second data information of the plurality of supply sites, an initial population is randomly generated by real number coding; wherein the plurality of initial individuals in the initial population are the scheduling results indicating whether the supply site provides resources for the disaster-affected site; and the number of the initial individuals is a value obtained by multiplying the number of the disaster-affected sites by the number of the supply sites;

[0044] According to the preset fitness function in the preset genetic algorithm, the fitness of the multiple initial individuals in the initial population is calculated to obtain the fitness values ​​of the multiple initial individuals; wherein the preset fitness function is determined by the multi-objective emergency resource scheduling optimization function and the preset static penalty function; the preset static penalty function is used to eliminate the initial individuals that do not meet the preset constraint conditions;

[0045] According to taking the individual with the lowest fitness value among the multiple initial individuals as the offspring of the initial population, performing population iterative updating on the initial population;

[0046] When the number of iterations reaches a preset number of iterations, the population iteration is terminated, and the scheduling result corresponding to the individual with the lowest fitness value among the multiple target individuals obtained after the population iteration update is used as the emergency resource scheduling optimization result.

[0047] In a second aspect, an embodiment of the present application provides an emergency resource scheduling device considering network vulnerability, the device comprising:

[0048] An acquisition module is used to acquire first data information of multiple disaster-stricken sites and second data information of multiple supply sites among all sites of the rail transit hub when an emergency occurs in any rail transit hub, wherein the first data information is used to indicate the disaster-stricken locations, resource requirements, target time of required resources, and rescue priority coefficients of the multiple disaster-stricken sites; and the second data information is used to indicate the supply locations and resource reserves of the multiple supply sites;

[0049] A construction module, configured to construct a multi-objective emergency resource scheduling optimization function based on the first data information of the plurality of disaster-stricken sites and the second data information of the plurality of supply sites, with the shortest emergency scheduling time cost, the minimum additional penalty cost and the minimum emergency resource allocation cost as optimization objectives;

[0050] A solution module is used to solve the multi-objective emergency resource scheduling optimization function under preset constraints based on the first data information of multiple disaster-stricken sites, the second data information of multiple supply sites and a preset genetic algorithm to obtain an emergency resource scheduling optimization result.

[0051] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-mentioned emergency resource scheduling methods considering network vulnerability when executing the computer program.

[0052] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the emergency resource scheduling method considering network vulnerability as described in any one of the above items is implemented.

[0053] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, the terminal device executes the emergency resource scheduling method considering network vulnerability as described in any one of the above-mentioned first aspects.

[0054] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0055] An embodiment of the present application provides an emergency resource scheduling method that takes network vulnerability into consideration. When an emergency occurs in any rail transit hub, first data information of multiple disaster-stricken sites and second data information of multiple supply sites among all sites of the rail transit hub are obtained, wherein the first data information is used to represent the disaster-stricken locations, resource demands, target times of demanded resources, and rescue priority coefficients of the multiple disaster-stricken sites; the second data information is used to represent the supply locations and resource reserves of the multiple supply sites; based on the first data information of the multiple disaster-stricken sites and the second data information of the multiple supply sites, a multi-objective emergency resource scheduling optimization function is constructed with the shortest emergency scheduling time cost, the minimum additional penalty cost, and the minimum emergency resource allocation cost as optimization objectives; based on the first data information of the multiple disaster-stricken sites, the second data information of the multiple supply sites, and a preset genetic algorithm, the multi-objective emergency resource scheduling optimization function is solved under preset constraints to obtain an emergency resource scheduling optimization result. By establishing a multi-objective emergency resource scheduling optimization function and solving the emergency resource scheduling optimization result, we can solve the problem of uneven rescue resource distribution and low rescue efficiency caused by the lack of consideration of the importance of each station in the rail transit hub when facing the emergency resource scheduling of complex rail transit hubs. This greatly reduces the risk of rail transit hubs being impacted by emergencies and maximizes the normal operation of the entire rail transit hub. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 This is a flow chart of an emergency resource scheduling method considering network vulnerability provided by an embodiment of the present application;

[0058] Figure 2 is a flowchart of an emergency resource scheduling method considering network vulnerability provided by another embodiment of the present application;

[0059] Figure 3 It is a structural diagram of an emergency resource scheduling device considering network vulnerability provided by an embodiment of the present application;

[0060] Figure 4 It is a structural schematic diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0061] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0062] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0063] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0064] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0065] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0066] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0067] See also Figure 1 , Figure 11 is a flow chart of an emergency resource scheduling method considering network vulnerability provided by an embodiment of the present application. The method includes:

[0068] S11. When an emergency occurs in any rail transit hub, first data information of multiple disaster-stricken sites and second data information of multiple supply sites among all sites of the rail transit hub are obtained, wherein the first data information is used to indicate the disaster-stricken locations, resource requirements, target time of required resources, and rescue priority coefficients of the multiple disaster-stricken sites; and the second data information is used to indicate the supply locations and resource reserves of the multiple supply sites;

[0069] S12, constructing a multi-objective emergency resource scheduling optimization function based on the first data information of the plurality of disaster-affected sites and the second data information of the plurality of supply sites, taking the shortest emergency scheduling time cost, the minimum additional penalty cost and the minimum emergency resource allocation cost as optimization objectives;

[0070] S13. According to the first data information of the multiple disaster-stricken sites, the second data information of the multiple supply sites and the preset genetic algorithm, the multi-objective emergency resource scheduling optimization function is solved under preset constraints to obtain the emergency resource scheduling optimization result.

[0071] It should be noted that, in this embodiment, the execution subject may be a terminal device such as a server, and no specific limitation is made to this.

[0072] It should be noted that rail transit hub refers to an urban transportation network composed of several rail transit lines, which can be composed of lines of different levels and performances such as subways, light rails, trams or urban railways. Stations refer to the places where multiple lines intersect and transfer in rail transit hubs. Emergency events refer to natural disasters, accidents and disasters that occur suddenly during the normal operation of rail transit hubs and may cause major casualties, property losses, harm to society, etc., and emergency measures need to be taken to respond to them. Network vulnerability refers to the serious damage and loss of function that rail transit hubs may suffer when emergencies (such as natural disasters, accidents and disasters) occur. These disasters may cause line interruptions, station damage, equipment damage and other problems, thereby affecting the normal operation of rail transit hubs and even paralyzing the entire rail transit hub. The existence of network vulnerability makes emergency resource scheduling a key link for rail transit hubs to ensure safety and resume operation in emergencies.

