Equipment system resilience optimization method and device based on recovery strategy

Abstract

This invention discloses a method and apparatus for optimizing the resilience of an equipment system based on a recovery strategy. The method includes: acquiring a set of damaged equipment, including all damaged equipment, and determining a set of possible alternative recovery schemes. Each alternative recovery scheme includes at least one maintenance support team and the recovery order of each maintenance support team for the damaged equipment; constructing an objective function and constraints for recovering each damaged piece of equipment in the set of damaged equipment, with the recovery resilience value of the equipment system as the objective; applying a genetic algorithm to select the optimal recovery scheme that satisfies the constraints and maximizes the objective function from the set of alternative recovery schemes; and performing resilience recovery on the equipment system according to the optimal recovery scheme to achieve resilience optimization. Through this method, this invention can help efficiently recover damaged equipment systems, provide decision support for the stability of equipment systems, and improve the recovery capability of equipment systems.

Description

Technical Field

[0001] This invention relates to the field of equipment system optimization technology, specifically to a method and apparatus for optimizing the resilience of equipment systems based on recovery strategies. Background Technology

[0002] In the context of network-based warfare, adversaries constantly seek opportunities to disrupt and damage equipment systems, weakening their combat capabilities by compromising system components. Pre-configuring redundancy for system components during the system's development phase, for replacement in case of component failure, can, to some extent, maintain the integrity of the equipment system and mitigate the impact of system damage.

[0003] However, pre-configured redundant resources are limited. In high-intensity and sustained system-wide confrontation environments, situations inevitably arise where system members are damaged but there is no redundancy to replace them. At this stage, in response to damage to the equipment system, a change in strategy is necessary, adopting more proactive measures. This involves various methods such as equipment repair and component replacement to restore damaged members and achieve system recovery. Therefore, when facing damage to multiple system members, a scientific recovery strategy is needed to determine a recovery plan with clear priorities and reasonable resource allocation, enabling the equipment system to recover efficiently and quickly, thereby ensuring the smooth execution of subsequent objectives and missions. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention provide a method and apparatus for optimizing the resilience of equipment systems based on recovery strategies, which overcomes the problem of how to quickly restore equipment systems.

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

[0006] Optionally, the step of constructing the objective function and constraints for restoring each damaged piece of equipment in the equipment set with the recovery resilience value of the equipment system as the objective includes: obtaining the cumulative capacity recovery rate from the start of the restoration work to the completion of the restoration work based on any alternative restoration scheme; calculating the ratio of the time it takes for the equipment system to recover to the capacity requirement threshold to the total restoration time, thus obtaining the restoration time ratio; calculating the ratio of the cumulative capacity recovery rate to the restoration time ratio, thus obtaining the recovery resilience value of the equipment system as the objective function; and determining the constraints for resilience restoration of the equipment system based on the set of alternative restoration schemes.

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

[0008]

[0009] Where, μ p t represents the cumulative recovery rate of energy. e Indicates the start time of resumption of work, t f P(t) represents the time when the recovery work is completed, and P(t) represents the equipment system capability value at time t.

[0010] Optionally, the alternative recovery scheme restores the equipment system in n stages. The step of calculating the ratio of the cumulative capacity recovery rate to the recovery time ratio to obtain the recovery resilience value of the equipment system as the objective function includes: applying the following formula to calculate the ratio of the cumulative capacity recovery rate to the recovery time ratio to obtain the recovery resilience value of the equipment system as the objective function:

[0011]

[0012] Among them, R rec (S i θ represents the recovery resilience value obtained by implementing the i-th recovery scheme. t The recovery time ratio, where n represents the recovery plan S. i The number of stages, t m P(t) represents the time when the m-th stage of recovery is completed. m ) represents t m The system capability value of equipment at all times, P(t) f ) represents the equipment system capability value after restoration, t e Indicates the start time of resumption of work, t f Indicates the time when the recovery work is completed, t * This indicates the moment when the system's capability value reaches the capability requirement threshold.

