Simulation model construction method and device, computer device and storage medium

Abstract

Embodiments of the present application disclose a simulation model construction method and device, computer equipment and a storage medium. The method comprises the following steps: determining a function coverage range corresponding to a plurality of infrastructures, and determining a level of each infrastructure in the function coverage range; determining each infrastructure as a node, and connecting each node to form a node network according to the level; determining a state of an infrastructure of a target level node in the node network, and determining a state value of the target level node according to the state; determining a state value of a node of a previous level of the target level node according to the state value of the target level node, and determining the node of the previous level as a node of a current level; determining a state value of a node of a previous level of the node of the current level according to the state value of the node of the current level, and returning to execute the step of determining the node of the previous level as the node of the current level until a state value of a node of a highest level is determined; and generating a simulation model according to the node network and the state value of each node.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to a simulation model construction method, apparatus, computer equipment, and storage medium. Background Technology

[0002] In the infrastructure that enables the operation of society, simulation models need to be established to verify the stability of the infrastructure. For example, infrastructure can be in various scenarios such as electricity, water conservancy, and transportation, and stability verification is required for each of these infrastructures.

[0003] Related technologies for infrastructure simulation models mainly include graph theory-based topology analysis models, physical process-based simulation models, agent-based modeling methods, load-capacity-based dynamic redistribution models, and data-driven models based on machine learning that have emerged in recent years. Although these technologies have achieved certain application results at different levels and in specific scenarios, they generally suffer from the following shortcomings:

[0004] The simplistic description of node states in simulation models makes it impossible to accurately quantify the functional integrity of nodes, leading to inaccurate assessments of the impact of cascading infrastructure failures on the overall system stability. In other words, there are technical problems in related technologies due to inaccurate simulation model construction. Summary of the Invention

[0005] This application provides a simulation model construction method, apparatus, computer equipment, and storage medium, which can establish a simulation model that is highly matched with multiple infrastructures, so as to achieve accurate evaluation of the stability of multiple infrastructures through the simulation model.

[0006] To achieve the above objectives, one embodiment of this application provides a simulation model construction method, including:

[0007] Determine the functional coverage of multiple infrastructures, and determine the level corresponding to each infrastructure within the functional coverage;

[0008] Each infrastructure element is identified as a node, and each node is connected according to the hierarchy to form a node network;

[0009] In the node network, determine the state of the infrastructure corresponding to the node at the target level, and determine the state value of the node at the target level based on the state.

[0010] Based on the state value of the node at the target level, determine the state value of the node at the next higher level, and then determine the node at the next higher level as the node at the current level.

[0011] determining a state value of a node of a next level of the node of the current level in the node network according to the state value of the node of the current level, and returning to determine the node of the next level as the node of the current level until a state value corresponding to a node of a highest level is determined;

[0012] generating a simulation model corresponding to the plurality of infrastructures according to the node network and the state value of each node in the node network.

[0013] To achieve the above object, the embodiment of the present application provides a simulation model construction device, which comprises:

[0014] a first determining module configured to determine a functional coverage range corresponding to a plurality of infrastructures, and determine a level corresponding to each infrastructure in the functional coverage range;

[0015] a second determining module configured to determine each infrastructure as a node, and connect each node according to the level to form a node network;

[0016] a third determining module configured to determine a state of an infrastructure corresponding to a node of a target level in the node network, and determine a state value of the node of the target level according to the state;

[0017] a fourth determining module configured to determine a state value of a node of a next level of the node of the target level according to the state value of the node of the target level, and determine the node of the next level as the node of the current level;

[0018] a fifth determining module configured to determine a state value of a node of a next level of the node of the current level in the node network according to the state value of the node of the current level, and return to determine the node of the next level as the node of the current level until a state value corresponding to a node of a highest level is determined;

[0019] a construction module configured to generate a simulation model corresponding to the plurality of infrastructures according to the node network and the state value of each node in the node network.

[0020] In some embodiments, the simulation model construction device further comprises a simulation module configured to:

[0021] after the simulation model corresponding to the plurality of infrastructures is generated according to the node network and the state value of each node in the node network, an input event corresponding to a target node in the simulation model is acquired;

[0022] a state value corresponding to the target node at a next time is determined according to the input event and the state value of the target node;

[0023] determine a state value of a node associated with the target node in the simulation model according to the state value corresponding to a next time of the target node;

[0024] determine the stability verification result corresponding to the plurality of infrastructures according to the state value of the associated node.

[0025] In some embodiments, a simulation module is configured to:

[0026] determine a state value of a node of a previous level of the associated node in the simulation model according to the state value of the associated node;

[0027] determine the node of the previous level of the associated node as a to-be-processed node, and determine a state value of a node of a previous level of the to-be-processed node according to the state value of the to-be-processed node;

[0028] determine the node of the previous level of the to-be-processed node as a to-be-processed node, and return to determine the state value of the node of the previous level of the to-be-processed node according to the state value of the to-be-processed node until the state value of each node in the simulation model does not change, and obtain a current state value of each node in the simulation model;

[0029] determine the stability verification result corresponding to the plurality of infrastructures according to the current state value of each node in the simulation model.

[0030] In some embodiments, a simulation module is configured to:

[0031] determine a historical state value of the target node in a historical time period;

[0032] determine a state transition probability of the input event in each preset state according to the historical state value and the state value of the target node;

[0033] determine a state value of a preset state with the maximum state transition probability as the state value corresponding to a next time of the target node.

[0034] In some embodiments, a first determination module is configured to:

[0035] determine geographical ranges, functional logic ranges and physical connection ranges corresponding to the plurality of infrastructures;

[0036] determine a functional coverage range corresponding to the plurality of infrastructures according to at least one of the geographical ranges, the functional logic ranges and the physical connection ranges.

[0037] In some embodiments, a third determination module is configured to:

[0038] determine a plurality of preset states of the infrastructure corresponding to the node of the target level, and determine a state value corresponding to each preset state according to a degree of influence of each preset state on the function of the infrastructure;

[0039] determine a target preset state matched with the state, and determine a state value corresponding to the target preset state as the state value of the node of the target level.

[0040] In some embodiments, the fifth determining module is configured to:

[0041] determine a lower-level adjacent node of a node of a previous level of the node of the current level and a state value of each lower-level adjacent node;

[0042] determine a weight value corresponding to the node of the current level and each lower-level adjacent node respectively;

[0043] multiply the state value of the node of the current level by the corresponding weight value to obtain a first result;

[0044] multiply the weight value and the state value corresponding to each lower-level adjacent node respectively to obtain a second result;

[0045] add the first result and the second result and divide the sum by the sum of the weight values corresponding to the node of the current level and each lower-level adjacent node respectively to obtain the state value of the node of the previous level of the node of the current level in the node network.

[0046] In some embodiments, the fifth determining module is configured to:

[0047] determine a lower-level adjacent node of a node of a previous level of the node of the current level and a state value of each lower-level adjacent node;

[0048] determine a minimum state value or a maximum state value from the state values corresponding to the node of the current level and each lower-level adjacent node respectively;

[0049] determine the state value of the node of the previous level of the node of the current level in the node network according to the minimum state value or the maximum state value.

[0050] In some embodiments, the fifth determining module is configured to:

[0051] determine a lower-level adjacent node of a node of a previous level of the node of the current level and a state value of each lower-level adjacent node;

[0052] multiply the state values corresponding to the node of the current level and each lower-level adjacent node respectively to obtain the state value of the node of the previous level of the node of the current level in the node network.

[0053] To achieve the above object, the embodiment of the present application provides a computer readable storage medium, which stores a plurality of instructions, and the instructions are adapted to be loaded by a processor to execute a simulation model construction method provided by the embodiment of the present application.

[0054] To achieve the above object, the embodiment of the present application provides a computer device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the processor executes the computer program to implement a simulation model construction method provided by the embodiment of the present application.

[0055] In the embodiment of the present application, the function coverage ranges corresponding to the plurality of infrastructures are determined, and the level corresponding to each infrastructure is determined in the function coverage range; each infrastructure is determined as a node, and each node is connected to form a node network according to the level; the state of the infrastructure corresponding to the node of the target level is determined in the node network, and the state value of the node of the target level is determined according to the state; the state value of the node of the upper level of the node of the target level is determined according to the state value of the node of the target level, and the node of the upper level is determined as the node of the current level; the state value of the node of the upper level of the node of the current level in the node network is determined according to the state value of the node of the current level, and the node of the upper level is determined as the node of the current level is returned to execute until the state value corresponding to the node of the highest level is determined; and the simulation model corresponding to the plurality of infrastructures is generated according to the node network and the state value of each node in the node network.

[0056] Therefore, by determining the functional coverage of multiple infrastructures, then connecting each node in the functional coverage according to the corresponding level of each infrastructure to form a node network, the range of the node network can match the range of the system composed of multiple infrastructures, and the level division of each node in the node network is clear. Then, the state of the infrastructure corresponding to the node of the target level is determined in the node network, and the state value of the node of the target level is determined according to the state. The state value of the node of the next level of the node of the target level is determined according to the state value of the node of the target level, and the node of the next level is determined as the node of the current level. The state value of the node of the next level of the node of the current level in the node network is determined according to the state value of the node of the current level, and the node of the next level is determined as the node of the current level until the state value corresponding to the node of the highest level is determined. In this way, the state of each infrastructure can be quantified, so that the state of each infrastructure can be more accurately evaluated, and finally, the simulation model corresponding to multiple infrastructures is generated according to the node network and the state value of each node in the node network. The simulation model can reflect the functional coverage of multiple infrastructures, and can clearly describe the level of multiple infrastructures and quantify the state of each infrastructure. Compared with the simulation model in the related technical solution, the simulation model in the present application is highly matched with multiple infrastructures, so that the stability of multiple infrastructures can be accurately evaluated through the simulation model.