[0073] A disaster-stricken site is a site in a rail transit hub that is affected by an emergency, and the disaster-stricken site requires resource rescue. The first data information is data representing the disaster situation of the disaster-stricken site, mainly including the disaster-stricken location of the disaster-stricken site, the resource demand, the target time of the required resources, and the rescue priority coefficient. Among them, the disaster-stricken location is the specific location of the disaster-stricken site in the rail transit hub; the resource demand is the number of external rescue resources required by the disaster-stricken site after the emergency occurs; the target time of the required resources is the time when the disaster-stricken site hopes to obtain external rescue resources after the emergency occurs; the rescue priority coefficient is used to indicate the rescue priority of the disaster-stricken site in the emergency resource scheduling of the rail transit hub.

[0074] The supply station is a rail transit station or material distribution station that can provide rescue resources when an emergency occurs in a rail transit hub. The second data information is data indicating the resource supply situation of the supply station, mainly including the supply location and resource reserve of the supply station. Among them, the supply location is the specific location of the supply station in the rail transit hub; the resource reserve is the total number of rescue resources currently available at the supply station.

[0075] In step S11, when an emergency occurs in any rail transit hub, first data information of multiple affected stations and second data information of multiple supply stations in all stations of the rail transit hub are obtained to provide data support for subsequent emergency resource scheduling.

[0076] In step S12, the emergency dispatch time cost refers to the rescue time required to send rescue resources from the supply site to the disaster site. The additional penalty cost refers to the additional cost or loss incurred by each disaster site when the rescue resources obtained do not meet or exceed the demand. The emergency resource allocation cost refers to the allocation cost of transportation or manpower generated in resource scheduling. Accordingly, the shortest emergency dispatch time cost is the shortest rescue time required to send rescue resources from the supply site to the disaster site; the minimum additional penalty cost is the minimum additional cost or minimum loss incurred by each disaster site when the rescue resources obtained do not meet or exceed the demand; the minimum emergency resource allocation cost is the minimum allocation cost of transportation or manpower generated in resource scheduling.

[0077] The multi-objective emergency resource scheduling optimization function is a mathematical model that comprehensively considers the emergency scheduling time cost, additional penalty cost and emergency resource allocation cost. It is used to obtain an optimal resource scheduling result by solving the multi-objective emergency resource scheduling optimization function and optimizing the shortest emergency scheduling time cost, minimum additional penalty cost and minimum emergency resource allocation cost of the resources at the same time.

[0078] In step S13, the preset genetic algorithm is a preset algorithm for solving the multi-objective emergency resource scheduling optimization function, that is, the optimal solution of the multi-objective emergency resource scheduling optimization function is searched through the genetic mechanism. The preset constraint condition is a preset constraint rule or restriction in the process of solving the multi-objective emergency resource scheduling optimization function. The emergency resource scheduling optimization result is the optimal emergency resource scheduling scheme obtained by solving the multi-objective emergency resource scheduling optimization function. The emergency resource scheduling optimization result mainly includes the scheduling result, that is, whether the supply site provides resources for the disaster-stricken site, and can also include the resource supply provided by the supply site to the disaster-stricken site. The multi-objective emergency resource scheduling optimization function is solved under the preset constraint conditions by the preset legacy algorithm to obtain the optimal resource scheduling result, and the emergency resources are delivered to the disaster-stricken site in the shortest time, with the minimum cost and the minimum additional penalty.

[0079] An embodiment of the present application provides an emergency resource scheduling method that takes network vulnerability into consideration. When an emergency occurs in any rail transit hub, first data information of multiple disaster-stricken sites and second data information of multiple supply sites among all sites of the rail transit hub are obtained, wherein the first data information is used to represent the disaster-stricken locations, resource demands, target times of demanded resources, and rescue priority coefficients of the multiple disaster-stricken sites; the second data information is used to represent the supply locations and resource reserves of the multiple supply sites; based on the first data information of the multiple disaster-stricken sites and the second data information of the multiple supply sites, a multi-objective emergency resource scheduling optimization function is constructed with the shortest emergency scheduling time cost, the minimum additional penalty cost, and the minimum emergency resource allocation cost as optimization objectives; based on the first data information of the multiple disaster-stricken sites, the second data information of the multiple supply sites, and a preset genetic algorithm, the multi-objective emergency resource scheduling optimization function is solved under preset constraints to obtain an emergency resource scheduling optimization result. By establishing a multi-objective emergency resource scheduling optimization function and solving the emergency resource scheduling optimization result, we can solve the problem of uneven rescue resource distribution and low rescue efficiency caused by the lack of consideration of the importance of each station in the rail transit hub when facing the emergency resource scheduling of complex rail transit hubs. This greatly reduces the risk of rail transit hubs being impacted by emergencies and maximizes the normal operation of the entire rail transit hub.

[0080] In a possible implementation, before obtaining first data information of multiple disaster-stricken sites and second data information of multiple supply sites among all sites of the rail transit hub, the emergency resource scheduling method considering network vulnerability includes:

[0081] According to the collective influence key node identification formula, the collective influence of all stations in the rail transit hub is calculated to obtain the collective influence value of all stations, where the collective influence is used to characterize the importance of the station in the rail transit hub;

[0082] Normalize the collective influence values ​​of all sites to obtain the priority coefficients of all sites;

[0083] The rescue priority coefficients of the multiple disaster-affected sites are determined from the priority coefficients of all the sites.

[0084] It should be noted that the collective influence key node identification formula is used to calculate the collective influence of each station in the rail transit hub. Among them, the collective influence is used to characterize the importance of the station in the rail transit hub, that is, the comprehensive influence of a station in the rail transit hub relative to other stations. The collective influence value is a specific value of the importance of the station calculated according to the collective influence key node identification formula. The collective influence value can represent the size of the collective influence of each station.

[0085] After calculating the collective influence of all stations in the rail transit hub through the collective influence key node identification formula and obtaining the collective influence value of all stations, the collective influence values ​​need to be normalized to obtain the priority coefficients of all stations due to significant differences. After obtaining the priority coefficients of all stations, the rescue priority coefficients of multiple disaster-stricken stations are screened out so that rescue dispatch can be given priority to stations with high priority levels.