[0013] Optionally, the constraints for resilience restoration of the equipment system determined according to the set of alternative restoration schemes include: determining that the alternative restoration scheme is one of the alternative restoration schemes in the set of alternative restoration schemes; and that the number of maintenance support teams performing restoration work at any given time is less than or equal to the number of maintenance support teams in the alternative schemes that can perform restoration work simultaneously.

[0014] Optionally, the application of the genetic algorithm to select the optimal recovery scheme that satisfies the constraints and maximizes the objective function from the set of candidate recovery schemes includes: determining the chromosome gene encoding of the genetic algorithm based on any candidate recovery scheme from the set of candidate recovery schemes, and initializing the population; using the recovery resilience value as the individual fitness of chromosomes in the population, performing repeated genetic algorithm operations on the population until the iteration termination condition is met; selecting the individual with the largest recovery resilience value in the population, and decoding it to obtain the optimal recovery scheme.

[0015] Optionally, the genetic algorithm operations include selection, mutation, and crossover.

[0016] Based on the same inventive concept, a device for optimizing the resilience of an equipment system based on a recovery strategy is provided, comprising: a recovery scheme set unit, used to acquire a set of damaged equipment including each damaged piece of equipment in the equipment system, and to determine a set of possible alternative recovery schemes, wherein each alternative recovery scheme in the set of alternative recovery schemes includes at least one maintenance support team and the recovery order of each maintenance support team for the damaged equipment; an objective function acquisition unit, used to construct an objective function and constraints for recovering each damaged piece of equipment in the set of damaged equipment with the recovery resilience value of the equipment system as the objective; and a resilience optimization unit, used to apply a genetic algorithm to select the optimal recovery scheme that satisfies the constraints and maximizes the objective function from the set of alternative recovery schemes, and to recover the equipment system according to the optimal recovery scheme.

[0017] Based on the same inventive concept, this invention also 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 executes the program to implement the aforementioned method.

[0018] Based on the same inventive concept, embodiments of the present invention also propose a computer storage medium storing at least one executable instruction that causes a processor to execute the aforementioned method.

[0019] This invention, through its embodiments, obtains the clustering probability of any node based on the linking of nodes in a complex equipment system; obtains a set of damaged equipment including all damaged equipment in the equipment system, and determines a set of possible alternative recovery schemes. Each alternative recovery scheme in the set includes at least one maintenance support team and the recovery order of each maintenance support team for the damaged equipment; constructs an objective function and constraints for recovering each damaged piece of equipment in the set of damaged equipment with the recovery resilience value of the equipment system as the objective; applies a genetic algorithm to select the optimal recovery scheme that satisfies the constraints and maximizes the objective function from the set of alternative recovery schemes, and recovers the equipment system according to the optimal recovery scheme. This can help to efficiently recover damaged equipment systems, provide decision support for the stability of equipment systems, and improve the recovery capability of equipment systems.

[0020] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0021] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0022] Figure 1 A flowchart illustrating the equipment system resilience optimization method based on recovery strategy provided in an embodiment of the present invention is shown.

[0023] Figure 2 This diagram illustrates the process of restoring the equipment system capability according to an embodiment of the present invention.

[0024] Figure 3 This diagram illustrates the changes in the recovery capabilities of the equipment system according to different recovery schemes in an embodiment of the present invention.

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

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

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

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

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

[0030] Figure 9 A schematic diagram of an electronic device according to an embodiment of the present invention is shown. Detailed Implementation

[0031] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0032] Figure 1 A flowchart illustrating the equipment system resilience optimization method based on recovery strategy provided in an embodiment of the present invention is shown. Figure 1 As shown, this equipment system resilience optimization based on recovery strategy is applied to servers. The equipment system resilience optimization method based on recovery strategy includes:

[0033] Step S11: Obtain the set of damaged equipment, including each damaged piece of equipment, from the equipment system, and determine the set of possible alternative recovery schemes. Each alternative recovery scheme in the set of alternative recovery schemes includes at least one maintenance and support team and the recovery order of each maintenance and support team for the damaged equipment.

