Equipment system toughness optimization method and device based on recovery strategy

Abstract

The embodiment of the invention discloses an equipment system toughness optimization method and device based on a recovery strategy, and the method comprises the steps: obtaining a damaged equipment set, comprising damaged equipment, of an equipment system, and determining a possible alternative recovery scheme set, any alternative recovery scheme in the alternative recovery scheme set comprises at least one maintenance support unit and a recovery sequence of the damaged equipment by each maintenance support unit; taking the recovery toughness value of the equipment system as a target to construct a target function and a constraint condition for recovering each damaged equipment in the damaged equipment set; and selecting an optimal recovery scheme which meets a constraint condition and enables the objective function to be maximum from the alternative recovery scheme set by applying a genetic algorithm, and performing toughness recovery on the equipment system according to the optimal recovery scheme to realize toughness optimization. By means of the mode, the damaged equipment system can be efficiently recovered, decision support is provided for stability of the equipment system, and the recovery capacity of the equipment system is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of equipment system optimization, and specifically to a method and device for optimizing the resilience of an equipment system based on a recovery strategy. Background Art

[0002] In the context of network system confrontation, the adversary constantly seeks opportunities to interfere with and destroy the equipment system, and weakens the confrontation capability of the equipment system by destroying system members. During the system construction period, pre-configuring redundancy for system members for redundant replacement after member failure can maintain the integrity of the equipment system to a certain extent and alleviate the impact of system damage.

[0003] However, the pre-configured redundant resources are limited. In a high-intensity and continuous system confrontation environment, it is inevitable that system members will be damaged but there is no redundancy to replace them. At this stage, in response to the damage to the equipment system, it is necessary to change the strategy and take more proactive measures to restore the damaged members through equipment maintenance, component replacement and other methods to achieve the purpose of system recovery. Therefore, in the face of the damage to multiple system members, it is necessary to use scientific recovery strategies to determine a recovery plan with clear priorities and reasonable resource allocation, so that the equipment system can be restored efficiently and quickly, thereby ensuring the smooth execution of subsequent target tasks. Summary of the invention

[0004] In view of the above problems, an embodiment of the present invention provides a method and device for optimizing the resilience of an equipment system based on a recovery strategy, which overcomes the problem of how to quickly restore the equipment system.

[0005] According to one aspect of an embodiment of the present invention, a method for optimizing the resilience of an equipment system based on a recovery strategy is provided, the method comprising: obtaining a damaged equipment set of an equipment system including various damaged equipment, and determining a set of possible alternative recovery plans, wherein any alternative recovery plan in the set of alternative recovery plans comprises at least one maintenance and support team and the order in which each maintenance and support team recovers the damaged equipment; constructing an objective function and constraints for recovering each damaged equipment in the damaged equipment set with the recovery resilience value of the equipment system as the target; applying a genetic algorithm to select an optimal recovery plan that satisfies the constraints and maximizes the objective function from the set of alternative recovery plans, and recovering the equipment system according to the optimal recovery plan.

[0006] Optionally, the objective function and constraints for recovering each damaged equipment in the equipment set are constructed with the recovery resilience value of the equipment system as the target, including: based on any alternative recovery plan, obtaining the cumulative capacity recovery rate from the start time of the recovery work to the completion of the recovery work; calculating the ratio of the time for the equipment system to recover to the capacity requirement threshold to the entire recovery time, and obtaining the recovery time ratio; calculating the ratio of the cumulative capacity recovery rate to the recovery time ratio, and obtaining the recovery resilience value of the equipment system as the objective function; and determining the constraints for resilient recovery of the equipment system according to the set of alternative recovery plans.

[0007] Optionally, obtaining the cumulative capacity recovery rate from the start time of the recovery work to the completion time of the recovery work includes: calculating the ratio of the integral of the equipment system capacity over time to the integral of the equipment system's steady-state capacity over time:

[0008]

[0009] Among them, μ p Indicates the cumulative recovery rate of ability, t e Indicates the time when the recovery work starts, t f It indicates the time when the recovery work is completed, and P(t) indicates the capability value of the equipment system at time t.