[0086] Among them, normalization processing is used to convert values ​​of different magnitudes or ranges into a unified standard form. In this embodiment, by setting the lowest value of the collective influence values ​​of all sites to 1, the other collective influence values ​​are converted into relative values ​​by dividing by the lowest value, thereby obtaining a priority coefficient, that is, converting the collective influence values ​​of all sites into a value between 0 and 1. The normalization process can reduce the potential impact of values ​​of different magnitudes on model performance, which is beneficial for comparison and calculation, and helps to improve the convergence speed of the algorithm. The priority coefficient is obtained after normalization processing based on the collective influence value of the site. The rescue priority coefficient is used to indicate the degree to which each site needs to be given priority for rescue in an emergency. Generally, the higher the rescue priority coefficient, the higher the priority level of the site in rescue.

[0087] It can be understood that the collective influence key node identification formula can effectively identify key but neglected weakly connected sites, and important sites can be effectively identified in rail transit hubs of different scales and structures.

[0088] Specifically, the formula for identifying the key nodes of collective influence is:

[0089]

[0090] Among them, CI r (a) is the collective influence value of the site, a is the site, k a is the degree of site a, Ball(a,r) is the set of all sites inside a sphere with radius r around site a. is the set of all sites on the frontier sphere, b is the frontier sphere The site in k b is the degree of site b.

[0091] It should be noted that the specific calculation process of the collective influence value is as follows: 1) Input the rail transit hub network G, where the nodes in the rail transit hub network G represent all stations, and the edges in the rail transit hub network G represent the connection between every two stations; initialize a data list to store all node information and the corresponding CI value (collective influence value); 2) Traverse all nodes in the rail transit hub network G, and calculate the CI value of each node according to the collective influence key node identification formula; 3) Among all nodes, find the node i with the highest CI value; 4) Store the information of node i and its CI value in the initialized data list; 5) Delete node i from the rail transit hub network G, and update the rail transit hub network G; 6) For each adjacent node of the deleted node i, reduce its degree by 1; 7) Repeat the above steps until the largest connected subgraph no longer exists in the rail transit hub network G, the algorithm terminates, and outputs a data list storing the node information and CI value, that is, the collective influence value of each station is obtained.

[0092] It should be noted that, in actual application, the collective influence key node identification formula can be appropriately adjusted and optimized according to the specific conditions of the rail transit hub and rescue needs.

[0093] Specifically, see Figure 2 , Figure 2It is a flow chart of an emergency resource scheduling method considering network vulnerability provided by another embodiment of the present application. The emergency resource scheduling method considering network vulnerability includes: first, according to the collective influence key node identification formula, all stations of the rail transit hub are identified; that is, the collective influence of all stations of the rail transit hub is calculated to obtain the collective influence value of all stations. Secondly, after the node identification, the priority coefficient of the station is converted into a coefficient, that is, the collective influence value of all stations is normalized to obtain the priority coefficient of all stations. Then, based on the first data information of the multiple disaster-stricken sites and the second data information of the multiple supply sites obtained, a multi-objective emergency resource scheduling optimization function is constructed with the shortest emergency scheduling time cost, the minimum additional penalty cost and the minimum emergency resource allocation cost as the optimization objectives. Finally, the multi-objective emergency resource scheduling optimization function is solved to obtain the emergency resource scheduling optimization result.

[0094] It can be understood that the collective influence key node identification formula can effectively identify key but neglected weakly connected sites, and important sites can be effectively identified in rail transit hubs of different sizes and structures. By considering the multi-objective emergency resource scheduling optimization function of the rescue priority coefficients of the disaster-stricken sites in the rail transit hub, the emergency resource scheduling problem of the rail transit hub under emergencies can be effectively solved, and the efficient use of traditional emergency settings can be achieved and the vulnerability of the rail transit hub can be reduced. Compared with the traditional multi-objective optimization model, the multi-objective emergency resource scheduling optimization function in this embodiment is more suitable for emergency scheduling decisions of rail transit hubs under emergencies, which not only guarantees the resource requirements of important sites, but also greatly reduces the risk of disaster impact on the rail transit hub, and maximizes the normal operation of the entire rail transit hub.

[0095] In a possible implementation, based on the first data information of multiple disaster-affected sites and the second data information of multiple supply sites, a multi-objective emergency resource scheduling optimization function is constructed with the shortest emergency scheduling time cost, the minimum additional penalty cost and the minimum emergency resource allocation cost as optimization objectives, including:

[0096] A first objective function is constructed according to the disaster locations of the multiple disaster-stricken sites, the supply locations of the multiple supply sites, and the target time for the multiple disaster-stricken sites to demand resources, wherein the first objective function is used to characterize the time cost of emergency dispatch from the multiple supply sites to the multiple disaster-stricken sites;

[0097] A second objective function is constructed according to the rescue priority coefficients of the multiple disaster-stricken sites, the resource demands of the multiple disaster-stricken sites, and the resource reserves of the multiple supply sites, wherein the second objective function is used to characterize the additional penalty costs from the multiple supply sites to the multiple disaster-stricken sites;

[0098] A third objective function is constructed according to the disaster locations of the multiple disaster-stricken sites, the supply locations of the multiple supply sites, and the resource reserves of the multiple supply sites, wherein the third objective function is used to characterize the emergency resource allocation cost from the multiple supply sites to the multiple disaster-stricken sites;

[0099] According to the first objective function, the second objective function and the third objective function, a multi-objective emergency resource scheduling optimization function is constructed.

[0100] It should be noted that the first objective function is a function used to represent the time cost of emergency dispatch from the supply site to the disaster site. The first objective function is constructed based on the disaster locations of multiple disaster sites, the supply locations of multiple supply sites, and the target time for multiple disaster sites to demand resources, with the aim of minimizing the emergency dispatch time to ensure that resources can be delivered to the disaster site as soon as possible.

[0101] The second objective function is a function used to represent the additional penalty cost incurred by each disaster site when the allocated resources do not meet or exceed the demand. The second objective function is constructed based on the rescue priority coefficients of multiple disaster sites, the resource requirements of multiple disaster sites, and the resource reserves of multiple supply sites. Since disaster sites with high rescue priority coefficients will incur higher penalty costs when the allocated resources do not meet or exceed the demand, the priority coefficient is introduced to differentiate the additional penalty costs.

[0102] The third objective function is a function for representing the emergency resource allocation cost of allocating resources from the supply site to the disaster-affected site. The third objective function is constructed according to the disaster locations of the multiple disaster-affected sites, the supply locations of the multiple supply sites, and the resource reserves of the multiple supply sites, with the purpose of minimizing the cost in the resource allocation process.