[0034] In this embodiment of the invention, the equipment system can be a network of devices in an industrial system or a system composed of devices in a social network. See also Figure 2 The high-intensity interference and attacks from the opposing side damaged the equipment system, in t e At that moment, the equipment system capability drops to its lowest p(t) e At this point, the maintenance and support team responsible for the support mission quickly took action to restore the damaged equipment members. In actual combat scenarios, there are often more than one damaged equipment member, but the number of maintenance and support teams is limited, making it impossible to restore multiple damaged equipment members simultaneously. Therefore, the restoration must be carried out in stages. t1 is the time when the first stage of restoration work is completed. After restoration, the original damaged equipment member is reintegrated into the equipment system, establishing connections with other equipment members, thus enabling the equipment system capability to improve from P(t... e The value is increased to P(t1), and the subsequent recovery process follows the same logic. This continues until t... fAll restoration work is complete, and the equipment system capability has been upgraded to p(t). f A suitable recovery strategy and the resulting recovery plan can enable the equipment system to recover its capabilities more quickly and efficiently.

[0035] In step S11, when equipment in the equipment system is damaged, the damaged equipment is acquired, and a set of damaged equipment is constructed. Recovery resources are determined. In this embodiment of the invention, all resources required to restore each piece of equipment in the equipment system, including but not limited to personnel, equipment, tools, spare parts, and materials, are uniformly integrated and abstracted into multiple maintenance and support teams. Each maintenance and support team is considered an independent unit with specific resource combinations and recovery capabilities, responsible for executing the recovery tasks of the system's equipment members. Total recovery resources K max This refers to the number of maintenance and support teams capable of simultaneously carrying out restoration work. Based on the restoration resources and the set of damaged equipment, all possible alternative restoration plans are determined, resulting in a set of alternative restoration plans. Each alternative restoration plan in the set includes at least one maintenance and support team and the restoration order of the damaged equipment by each maintenance and support team.

[0036] Step S12: Construct an objective function and constraints for restoring each damaged piece of equipment in the set of damaged equipment, with the recovery resilience value of the equipment system as the objective.

[0037] Resilience is typically defined from a capability perspective, encompassing multiple aspects such as the responsiveness, adaptability, recovery capability, and sustainability of a system when encountering disturbances or stress. It represents the ability of engineering systems and infrastructure to prevent, defend against, respond to, recover from, and adapt to natural and man-made threats, aiming to rapidly restore original functionality with minimal social disruption and economic loss within a short period, thus continuing to serve. In practical applications, resilience means the ability to predict, prepare for, and adapt to continuous change, possessing the capacity to withstand and quickly recover from disruptions. Considering the entire process of system confrontation, resilience is a comprehensive entity of resistance, adaptability, recovery capability, and reconstruction capability. This invention embodiment constructs an objective function for restoring each damaged piece of equipment in the set of damaged equipment, with the recovery resilience value of the equipment system as the target. That is, the objective function for resilience optimization in this invention embodiment 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 must be met, i.e., the resources used to restore the damaged equipment must be less than the total recovery resources.

[0038] Step S13: Apply a genetic algorithm to select the optimal recovery scheme that satisfies the constraints and maximizes the objective function from the set of alternative recovery schemes, and perform resilience recovery on the equipment system according to the optimal recovery scheme to achieve resilience optimization.