[0057] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application can be realized and achieved by the structure particularly pointed out in the specification, claims and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creating laborious work.

[0059] Figure 1 is a system framework schematic diagram of the simulation model construction method provided by the embodiments of the present application;

[0060] Figure 2 is a scene schematic diagram of the simulation model construction method provided by the embodiments of the present application;

[0061] Figure 3 is a flow schematic diagram of the simulation model construction method provided by the embodiments of the present application;

[0062] Figure 4 is a flowchart of a simulation test provided by an embodiment of the present application;

[0063] Figure 5 is another flowchart of a simulation model construction method provided by an embodiment of the present application;

[0064] Figure 6 is a structural diagram of a simulation model construction device provided by an embodiment of the present application;

[0065] Figure 7 is a structural diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0066] In order to enable persons skilled in the art to better understand the schemes of the present application, the technical schemes in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor fall within the scope of protection of the present application.

[0067] It should be noted that in each of the specific embodiments of the present application, when the related processing of the data corresponding to the infrastructure is involved, the permission or consent of the user will be obtained first, and the collection, use and processing of the data will comply with the relevant laws, regulations and standards. In addition, when the embodiments of the present application need to obtain sensitive personal information of the user, the separate permission or separate consent of the user will be obtained through a pop-up window or a jump to a confirmation page, and after obtaining the separate permission or separate consent of the user, the necessary user-related data for enabling the embodiments of the present application to operate normally will be obtained.

[0068] In some processes described in the specification, claims and the above drawings, a plurality of steps appearing in a specific order are included, but it should be clearly understood that these steps can be executed or executed in parallel without the order in which they appear in this text, and the step number is only used to distinguish different steps, and the number itself does not represent any execution order.

[0069] The simulation model construction method provided by the embodiments of the present application relates to the technical field of computers. The simulation model construction method provided by the embodiments of the present application can be used in a plurality of general-purpose or special-purpose computer system environments or configurations, for example, in a terminal, and can also be used in a server end, and can also be software running in a terminal or a server end. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc.; the server end can be configured as a stand-alone physical server, or can be configured as a server cluster or a distributed system formed by a plurality of physical servers, or can be configured as a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, and basic cloud computing services such as big data and artificial intelligence platforms; and the software can be an application that implements the simulation model construction method, but is not limited to the above forms.

[0070] The simulation model construction method provided by the embodiments of the present application can be executed by a program module of a computer, which is integrated in a simulation model construction device. Generally, the program module includes routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment, in which tasks are performed by remote processing devices connected by a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0071] Before the embodiments of the present application are further described in detail, the terms and phrases involved in the embodiments of the present application are explained, and the terms and phrases involved in the embodiments of the present application are applicable to the following explanations:

[0072] Functional coverage range: the range involved in the services or functions provided by a system composed of a plurality of infrastructures, for example, the infrastructures in the power scenario are transformers, electric meters, electric towers, and security devices, and these infrastructures can provide a power coverage range, which is the functional coverage range corresponding to the plurality of infrastructures.

[0073] Node network: a network composed of a plurality of nodes connected, wherein a node represents an individual or a unit in the network, that is, an infrastructure (such as a power station in a power network). The connection between nodes forms an edge, which represents the relationship or connection between nodes (such as a power transmission line in a power network).

[0074] Infrastructure: an essential facility for providing functional services, for example, power stations, transformers, electric boxes, electric meters, and other facilities for providing power, and for example, highways, railways, airports, ports, subways, and traffic lights in the traffic scenario.

[0075] The above is a detailed description of some related terms in this application. If other terms are mentioned later, they will be described in detail later.

[0076] The technical problems existing in the related art are as follows:

[0077] In the infrastructure of social operation, it is necessary to establish a simulation model for these infrastructures to realize the stability verification of the infrastructures. For example, the infrastructure can be infrastructure in various scenarios such as power, water conservancy, transportation, etc., and the stability verification of these infrastructures is required.

[0078] The simulation model of the related art for the infrastructure mainly includes a topological analysis model based on graph theory, a simulation model based on physical process, a simulation model constructed by an agent-based modeling method, a dynamic redistribution model based on load-capacity, and a data-driven model based on machine learning rising in recent years, etc. Although the above technologies have achieved certain application results in different aspects and specific scenarios, there are generally the following defects:

[0079] The node state description of the simulation model is simplified, which leads to the inability to accurately quantify the node function integrity, resulting in inaccurate evaluation of the influence of the cascading failure of the infrastructure on the stability of the entire system. That is, there is a technical problem of inaccurate simulation model construction in the related art.

[0080] In order to solve the above problems, the embodiment of the application determines the functional coverage of multiple infrastructures, and then constructs a node network by connecting each node in the functional coverage according to the corresponding level of each infrastructure, so as to ensure that the range of the node network matches the range of the system composed of multiple infrastructures, and the level division of each node in the node network is clear. Then, the state of the infrastructure corresponding to the node of the target level is determined in the node network, and the state value of the node of the target level is determined according to the state. The state value of the node of the next level of the node of the target level is determined according to the state value of the node of the target level, and the node of the next level is determined as the node of the current level. The state value of the node of the next level of the node of the current level in the node network is determined according to the state value of the node of the current level, and the node of the next level is determined as the node of the current level until the state value corresponding to the node of the highest level is determined. In this way, the state of each infrastructure can be quantified, so that the state of each infrastructure can be more accurately evaluated, and finally, the simulation model corresponding to multiple infrastructures is generated according to the node network and the state value of each node in the node network. The simulation model can reflect the functional coverage of multiple infrastructures, and can clearly describe the level of multiple infrastructures and quantify the state of each infrastructure. Compared with the simulation model in the related technical solution, the simulation model in the application is highly matched with multiple infrastructures, so that the stability of multiple infrastructures can be accurately evaluated through the simulation model.

[0081] The system architecture to which the embodiment of the application is applied is as follows:

[0082] Please refer to Figure 1 , Figure 1 is a system framework diagram corresponding to the simulation model construction method provided by the embodiment of the application. The simulation model construction method provided by the embodiment of the application can be applied in the system framework.

[0083] It includes a terminal 140, an Internet 130, a gateway 120, a server 110, etc.

[0084] The terminal 140 or the server 110 can be a device for executing the simulation model construction method.

[0085] The terminal 140 includes but is not limited to a mobile phone, a computer, a smart voice interaction device, a smart home appliance, a vehicle-mounted terminal, an aircraft, and the like. The embodiments of the present application can be applied to various scenarios, including but not limited to power, transportation, water conservancy, network, and the like. In addition, it can be a single device or a combination of multiple devices. For example, multiple desktop computers are connected to each other through a local area network and share a display to work cooperatively, and together constitute a terminal 140. The terminal 140 can communicate with the Internet 130 in a wired or wireless manner to exchange data.

[0086] The server 110 refers to a computer system capable of providing certain services to the terminal 140. Compared with the ordinary terminal 140, the server 110 has higher requirements in stability, security, performance, and the like. The server 110 can be a standalone physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, and basic cloud computing services such as big data and artificial intelligence platforms.

[0087] The gateway 120 is also called an inter-network connector or a protocol converter. The gateway realizes network interconnection at the transport layer and is a computer system or device that acts as a conversion role. In the case of two systems using different communication protocols, data formats or languages, or even having completely different architectures, the gateway is a translator. At the same time, the gateway can also provide filtering and security functions. The messages sent by the terminal 140 to the server 110 are sent to the corresponding server 110 through the gateway 120. The messages sent by the server 110 to the terminal 140 are also sent to the corresponding terminal 140 through the gateway 120.

[0088] The simulation model construction method in the embodiments of the present application can be applied in various scenarios, such as power, transportation, water conservancy, network, and the like. The simulation model construction method in the embodiments of the present application is not limited to the scenarios in which it is applied.

[0089] The scenarios to which the embodiments of the present application are applied are as follows:

[0090] Please refer to Figure 2 , Figure 2 is a scenario diagram of the simulation model construction method provided by the embodiments of the present application.

[0091] As shown in a of Figure 2 , taking the power scenario as an example, it contains multiple power stations, towers, transformers, electrical boxes, and meters, and the like. These infrastructures can provide power services for a city, and then corresponding simulation models need to be constructed for these infrastructures, and the stability of the power system composed of multiple infrastructures can be tested through the simulation models.

[0092] In the process of building the simulation model, the functional coverage areas corresponding to multiple infrastructures are first determined, and then the hierarchy corresponding to each infrastructure is determined within the functional coverage areas. For example, the power service area covered by multiple infrastructures can be determined, and the power service area is defined as the functional coverage area.

[0093] Then, each infrastructure element is identified as a node, and these nodes are connected according to their hierarchy to form a node network. For example... Figure 2 As shown in b, it contains multiple nodes corresponding to infrastructure, which can be connected according to hierarchical relationships to form a node network.

[0094] In the node network, determine the state of the infrastructure corresponding to the node at the target level, and determine the state value of the node at the target level based on the state. For example, the node corresponding to the electricity meter entering the house is the node corresponding to the lowest level (target level). Then determine the state of the electricity meter, such as power outage, intermittent power outage, normal operation, etc. A state value can be set for each state. When the infrastructure is in a certain state, the state value of that state is determined.