[0103] The multi-objective emergency resource scheduling optimization function is a mathematical model that integrates the first objective function, the second objective function and the third objective function. It is used to simultaneously optimize the emergency scheduling time cost, the additional penalty cost and the emergency resource allocation cost of resources by solving the multi-objective emergency resource scheduling optimization function to obtain an optimal resource scheduling result.

[0104] Specifically, the first objective function is:

[0105]

[0106] The second objective function is:

[0107]

[0108] The third objective function is:

[0109]

[0110] Among them, Z1 is the first objective function, which is used to represent the time cost of emergency dispatch; Z2 is the second objective function, which is used to represent the additional penalty cost; Z3 is the third objective function, which is used to represent the emergency resource allocation cost; let the supply site be G i , where i is a natural number, used to represent the location of the supply site, i∈{1,…,m}; the affected site is Q j , where j is a natural number, used to represent the location of the disaster site, j∈{1,…,n}; T1 is the supply site G i To the disaster site Q j T2 is the total rescue time from the supply site to the disaster site beyond the standard rescue time; x ij is the scheduling result, which is used to indicate whether the supply site provides resources to the disaster site. i To the affected site Q j When providing resources, x ij =1, when supply site G i No disaster site Q j When providing resources, x ij =0; t cost is the unit time conversion cost coefficient for emergency dispatch; l ij Supply site G i To the disaster site Q j distance; p is the penalty coefficient for being late; v is the target speed of the rescue vehicle on the road; t j For the affected site Q j The target time for resource demand; s is the affected site Q j The unit penalty cost when resources are not satisfied; f j For the affected site Q j The rescue priority coefficient; R ij For the affected site Q j The resource demand; y ij Supply site G i To the affected site Q j The supply of resources provided; ij Supply site G i To the affected site Q j The unit cost of the resource provided.

[0111] It should be noted that the supply site G i To the disaster site Q j The distance l ij It can be determined based on the disaster locations of multiple disaster-affected sites and the supply locations of multiple supply sites; the disaster-affected site Q j The rescue priority coefficient fj The collective influence value can be calculated by the collective influence key node identification formula and then converted into a coefficient. Among them, the emergency dispatch unit time conversion cost coefficient t cost , the penalty coefficient p for lateness, the target speed v of the rescue vehicle on the road, the disaster site Q j The target time t of the required resource j 、Affected site Q j Unit penalty cost s for unsatisfied resources, supply site G i To the affected site Q j Unit cost of the resource provided c ij Parameters such as are preset values ​​and are not specifically limited in this embodiment.

[0112] It is understandable that by considering the rescue priority coefficients of the affected stations in the rail transit hub, the multi-objective emergency resource scheduling optimization function can effectively solve the emergency resource scheduling problem of the rail transit hub under emergencies, realize the efficient use of traditional emergency settings and reduce the vulnerability of the rail transit hub. Compared with the traditional multi-objective optimization model, the multi-objective emergency resource scheduling optimization function in this embodiment is more suitable for emergency scheduling decisions of rail transit hubs under emergencies, which not only guarantees the resource requirements of important stations, but also greatly reduces the risk of disaster impact on the rail transit hub, and maximizes the normal operation of the entire rail transit hub.

[0113] In a possible implementation, a multi-objective emergency resource scheduling optimization function is constructed according to the first objective function, the second objective function, and the third objective function, including:

[0114] Multiplying the first objective function by a first cost weight corresponding to the first objective function to obtain a first optimization objective function corresponding to the first objective function;

[0115] Multiplying the second objective function by a second cost weight corresponding to the second objective function to obtain a second optimization objective function corresponding to the second objective function;

[0116] Multiplying the third objective function by a third cost weight corresponding to the third objective function to obtain a third optimization objective function corresponding to the third objective function;

[0117] The first optimization objective function, the second optimization objective function and the third optimization objective function are added together to obtain a multi-objective emergency resource scheduling optimization function.

[0118] It should be noted that the first cost weight is used to measure the relative importance of the first objective function in the multi-objective emergency resource scheduling optimization function. The larger the value of the first cost weight, the larger the proportion of the corresponding first objective function in the solution process. The first optimization objective function is a function obtained by multiplying the first objective function and its corresponding first cost weight, which is used to calculate the emergency scheduling time cost. The second cost weight is used to measure the relative importance of the second objective function in the multi-objective emergency resource scheduling optimization function. The larger the value of the second cost weight, the larger the proportion of the corresponding second objective function in the solution process. The second optimization objective function is a function obtained by multiplying the second objective function and its corresponding second cost weight, which is used to calculate the additional penalty cost. The third cost weight is used to measure the relative importance of the third objective function in the multi-objective emergency resource scheduling optimization function. The larger the value of the third cost weight, the larger the proportion of the corresponding third objective function in the solution process. The third optimization objective function is a function obtained by multiplying the third objective function and its corresponding third cost weight, which is used to calculate the emergency resource allocation cost. Specifically, the first optimization objective function, the second optimization objective function and the third optimization objective function are added together to obtain the final multi-objective emergency resource scheduling optimization function.

[0119] The multi-objective emergency resource scheduling optimization function can be expressed as:

[0120]

[0121] Among them, Z represents the multi-objective emergency resource scheduling optimization function, F1 represents the first cost weight, Z1 represents the first objective function, F2 represents the second cost weight, Z2 represents the second objective function, F3 represents the third cost weight, and Z3 represents the third objective function.

[0122] It should be noted that, in this embodiment, the first cost weight may be 0.4, the second cost weight may be 0.4, and the third cost weight may be 0.2. The specific values ​​of the first cost weight, the second cost weight, and the third cost weight are not limited.

[0123] In a possible implementation, before solving a multi-objective emergency resource scheduling optimization function under preset constraints according to first data information of multiple disaster-stricken sites, second data information of multiple supply sites and a preset genetic algorithm to obtain an emergency resource scheduling optimization result, the emergency resource scheduling method considering network vulnerability includes:

[0124] Setting preset constraints for the multi-objective emergency resource scheduling optimization function;

[0125] Among them, the preset constraints include a first preset constraint, a second preset constraint, a third preset constraint, a fourth preset constraint and a fifth preset constraint; the first preset constraint is used to indicate that the amount of resources obtained by the disaster-stricken site does not exceed the resource demand of the disaster-stricken site; the second preset constraint is used to indicate that the amount of resources provided by the supply site does not exceed the resource reserve of the supply site; the third preset constraint is used to indicate that the resource scheduling transportation volume is non-negative; the fourth preset constraint is used to indicate an integer state constraint on whether the supply site provides resources for the disaster-stricken site; the fifth preset constraint is used to characterize that each disaster-stricken site has resources provided by a supply site.