[0010] Optionally, the alternative recovery scheme recovers the equipment system in n stages, and the calculating the ratio of the cumulative recovery rate of the capability to the recovery time ratio to obtain the recovery toughness value of the equipment system as the objective function includes: applying the following relationship to calculate the ratio of the cumulative recovery rate of the capability to the recovery time ratio to obtain the recovery toughness value of the equipment system as the objective function:

[0011]

[0012] Among them, R rec (S i ) represents the recovery toughness value obtained by executing the i-th recovery scheme, θ t is the recovery time ratio, n represents the recovery plan S i The number of stages, t m represents the time when the recovery of the mth stage is completed, P(t m ) indicates t m Time equipment system capability value, P(t f ) is the equipment system capability value after restoration is completed, t e Indicates the time when the recovery work starts, t f Indicates the time when the recovery work is completed, t * Indicates the time when the system capability value reaches the capability requirement threshold.

[0013] Optionally, the constraints for resilient recovery of the equipment system determined according to the set of alternative recovery plans include: determining that the alternative recovery plan is an alternative recovery plan in the set of alternative recovery plans; the number of maintenance and support teams performing recovery work at any moment is less than or equal to the number of maintenance and support teams in the alternative plans that can perform recovery work simultaneously.

[0014] Optionally, the application of a genetic algorithm selects an optimal recovery plan that satisfies the constraints and maximizes the objective function from the set of alternative recovery plans, including: determining the chromosome gene encoding of the genetic algorithm based on any alternative recovery plan from the set of alternative recovery plans, and initializing the population; using the recovery toughness value as the individual fitness of the chromosomes in the population, and repeating the genetic algorithm operation on the population until it is determined that the iteration termination condition is met; selecting the individual with the largest recovery toughness value in the population, and decoding it to obtain the optimal recovery plan.

[0015] Optionally, the genetic algorithm operation includes: a selection operation, a mutation operation and a crossover operation.

[0016] Based on the same inventive concept, a recovery strategy-based equipment system resilience optimization device is provided, including: a recovery plan set unit, used to obtain a damaged equipment set of the equipment system including each damaged equipment, and determine a possible set of alternative recovery plans, any alternative recovery plan in the alternative recovery plan set includes at least one maintenance and support team and the recovery order of each maintenance and support team for the damaged equipment; an objective function acquisition unit, used to construct an objective function and constraints for restoring each damaged equipment in the damaged equipment set with the recovery resilience value of the equipment system as the target; a resilience optimization unit, used to apply a genetic algorithm to select an optimal recovery plan that satisfies the constraints and maximizes the objective function from the alternative recovery plan set, and restore the equipment system according to the optimal recovery plan.

[0017] Based on the same inventive concept, an embodiment of the present invention further proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the aforementioned method when executing the program.

[0018] Based on the same inventive concept, an embodiment of the present invention further proposes a computer storage medium, in which at least one executable instruction is stored, and the executable instruction enables a processor to execute the aforementioned method.

[0019] The embodiment of the present invention obtains the clustering possibility of any node according to the link status of each node in a complex equipment system; obtains a damaged equipment set of the equipment system including each damaged equipment, and determines a possible set of alternative recovery plans, wherein any alternative recovery plan in the set of alternative recovery plans includes at least one maintenance and support team and the recovery order of each maintenance and support team for the damaged equipment; constructs an objective function and constraints for recovering each damaged equipment in the damaged equipment set with the recovery resilience value of the equipment system as the target; applies a genetic algorithm to select an optimal recovery plan that satisfies the constraints and maximizes the objective function from the set of alternative recovery plans, and recovers the equipment system according to the optimal recovery plan, which can help to efficiently recover the damaged equipment system, provide decision support for the stability of the equipment system, and improve the recovery capability of the equipment system.

[0020] The above description is only an overview of the technical solution of the embodiment of the present invention. In order to more clearly understand the technical means of the embodiment of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0022] Figure 1 A schematic diagram of a process of optimizing the resilience of an equipment system based on a recovery strategy provided by an embodiment of the present invention is shown;

[0023] Figure 2 A schematic diagram showing a process of equipment system capability recovery according to an embodiment of the present invention is shown;

[0024] Figure 3 A schematic diagram showing the change in the ability of the equipment system according to the embodiment of the present invention to be restored using different restoration schemes;

[0025] Figure 4 A chromosome schematic diagram of an equipment system resilience optimization method based on a recovery strategy according to an embodiment of the present invention is shown;

[0026] Figure 5 A schematic diagram of cross-operation of a method for optimizing equipment system resilience based on a recovery strategy according to an embodiment of the present invention is shown;

[0027] Figure 6 A schematic diagram of variation operation of the equipment system resilience optimization method based on the recovery strategy according to an embodiment of the present invention is shown;