[0095] Next, based on the state value of the node at the target level, the state value of the node at the next higher level is determined, and this node is designated as the node at the current level. Then, based on the state value of the node at the current level, the state value of the node at the next higher level in the node network is determined, and the process of designating the node at the next higher level as the node at the current level is repeated until the state value corresponding to the highest-level node is determined. In this way, the state value of each node in the node network is determined, thereby quantifying the state of each infrastructure element.

[0096] Finally, simulation models corresponding to multiple infrastructures are generated based on the node network and the state values ​​of each node in the node network. For example, the node network is equivalent to a power network composed of multiple infrastructures, and the state value of each node is equivalent to the functional state of each infrastructure. This constitutes a complete simulation model, within which stability testing, security testing, and other tests can be performed.

[0097] This simulation model can demonstrate the functional coverage of multiple infrastructures, clearly describe the hierarchy of multiple infrastructures, and quantify the state of each infrastructure. Compared with the simplified simulation models of node states in related technical solutions, the simulation model in this application is highly compatible with multiple infrastructures, so the stability of multiple infrastructures can be accurately evaluated through the simulation model in the future.

[0098] The simulation model construction method, device, computer device, and storage medium provided in the embodiments of the present application will be described in detail below.

[0099] Please refer to Figure 3 , Figure 3 is a flowchart of the simulation model construction method provided in the embodiments of the present application. The simulation model construction method provided in the embodiments of the present application can include the following steps:

[0100] Step 210, determining the functional coverage range corresponding to the plurality of infrastructures, and determining the level corresponding to each infrastructure within the functional coverage range;

[0101] Step 220, determining each infrastructure as a node, and connecting each node to form a node network according to the level;

[0102] Step 230, determining the state of the infrastructure corresponding to the node of the target level in the node network, and determining the state value of the node of the target level according to the state;

[0103] Step 240, determining the state value of the node of the previous level of the node of the target level according to the state value of the node of the target level, and determining the node of the previous level as the node of the current level;

[0104] Step 250, determining the state value of the node of the previous level of the node of the current level in the node network according to the state value of the node of the current level, and returning to execute the step of determining the node of the previous level as the node of the current level until the state value corresponding to the node of the highest level is determined;

[0105] Step 260, generating the simulation model corresponding to the plurality of infrastructures according to the node network and the state value of each node in the node network.

[0106] The steps 210 to 260 will be described in detail below.

[0107] In step 210, the functional coverage range corresponding to the plurality of infrastructures is determined, and the level corresponding to each infrastructure within the functional coverage range is determined.

[0108] The plurality of infrastructures can be infrastructures in different scenarios, such as infrastructures such as electric boxes, electric meters, electric towers, and transformers in the power scenario, such as infrastructures such as total gates, branch gates, and pressure boosters in the water conservancy scenario, such as infrastructures such as traffic lights, electronic barriers, and public transportation tools in the traffic scenario, and such as infrastructures such as routers, splitters, gateways, and computer rooms in the network scenario.

[0109] The functional coverage of the plurality of infrastructures can be determined. For example, in the power supply scenario, the power supply range (i.e., the functional coverage) covered by the power supply network composed of the plurality of infrastructures can be determined. For another example, in the network scenario, the network range (i.e., the functional coverage) covered by the network composed of the plurality of infrastructures can be determined.

[0110] The level of each infrastructure in the functional coverage can be determined. The level of each infrastructure can be determined according to the functional service provided by the infrastructure. For example, in the power supply scenario, the power station is the infrastructure that provides power from the source, and thus the level of the power station is the highest. Then, the power tower is the infrastructure that transmits the power, and thus the level of the power tower is lower than that of the power station. Then, the community transformer station is the infrastructure that steps down the voltage of the power transmitted by the power tower, and thus the level of the community transformer station is lower than that of the power tower. In this way, the levels of the plurality of infrastructures in the power supply scenario can be determined.

[0111] In some embodiments, the functional coverage of the plurality of infrastructures can be determined by:

[0112] (1.1) determining the geographical range, the functional logical range, and the physical connection range of the plurality of infrastructures;

[0113] (1.2) determining the functional coverage of the plurality of infrastructures according to at least one of the geographical range, the functional logical range, and the physical connection range.

[0114] The plurality of infrastructures has a geographical range, a functional logical range, and a physical connection range. The geographical range can be understood as the area in the real world where the plurality of infrastructures is located, for example, a certain city, an industrial park, or a single building (e.g., “ABC data center room”).

[0115] The functional logical range is the range covered by the functional service provided by the plurality of infrastructures. For example, in order to ensure the continuous operation of the transaction system, all IT facilities, communication links, power supply, environmental control, etc. that directly or indirectly support the transaction system, regardless of their geographical location, can be included in this logical scenario.

[0116] The physical connection range is the range formed by the plurality of infrastructures after being connected in dependence on each other. For example, for a certain entity (e.g., a large hospital or a precision manufacturing plant), the key resource supply system directly dependent thereon, such as a dedicated transformer substation and power transmission line for power supply, a pipe network system for water / gas supply, etc.

[0117] The functional coverage range corresponding to the plurality of infrastructures is determined according to at least one of the geographical range, the functional logical range, and the physical connection range. For example, a first functional coverage range of the plurality of infrastructures can be determined according to the geographical range, and then a second functional coverage range of the plurality of infrastructures can be determined according to the physical connection range, and then a third functional coverage range of the plurality of infrastructures can be determined according to the functional logical range. Finally, a union of the first functional coverage range, the second functional coverage range, and the third functional coverage range is determined, so as to determine the functional coverage range corresponding to the plurality of infrastructures.

[0118] The functional coverage range corresponding to the plurality of infrastructures can also be determined according to one of the geographical range, the functional logical range, and the physical connection range. Specifically, the system environment that needs to be simulated can be considered, for example, the local area network of an industrial park is simulated and evaluated, and the functional coverage range corresponding to the plurality of infrastructures can be determined according to the geographical range.

[0119] As can be seen from the above, the advantage of this is that the user can customize the boundary of the analysis of the scenario corresponding to the plurality of infrastructures according to the specific analysis target (such as a specific geographical area, a specific logical service chain, a specific physical infrastructure supply, or a specific network system), so as to accurately circumscribe the range of the key infrastructure studied, and subsequent simulation and evaluation of the analysis target (the system composed of the plurality of infrastructures) can be more accurate.

[0120] In some embodiments, a level corresponding to each infrastructure in the functional coverage range is determined, including:

[0121] (1.1) determining a function corresponding to each infrastructure in the functional coverage range;

[0122] (1.2) determining a level corresponding to each infrastructure according to the function corresponding to each infrastructure.

[0123] In the functional coverage range, the function corresponding to each infrastructure can be determined, for example, in the power scenario, the power station as an infrastructure provides power from the source, so the level of the power station is the highest, then the power tower, which is a link for transmitting power, has a lower level, then the community transformer station, which has a lower level, which further reduces the power transmitted by the power tower, and so on. The level of the power station can be determined.

[0124] By analogy, the function of each infrastructure can be subdivided, so that the infrastructure at each level is gradually decomposed from the top level, until the minimum unit node that can independently provide a certain minimum service or function is reached. The granularity of the minimum unit node can be flexibly set according to the analysis requirements. For example, the minimum unit node in the power scenario can be the power switch of each region.

[0125] The advantage of this is that each infrastructure can be subdivided, avoiding each infrastructure being too abstracted or too granular, which can lead to inaccurate stability assessments of the system composed of multiple infrastructures.

[0126] Step 220, each infrastructure is determined as a node, and each node connection is connected to form a node network according to the hierarchy.

[0127] In this application, each infrastructure is determined as a node, the relationship between the infrastructure and other infrastructures can be regarded as an edge, and the hierarchy of each infrastructure is regarded as the hierarchy of the node. Thus, the node network is formed according to each node, edge and hierarchy of each node, which is similar to a graph network.

[0128] For example, within the determined functional coverage, the most important and top-level service or function provided by the system is identified and clearly defined, such as the infrastructure "ABC data center room", whose top-level function can be described as "providing stable, reliable and secure data processing and information services for customers", and the hierarchy of this infrastructure is the highest, which can be used as the starting point for hierarchical modeling.

[0129] Primary node: represents a unit providing top-level functions or core services, and in general, the number of primary nodes is small, which is the highest degree of generalization of the overall function of the system.

[0130] Sub-node hierarchy: each primary node can be decomposed into several secondary sub-nodes, which represent the main functional modules or subsystems of the next level supporting the function of the primary node. For example, the "information service" primary node of the data center can be decomposed into "computing resource service", "storage resource service" and "network communication service" secondary sub-nodes. Similarly, each secondary sub-node can be further decomposed into tertiary sub-nodes, and so on.

[0131] Dependency relationship between nodes: the hierarchy reflects the functional support and dependency relationship, the normal operation of the lower layer node is the basis for the implementation of the function of the upper layer node, and there may be mutual dependence or influence relationship between nodes in the same hierarchy, forming a mesh feature.

[0132] It should be noted that in the embodiments of the present application, the granularity of the node is flexible, and the granularity of the lowest level node (the smallest unit node) is not fixed but can be flexibly set according to the depth of analysis and data availability. For example, in the power scenario, the lowest level node can be a transformer, a line, or even a circuit breaker; in the network scenario, it can be a physical server, a virtual machine, a core switch port, or a specific application software instance.