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

[0040] Compared to traditional optimization algorithms, genetic algorithms (GALs) excel in their strong adaptability to global search and their parallel search mechanism, making them uniquely efficient at solving complex optimization problems. The optimization process of GALs is independent of the specific form of the problem and does not require the problem to be continuous or differentiable, making them highly suitable for handling discrete and highly complex optimization problems such as determining recovery schemes for damaged systems. By evaluating the performance of each individual (i.e., the resilience value corresponding to the recovery scheme) through a fitness function, GALs retain superior individuals in the population while introducing new genetic mutations, effectively exploring the solution space. This allows them to quickly converge to a high-quality solution within a finite number of iterations, obtaining the optimal or near-optimal recovery scheme. This ensures timely decision support for the recovery of damaged systems in adversarial scenarios.

[0041] In this embodiment of the invention, the resilience value corresponding to each alternative scheme is actually a comprehensive reflection of the combined effects of multiple factors such as system architecture changes, recovery time, and recovery resources. This embodiment of the invention aims to maximize the resilience during the recovery phase. Under the condition of satisfying resource constraints, a recovery strategy model is constructed, comprehensively considering multiple factors such as recovery resources, recovery time, and recovery order. Considering the large scale of the alternative recovery schemes, a genetic algorithm is used for efficient solution, which helps to efficiently recover the damaged equipment system, provides decision support for the stability of the equipment system, and improves the recovery capability of the equipment system.

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

[0043] (1) All resources required for the recovery of the equipment system members, including but not limited to personnel, equipment, tools, spare parts, and materials, are uniformly integrated and abstracted into multiple "maintenance and support teams". Each maintenance and support team is regarded as an independent unit with specific resource combinations and recovery capabilities, and is responsible for carrying out the recovery tasks of the system members.

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

[0045] (3) During the restoration of the damaged system member, the system capability of the equipment remains unchanged; when the member is restored and reconnected 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 continuous process. After the member is recovered 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 spent by each maintenance support team in transferring between different damaged members and the difference 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 the recovery strategy implemented in this invention is to determine the optimal recovery plan. This plan can, after the equipment system has been damaged, utilize limited recovery resources to quickly enhance the system's capabilities and rapidly restore it to its initial state. As can be seen from the analysis of system capability changes during the recovery phase in Chapter 2, the resilience of the equipment system during the recovery phase is a crucial indicator of its post-damage recovery capability. 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's decision variable. The recovery plan that maximizes resilience during the recovery phase is the optimal recovery plan to be solved.

[0049] During the recovery phase of damaged equipment, resilience plays a crucial role. Through the implementation of a series of recovery measures, the equipment system's capabilities are efficiently and rapidly enhanced. The ratio of the system's capabilities to the integral of time from the start to the completion of the recovery work directly reflects the equipment system's recovery capabilities. The environment in which the equipment system operates changes rapidly, and opportunities are fleeting. It is necessary to restore the equipment system's capabilities to the required threshold as quickly as possible to effectively guarantee the execution of subsequent activities. Therefore, it is necessary not only to consider the cumulative improvement of the equipment system's capabilities during the recovery process but also to focus on whether the equipment system's capabilities can be restored to the required threshold within a short period of time. Based on the above considerations, in step S12, optionally, the cumulative capability recovery rate from the start of the recovery work to the completion of the recovery work is obtained based on any alternative recovery scheme. The cumulative capability recovery rate describes the ratio of the integral of the equipment system's capabilities to time to the integral of the equipment system's re-steady-state capabilities to time from the start to the completion of the recovery work. Preferably, the following relationship is used to calculate the ratio of the integral of the equipment system's capabilities to time to the integral of the equipment system's re-steady-state capabilities to time:

[0050]

[0051] Where, μ p t represents the cumulative recovery rate of energy.e Indicates the start time of resumption of work, t f P(t) represents the time when the recovery work is completed, and P(t) represents the equipment system capability value at time t.

[0052] Simultaneously, the ratio of the time required for the equipment system to recover to the capability requirement threshold to the total recovery time is calculated to obtain the recovery time ratio; the calculation formula is:

[0053]

[0054] Where, θ t The recovery time ratio, Δt represents the time required to restore capacity to the capacity demand threshold P. * The required time, T represents the total time of the entire recovery process, t * This indicates that the equipment system's capabilities have recovered to the capability requirement threshold P. * At that moment.