[0028] Figure 7 A schematic diagram of a genetic algorithm for an equipment system resilience optimization method based on a recovery strategy according to an embodiment of the present invention is shown;

[0029] Figure 8 A schematic diagram of the structure of an equipment system resilience optimization device based on a recovery strategy provided by an embodiment of the present invention is shown;

[0030] Fig. 9 A schematic diagram of an electronic device in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0031] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0032] Figure 1 FIG. 1 is a flow chart of a method for optimizing equipment system resilience based on a recovery strategy provided by an embodiment of the present invention. Figure 1 As shown, the equipment system resilience optimization based on the recovery strategy is applied to the server, and the equipment system resilience optimization method based on the recovery strategy includes:

[0033] Step S11: Obtain a damaged equipment set including each damaged equipment of the equipment system, and determine a possible set of alternative recovery plans, wherein any alternative recovery plan in the set of alternative recovery plans includes at least one maintenance and support team and the recovery order of each maintenance and support team for the damaged equipment.

[0034] In the embodiment of the present invention, the equipment system may be a device network in an industrial system or a system composed of various devices in a social network. Figure 2 , the high-intensity interference and attack of the adversary caused damage to the equipment system. e At this moment, the equipment system capability drops to the minimum p(t e ). At this time, the maintenance and support team responsible for the support mission quickly took action to restore the damaged system equipment members. In actual confrontation scenarios, there are often more than one damaged system equipment member, but the number of maintenance and support teams is limited, and it is impossible to achieve simultaneous recovery of multiple damaged equipment members. It must be carried out in stages. t1 is the time when the first stage of recovery work is completed. After the original damaged system equipment member is restored, it is re-entered into the equipment system and establishes a connection relationship with other equipment members, so that the equipment system capability is increased from P(t e ) is raised to P(t1), and the subsequent recovery process is similar. fAll restoration work is completed at the moment, and the equipment system capacity is increased to p(t f ). The recovery plan determined by the appropriate recovery strategy can restore the equipment system capabilities more quickly and efficiently.

[0035] In step S11, when equipment in the equipment system is damaged, the damaged equipment is obtained and a damaged equipment set is constructed. Determine the recovery resources. In the embodiment of the present invention, all resources required to recover each equipment in the equipment system, including but not limited to personnel, equipment, tools, spare parts, materials, etc., are unified and abstracted into multiple maintenance and support teams. Each maintenance and support team is regarded as an independent unit with a specific resource combination and recovery capability, responsible for executing the system equipment member recovery task. The total amount of recovery resources K max It is the number of maintenance and support teams that can perform recovery work at the same time. According to the recovery resources and the set of damaged equipment, all possible alternative recovery plans are determined to obtain a set of alternative recovery plans. Any alternative recovery plan in the set of alternative recovery plans includes at least one maintenance and support team and the order in which each maintenance and support team recovers the damaged equipment.

[0036] Step S12: constructing an objective function and constraint conditions for restoring each damaged equipment in the damaged equipment set with the recovery toughness value of the equipment system as the target.

[0037] Resilience is usually defined from the perspective of capability, covering multiple aspects such as the responsiveness, adaptability, recovery and sustainability of a system when it encounters interference or pressure. It is the ability of engineering systems and infrastructure to prevent, resist, respond, recover and adapt when facing natural and man-made threats. Its purpose is to quickly restore the original function with minimal social interruption and economic loss in a short time, so as to continue to serve. In practical applications, resilience means predicting, preparing and adapting to constant changes, and having the ability to withstand and recover quickly from interruptions. Combined with the whole process of system confrontation, resilience is a combination of resistance, adaptability, recovery and reconstruction capabilities. In the embodiment of the present invention, the objective function of restoring each damaged equipment in the damaged equipment set is constructed with the recovery resilience value of the equipment system as the target, that is, the objective function of the resilience optimization in the embodiment of the present invention is the recovery resilience value of the equipment system, and the goal of resilience optimization is to maximize the recovery resilience value of the equipment system. The constraint condition is that the recovery resource requirements need to be met, that is, the resources used when restoring the damaged equipment are less than the total recovery resources.

[0038] Step S13: applying a genetic algorithm to select an optimal recovery plan that satisfies the constraint conditions and maximizes the objective function from the set of alternative recovery plans, and performing resilience recovery on the equipment system according to the optimal recovery plan to achieve resilience optimization.

[0039] Genetic Algorithm (GA) is a heuristic search algorithm that is inspired by the theory of biological evolution. It simulates natural selection and genetic mechanisms to perform resilient optimization solutions. Its core lies in the iteration of the population, and through the three basic genetic operations of selection, crossover and mutation, it gradually improves the adaptability of individuals.