[0133] No matter how the granularity is selected, each lowest level node must meet the following conditions: it can independently provide an identifiable, measurable specific service or function; its running state can be clearly defined and evaluated; its failure will have an identifiable impact on other nodes directly dependent on it or upper layer functions.

[0134] This can ensure that the node network is dynamically set according to actual needs, increasing the flexibility of simulation evaluation of a system composed of multiple infrastructures.

[0135] In step 230, the state of the infrastructure corresponding to the target level node in the node network is determined, and the state value of the target level node is determined according to the state.

[0136] The target level node can be a lowest level node or an intermediate level node, and a set of states reflecting different running efficiencies can be defined for the target level node according to its service function characteristics. The set of states should at least include a completely normal state and a completely failed state, and several intermediate states between the completely normal state and the completely failed state.

[0137] For example, for a computing node, the corresponding states include a normal state, a performance degradation state (such as high CPU occupancy leading to slow response), a partially available state, and a complete outage state.

[0138] For a network link, the states include a smooth state, a congestion state (reduced bandwidth and increased latency), an intermittent packet loss state, and a complete interruption state.

[0139] For a power supply device, the corresponding states include a rated output state, a voltage / frequency deviation state (still within the allowed range but with degraded service quality), and an output interruption state.

[0140] In the embodiments of the present application, the state of the infrastructure corresponding to the target level node can be divided into the following states:

[0141] Normal state: the node provides all functions as designed, and the performance indicators are within the normal range. Service-limited state: the node can still provide partial functions, or the performance of main functions is decreased but not completely interrupted. Service-interrupted state: the node function frequently switches between available and unavailable, or the service quality is extremely unstable. Service-interrupted state: the node completely loses its predetermined functions.

[0142] The above states can be preset states, and the state corresponding to the target level node during the running of the target level node can be one of the preset states.

[0143] In some embodiments, determining the state value of the target level node according to the state includes:

[0144] (1.1) determine a plurality of preset states of the infrastructure corresponding to the node of the target level, and determine a degree of influence of each preset state on the function of the infrastructure, and set a state value corresponding to each preset state;

[0145] (1.2) determine a target preset state matched with the state, and determine the state value corresponding to the target preset state as the state value of the node of the target level.

[0146] Among them, a plurality of preset states of the infrastructure corresponding to the node of the target level can be determined, such as the four preset states described above: normal state, service limited state, service interruption state, and service interruption state.

[0147] Then, a degree of influence of each preset state on the function of the infrastructure is determined, and a state value corresponding to each preset state is set. For example, the normal state is a normal running state for the infrastructure, and the state value corresponding to the normal state is 1; the service limited state is slightly affected on the normal running of the infrastructure, and the state value corresponding to the service limited state is 0.7 (indicating that the function completeness is 70%); the service interruption state is seriously affected on the normal running of the infrastructure, and the state value corresponding to the service interruption state is 0.3; the service interruption state is a state that causes the infrastructure to be unable to run, and the state value corresponding to the service interruption state is 0. The specific quantitative value can be determined based on historical data statistics or normalization processing of function performance indicators.

[0148] Finally, a target preset state matched with the state of the node of the target level is determined, and the state value corresponding to the target preset state is determined as the state value of the node of the target level. For example, the state of the node of the target level is the normal state, and the state value of the node of the target level is 1.

[0149] In step 240, the state value of the node of the upper level of the node of the target level is determined according to the state value of the node of the target level, and the node of the upper level is determined as the node of the current level.

[0150] Among them, in the embodiment of the present application, the state quantitative value of the upper node can be obtained through the state value of the associated lower node, that is, the state of the upper node will be affected by the state of the associated lower node. The state value of the node of the upper level of the node of the target level can be determined according to the state value of the node of the target level, and the node of the upper level is determined as the node of the current level.

[0151] For example, the state quantization value of the upper level node can be determined by weighted aggregation of the state values of its associated lower level nodes, or the state quantization value of the upper level node can be determined by the state value of a certain node in its associated lower level nodes. After determining the state value of the node at the upper level of the node at the target level, the node at the upper level is determined as the node at the current level.

[0152] In step 250, the state value of the node at the upper level of the node at the current level in the node network is determined according to the state value of the node at the current level, and the node at the upper level is determined as the node at the current level until the state value corresponding to the node at the highest level is determined.

[0153] In some embodiments, the state value of the node at the upper level of the node at the current level in the node network is determined according to the state value of the node at the current level, including:

[0154] In some embodiments, the state value of the node at the upper level of the node at the current level in the node network is determined according to the state value of the node at the current level, including:

[0155] (1.1) determining the lower adjacent nodes of the node at the upper level of the node at the current level and the state values of each lower adjacent node;

[0156] (1.2) determining the weight values corresponding to the node at the current level and each lower adjacent node, respectively;

[0157] (1.3) multiplying the state value of the node at the current level by the corresponding weight value to obtain a first result;

[0158] (1.4) multiplying the weight value and the state value corresponding to each lower adjacent node to obtain a second result;

[0159] (1.5) adding the first result and the second result and dividing by the sum of the weight values corresponding to the node at the current level and each lower adjacent node to obtain the state value of the node at the upper level of the node at the current level in the node network.

[0160] wherein the node at the upper level comprising n lower level nodes, the n lower level nodes are respectively represented as , and the state values corresponding to the n lower level nodes are represented as The low-layer nodes include the node of the current level and each low-layer adjacent node.

[0161] The weight value corresponding to the node of the current level and each low-layer adjacent node respectively can be expressed as .

[0162] Then, the state value of the node of the previous level is calculated according to the state value corresponding to each low-layer adjacent node and the weight value corresponding to each low-layer adjacent node, which is expressed as:

[0163] . Wherein, the state value of the node of the previous level is calculated according to the state value corresponding to each low-layer adjacent node and the weight value corresponding to each low-layer adjacent node, which is expressed as: n represents n nodes, i is the node number, the first result and the second result are added, the weight value corresponding to the node of the current level and each low-layer adjacent node respectively, and finally the added result is divided by the sum of the weight values to obtain the state value of the node of the previous level of the node of the current level in the node network.

[0164] The application scenarios are: when the upper-layer function is a collection of contributions of multiple sub-functions, and the importance of each sub-function is distinguishable. For example, the overall service level of a "data processing cluster" may be a weighted average of the service levels of each server node under it, and the server with higher performance may have higher weight.

[0165] The advantage of this is that the state value of the node of the previous level of the node of the current level can be accurately determined in the corresponding application scenario.

[0166] In some embodiments, the state value of the node of the previous level of the node of the current level in the node network is determined according to the state value of the node of the current level, which includes:

[0167] (2.1) determining the low-layer adjacent nodes of the node of the previous level of the node of the current level and the state values of each low-layer adjacent node;

[0168] (2.2) determining the minimum state value or the maximum state value from the state values corresponding to the node of the current level and each low-layer adjacent node respectively;

[0169] (2.3) determining the state value of the node of the previous level of the node of the current level in the node network according to the minimum state value or the maximum state value.

[0170] Wherein, the node of the previous level contains n low-layer nodes, which are respectively expressed as , and the state values corresponding to the n low-layer nodes are expressed as The low-layer nodes include the node of the current level and each low-layer adjacent node.

[0171] Then the minimum state value is determined in the state values corresponding to the node of the current level and each low-layer adjacent node, which is specifically represented as: .

[0172] The minimum state value is determined in the state values corresponding to the node of the current level and each low-layer adjacent node, which is specifically represented as: .

[0173] Finally, the state value of the node of the previous level of the node of the current level is determined according to the minimum state value or the maximum state value. For example, the minimum state value or the maximum state value is determined as the state value of the node of the previous level of the node of the current level.

[0174] The minimum state value is determined as the state value of the node of the previous level of the node of the current level, that is, the state of the parent node is determined by the state of the worst one of all the child nodes. The applicable scenario is: a series system or a function chain, and the failure or serious degradation of any child node will lead to the failure or degradation of the entire upper function. For example, the overall output state of a production line can depend on the state of the slowest or highest failure rate process equipment. If a "secure communication link" depends on the serial work of an encryption module, a transmission module and an authentication module, the overall security service state of the link can be limited by the worst one of the three modules.

[0175] The maximum state value is determined as the state value of the node of the previous level of the node of the current level, which has a more complex redundancy logic, for example, a k-out-of-n system (at least k normal working nodes in n child nodes, and the parent node is normal), and the state calculation will be more complex, which can need to combine Boolean logic or a special reliability model. For simple parallel redundancy (as long as one works), the maximum value method is an approximation.

[0176] The maximum state value is determined as the state value of the node of the previous level of the node of the current level, that is, the state of the parent node is determined by the state of the best one of all the child nodes, or as long as a certain number of child nodes work normally, the parent node can maintain a high state. The applicable scenario is: a parallel redundancy system, in which the child nodes provide backup functions. For example, the "power supply reliability" state of a system powered by multiple UPSs in parallel can still maintain a high level when some UPSs fail but there are still normal UPSs, and the overall state can be closer to the state of the best UPS (or group of UPSs).

[0177] The advantage of this is that the state value of the node of the previous level of the node of the current level can be accurately determined in the corresponding application scenario.

[0178] In some embodiments, the state value of the node of the previous level of the node of the current level in the node network is determined according to the state value of the node of the current level, comprising:

[0179] (3.1) determining the lower adjacent nodes of the node of the previous level of the node of the current level and the state value of each lower adjacent node;

[0180] (3.2) multiplying the state values corresponding to the node of the current level and each lower adjacent node respectively to obtain the state value of the node of the previous level of the node of the current level in the node network.