[0126] It should be noted that when solving the multi-objective emergency resource scheduling optimization function, in order to ensure the feasibility and practical operability of the solution process, it is necessary to set a series of restrictions on the multi-objective emergency resource scheduling optimization function, that is, preset constraints.

[0127] Specifically, the first preset constraint is a constraint indicating that the amount of resources obtained by the disaster site does not exceed the resource demand of the disaster site; that is, in emergency resource scheduling, it must be ensured that the amount of resources obtained by each disaster site does not exceed the amount of resources it needs to avoid waste or shortage of resources. The second preset constraint is used to indicate that the amount of resources provided by the supply site does not exceed the resource reserve of the supply site. The third preset constraint is used to indicate that the resource scheduling transportation volume is non-negative; that is, in emergency resource scheduling, the scheduling transportation volume of resources cannot be negative, and the third preset constraint ensures that it cannot be invalid scheduling. The fourth preset constraint is used to indicate whether the supply site provides resources to the disaster site. In emergency resource scheduling, a binary variable (0 or 1) is usually used to indicate whether the supply site provides resources to the disaster site, that is, the scheduling result; the fourth preset constraint ensures the clarity and operability of the scheduling decision. The fifth preset constraint is used to characterize that each disaster site has a supply site to provide resources; in emergency resource scheduling, each disaster site needs to obtain the necessary resources to support its recovery work, and the fifth preset constraint ensures that each disaster site has at least one supply site to provide it with the required resources.

[0128] Specifically, the first preset constraint condition is: The second preset constraint is: The third preset constraint is: ij ≥0,y ij is an integer; the fourth preset constraint is: The fifth preset constraint is:

[0129] Among them, let the supply site be G i, where i is a natural number, used to represent the location of the supply site, i∈{1,…,m}; the affected site is Q j , where j is a natural number, used to represent the location of the disaster site, j∈{1,…,n}; x ij is the scheduling result, which is used to indicate whether the supply site provides resources to the disaster site. i To the affected site Q j When providing resources, x ij =1, when supply site G i No disaster site Q j When providing resources, x ij =0;y ij Supply site G i To the affected site Q j The amount of resource supply provided; q j For the affected site Q j The resource demand; g i Supply site G i of resource reserves.

[0130] It is understandable that by setting these preset constraints, solutions that do not conform to the actual situation or cannot meet the needs can be excluded, so as to find a more reasonable and effective resource scheduling solution. When solving the multi-objective emergency resource scheduling optimization function, it is necessary to consider these preset constraints at the same time to find the optimal solution that meets all the preset constraints, that is, to find the optimal resource scheduling result to maximize the needs of the disaster-stricken sites and minimize the emergency scheduling time cost, additional penalty cost and emergency resource allocation cost.

[0131] In a possible implementation, based on the first data information of multiple disaster-affected sites, the second data information of multiple supply sites and a preset genetic algorithm, a multi-objective emergency resource scheduling optimization function is solved under preset constraints to obtain an emergency resource scheduling optimization result, including:

[0132] According to the first data information of the plurality of disaster-affected sites and the second data information of the plurality of supply sites, an initial population is randomly generated by real number coding; wherein the plurality of initial individuals in the initial population are scheduling results for indicating whether the supply site provides resources for the disaster-affected site; and the number of the initial individuals is a value obtained by multiplying the number of the disaster-affected sites by the number of the supply sites;

[0133] According to the preset fitness function in the preset genetic algorithm, the fitness of multiple initial individuals in the initial population is calculated to obtain the fitness values ​​of the multiple initial individuals; wherein the preset fitness function is determined by the multi-objective emergency resource scheduling optimization function and the preset static penalty function; the preset static penalty function is used to eliminate the initial individuals that do not meet the preset constraint conditions;

[0134] According to taking the individual with the lowest fitness value among multiple initial individuals as the offspring of the initial population, the initial population is iteratively updated;

[0135] When the number of iterations reaches the preset number of iterations, the population iteration is terminated, and the scheduling result corresponding to the individual with the lowest fitness value among the multiple target individuals obtained after the population iteration update is used as the emergency resource scheduling optimization result.

[0136] It should be noted that the real number encoding method is a method of encoding the genes of individuals in genetic algorithms using real numbers, and each gene corresponds to a parameter or variable of the problem solution. The initial population is a set of initial individuals when performing genetic algorithms, representing potential solutions to the problem. In emergency resource scheduling, each initial individual in the initial population represents a possible resource scheduling result. The initial individual is an element in the initial population. Under the real number encoding method, the initial individual consists of a set of real numbers, each of which corresponds to the scheduling result of whether a supply site provides resources to a disaster site, that is, x ij , the range of real numbers is between the resource requirements of multiple disaster-affected sites, and is randomly generated between the predetermined lower and upper bounds. The number of initial individuals is the product of the number of disaster-affected sites and the number of supply sites. That is, assuming there are i supply sites and j disaster-affected sites, the total number of initial individuals is i*j.

[0137] The preset fitness function is a pre-set function for evaluating the quality of an individual. Usually, the fitness value of an individual is calculated based on the performance of the individual (i.e., the resource scheduling result). The higher the fitness value, the better the individual is and the more likely it is to become the final solution. The fitness value is a numerical value obtained by calculating the preset fitness function for an individual in a population to measure the quality of an individual. In this embodiment, the preset fitness function is determined by a multi-objective emergency resource scheduling optimization function and a preset static penalty function. The static penalty function performs a preset constraint judgment on each individual, squares the solutions corresponding to all individuals that do not meet the preset constraints, sums them, and finally takes the square root. That is, in the genetic algorithm, the lowest fitness value is selected as the offspring to be inherited in the next round of calculation after each calculation. In this embodiment, by adding a static penalty function, the fitness value of the individual that does not meet the preset constraints is improved, so that the individuals that do not meet the preset constraints will be gradually eliminated during the iteration process, and the individuals that meet all the preset constraints are finally obtained after iterative calculation.