[0040] Compared with traditional optimization algorithms, the advantage of genetic algorithms lies in their strong adaptability to global search capabilities and parallel search mechanisms, which make them uniquely efficient in solving complex optimization problems. The optimization process of genetic algorithms does not depend on the specific form of the problem, and does not require the problem to be continuous or differentiable. Therefore, it is very suitable for dealing with discrete and highly complex optimization problems such as determining the recovery plan for a damaged system. By evaluating the performance of each individual (i.e., the resilience value corresponding to the recovery plan) through the fitness function, the genetic algorithm retains excellent individuals in the population, while introducing new genetic mutations to effectively explore the solution space, so that it can quickly converge to a high-quality solution within a limited number of iterations, and obtain the optimal or approximately optimal recovery plan, ensuring that timely decision support can be provided for the recovery of the damaged system in the confrontation scenario.

[0041] In the embodiment of the present invention, the resilience value corresponding to each alternative solution is actually a comprehensive reflection of the combined effects of multiple factors such as system architecture changes, recovery time, and recovery resources. The embodiment of the present invention chooses to maximize the resilience of the recovery phase as the goal, and under the condition of satisfying resource constraints, constructs a recovery strategy model, comprehensively considers multiple factors such as recovery resources, recovery time, and recovery order. Considering the large scale of the alternative recovery solution, the genetic algorithm is used for efficient solution, which helps to efficiently restore the damaged equipment system, provide decision support for the stability of the equipment system, and improve the recovery capability of the equipment system.

[0042] In the embodiment of the present invention, considering the complexity of the equipment system recovery work and the dynamic change characteristics of the equipment system capabilities, the equipment system recovery strategy model of the embodiment of the present invention makes the following assumptions:

[0043] (1) All resources required to restore the members of the equipment system, including but not limited to personnel, equipment, tools, spare parts, materials, etc., are unified and integrated and abstracted into multiple "maintenance support teams". Each maintenance support team is regarded as an independent unit with a specific resource combination and recovery capabilities, responsible for executing the system member recovery task.

[0044] (2) The specific recovery measures taken by the maintenance and support team for damaged members vary depending on the damage to the system members, such as parts replacement, fault repair, redeployment of new equipment, etc., and will not be distinguished in the future and are collectively referred to as recovery work.

[0045] (3) During the restoration of the damaged system member, the capability of the equipment system does not change; when the member is restored and connected to the system, the system capability is improved accordingly.

[0046] (4) For a single maintenance and support team, the recovery work for multiple damaged members is a streamlined operation. After the member is restored and connected to the system, the maintenance and support team moves to the next damaged member to perform the next stage of recovery work.

[0047] (5) The time taken by each maintenance support team to transfer between different damaged members and the differences in their ability to perform recovery work are negligible. The recovery time of each damaged member is only related to the member's own characteristics and the degree of damage.

[0048] The fundamental purpose of executing the recovery strategy in the embodiment of the present invention is to determine the optimal recovery plan, which can use limited recovery resources to improve the system capacity as quickly as possible and quickly restore it to its initial state after the equipment system is damaged. From the analysis of the changes in system capacity during the recovery phase in Chapter 2, it can be seen that the resilience of the equipment system during the recovery phase is an important manifestation of the system's recovery capacity after damage. Therefore, the resilience during the recovery phase can be used as the objective function of the model, and the recovery plan itself can be used as the model decision variable, so that the recovery plan with the best resilience during the recovery phase is the optimal recovery plan to be solved.

[0049] In the recovery phase of damaged equipment, the resilience of resilience comes into play. Through the implementation of a series of recovery measures, the equipment system capability can be efficiently and quickly improved. From the start of the recovery work to the completion of the recovery, the ratio of the integral of the system capability to time can intuitively reflect the recovery capability of the equipment system. The environment in which the equipment system is located changes rapidly, and the opportunity is fleeting. It is necessary to restore the equipment system capability to the capability requirement threshold as soon as possible, so as to effectively guarantee the execution of subsequent activities. Therefore, not only the cumulative improvement of the equipment system capability during the recovery process should be considered, but also whether the equipment system capability can be restored to the required capability requirement threshold in a relatively short time. Based on the above considerations, in step S12, optionally, firstly based on any alternative recovery scheme, the cumulative recovery rate of the capability from the start of the recovery work to the completion of the recovery work is obtained. The cumulative recovery rate of capability describes the ratio of the integral of the equipment system capability to time and the integral of the equipment system's steady-state capability to time from the start of the recovery work to the completion of the recovery work. Preferably, the following relationship is used to calculate the ratio of the integral of the equipment system capability to time and the integral of the equipment system's steady-state capability to time:

[0050]

[0051] Among them, μ p Indicates the cumulative recovery rate of ability, te Indicates the time when the recovery work starts, t f It indicates the time when the recovery work is completed, and P(t) indicates the capability value of the equipment system at time t.