[0055] For equipment systems, a higher cumulative capability recovery rate indicates greater resilience; a lower recovery time ratio indicates that the equipment system's capabilities can reach the capability requirement threshold earlier, signifying higher recovery efficiency and greater resilience. Therefore, the indicator μ... p and θ t By combining these metrics, we can obtain a resilience metric for the equipment system during the resistance phase, namely, the recovery resilience value:

[0056]

[0057] Among them, R rec This refers to the resilience value of the equipment system.

[0058] After obtaining the ratio of cumulative capability recovery rate to recovery time, the ratio of the cumulative capability recovery rate to the recovery time ratio is calculated to obtain the recovery resilience value of the equipment system as the objective function. Preferably, the ratio of the cumulative capability recovery rate to the recovery time ratio is calculated using the following formula to obtain the recovery resilience value of the equipment system as the objective function:

[0059]

[0060] Among them, R rec (S i θ represents the recovery resilience value obtained by implementing the i-th recovery scheme. t The recovery time ratio, where n represents the recovery plan S. i The number of stages, t m P(t) represents the time when the m-th stage of recovery is completed. m ) represents t m The system capability value of equipment at all times, P(t) f ) represents the equipment system capability value after restoration, te Indicates the start time of resumption of work, t f Indicates the time when the recovery work is completed, t * This indicates the moment when the system's capability value reaches the capability requirement threshold.

[0061] Finally, constraints for resilience restoration of the equipment system are determined based on the set of alternative recovery schemes. Optionally, the constraints include two aspects: one is determining that the alternative recovery scheme is one of the alternative recovery schemes in the set of alternative recovery schemes, i.e.

[0062] S i ∈S

[0063] Among them, S i Let S be the i-th recovery scheme, and S be the set of alternative recovery schemes.

[0064] Another condition is that the number of maintenance support teams performing restoration work at any given time is less than or equal to the number of maintenance support teams in the alternative plans that can simultaneously perform restoration work. That is...

[0065] K t ∈K max

[0066] Among them, K max K represents the total amount of resources restored, i.e., the number of maintenance and support teams capable of performing restoration work simultaneously. t This indicates the number of maintenance and support teams performing restoration work at time t.

[0067] In this embodiment of the invention, when the interference or attack suffered by the equipment system is not severe and the number of damaged equipment system members is small, the resilience values ​​corresponding to all alternative recovery schemes can be enumerated and calculated through exhaustive methods to determine the optimal recovery scheme. However, the target mission is often highly complex, and the equipment system consists of a large number of equipment members. Therefore, as the number of damaged equipment increases, the scale of alternative recovery schemes will grow exponentially, which greatly increases the difficulty of selecting a recovery scheme and the computational complexity. For example, in the case of 11 damaged equipment members, the solution space that meets the constraints will reach tens of millions. Therefore, this 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 scheme.

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

[0069] Encoding and decoding are prerequisites for using genetic algorithms to solve practical problems. Encoding transforms the recovery scheme into a data structure that can be manipulated within the genetic algorithm; decoding maps the optimal individual to a specific recovery scheme. Common encoding methods in genetic algorithms include real-number encoding, binary encoding, permutation encoding, tree encoding, and multi-level encoding. The recovery scheme for an equipment system involves not only the recovery order of equipment personnel but also the arrangement of maintenance and support teams, making it more complex than general problems. Therefore, this paper chooses multi-level encoding to map the recovery scheme to chromosomes.