[0138] It should be noted that the individual with the lowest fitness value among multiple initial individuals is used as the offspring of the initial population, and the initial population is iteratively updated. In the process of iterative updating of the population, this embodiment adopts the tournament selection strategy, and the mutation operation adopts uniform crossover and bit flip mutation, wherein uniform crossover is to specify a mutation probability, and each gene in the two parents crosses with this probability; bit flip mutation is to negate each gene in the individual according to a given mutation probability. By using the tournament selection method, the core genetic operations of uniform crossover and bit flip mutation, a new generation of population is generated, thereby re-evaluating the fitness of the new individuals. This embodiment uses the elite preservation strategy to screen the generated breeding offspring and retain the more outstanding individuals among them, so that the algorithm can converge faster.

[0139] The number of iterations is the number of generations of population updates performed by the genetic algorithm. The preset number of iterations is the maximum number of generations to be performed before the iteration is stopped. When the number of iterations reaches the preset number of iterations, the genetic algorithm stops.

[0140] Specifically, first, according to the first data information of multiple disaster-stricken sites and the second data information of multiple supply sites, an initial population is randomly generated by real number coding; then, according to a preset fitness function in a preset genetic algorithm, the fitness of multiple initial individuals in the initial population is calculated to obtain the fitness values ​​of the multiple initial individuals; the individual with the lowest fitness value among the multiple initial individuals is taken as the offspring of the initial population, and the initial population is iteratively updated; finally, the population iteration is terminated when the number of iterations reaches the preset number of iterations, and the scheduling result corresponding to the individual with the lowest fitness value among the multiple target individuals obtained after the iterative update of the population is taken as the emergency resource scheduling optimization result.

[0141] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0142] Corresponding to an emergency resource scheduling method considering network vulnerability in the above embodiment, Figure 3 A structural schematic diagram of an emergency resource scheduling device considering network vulnerability provided by an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0143] Reference Figure 3 The emergency resource scheduling device 3 considering network vulnerability includes:

[0144] The acquisition module 31 is used to acquire first data information of multiple disaster-affected sites and second data information of multiple supply sites in all sites of the rail transit hub when an emergency occurs in any rail transit hub, wherein the first data information is used to indicate the disaster-affected locations, resource requirements, target time of the required resources and priority coefficients of the multiple disaster-affected sites; and the second data information is used to indicate the supply locations and resource reserves of the multiple supply sites;

[0145] A construction module 32 is used to construct a multi-objective emergency resource scheduling optimization function based on the first data information of the plurality of disaster-affected sites and the second data information of the plurality of supply sites, taking the shortest emergency scheduling time cost, the minimum additional penalty cost and the minimum emergency resource allocation cost as optimization objectives;

[0146] The solution module 33 is used to solve the multi-objective emergency resource scheduling optimization function under preset constraints according to the first data information of multiple disaster-stricken sites, the second data information of multiple supply sites and a preset genetic algorithm to obtain the emergency resource scheduling optimization result.

[0147] It can be understood that the embodiment of the present application provides an emergency resource scheduling device 3 that takes network vulnerability into consideration. When an emergency occurs in any rail transit hub, the acquisition module 31 acquires first data information of multiple disaster-stricken sites and second data information of multiple supply sites among all sites of the rail transit hub, wherein the first data information is used to represent the disaster-stricken locations, resource demands, target time of demanded resources and priority coefficients of the multiple disaster-stricken sites; the second data information is used to represent the supply locations and resource reserves of the multiple supply sites; then, the construction module 32 constructs a multi-objective emergency resource scheduling optimization function based on the first data information of the multiple disaster-stricken sites and the second data information of the multiple supply sites, with the shortest emergency scheduling time cost, the minimum additional penalty cost and the minimum emergency resource allocation cost as optimization objectives; finally, the solution module 33 solves the multi-objective emergency resource scheduling optimization function under preset constraints based on the first data information of the multiple disaster-stricken sites, the second data information of the multiple supply sites and the preset genetic algorithm, and obtains the emergency resource scheduling optimization result. By establishing a multi-objective emergency resource scheduling optimization function and solving the emergency resource scheduling optimization result, we can solve the problem of uneven rescue resource distribution and low rescue efficiency caused by the lack of consideration of the importance of each station in the rail transit hub when facing the emergency resource scheduling of complex rail transit hubs. This greatly reduces the risk of rail transit hubs being impacted by emergencies and maximizes the normal operation of the entire rail transit hub.

[0148] Furthermore, the emergency resource scheduling device 3 considering network vulnerability includes a priority coefficient determination module, which is specifically used for:

[0149] According to the collective influence key node identification formula, the collective influence of all stations in the rail transit hub is calculated to obtain the collective influence value of all stations, where the collective influence is used to characterize the importance of the station in the rail transit hub;

[0150] Normalize the collective influence values ​​of all sites to obtain the priority coefficients of all sites;

[0151] The rescue priority coefficients of the multiple disaster-affected sites are determined from the priority coefficients of all the sites.

[0152] Further, the building block 32 includes:

[0153] A first objective function construction submodule is used to construct a first objective function according to the disaster locations of the multiple disaster-stricken sites, the supply locations of the multiple supply sites, and the target time of the multiple disaster-stricken sites demanding resources, wherein the first objective function is used to characterize the time cost of emergency dispatch from the multiple supply sites to the multiple disaster-stricken sites;

[0154] A second objective function construction submodule is used to construct a second objective function according to the rescue priority coefficients of the multiple disaster-stricken sites, the resource requirements of the multiple disaster-stricken sites, and the resource reserves of the multiple supply sites, wherein the second objective function is used to characterize the additional penalty costs of the multiple supply sites to the multiple disaster-stricken sites;

[0155] A third objective function construction submodule is used to construct a third objective function according to the disaster locations of the multiple disaster-stricken sites, the supply locations of the multiple supply sites, and the resource reserves of the multiple supply sites, wherein the third objective function is used to characterize the emergency resource allocation cost from the multiple supply sites to the multiple disaster-stricken sites;

[0156] The multi-objective function construction submodule is used to construct a multi-objective emergency resource scheduling optimization function according to the first objective function, the second objective function and the third objective function.

[0157] Furthermore, the multi-objective function construction submodule includes:

[0158] A first optimization objective function determining unit, configured to multiply the first objective function by a first cost weight corresponding to the first objective function to obtain a first optimization objective function corresponding to the first objective function;

[0159] A second optimization objective function determination unit, configured to multiply the second objective function by a second cost weight corresponding to the second objective function to obtain a second optimization objective function corresponding to the second objective function;

[0160] A third optimization objective function determining unit, configured to multiply the third objective function by a third cost weight corresponding to the third objective function to obtain a third optimization objective function corresponding to the third objective function;

[0161] The multi-objective optimization function determination unit is used to add the first optimization objective function, the second optimization objective function and the third optimization objective function to obtain a multi-objective emergency resource scheduling optimization function.