[0181] Wherein, the node of the previous level The n lower nodes are respectively represented as The state values corresponding to the n lower nodes are respectively represented as The lower nodes include the node of the current level and each lower adjacent node.

[0182] Then the state values corresponding to the node of the current level and each lower adjacent node are multiplied respectively to obtain the state value of the node of the previous level of the node of the current level in the node network. Specifically represented as:

[0183] Wherein, The state value of the node of the previous level of the node of the current level, since In the interval [0, 1], any significant decrease (close to 0) of the state of a child node will lead to a sharp decrease of the state of the parent node.

[0184] The applicable scenario is: when the sub-functions are strongly coupled and indispensable, and the degradation of the sub-function will affect the upper function with a multiplier effect. For example, the "user satisfaction" of a complex service may depend on "response speed", "data accuracy" and "interface friendliness" three sub-factors, if the state of the three factors is quantified and multiplied, then any factor will perform poorly will lead to the overall satisfaction is very low.

[0185] The advantage of this is that the state value of the node of the previous level of the node of the current level can be accurately determined in the corresponding application scenario.

[0186] In step 260, a plurality of simulation models corresponding to the infrastructure are generated according to the node network and the state value of each node in the node network.

[0187] From the above, in the present application, by determining the node network and the state value of each node in the node network, the node network with the state value can be determined as a simulation model corresponding to multiple infrastructures. Subsequently, simulation evaluation of a system composed of multiple infrastructures can be implemented based on the node network with the state value, for example, stability verification.

[0188] Referring to Figure 4 , Figure 4 is a flowchart of the simulation test provided by the embodiments of the present application. In some embodiments, after generating the simulation model corresponding to multiple infrastructures according to the node network and the state value of each node in the node network, the following steps are further included:

[0189] Step 301, obtaining an input event corresponding to a target node in the simulation model;

[0190] Step 302, determining a state value of the target node at a next time according to the input event and the state value of the target node;

[0191] Step 303, determining a state value of an associated node associated with the target node in the simulation model according to the state value of the target node at the next time;

[0192] Step 304, determining a stability verification result corresponding to multiple infrastructures according to the state value of the associated node.

[0193] The steps 301 to 304 will be described in detail below.

[0194] In step 301, an input event corresponding to a target node in the simulation model is obtained.

[0195] The input event can be an internal event or an external event. The external input event is an event caused by factors outside the boundary of the analyzed node. Mainly includes:

[0196] State change of directly or indirectly dependent upstream nodes (for example, power supply node interruption causes server node power failure). The dramatic change of environmental conditions exceeds the normal working range of the node (for example, the temperature of the machine room is too high, causing the equipment to overheat and reduce the frequency or shut down). External physical attack or network attack.

[0197] The internal native event is an event caused by factors inside the analyzed node itself. Mainly includes: aging, wear and tear or random failure of components of the node itself (for example, hard disk failure, software bug triggering). State change of directly contained lower sub-nodes (for non-minimal unit nodes). Scheduled or unscheduled maintenance operation.

[0198] In the simulation model, the target node can be a certain node in multiple nodes.

[0199] In step 302, a state value corresponding to the target node at the next time is determined according to the input event and the state value of the target node.

[0200] The state value corresponding to the target node at the next time can be changed based on the input event and the current state value of the target node. For example, the state transition probability of the target node can be determined based on the input event and the current state value of the target node, and then the state value corresponding to the target node at the next time is determined based on the state transition probability.

[0201] The state transition probability can be obtained based on the following approaches:

[0202] Historical failure data statistical analysis: if there is sufficient historical operation and failure data. Device reliability parameters: such as the mean time between failures (MTBF) and the mean time to repair (MTTR) claimed by the manufacturer. Expert system and experience judgment: especially suitable for sparse data or new systems. Fault tree analysis (FTA) / event tree analysis (ETA): logical deduction of specific failure modes. Physical model simulation or experiment: test the response of the node to specific events under controllable conditions.

[0203] In some embodiments, determining the state value corresponding to the target node at the next time according to the input event and the state value of the target node comprises:

[0204] (1.1) determining the historical state value of the target node in a historical time period;

[0205] (1.2) determining the state transition probability of the input event in each preset state according to the historical state value and the state value of the target node;

[0206] (1.3) determining the state value of the preset state with the maximum state transition probability as the state value corresponding to the target node at the next time.

[0207] For example, the target node is a water pump, and the preset states include “normal”, “performance degradation” and “failure”. In the historical time period, 100 times of “voltage anomaly” events are observed when the water pump is in the “normal” state. The input event can be the “voltage anomaly” event.

[0208] In these 100 events, the state changes (within a set historical time period Δt) are observed as follows:

[0209] 70 times, the state of the water pump is still “normal” (the voltage fluctuation may be small, or the water pump has strong anti-disturbance ability);

[0210] 25 times, the state of the water pump changes to “performance degradation” (for example, the rotating speed decreases).

[0211] 5 times, the water pump state becomes "fault" (e.g., protective shutdown or damage).

[0212] The above states include the state corresponding to the historical state value and the state value of the target node. Based on the above data, the state transition probability can be calculated:

[0213] P(normal | normal, voltage abnormal) = 70 / 100 = 0.7

[0214] P(declining performance | normal, voltage abnormal) = 25 / 100 = 0.25

[0215] P(fault | normal, voltage abnormal) = 5 / 100 = 0.05

[0216] 0.7 + 0.25 + 0.05 = 1.0, the probability sum is 1, which satisfies the completeness, and it is concluded that the next state of the target node has a probability of 70% "normal", 25% "performance decline", and 5% "fault". That is, the state transition probabilities of the three preset states "normal", "performance decline" and "fault" are 70%, 25% and 5% respectively.

[0217] The state value of the preset state with the maximum state transition probability is determined as the state value corresponding to the target node at the next time. That is, the "normal" state is determined as the state value corresponding to the target node at the next time.

[0218] The advantage of this is that by introducing input events, the authenticity and accuracy of the simulation model during simulation testing can be increased.

[0219] In step 303, the state values of the associated nodes associated with the target node in the simulation model are determined according to the state value corresponding to the target node at the next time.

[0220] Among them, after determining the state value corresponding to the target node at the next time, the associated nodes directly affected by the change of the state value of the target node can be determined. Then the state of the associated nodes associated with the target node in the simulation model is obtained, and the state values of the associated nodes associated with the target node in the simulation model are determined based on the mapping relationship between the preset states and the preset state values.

[0221] In step 304, the stability verification results corresponding to a plurality of infrastructures are determined according to the state values of the associated nodes.

[0222] In this process, the state values ​​of other nodes can be determined based on the state values ​​of associated nodes, thereby determining the state of the simulation model and determining the stability verification results of multiple infrastructures based on the state of the simulation model.

[0223] In some implementations, stability verification results for multiple infrastructures are determined based on the state values ​​of associated nodes, including:

[0224] (1.1) Determine the state value of the node at the next higher level of the associated node in the simulation model based on the state value of the associated node;

[0225] (1.2) Determine the node at the next level above the associated node as the node to be processed, and determine the state value of the node at the next level above the node to be processed based on the state value of the node to be processed.

[0226] (1.3) Determine the parent node of the node to be processed as the node to be processed, and return to execute the determination of the parent node of the node to be processed based on the state value of the node to be processed, until the state value of each node in the simulation model does not change, and obtain the current state value of each node in the simulation model.

[0227] (1.4) Determine the stability verification results of multiple infrastructures based on the current state value of each node in the simulation model.

[0228] In this way, the state value of the node at the next higher level of the associated node can be determined in the simulation model based on the state value of the associated node. For example, the lower level node of the node at the next higher level of the associated node can be determined, and the state value of the node at the next higher level of the associated node can be determined in the simulation model based on the state value of the lower level node and the state value of the associated node.

[0229] Then, the node at the next higher level of the associated node is identified as the node to be processed, and the state value of the node at the next higher level is determined based on the state value of the node to be processed. This process is repeated until the state value of each node in the simulation model remains unchanged, thus obtaining the current state value of each node in the simulation model. Finally, the stability verification results for multiple infrastructure components are determined based on the current state value of each node in the simulation model.

[0230] Alternatively, when the state values ​​of nodes in the simulation model change over a certain period of time, the stability verification results corresponding to multiple infrastructures can be determined based on the state values ​​of nodes in the simulation model.

[0231] As can be known from steps 301 to 304, the input event can be introduced to accurately verify and evaluate the stability of the plurality of infrastructures.

[0232] As can be known from the above, in the embodiment of the application, the functional coverage range corresponding to the plurality of infrastructures is determined, and the level corresponding to each infrastructure is determined in the functional coverage range; each infrastructure is determined as a node, and each node is connected to form a node network according to the level; the state of the infrastructure corresponding to the node of the target level is determined in the node network, and the state value of the node of the target level is determined according to the state; the state value of the node of the upper level of the node of the target level is determined according to the state value of the node of the target level, and the node of the upper level is determined as the node of the current level; the state value of the node of the upper level of the node of the current level in the node network is determined according to the state value of the node of the current level, and the node of the upper level is determined as the node of the current level is returned to execute until the state value corresponding to the node of the highest level is determined; and the simulation model corresponding to the plurality of infrastructures is generated according to the node network and the state value of each node in the node network.