[0070] The chromosome can be divided into two layers: the first layer indicates the order of recovery of damaged equipment, and the second layer indicates the number of the maintenance and support unit performing the recovery work. See also Figure 4 Nodes S3, D2, D4, and I5 are nodes to be restored. Assume there are two maintenance support 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 restore nodes D2 and D4 respectively. After U1 completes the restoration of D4, it proceeds to restore node S3. After U2 completes the restoration of D2, it proceeds to restore node I5. This application encodes genes according to alternative restoration schemes, obtains multiple chromosomes, and combines the obtained chromosomes to obtain an initial population.

[0071] After obtaining the initial population, the recovery resilience value is used as the fitness of individual chromosomes in the population. The population is subjected to repeated genetic algorithm operations until the iteration termination condition is met. Then, the individual with the largest recovery resilience value in the population is selected and decoded to obtain the optimal recovery scheme.

[0072] In genetic algorithms, the fitness function quantifies the performance of individual chromosomes. During the search process, individual chromosomes are evaluated, and based on the evaluation results, chromosomes are selected for subsequent crossover and mutation operations to ensure the search direction is correct and gradually approaches the optimal solution. The execution of a recovery plan corresponds to the change in the equipment system's capabilities. Different recovery plans will cause the equipment system to exhibit different resilience; therefore, the recovery resilience 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 This represents the recovery resilience value corresponding to the recovery plan. The chromosome is decoded into a specific solution, code is written to simulate the system's changes, and the equipment system's capabilities at different times are calculated to obtain the chromosome's fitness value. A chromosome with a higher fitness value corresponds to a better recovery plan.

[0075] In this embodiment, the genetic algorithm operations include selection, mutation, and crossover. Selection is the process of determining which individuals will be retained for the next generation; the probability of each individual being selected is closely related to its fitness value. Roulette wheel selection is a widely used selection method in genetic algorithms, allowing each individual to be selected based on its fitness, and individuals with low fitness also have a certain probability of being selected. After calculating the fitness of individuals in the population, normalization can be performed, and roulette wheel selection can be constructed based on the normalized fitness values ​​until enough individuals are selected for crossover and mutation operations. Normalization can be performed according to the following relationship:

[0076]

[0077] Where, p i p represents the probability that the i-th individual is selected, N represents the number of individuals in the population, and p i This represents the probability that an individual is selected.

[0078] After the selection operation, simulating the genetic mechanisms of nature, crossover allows for the combination of parental gene fragments, enabling superior individuals to exchange useful genetic information, thereby improving search efficiency and producing offspring more adapted to the environment. This application employs a multi-layered coding system, randomly assigning recovery tasks to maintenance and support teams. Therefore, only the first layer needs to undergo a crossover operation to generate a new recovery order; the second layer is adjusted based on the recovery time. The crossover operation is as follows: Figure 5 As shown, to address the possibility of duplicate members within the same individual during crossover, adjustments can be made through local mapping while retaining non-duplicate members.

[0079] The purpose of mutation is to introduce new genetic variations during the evolution of a genetic algorithm, thereby increasing the genetic diversity of the population, preventing the algorithm from converging prematurely to a local optimum, enabling the search process to cover a wider solution space, and improving global search capabilities. Mutation can be performed at different levels. See also... Figure 6 Two predetermined intervals of random numbers are generated as the start and end points of the mutation operation. The genes from the start to the end are arranged in reverse order to obtain the mutated chromosome.

[0080] The complete process of this application using a genetic algorithm to select the optimal recovery scheme that satisfies the constraints and maximizes the objective function from the set of candidate recovery schemes is as follows: Figure 7As shown, the process first inputs the set of members of the damaged system, with input parameters including: population size, crossover probability, mutation probability, and maximum number of iterations (max_gen). Chromosomal gene encoding is performed, and the population is initialized, with the counter initialized to gen = 1. Constraints are applied to the population, fitness is calculated, and it is determined whether the generation termination condition is met. If not, selection, crossover, and mutation operations are performed to generate a new generation of population, setting gen = gen + 1, and then returning to the step of constraining the population. If yes, that is, the generation termination condition is met, the optimal individual is output, and this optimal individual is decoded into the optimal recovery scheme.