[0052] At the same time, the ratio of the time taken for the equipment system to recover to the capability requirement threshold to the entire recovery time is calculated to obtain the recovery time ratio; the calculation formula is:

[0053]

[0054] Among them, θ t is the recovery time ratio, Δt represents the time required to restore the capacity to the capacity requirement threshold P * The required time, T represents the total time of the entire recovery process, t * Indicates that the equipment system capability has been restored to the capability requirement threshold P * moment.

[0055] For the equipment system, the higher the cumulative recovery rate, the higher the resilience; the lower the recovery time ratio, the earlier the equipment system can reach the required threshold, the higher the recovery efficiency, and the higher the resilience. p and θ t By synthesizing, we can obtain the toughness measurement index of the equipment system in the resistance stage, that is, the recovery toughness value:

[0056]

[0057] Among them, R rec It is the recovery toughness value of the equipment system.

[0058] After obtaining the ratio of the cumulative capacity recovery rate to the recovery time, the ratio of the cumulative capacity recovery rate to the recovery time ratio is calculated to obtain the recovery toughness value of the equipment system as the objective function. Preferably, the following relationship is used to calculate the ratio of the cumulative capacity recovery rate to the recovery time ratio to obtain the recovery toughness value of the equipment system as the objective function:

[0059]

[0060] Among them, R rec (S i ) represents the recovery toughness value obtained by executing the i-th recovery scheme, θ t is the recovery time ratio, n represents the recovery plan S i The number of stages, t m represents the time when the recovery of the mth stage is completed, P(t m ) indicates t m Time equipment system capability value, P(t f ) is the equipment system capability value after restoration is completed, te Indicates the time when the recovery work starts, t f Indicates the time when the recovery work is completed, t * Indicates the time when the system capability value reaches the capability requirement threshold.

[0061] Finally, the constraint conditions for performing resilience recovery on the equipment system are determined based on the set of alternative recovery solutions. Optionally, the constraint conditions include two: one is to determine that the alternative recovery solution is an alternative recovery solution in the set of alternative recovery solutions, that is,

[0062] S i ∈S

[0063] Among them, S i is the i-th recovery plan, and S is the set of alternative recovery plans.

[0064] The other is that the number of maintenance and support teams performing recovery work at any time is less than or equal to the number of maintenance and support teams that can perform recovery work at the same time in the alternative solution.

[0065] K t ∈K max

[0066] Among them, K max represents the total amount of recovery resources, that is, the number of maintenance support teams that can perform recovery work at the same time, K t Indicates the number of maintenance support teams performing recovery work at time t.

[0067] In an embodiment of the present invention, when the interference or attack suffered by the equipment system is not serious and the number of damaged equipment system members is small, the toughness values ​​corresponding to all alternative recovery plans can be listed and calculated in an exhaustive manner to determine the optimal recovery plan. However, the target task is often more complex, and the equipment system is composed of a large number of equipment members. Therefore, as the number of damaged equipment increases, the scale of alternative recovery plans will grow exponentially, which greatly increases the difficulty of selecting recovery plans and the complexity of calculations. For example, when 11 equipment are damaged, the scale of the solution space that meets the constraints will reach tens of millions. To this end, the present application chooses to use a genetic algorithm to solve the equipment system recovery strategy model in order to efficiently and quickly determine the optimal recovery plan.

[0068] In step S13, optionally, firstly, the chromosome gene encoding of the genetic algorithm is determined according to any alternative recovery scheme from the set of alternative recovery schemes, and the population is initialized.

[0069] Encoding and decoding operations are the premise for using genetic algorithms to solve practical problems. Encoding can convert the recovery plan into a data structure that can be operated in the genetic algorithm; decoding can map the optimal individual solved into a specific recovery plan. In genetic algorithms, common encoding methods include real number encoding, binary encoding, permutation encoding, tree encoding, multi-layer encoding, etc. The recovery plan of the equipment system not only includes the recovery order of equipment members, but also involves the arrangement of maintenance and support teams, which is more complicated than general problems. Therefore, this paper chooses a multi-layer encoding method to map the recovery plan and chromosomes.