[0233] In this way, by determining the functional coverage range of the plurality of infrastructures, then connecting each node according to the level corresponding to each infrastructure in the functional coverage range to form a node network, the range of the node network can be ensured to match the range of the system composed of the plurality of infrastructures, and the level division of each node in the node network is clear, then the state of the infrastructure corresponding to the node of the target level is determined in the node network, and the state value of the node of the target level is determined according to the state; the state value of the node of the upper level of the node of the target level is determined according to the state value of the node of the target level, and the node of the upper level is determined as the node of the current level; the state value of the node of the upper level of the node of the current level in the node network is determined according to the state value of the node of the current level, and the node of the upper level is determined as the node of the current level is returned to execute until the state value corresponding to the node of the highest level is determined; in this way, the state of each infrastructure can be quantified, so that the state of each infrastructure can be more accurately evaluated, and finally the simulation model corresponding to the plurality of infrastructures is generated according to the node network and the state value of each node in the node network. The simulation model can reflect the functional coverage range of the plurality of infrastructures, and can clearly describe the level of the plurality of infrastructures and quantify the state of each infrastructure. Compared with the simulation model in the related technical solution, the simulation model in the application is highly matched with the plurality of infrastructures, so that the stability of the plurality of infrastructures can be accurately evaluated through the simulation model subsequently.

[0234] In order to more clearly understand the construction and simulation process of the simulation model, a scene will be described below.

[0235] Scenario Boundary Definition: This analysis is confined within the physical perimeter of "Data Center A of a Large Internet Company" and its direct power interface with the outside world. The scenario includes all relevant power supply facilities such as high-voltage distribution cabinets, transformers, backup generators, automatic transfer switches (ATS), uninterruptible power supply (UPS) systems, and power distribution units (PDU) that supply power to the server cabinets.

[0236] Top-level Function Description: The top-level function of this power supply room is to "provide stable, uninterrupted, high-quality power for the data center's IT load."

[0237] Model this scenario as a two-level structure:

[0238] Primary Node: N0 - Overall Power Supply Service (Represents Top-level Function)

[0239] Secondary Nodes: The primary node N0 is composed of the following five core functional subsystems (as secondary nodes), which collectively support the realization of the top-level function:

[0240] N1: Mains Input System - Includes high-voltage switch cabinets and transformers connected from the external power grid, responsible for receiving and initially processing mains power.

[0241] N2: Backup Generator System - Includes diesel generators and their associated facilities, serving as backup power after mains power interruption.

[0242] N3: Uninterruptible Power Supply (UPS) System - The core system, responsible for providing uninterrupted power during mains / backup power switching intervals and stabilizing voltage and frequency.

[0243] N4: Terminal Power Distribution System - Includes power distribution units (PDU) within the room, responsible for safely delivering clean power from the UPS to server cabinets.

[0244] N5: Automatic Transfer Switch (ATS) System - Responsible for automatically switching loads to backup power (generators) when detecting main power (mains) failure.

[0245] Inter-node dependency relationship: Under normal circumstances, the power flow is N1>N5>N2>N3>N4>IT load. When N1 fails, N5 will attempt to switch to N2, and N3 will rely on its own battery to provide transitional power.

[0246] Build a node network through node relationships and node levels, and then determine the state values of the nodes. For example, the state value definition of node N3:

[0247] Normal, S=1.0: Powered by mains or generator, stable output of clean power;

[0248] Battery Mode, S=0.7: Input power is interrupted, relying on its own battery power. Although the output quality is unchanged, the sustainability is limited, the system is in a high-risk state, so the service level is reduced;

[0249] Bypass Mode, S=0.4: UPS internal failure, input power is directly output without processing. The power supply is not interrupted, but the IT load loses protection, with extremely high risk;

[0250] Failed, S=0.0: No power output.

[0251] The state value of node N2 is defined as:

[0252] Standby, S=1.0: In a state of readiness;

[0253] Running, S=0.9: Successfully started and stable power supply. The service level is slightly lower than the mains, because it also has the risk of failure itself;

[0254] Start Failure, S=0.0: Received a start signal but failed to start successfully;

[0255] Fault Shutdown, S=0.0: Shutdown due to failure during operation.

[0256] Through the above way, the state values of all nodes in the node network can be determined, and then a simulation model is constructed based on the state values of the nodes and the node network.

[0257] Now, based on the simulation model, simulate the whole process of a cascading failure event.

[0258] Step 1: Initial disturbance injection (t=0)

[0259] Due to external grid failure, the mains input system (N1) state changes from “Normal (S=1.0)” to “Failed (S=0.0)”.

[0260] Step 2: Failure propagation simulation (t=1, t is the number of updates)

[0261] The “Failed” state of N1 triggers the external input event E_InputLoss for downstream nodes N5 (ATS) and N3 (UPS).

[0262] For N3 (UPS): Input power loss is detected, its state immediately changes from "OK (S=1.0)" to "Battery powered (S=0.7)". The UPS starts to power the entire IT load of the room, at which point the battery runtime clock starts (e.g. designed for 15 minutes).

[0263] For N5 (ATS): The E_InputLoss event is received, its current state is "Ready". The system makes a random decision according to the probability we determined in step 4. Assume that in this simulation, the random number falls in the 99.5% success interval.

[0264] The state of N5 changes to "Switch successful".

[0265] N5 immediately sends a start signal to the standby generator system (N2), which constitutes an external input event E_StartSignal to N2.

[0266] Step 3: Iterative analysis (t=2)

[0267] For N2 (Generator): The E_StartSignal event is received, its current state is "Standby (S=1.0)". Assume its start success probability is P(Running | Standby, E_StartSignal) = 0.98. The system makes a random decision again.

[0268] Scenario A (high probability event): Start successful. The state of N2 changes to "Running (S=0.9)". The generator reaches the rated speed and voltage in about 30 seconds.

[0269] Scenario B (low probability event): Start failed. The state of N2 changes to "Start failed (S=0.0)".

[0270] Step 4: Subsequent iterations and result evaluation

[0271] Under scenario A (generator start successful):

[0272] (t=3): N5 (ATS) detects stable power from N2, performs switching action to switch the load from the mains input to the generator input.

[0273] (t=4): N3 (UPS) detects stable input power restoration, stops battery power, and the state returns from "Battery powered (S=0.7)" to "OK (S=1.0)". The battery stops consuming.

[0274] (Final outcome): System is stable in backup power mode. The state value of primary node N0 (overall power service) can be calculated by aggregating the state values (e.g. weighted values) of its secondary child nodes, such as S=0.92. The system has degraded but the core function is maintained. The critical path is identified as N1 failure -> N5 switch -> N2 start -> N3 recovery.

[0275] In scenario B (generator start-up failure):

[0276] (t=3 to t=15 minutes): N2 fails to provide power, N3 (UPS) will remain in "battery power (S=0.7)" state until the battery is depleted.

[0277] (t=15 minutes later): N3 battery is depleted, state becomes "outage (S=0.0)".

[0278] (t=15 minutes+1 second): The "outage" state of N3 triggers an E_InputLoss event to N4 (end distribution), N4 state immediately becomes "outage (S=0.0)".

[0279] (Final outcome): Power is completely interrupted, data center business is paralyzed. The state value of primary node N0 eventually becomes S=0.0. Through this simulation, the backup generator system (N2) and the ATS system (N5) are identified as the core vulnerable nodes / bottleneck links in this cascading failure scenario.

[0280] In this way, the simulation of multiple infrastructures is realized through the simulation model, and the stability evaluation of the system composed of multiple infrastructures is realized.

[0281] Based on the state of the simulation model, we can determine the final impact range of the cascading failure (which nodes are affected and their final state). The critical failure propagation path. The change of the state quantitative value of the overall system top function, and the loss degree of the overall performance of the system is evaluated. Identify the vulnerable nodes or bottleneck links in the system.

[0282] For example, the state value of each secondary node Ni at time t is Si(t), and we assign it a weight wi. The weight wi represents the importance of the node to the upper function, which can be determined based on its design capacity, load bearing ratio, expert score, etc.

[0283] Calculation of node function loss degree (NFL):

[0284] For any node i, the function loss degree NFLi(t) at time t is calculated as: NFLi(t)=1-Si(t).

[0285] Example: When the UPS system (N3) enters the battery power supply mode, its state S3(t) = 0.7, then its node function loss degree NFL3(t) = 1 - 0.7 = 0.3, i.e. 30% of the function integrity (here referring to sustainability) is lost.

[0286] Calculation of system instantaneous function loss degree (ISFL):

[0287] First, the aggregated state value of the primary top node N0 at time t needs to be calculated . The weighted average method is used for aggregation: . Where n is the total number of secondary nodes.

[0288] Then, the system instantaneous function loss degree ISFL(t) is calculated as follows: ISFL(t) = 1 - S0(t);

[0289] Example: Assuming that the weights of all secondary nodes are 1. At a certain time t, the states of the subsystems are: S1 (mains) = 0.0, S2 (generator) = 0.9, S3 (UPS) = 1.0, S4 (power distribution) = 1.0, S5 (ATS) = 1.0.

[0290] S0(t) = (1*0.0 + 1*0.9 + 1*1.0 + 1*1.0 + 1*1.0) / 5 = 3.9 / 5 = 0.78;

[0291] ISFL(t) = 1 - 0.78 = 0.22, i.e. the function of the entire power supply system is lost by 22% at this moment.

[0292] In this way, the simulation test of the simulation model as described above can achieve accurate evaluation of a system composed of multiple infrastructures.