[0081] After obtaining the optimal recovery plan, the equipment system is restored according to the optimal recovery plan. This can efficiently and accurately restore the damaged equipment system, especially in combat scenarios, enabling the equipment system to quickly restore its capabilities to the required threshold, or even quickly restore it to full recovery, thereby optimizing the resilience of the equipment system.

[0082] In summary, this embodiment of the invention obtains a set of damaged equipment, including all damaged equipment, from an equipment system and determines a set of possible alternative recovery schemes. Each alternative recovery scheme includes at least one maintenance support team and the recovery order of each maintenance support team for the damaged equipment. An objective function and constraints for recovering each damaged piece of equipment in the set of damaged equipment are constructed with the recovery resilience value of the equipment system as the objective. A genetic algorithm is applied to select the optimal recovery scheme from the set of alternative recovery schemes that satisfies the constraints and maximizes the objective function. Based on the optimal recovery scheme, the equipment system is resiliently restored, achieving resilience optimization. This can help efficiently recover damaged equipment systems, provide decision support for the stability of the equipment system, and improve the recovery capability of the equipment system.

[0083] The foregoing has described specific embodiments of the present invention. In some cases, the actions or steps described in the embodiments of the present invention may be performed in a different order than that shown in the embodiments and the desired results may still be achieved. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order 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, embodiments of the present invention also provide a hybrid equipment system resilience optimization device based on recovery strategies. Applied to servers. (See appendix) Figure 3 As shown, the equipment system resilience optimization device based on recovery strategy includes: a recovery scheme set unit, an objective function acquisition unit, and a resilience optimization unit. Among them,

[0085] The recovery plan set unit is used to acquire the set of damaged equipment in the equipment system, including each damaged piece of equipment, and to determine the set of possible alternative recovery plans. Each alternative recovery plan in the set of alternative recovery plans includes at least one maintenance support team and the recovery sequence of each maintenance support team for the damaged equipment.

[0086] The objective function acquisition unit is used to construct an objective function and constraints for recovering each damaged piece of equipment in the set of damaged equipment, with the recovery resilience value of the equipment system as the objective.

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

[0088] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing the embodiments of the present invention, the functions of each module can be implemented in one or more software and / or hardware.

[0089] The apparatus of the above embodiments is applied to the corresponding methods in the foregoing embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0090] Based on the same inventive concept, embodiments of the present invention also provide an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the method described in any of the above embodiments.

[0091] This invention provides a non-volatile computer storage medium storing at least one executable instruction that can execute the method described in any of the above embodiments.

[0092] Figure 9 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 901, a memory 902, an input / output interface 903, a communication interface 904, and a bus 905. The processor 901, memory 902, input / output interface 903, and communication interface 904 are interconnected internally via the bus 905.

[0093] The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments 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 the 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 is called and executed by the processor 901.

[0095] The input / output interface 903 is used to connect input / output modules to enable information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0096] The communication interface 904 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (e.g., USB, Ethernet cable) or wireless means (e.g., mobile device systems, Wi-Fi, Bluetooth).

[0097] Bus 905 includes a pathway for transmitting information between various components of the device, such as processor 901, memory 902, input / output interface 903, and communication interface 904.

[0098] It should be noted that although the above-described device only shows the processor 901, memory 902, input / output interface 903, communication interface 904, and bus 905, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of the present invention, and not necessarily all the components shown in the figures.

[0099] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this disclosure is limited to these examples; within the framework of this disclosure, the technical features of the above embodiments or different embodiments can also be combined, the steps can 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 brevity.

[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 this invention should be included within the protection scope of this disclosure.