[0162] Furthermore, the emergency resource scheduling device 3 considering network vulnerability includes a preset constraint condition setting module, which is specifically used for:

[0163] Setting preset constraints for the multi-objective emergency resource scheduling optimization function;

[0164] Among them, the preset constraints include a first preset constraint, a second preset constraint, a third preset constraint, a fourth preset constraint and a fifth preset constraint; the first preset constraint is used to indicate that the amount of resources obtained by the disaster-stricken site does not exceed the resource demand of the disaster-stricken site; the second preset constraint is used to indicate that the amount of resources provided by the supply site does not exceed the resource reserve of the supply site; the third preset constraint is used to indicate that the resource scheduling transportation volume is non-negative; the fourth preset constraint is used to indicate an integer state constraint on whether the supply site provides resources for the disaster-stricken site; the fifth preset constraint is used to characterize that each disaster-stricken site has resources provided by a supply site.

[0165] Furthermore, the solution module 33 includes:

[0166] An initial population generating unit is used to randomly generate an initial population by real number coding according to first data information of multiple disaster-affected sites and second data information of multiple supply sites; wherein multiple initial individuals in the initial population are scheduling results used to indicate whether the supply site provides resources for the disaster-affected site; and the number of initial individuals is a value obtained by multiplying the number of disaster-affected sites by the number of supply sites;

[0167] A fitness value calculation unit is used to calculate the fitness of multiple initial individuals in the initial population according to a preset fitness function in a preset genetic algorithm to obtain fitness values ​​of the multiple initial individuals; wherein the preset fitness function is determined by a multi-objective emergency resource scheduling optimization function and a preset static penalty function; the preset static penalty function is used to eliminate the initial individuals that do not meet the preset constraint conditions;

[0168] A population iterative updating unit, used for iteratively updating the initial population by taking the individual with the lowest fitness value among the multiple initial individuals as the offspring of the initial population;

[0169] The scheduling result determination unit is used to terminate the population iteration when the number of iterations reaches a preset number of iterations, and use the scheduling result corresponding to the individual with the lowest fitness value among the multiple target individuals obtained after the population iterative update as the emergency resource scheduling optimization result.

[0170] It should be noted that the information interaction, execution process, etc. between the modules in the above-mentioned emergency resource scheduling device 3 considering network vulnerability are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0171] The present application also provides an electronic device, such as Figure 4 As shown, Figure 4 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 4 The electronic device 4 of this embodiment includes: a memory 41, a processor 42, and a computer program stored in the memory 41 and executable on the processor 42. When the processor 42 executes the computer program, it implements any of the steps in the above-mentioned emergency resource scheduling method embodiment considering network vulnerability.

[0172] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0173] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0174] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera / terminal device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0175] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0176] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0177] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0178] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0179] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An emergency resource scheduling method considering network vulnerability, characterized in that: include: When an emergency occurs in any rail transit hub, first data information of multiple disaster-stricken sites and second data information of multiple supply sites among all sites of the rail transit hub are obtained, wherein the first data information is used to indicate the disaster-stricken locations, resource requirements, target time of required resources, and rescue priority coefficients of the multiple disaster-stricken sites; and the second data information is used to indicate the supply locations and resource reserves of the multiple supply sites; According to the first data information of the plurality of disaster-affected sites and the second data information of the plurality of supply sites, a multi-objective emergency resource scheduling optimization function is constructed with the shortest emergency scheduling time cost, the minimum additional penalty cost and the minimum emergency resource allocation cost as optimization objectives; According to the first data information of the plurality of disaster-stricken sites, the second data information of the plurality of supply sites and a preset genetic algorithm, the multi-objective emergency resource scheduling optimization function is solved under preset constraints to obtain an emergency resource scheduling optimization result.

2. The method for emergency resource scheduling considering network vulnerability according to claim 1, characterized in that: Before obtaining first data information of a plurality of disaster-affected sites and second data information of a plurality of supply sites among all sites of the rail transit hub, the method includes: According to the collective influence key node identification formula, the collective influence of all the stations in the rail transit hub is calculated to obtain the collective influence value of all the stations, wherein the collective influence is used to characterize the importance of the station in the rail transit hub; Normalizing the collective influence values ​​of all the sites to obtain priority coefficients of all the sites; The rescue priority coefficients of the plurality of disaster-affected sites are determined from the priority coefficients of all the sites.

3. The method for emergency resource scheduling considering network vulnerability as claimed in claim 2, characterized in that: The collective influence key node identification formula is: Among them, CI r (a) is the collective influence value of the site, a is the site, k a is the degree of the site a, Ball(a, r) ​​is the set of all sites inside a sphere with a radius of r and the site a as the center. is the set of all sites on the frontier sphere, b is the frontier sphere The site in k b is the degree of the site b.

4. The method for emergency resource scheduling considering network vulnerability according to claim 1, characterized in that: The method constructs a multi-objective emergency resource scheduling optimization function based on the first data information of the plurality of disaster-stricken sites and the second data information of the plurality of supply sites, taking the shortest emergency scheduling time cost, the minimum additional penalty cost and the minimum emergency resource allocation cost as optimization objectives, including: A first objective function is constructed according to the disaster locations of the multiple disaster-stricken sites, the supply locations of the multiple supply sites, and the target time of the demand resources of the multiple disaster-stricken sites, wherein the first objective function is used to characterize the time cost of emergency dispatch from the multiple supply sites to the multiple disaster-stricken sites; A second objective function is constructed according to the rescue priority coefficients of the plurality of disaster-stricken sites, the resource requirements of the plurality of disaster-stricken sites, and the resource reserves of the plurality of supply sites, wherein the second objective function is used to characterize the additional penalty costs of the plurality of supply sites to the plurality of disaster-stricken sites; A third objective function is constructed according to the disaster locations of the multiple disaster-stricken sites, the supply locations of the multiple supply sites, and the resource reserves of the multiple supply sites, wherein the third objective function is used to characterize the emergency resource allocation cost from the multiple supply sites to the multiple disaster-stricken sites; The multi-objective emergency resource scheduling optimization function is constructed based on the first objective function, the second objective function, and the third objective function.