[0293] Please refer to Figure 5 , Figure 5 is another flowchart of the simulation model construction method provided by the embodiments of the present application. The simulation model construction method provided by the embodiments of the present application can include the following steps:

[0294] Step 401, determining the geographical range, functional logic range and physical connection range corresponding to the multiple infrastructures;

[0295] Step 402, determining the functional coverage range corresponding to the multiple infrastructures according to at least one of the geographical range, functional logic range and physical connection range;

[0296] Step 403, determining the function corresponding to each infrastructure within the functional coverage range;

[0297] Step 404, determining the level of each infrastructure according to the function corresponding to each infrastructure;

[0298] Step 405, determining each infrastructure as a node, and connecting each node according to the level to form a node network;

[0299] Step 406, determining the state of the infrastructure corresponding to the node of the target level in the node network, and determining the state value of the node of the target level according to the state;

[0300] Step 407, determining the state value of the node of the upper level of the node of the target level according to the state value of the node of the target level, and determining the node of the upper level as the node of the current level;

[0301] Step 408, determining the state value of the node of the upper level of the node of the current level in the node network according to the state value of the node of the current level, and returning to execute the step of determining the node of the upper level as the node of the current level until the state value corresponding to the node of the highest level is determined;

[0302] Step 409, generating a simulation model corresponding to the plurality of infrastructures according to the node network and the state value of each node in the node network;

[0303] Step 410, obtaining an input event corresponding to a target node in the simulation model;

[0304] Step 411, determining the state value corresponding to the target node at the next moment according to the input event and the state value of the target node;

[0305] Step 412, determining the state value of an associated node associated with the target node in the simulation model according to the state value corresponding to the target node at the next moment;

[0306] Step 413, determining a stability verification result corresponding to the plurality of infrastructures according to the state value of the associated node.

[0307] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the detailed description of the simulation model construction method above, which will not be repeated here.

[0308] Please refer to Figure 6 , Figure 6FIG. 1 is a structural schematic diagram of a simulation model construction device provided by an embodiment of the present application. The simulation model construction device can execute the simulation model construction method described above. In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined target, and can be implemented entirely or partially by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of an overall module or unit that includes the functions of the module or unit.

[0309] The simulation model construction device 500 comprises:

[0310] The first determination module 510 is configured to determine the functional coverage range corresponding to the plurality of infrastructures, and determine the level corresponding to each infrastructure within the functional coverage range;

[0311] The second determination module 520 is configured to determine each infrastructure as a node, and connect each node to form a node network according to the levels;

[0312] The third determination module 530 is configured to determine the state of the infrastructure corresponding to the node of the target level in the node network, and determine the state value of the node of the target level according to the state;

[0313] The fourth determination module 540 is configured to determine the state value of the node of the previous level of the node of the target level according to the state value of the node of the target level, and determine the node of the previous level as the node of the current level;

[0314] The fifth determination module 550 is configured to determine the state value of the node of the previous level of the node of the current level in the node network according to the state value of the node of the current level, and return to execute the determination of the node of the previous level as the node of the current level until the state value corresponding to the node of the highest level is determined;

[0315] The construction module 560 is configured to generate the simulation model corresponding to the plurality of infrastructures according to the node network and the state value of each node in the node network.

[0316] In some embodiments, the simulation model construction device 500 further comprises a simulation module configured to:

[0317] After generating the simulation model corresponding to the plurality of infrastructures according to the node network and the state value of each node in the node network, an input event corresponding to a target node in the simulation model is obtained;

[0318] According to the input event and the state value of the target node, a state value corresponding to the target node at the next moment is determined;

[0319] determine, according to the state value corresponding to the target node at the next moment, a state value of an associated node associated with the target node in the simulation model;

[0320] determine, according to the state value of the associated node, a stability verification result corresponding to the plurality of infrastructures.

[0321] In some embodiments, the simulation module is configured to:

[0322] determine, according to the state value of the associated node, a state value of a node at a previous level of the associated node in the simulation model;

[0323] determine the node at the previous level of the associated node as a to-be-processed node, and determine, according to the state value of the to-be-processed node, a state value of a node at a previous level of the to-be-processed node;

[0324] determine the node at the previous level of the to-be-processed node as a to-be-processed node, and return to determine, according to the state value of the to-be-processed node, the state value of the node at the previous level of the to-be-processed node until the state value of each node in the simulation model does not change, and obtain the current state value of each node in the simulation model;

[0325] determine, according to the current state value of each node in the simulation model, a stability verification result corresponding to the plurality of infrastructures.

[0326] In some embodiments, the simulation module is configured to:

[0327] determine a historical state value of the target node in a historical time period;

[0328] determine, according to the historical state value and the state value of the target node, a state transition probability of the input event at each preset state;

[0329] determine, as the state value corresponding to the target node at the next moment, a state value of a preset state with the maximum state transition probability.

[0330] In some embodiments, the first determination module 510 is configured to:

[0331] determine a geographical range, a functional logic range and a physical connection range corresponding to the plurality of infrastructures;

[0332] determine, according to at least one of the geographical range, the functional logic range and the physical connection range, a functional coverage range corresponding to the plurality of infrastructures.

[0333] In some embodiments, the third determination module 530 is configured to:

[0334] determine a plurality of preset states of the infrastructure corresponding to the node of the target level, and determine a degree of influence of each preset state on the function of the infrastructure, and set a state value corresponding to each preset state;

[0335] determine a target preset state matched with the state, and determine a state value corresponding to the target preset state as the state value of the node of the target level.

[0336] In some embodiments, the fifth determining module 550 is configured to:

[0337] determine a lower adjacent node of the node of the previous level of the node of the current level and a state value of each lower adjacent node;

[0338] determine a weight value corresponding to the node of the current level and each lower adjacent node respectively;

[0339] multiply the state value of the node of the current level by the corresponding weight value to obtain a first result;

[0340] multiply the weight value and the state value corresponding to each lower adjacent node respectively to obtain a second result;

[0341] add the first result and the second result and divide the sum by the sum of the weight values corresponding to the node of the current level and each lower adjacent node respectively to obtain the state value of the node of the previous level of the node of the current level in the node network.

[0342] In some embodiments, the fifth determining module 550 is configured to:

[0343] determine a lower adjacent node of the node of the previous level of the node of the current level and a state value of each lower adjacent node;

[0344] determine a minimum state value or a maximum state value from the state values corresponding to the node of the current level and each lower adjacent node respectively;

[0345] determine the state value of the node of the previous level of the node of the current level in the node network according to the minimum state value or the maximum state value.

[0346] In some embodiments, the fifth determining module 550 is configured to:

[0347] determine a lower adjacent node of the node of the previous level of the node of the current level and a state value of each lower adjacent node;

[0348] multiply the state values corresponding to the node of the current level and each lower adjacent node respectively to obtain the state value of the node of the previous level of the node of the current level in the node network.

[0349] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the detailed description of the simulation model construction method described above, which will not be repeated here.

[0350] In the embodiments of the present application, the first determining module 510 determines the functional coverage range corresponding to the plurality of infrastructures, and determines the level corresponding to each infrastructure in the functional coverage range; the second determining module 520 determines each infrastructure as a node, and connects each node to form a node network according to the level; the third determining module 530 determines the state of the infrastructure corresponding to the node of the target level in the node network, and determines the state value of the node of the target level according to the state; the fourth determining module 540 determines the state value of the node of the previous level of the node of the target level according to the state value of the node of the target level, and determines the node of the previous level as the node of the current level; the fifth determining module 550 determines the state value of the node of the previous level of the node of the current level in the node network according to the state value of the node of the current level, and returns to execute the determination of the node of the previous level as the node of the current level until the state value corresponding to the node of the highest level is determined; and the construction module 560 generates the simulation model corresponding to the plurality of infrastructures according to the node network and the state value of each node in the node network.

[0351] In this way, by determining the functional coverage range of the plurality of infrastructures, then connecting each node according to the level corresponding to each infrastructure in the functional coverage range to form a node network, it can be ensured that the range of the node network matches the range of the system composed of the plurality of infrastructures, and at the same time, the level division of each node in the node network is clear, then the state of the infrastructure corresponding to the node of the target level in the node network is determined, and the state value of the node of the target level is determined according to the state; the state value of the node of the previous level of the node of the target level is determined according to the state value of the node of the target level, and the node of the previous level is determined as the node of the current level; the state value of the node of the previous level of the node of the current level in the node network is determined according to the state value of the node of the current level, and the node of the previous level is determined as the node of the current level, until the state value corresponding to the node of the highest level is determined; in this way, the state of each infrastructure can be quantified, so that the state of each infrastructure can be more accurately evaluated, and finally the simulation model corresponding to the plurality of infrastructures is generated according to the node network and the state value of each node in the node network. The simulation model can reflect the functional coverage range of the plurality of infrastructures, and can clearly describe the level of the plurality of infrastructures and quantify the state of each infrastructure. Compared with the simulation model in the related technical solution, the simulation model in the present application is highly matched with the plurality of infrastructures, so that the stability of the plurality of infrastructures can be accurately evaluated through the simulation model subsequently.

[0352] The embodiment of the present application further provides a computer device, which comprises a memory and a processor, the memory stores a computer program, and the processor implements the simulation model construction method when executing the computer program.

[0353] Please refer to Figure 7 , Figure 7 The hardware structure of the computer device of another embodiment is illustrated, and the computer device comprises:

[0354] The processor 601 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, and is used to execute related programs to implement the technical solutions provided by the embodiments of the present application.

[0355] The memory 602 can be implemented in the form of a ROM (ReadOnly Memory), a static storage device, a dynamic storage device, or a RAM (Random Access Memory). The memory 602 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present application are implemented by software or firmware, the related program codes are stored in the memory 602 and are called and executed by the processor 601 to implement the simulation model construction method of the embodiments of the present application.