[0070] Chromosomes can be divided into two layers. The first layer is used to indicate the order in which damaged equipment should be restored, and the second layer is used to indicate the number of the maintenance support team that performs the restoration work. Figure 4 , S3, D2, D4, I5 are the nodes to be restored. Assume that there are two maintenance teams responsible for this maintenance work, numbered U1 and U2 respectively. The structure of one chromosome is as follows Figure 4 As shown, U2 and U1 first recover nodes D2 and D4 respectively. After U1 completes the recovery work of D4, it performs the recovery work of S3. After U2 completes the recovery work of D2, it performs the recovery work of I5. The present application performs gene encoding according to the alternative recovery scheme, obtains multiple chromosomes, combines the obtained multiple chromosomes, and obtains the initialized population.

[0071] After obtaining the initialized population, the recovery toughness value is used as the individual fitness of the chromosome in the population, and the genetic algorithm operation is repeated on the population until it is determined that the iteration termination condition is met; then the individual with the largest recovery toughness value in the population is selected and decoded to obtain the optimal recovery plan.

[0072] In genetic algorithms, the fitness function is a quantification of the performance of individual chromosomes. During the search process, the individual chromosomes are evaluated, and the individual chromosomes are selected for subsequent crossover and mutation operations based on the evaluation results to ensure that the search direction is correct and gradually approach the optimal solution. The execution of the recovery plan will correspond to the change process of the equipment system's capabilities. Different recovery plans will make the equipment system show different toughness, so the recovery toughness value can be used as the fitness function:

[0073] f(i)=R rec

[0074] f(i) represents the individual fitness of chromosome i, R rec Indicates the recovery toughness value corresponding to the recovery plan. Decode the chromosome into a specific solution, write code to simulate the system's change process, and calculate the equipment system capability value at different times to obtain the chromosome's fitness value. The larger the chromosome's fitness value, the better the corresponding recovery plan.

[0075] In the embodiment of the present application, the genetic algorithm operation includes: selection operation, mutation operation and crossover operation. The selection operation is a process for determining which individuals will be retained into the next generation, and the probability of each individual being selected is closely related to its fitness value. Roulette is a selection method widely used in genetic algorithms, which allows each individual to be selected based on its fitness, and individuals with low fitness also have a certain probability of being selected. After the fitness of individuals in the population is calculated, it can be normalized and a roulette wheel can be constructed based on the normalized fitness value for selection until enough individuals are selected for crossover and mutation operations. Normalization can be performed according to the following relationship:

[0076]

[0077] Among them, p i represents the probability of the i-th individual being selected, N represents the number of individuals in the population, and p i represents the probability of an individual being selected.

[0078] After the selection operation, the genetic mechanism of nature is simulated, and the gene fragments of the parents can be combined through crossover, so that the excellent individuals can exchange useful genetic information with each other, thereby improving the search efficiency and producing offspring that are more adaptable to the environment. This application adopts multi-layer coding to randomly assign recovery work to the maintenance and support team, so only the crossover operation is performed on the first layer to generate a new recovery order, and the second layer can be adjusted according to the recovery time. Figure 5 As shown, in order to deal with the possibility of duplication of members in the same individual during crossover, local mapping can be performed to make adjustments while retaining non-duplicate members.

[0079] The purpose of mutation operation is to introduce new genetic mutations in the evolution process of genetic algorithm to increase the genetic diversity of the population, prevent the algorithm from converging to the local optimal solution too early, make the search process cover a wider solution space, and improve the global search ability. The mutation process can be performed at different levels. Figure 6 , generate two random numbers in a given interval as the starting point and end point of the mutation operation, and arrange the genes from the starting point to the end point in reverse order to obtain the mutated chromosome.

[0080] The complete process of using genetic algorithm to select the optimal recovery solution that satisfies the constraint conditions and maximizes the objective function from the set of alternative recovery solutions is as follows: Figure 7As shown, first input the damaged system member set, the input parameters include: population number, crossover probability, mutation probability, maximum number of iterations (max_gen), and perform chromosome gene encoding, initialize the population, and initialize the counter gen=1. Constrain the population, calculate the fitness, and determine whether it meets the algebraic termination condition. If not, perform selection operations, crossover operations, and mutation operations to generate a new generation of populations, set gen=gen+1, and then return to the step of constraining the population. If yes, that is, the algebraic termination condition is met, then output the optimal individual, and decode the optimal individual into the optimal recovery plan.