5. The method for emergency resource scheduling considering network vulnerability as claimed in claim 4, characterized in that: The first objective function is: The second objective function is: The third objective function is: Wherein, Z1 is the first objective function, which is used to represent the emergency dispatch time cost; Z2 is the second objective function, which is used to represent the additional penalty cost; Z3 is the third objective function, which is used to represent the emergency resource allocation cost; let the supply site be G i , where i is a natural number, used to represent the location of the supply site, i∈{1,…,m}; the affected site is Q j , where j is a natural number, used to represent the location of the disaster site, j∈{1,…,n}; T1 is the supply site G i Go to the disaster site Q j T2 is the sum of the rescue time from the supply site to the disaster site beyond the standard rescue time; x ij is the scheduling result, which is used to indicate whether the supply site provides resources for the disaster site. i To the affected site Q j When providing resources, x ij =1, when the supply site G i No disaster site Q j When providing resources, x ij =0; t cost is the unit time conversion cost coefficient for emergency dispatch; l ij The supply site G i Go to the disaster site Q j distance; p is the penalty coefficient for being late; v is the target speed of the rescue vehicle on the road; t j The affected site Q j The target time for resource demand; s is the affected site Q j The unit penalty cost when resources are not satisfied; f j The affected site Q j The rescue priority coefficient of ij The affected site Q j The resource demand of ij The supply site G i To the affected site Q j The amount of resources provided; ij The supply site G i To the affected site Q j The unit cost of the resource provided.

6. The method for emergency resource scheduling considering network vulnerability according to claim 5, characterized in that: The multi-objective emergency resource scheduling optimization function is constructed according to the first objective function, the second objective function, and the third objective function, including: Multiplying the first objective function by a first cost weight corresponding to the first objective function to obtain a first optimization objective function corresponding to the first objective function; Multiplying the second objective function by a second cost weight corresponding to the second objective function to obtain a second optimization objective function corresponding to the second objective function; Multiplying the third objective function by a third cost weight corresponding to the third objective function to obtain a third optimization objective function corresponding to the third objective function; The first optimization objective function, the second optimization objective function and the third optimization objective function are added together to obtain the multi-objective emergency resource scheduling optimization function.

7. The method for emergency resource scheduling considering network vulnerability according to any one of claims 1 to 6, characterized in that: Before solving the multi-objective emergency resource scheduling optimization function under preset constraints based on the first data information of the plurality of disaster-stricken sites, the second data information of the plurality of supply sites and a preset genetic algorithm to obtain an emergency resource scheduling optimization result, the method includes: Setting the preset constraint condition for the multi-objective emergency resource scheduling optimization function; Among them, the preset constraints include a first preset constraint, a second preset constraint, a third preset constraint, a fourth preset constraint and a fifth preset constraint; the first preset constraint is used to indicate that the amount of resources obtained by the disaster-stricken site does not exceed the resource demand of the disaster-stricken site; the second preset constraint is used to indicate that the amount of resources provided by the supply site does not exceed the resource reserve of the supply site; the third preset constraint is used to indicate that the resource scheduling transportation volume is non-negative; the fourth preset constraint is used to indicate an integer state constraint on whether the supply site provides resources for the disaster-stricken site; the fifth preset constraint is used to characterize that each of the disaster-stricken sites has resources provided by the supply site.

8. The method for emergency resource scheduling considering network vulnerability according to claim 7, characterized in that: The first preset constraint condition is: The second preset constraint condition is: The third preset constraint condition is: j ≥0,yi j is an integer; The fourth preset constraint condition is: The fifth preset constraint condition is: Wherein, suppose the supply site is G i , where i is a natural number, used to represent the location of the supply site, i∈{1,…,m}; the affected site is Q j , where j is a natural number, used to represent the location of the disaster site, j∈{1,…,n}; x ij is the scheduling result, which is used to indicate whether the supply site provides resources for the disaster site. i To the affected site Q j When providing resources, x ij =1, when the supply site G i No disaster site Q j When providing resources, x ij =0;y ij The supply site G i To the affected site Q j The amount of resource supply provided; q j The affected site Q j The resource demand of i The supply site G i of the resource reserves.

9. The method for emergency resource scheduling considering network vulnerability according to claim 8, characterized in that: According to the first data information of the plurality of disaster-affected sites, the second data information of the plurality of supply sites and a preset genetic algorithm, the multi-objective emergency resource scheduling optimization function is solved under preset constraints to obtain an emergency resource scheduling optimization result, including: According to the first data information of the plurality of disaster-affected sites and the second data information of the plurality of supply sites, an initial population is randomly generated by real number coding; wherein the plurality of initial individuals in the initial population are the scheduling results indicating whether the supply site provides resources for the disaster-affected site; and the number of the initial individuals is a value obtained by multiplying the number of the disaster-affected sites by the number of the supply sites; According to the preset fitness function in the preset genetic algorithm, the fitness of the multiple initial individuals in the initial population is calculated to obtain the fitness values ​​of the multiple initial individuals; wherein the preset fitness function is determined by the multi-objective emergency resource scheduling optimization function and the preset static penalty function; the preset static penalty function is used to eliminate the initial individuals that do not meet the preset constraint conditions; According to taking the individual with the lowest fitness value among the multiple initial individuals as the offspring of the initial population, performing population iterative updating on the initial population; When the number of iterations reaches a preset number of iterations, the population iteration is terminated, and the scheduling result corresponding to the individual with the lowest fitness value among the multiple target individuals obtained after the population iteration update is used as the emergency resource scheduling optimization result.

10. An emergency resource scheduling device considering network vulnerability, characterized in that: include: An acquisition module is used to acquire first data information of multiple disaster-stricken sites and second data information of multiple supply sites among all sites of the rail transit hub when an emergency occurs in any rail transit hub, wherein the first data information is used to indicate the disaster-stricken locations, resource requirements, target time of required resources, and rescue priority coefficients of the multiple disaster-stricken sites; and the second data information is used to indicate the supply locations and resource reserves of the multiple supply sites; A construction module, configured to construct a multi-objective emergency resource scheduling optimization function based on the first data information of the plurality of disaster-stricken sites and the second data information of the plurality of supply sites, with the shortest emergency scheduling time cost, the minimum additional penalty cost and the minimum emergency resource allocation cost as optimization objectives; A solution module is used to solve the multi-objective emergency resource scheduling optimization function under preset constraints based on the first data information of multiple disaster-stricken sites, the second data information of multiple supply sites and a preset genetic algorithm to obtain an emergency resource scheduling optimization result.

Images