Claims

1. A method for optimizing the resilience of an equipment system based on a recovery strategy, characterized in that, The method includes: The equipment system includes a set of damaged equipment, including each damaged piece of equipment, and a set of possible alternative recovery schemes is determined. Each alternative recovery scheme in the set of alternative recovery schemes 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 and constraints are constructed to restore each damaged piece of equipment in the set of damaged equipment, with the recovery resilience value of the equipment system as the objective. A genetic algorithm is applied to select the optimal recovery scheme that satisfies the constraints and maximizes the objective function from the set of alternative recovery schemes, and the equipment system is subjected to resilience recovery based on the optimal recovery scheme to achieve resilience optimization. The objective function and constraints for constructing the recovery resilience value of the equipment system to recover each damaged piece of equipment in the equipment set include: Based on any alternative recovery plan, obtain the cumulative capability recovery rate from the start of the recovery work to its completion, including: calculating the ratio of the integral of the equipment system capability over time to the integral of the equipment system's regained steady-state capability over time. in, Indicates the cumulative recovery rate of ability. Indicates the start time of resuming work. Indicates the time when the restoration work was completed. express Constantly equipped system capability values; The recovery time ratio is obtained by calculating the ratio of the time it takes for the equipment system to recover to the capability requirement threshold to the total recovery time. The alternative recovery plans are divided into The equipment system is restored in several stages, and the ratio of the cumulative capability recovery rate to the recovery time ratio is calculated to obtain the recovery resilience value of the equipment system as the objective function. This includes: calculating the ratio of the cumulative capability recovery rate to the recovery time ratio using the following formula to obtain the recovery resilience value of the equipment system as the objective function: in, Indicates execution of the first The recovery resilience value obtained from the recovery scheme To restore the duration ratio, Indicates recovery plan The number of stages, Indicates the first Phase recovery completion time express Always equip the system's capability value. To restore the equipment system's capability values ​​after the restoration is complete, Indicates the start time of resuming work. Indicates the time when the restoration work was completed. This indicates the moment when the system's capability value reaches the capability requirement threshold. The constraints for resilience restoration of the equipment system are determined based on the set of alternative restoration schemes, including: determining that the alternative restoration scheme is one of the alternative restoration schemes in the set of alternative restoration schemes; and that the number of maintenance support teams performing restoration work at any given time is less than or equal to the number of maintenance support teams in the alternative schemes that can perform restoration work simultaneously.

2. The method according to claim 1, characterized in that, The application of a genetic algorithm to select the optimal recovery scheme that satisfies the constraints and maximizes the objective function from the set of candidate recovery schemes includes: The chromosome gene encoding of the genetic algorithm is determined based on any one of the alternative recovery schemes from the set of alternative recovery schemes, and the population is initialized. Using the resilience value as the individual fitness of chromosomes in the population, the population is subjected to repeated genetic algorithm operations until the iteration termination condition is met; Select the individual with the highest recovery resilience value in the population and decode it to obtain the optimal recovery scheme.

3. The method according to claim 2, characterized in that, The genetic algorithm operations include selection, mutation, and crossover.

4. A device for optimizing the resilience of an equipment system based on a recovery strategy, employing the method described in any one of claims 1-3, characterized in that, The device includes: The recovery plan set unit is used to acquire the set of damaged equipment in the equipment system, including each damaged piece of equipment, and to determine the set of possible alternative recovery plans. Each alternative recovery plan in the set of alternative recovery plans includes at least one maintenance support team and the recovery sequence of each maintenance support team for the damaged equipment. The objective function acquisition unit is used to construct an objective function and constraints for recovering each damaged piece of equipment in the set of damaged equipment, with the recovery resilience value of the equipment system as the objective. The resilience optimization unit is used to apply a genetic algorithm to select the optimal recovery scheme that satisfies the constraints and maximizes the objective function from the set of alternative recovery schemes, and to restore the equipment system according to the optimal recovery scheme.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1-3.

6. A computer storage medium, characterized in that, The storage medium stores at least one executable instruction that causes the processor to perform the method as described in any one of claims 1-3.

Images