[0081] After obtaining the optimal recovery plan, the equipment system is restored according to the optimal recovery plan. In this way, the damaged equipment system can be restored efficiently and accurately, especially in confrontation scenarios, the equipment system capability can be quickly restored to the capability requirement threshold, or even quickly restored to full recovery, thereby optimizing the resilience of the equipment system.

[0082] In summary, the embodiment of the present invention obtains a damaged equipment set including each damaged equipment of the equipment system, and determines a possible set of alternative recovery plans, wherein any alternative recovery plan in the set of alternative recovery plans includes at least one maintenance and support team and the recovery order of each maintenance and support team for the damaged equipment; constructs an objective function and constraints for recovering each damaged equipment in the damaged equipment set with the recovery resilience value of the equipment system as the target; applies a genetic algorithm to select the optimal recovery plan that satisfies the constraints and maximizes the objective function from the set of alternative recovery plans, and performs resilience recovery on the equipment system according to the optimal recovery plan to achieve resilience optimization, which can help to efficiently recover the damaged equipment system, provide decision support for the stability of the equipment system, and improve the recovery capability of the equipment system.

[0083] The above specific embodiments of the present invention are described. In some cases, the actions or steps recorded in the embodiments of the present invention can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0084] Based on the same concept, the embodiment of the present invention also provides a hybrid recovery strategy-based equipment system resilience optimization device. Applied to the server. Figure 3 As shown, the equipment system resilience optimization device based on the recovery strategy includes: a recovery plan set unit, an objective function acquisition unit and a resilience optimization unit.

[0085] A recovery plan set unit, used to obtain a damaged equipment set including each damaged equipment of the equipment system, and determine a possible set of alternative recovery plans, wherein any alternative recovery plan in the set of alternative recovery plans includes at least one maintenance and support team and a recovery order of each maintenance and support team for the damaged device;

[0086] An objective function acquisition unit, used to construct an objective function and constraint conditions for restoring each damaged equipment in the damaged equipment set with the recovery toughness value of the equipment system as a target;

[0087] The resilience optimization unit is used to apply a genetic algorithm to select an optimal recovery plan that satisfies the constraint conditions and maximizes the objective function from the set of alternative recovery plans, and perform resilience recovery on the equipment system according to the optimal recovery plan to achieve resilience optimization.

[0088] For the convenience of description, the above device is described as various modules according to their functions. Of course, when implementing the embodiment of the present invention, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0089] The device of the above embodiment is applied to the corresponding method in the above embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0090] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in any one of the above embodiments is implemented.

[0091] An embodiment of the present invention provides a non-volatile computer storage medium, wherein the computer storage medium stores at least one executable instruction, and the computer executable instruction can execute the method described in any of the above embodiments.

[0092] Fig. 9 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 901, a memory 902, an input / output interface 903, a communication interface 904, and a bus 905. The processor 901, the memory 902, the input / output interface 903, and the communication interface 904 are connected to each other in communication within the device through the bus 905.

[0093] The processor 901 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solution provided by the method embodiment of the present invention.

[0094] The memory 902 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 902 can store an operating system and other application programs. When the technical solution provided by the method embodiment of the present invention is implemented by software or firmware, the relevant program code is stored in the memory 902 and called and executed by the processor 901.

[0095] The input / output interface 903 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0096] The communication interface 904 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile device system, WIFI, Bluetooth, etc.).

[0097] The bus 905 includes a path that transmits information between various components of the device (eg, the processor 901 , the memory 902 , the input / output interface 903 , and the communication interface 904 ).

[0098] It should be noted that, although the above device only shows the processor 901, the memory 902, the input / output interface 903, the communication interface 904 and the bus 905, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiment of the present invention, and does not necessarily include all the components shown in the figure.

[0099] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present disclosure is limited to these examples. Based on the concept of the present disclosure, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0100] This application is intended to cover all such substitutions, modifications and variations that fall within the broad scope of all embodiments. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the scope of protection of this disclosure.