[0356] The input / output interface 603 is used to realize information input and output.

[0357] The communication interface 604 is used to realize the communication interaction between the device and other devices, and can realize communication through a wired manner (for example, a USB, a network cable, etc.) or a wireless manner (for example, a mobile network, WIFI, Bluetooth, etc.).

[0358] The bus 605 is used to transmit information between various components (for example, the processor 601, the memory 602, the input / output interface 603, and the communication interface 604) of the device.

[0359] The processor 601, the memory 602, the input / output interface 603, and the communication interface 604 are connected to each other through the bus 605 to realize communication connection between them in the device.

[0360] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by the processor to implement the simulation model construction method.

[0361] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include a high-speed random access memory and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory that is remotely arranged with respect to the processor, and these remote memories can be connected to the processor through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0362] The simulation model construction method and device, computer device and storage medium provided by the embodiments of the present application can determine the functional coverage range of a plurality of infrastructures, then form a node network by connecting each node according to the corresponding level of each infrastructure within the functional coverage range, so as to ensure that the range of the node network matches the range of the system composed of the plurality of infrastructures, and at the same time ensure that the level division of each node in the node network is clear, then determine the state of the infrastructure corresponding to the node of the target level in the node network, and determine the state value of the node of the target level according to the state; determine the state value of the node of the next level of the node of the target level according to the state value of the node of the target level, and determine the node of the next level as the node of the current level; determine the state value of the node of the next level of the node of the current level in the node network according to the state value of the node of the current level, and return to execute the step of determining the node of the next level as the node of the current level, until the state value corresponding to the node of the highest level is determined; in this way, the state of each infrastructure can be quantified, so that the state of each infrastructure can be more accurately evaluated, and finally the simulation model corresponding to the plurality of infrastructures is generated according to the node network and the state value of each node in the node network. The simulation model can reflect the functional coverage range of the plurality of infrastructures, can clearly describe the levels of the plurality of infrastructures, and can quantify the state of each infrastructure. Compared with the simulation model in the related technical solution, the simulation model in the present application is highly matched with the plurality of infrastructures, so that the stability of the plurality of infrastructures can be accurately evaluated through the simulation model subsequently.

[0363] The embodiments described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0364] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation to the embodiments of the present application, and can include more or fewer steps than the figures, or combine certain steps, or different steps.

[0365] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separated, that is, can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments.

[0366] Those skilled in the art can understand that all or some steps in the above disclosed method, functional modules / units in the system and device can be implemented as software, firmware, hardware and appropriate combinations thereof.

[0367] The terms "first", "second", "third", "fourth" and the like (if any) in the specification of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those clearly listed steps or units, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0368] It should be understood that in the present application, "at least one" means one or more, and "multiple" means two or more. "And / or" is used to describe the association between the associated objects, which means that there can be three relationships, for example, "A and / or B" can represent three cases: only A, only B, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0369] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other manners. For example, the apparatus embodiments described above are merely illustrative, for example, the division of the above units is merely a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, apparatuses or units, and can be electrical, mechanical or other forms.

[0370] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they can be located in one place or distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0371] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0372] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art that makes a contribution or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method of each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media.

[0373] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, but this does not limit the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. A method for constructing a simulation model, characterized in that, include: Determine the functional coverage of multiple infrastructures, and determine the level corresponding to each infrastructure within the functional coverage; Each infrastructure element is identified as a node, and each node is connected according to the hierarchy to form a node network; In the node network, determine the state of the infrastructure corresponding to the node at the target level, and determine the state value of the node at the target level based on the state. Based on the state value of the node at the target level, determine the state value of the node at the next higher level, and then determine the node at the next higher level as the node at the current level. Based on the state value of the node at the current level, determine the state value of the node at the next higher level in the node network, and return to determine the node at the next higher level as the node at the current level, until the state value corresponding to the node at the highest level is determined. The step of determining the state value of the next-level node in the node network based on the state value of the current-level node includes: determining the lower-level neighbor nodes of the next-level node and the state value of each lower-level neighbor node; determining the weight values ​​corresponding to the current-level node and each lower-level neighbor node; multiplying the state value of the current-level node by the corresponding weight value to obtain a first result; multiplying the weight value and state value of each lower-level neighbor node to obtain a second result; adding the first result and the second result and dividing by the sum of the weight values ​​corresponding to the current-level node and each lower-level neighbor node to obtain the state value of the next-level node in the node network. The simulation models corresponding to the multiple infrastructures are generated based on the node network and the state values ​​of each node in the node network.

2. The simulation model construction method according to claim 1, characterized in that, Determining the functional coverage of multiple infrastructures includes: Determine the geographical scope, functional logical scope, and physical connectivity scope corresponding to multiple infrastructures; The functional coverage of the plurality of infrastructures is determined based on at least one of the geographical range, the functional logical range, and the physical connection range.

3. The simulation model construction method according to claim 1, characterized in that, The process of determining the level corresponding to each infrastructure within the functional coverage area includes: Within the scope of the defined functional coverage, the functions corresponding to each infrastructure element are determined. The level corresponding to each infrastructure is determined based on the function of each infrastructure.

4. The simulation model construction method according to claim 1, characterized in that, Determining the state value of the node at the target level based on the state includes: Determine multiple preset states of the infrastructure corresponding to the nodes of the target level, and determine the degree of influence of each preset state on the functionality of the infrastructure, and set the state value corresponding to each preset state. Determine the target preset state for the state matching, and determine the state value corresponding to the target preset state as the state value of the node at the target level.

5. The simulation model construction method according to claim 1, characterized in that, Determining the state value of the next-level node in the node network based on the state value of the current-level node includes: Determine the lower-level neighbor nodes of the node at the previous level of the current level, as well as the state value of each lower-level neighbor node; Determine the minimum or maximum state value from the state values ​​corresponding to the current level node and each lower-level adjacent node; The state value of the next-level node in the node network is determined based on the minimum or maximum state value.

6. The simulation model construction method according to claim 1, characterized in that, Determining the state value of the next-level node in the node network based on the state value of the current-level node includes: Determine the lower-level neighbor nodes of the node at the previous level of the current level, as well as the state value of each lower-level neighbor node; Multiply the state values ​​of the current-level node and each of the lower-level adjacent nodes together to obtain the state value of the node one level above the current-level node in the node network.

7. The simulation model construction method according to claim 1, characterized in that, After generating the simulation models corresponding to the multiple infrastructures based on the node network and the state values ​​of each node in the node network, the method further includes: Obtain the input events corresponding to the target nodes in the simulation model; Based on the input event and the state value of the target node, determine the state value of the target node at the next moment; The state values ​​of the associated nodes of the target node in the simulation model are determined based on the state value of the target node at the next moment. The stability verification results corresponding to the multiple infrastructures are determined based on the status values ​​of the associated nodes.

8. The simulation model construction method according to claim 7, characterized in that, The step of determining the stability verification results corresponding to the multiple infrastructures based on the state values ​​of the associated nodes includes: Based on the state value of the associated node, the state value of the node at the next higher level of the associated node is determined in the simulation model; The node at the next level above the associated node is identified as the node to be processed, and the state value of the node at the next level above the node to be processed is determined based on the state value of the node to be processed. The parent node of the node to be processed is identified as the node to be processed, and the process returns to determine the state value of the parent node of the node to be processed based on the state value of the node to be processed, until the state value of each node in the simulation model does not change, thus obtaining the current state value of each node in the simulation model. The stability verification results for the multiple infrastructures are determined based on the current state value of each node in the simulation model.

9. The simulation model construction method according to claim 7, characterized in that, The step of determining the state value of the target node at the next moment based on the input event and the state value of the target node includes: Determine the historical state values ​​of the target node within the historical time period; The state transition probability of the input event in each preset state is determined based on the historical state value and the state value of the target node; The state value of the preset state with the highest state transition probability is determined as the state value of the target node at the next moment.

10. A simulation model construction device, characterized in that, include: The first determining module is used to determine the functional coverage of multiple infrastructures and to determine the level of each infrastructure within the functional coverage. The second determining module is used to determine each infrastructure as a node and connect each node to form a node network according to the hierarchy; The third determining module is used to determine the state of the infrastructure corresponding to the node at the target level in the node network, and to determine the state value of the node at the target level based on the state. The fourth determining module is used to determine the state value of the node at the next higher level of the target level node based on the state value of the node at the target level, and to determine the node at the next higher level as the node at the current level. The fifth determining module is used to determine the state value of the node above the current level node in the node network based on the state value of the current level node, and return to determine the node above the current level node as the current level node, until the state value corresponding to the highest level node is determined. The fifth determining module is used to determine the lower-level neighbor nodes of the node at the previous level of the current level and the state value of each lower-level neighbor node; determine the weight values ​​corresponding to the node at the current level and each lower-level neighbor node; multiply the state value of the node at the current level by the corresponding weight value to obtain a first result; multiply the weight value and state value corresponding to each lower-level neighbor node to obtain a second result; add the first result and the second result and divide by the sum of the weight values ​​corresponding to the node at the current level and each lower-level neighbor node to obtain the state value of the node at the previous level of the current level in the node network; A construction module is used to generate simulation models corresponding to the multiple infrastructures based on the node network and the state values ​​of each node in the node network.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a plurality of instructions adapted for loading by a processor to execute the simulation model construction method according to any one of claims 1 to 9.

12. A computer device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, When the processor executes the computer program, it implements the simulation model construction method according to any one of claims 1 to 9.

Images