Claims

1. A method for optimizing equipment system resilience based on recovery strategy, characterized in that: The method comprises: Acquire a damaged equipment set including each damaged equipment of the equipment system, and determine a possible set of alternative recovery plans, wherein any alternative recovery plan in the set of alternative recovery plans includes at least one maintenance support unit and a recovery order of each maintenance support unit for the damaged equipment; Taking the recovery toughness value of the equipment system as a target, constructing an objective function and constraint conditions for recovering each damaged equipment in the damaged equipment set; A genetic algorithm is applied to select an optimal recovery scheme that satisfies the constraint conditions and maximizes the objective function from the set of alternative recovery schemes, and the equipment system is restored to resilience according to the optimal recovery scheme to achieve resilience optimization.

2. The method according to claim 1, characterized in that The objective function and constraint conditions for restoring each damaged equipment in the equipment set are constructed with the recovery toughness value of the equipment system as the target, including: Based on any alternative recovery plan, obtain the cumulative capacity recovery rate from the start of the recovery work to the completion of the recovery work; Calculate the ratio of the time it takes for the equipment system to recover to the capability requirement threshold to the entire recovery time to obtain a recovery time ratio; Calculating the ratio of the cumulative recovery rate of the capability to the recovery time ratio to obtain a recovery toughness value of the equipment system as an objective function; The constraint conditions for performing resilience recovery on the equipment system are determined based on the set of alternative recovery solutions.

3. The method according to claim 2, characterized in that The method of obtaining the cumulative capacity recovery rate from the start of the recovery work to the completion of the recovery work includes: Calculate the ratio of the integral of the equipment system's ability over time to the integral of the equipment system's ability to stabilize again over time: Among them, μ p Indicates the cumulative recovery rate of ability, t e Indicates the time when the recovery work starts, t f It indicates the time when the recovery work is completed, and P(t) indicates the capability value of the equipment system at time t.

4. The method according to claim 3, characterized in that The alternative recovery scheme recovers the equipment system in n stages, and the ratio of the cumulative capacity recovery rate to the recovery time ratio is calculated to obtain the recovery toughness value of the equipment system as an objective function, including: The following relationship is used to calculate the ratio of the cumulative recovery rate of the capability to the recovery time ratio, and the recovery toughness value of the equipment system as the objective function is obtained: Among them, R rec (S i ) represents the recovery toughness value obtained by executing the i-th recovery scheme, θ t is the recovery time ratio, n represents the recovery plan S i The number of stages, t m represents the time when the recovery of the mth stage is completed, P(t m ) indicates t m Time equipment system capability value, P(t f ) is the equipment system capability value after restoration is completed, t e Indicates the time when the recovery work starts, t f It indicates the time when the recovery work is completed, and t* indicates the time when the system capacity value reaches the capacity requirement threshold.

5. The method according to claim 2, characterized in that: The constraint conditions for performing resilience recovery on the equipment system determined according to the set of alternative recovery solutions include: Determining that the alternative recovery solution is an alternative recovery solution in the set of alternative recovery solutions; The number of maintenance and support teams performing recovery work at any one time is less than or equal to the number of maintenance and support teams that can perform recovery work simultaneously in the alternative solution.

6. The method according to claim 1, characterized in that The applying a genetic algorithm to select an optimal restoration solution that satisfies the constraint conditions and maximizes the objective function from the set of alternative restoration solutions comprises: Determine the chromosome gene code of the genetic algorithm according to any alternative recovery scheme from the set of alternative recovery schemes, and initialize the population; Using the recovery toughness value as the individual fitness of the chromosome in the population, repeating the genetic algorithm operation on the population until it is determined that the iteration termination condition is met; An individual with the largest recovery resilience value in the population is selected, and decoded to obtain an optimal recovery plan.

7. The method according to claim 6, characterized in that The genetic algorithm operation includes: selection operation, mutation operation and crossover operation.

8. A device for optimizing equipment system resilience based on recovery strategy, characterized in that: The device comprises: A recovery plan set unit, used to obtain a damaged equipment set including each damaged equipment of the equipment system, and determine a possible set of alternative recovery plans, wherein any alternative recovery plan in the set of alternative recovery plans includes at least one maintenance and support team and a recovery order of each maintenance and support team for the damaged device; An objective function acquisition unit, used to construct an objective function and constraint conditions for restoring each damaged equipment in the damaged equipment set with the recovery toughness value of the equipment system as a target; The resilience optimization unit is used to apply a genetic algorithm to select an optimal recovery plan that satisfies the constraint conditions and maximizes the objective function from the set of alternative recovery plans, and to restore the equipment system according to the optimal recovery plan.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A computer storage medium, characterized in that: The storage medium stores at least one executable instruction, and the executable instruction enables the processor to execute the method according to any one of claims 1 to 7.

Images