A network comprehensive capability evaluation method and evaluation system based on a digital twin

Abstract

The present application relates to a kind of network comprehensive capability evaluation method and evaluation system based on digital twin, belong to network capability evaluation technical field, solve the problem that the evaluation effect of existing network comprehensive capability evaluation method is not ideal.The method comprises: the network entity is mapped into network digital twin system, obtains the all ability state of the network digital twin system;Based on the all ability state of the network digital twin system, construct system state transition probability matrix;Based on the system state transition probability matrix, obtain the steady-state ability evaluation value and transient ability evaluation value of the network digital twin system;Based on the performance index of network digital twin system, obtain the task completion ability value of network digital twin system;Based on the steady-state ability evaluation value, transient ability evaluation value and task completion ability value of the network digital twin system, obtain the network comprehensive capability evaluation result of the network entity.

Description

Technical Field

[0001] This invention relates to the field of network capability assessment technology, and in particular to a method and system for assessing comprehensive network capabilities based on digital twins. Background Technology

[0002] In recent years, the internet industry has flourished, reaching a stage of technological maturity and solidified business models. Various industries have greatly expanded online work methods and business operations, making the integration of the physical and virtual worlds, and digital services based on digital twins, a current development focus. Furthermore, the emergence of the metaverse concept for future application scenarios has gradually led to the formation of integrated future solutions that leverage existing mobile internet development foundations, comprehensively integrate various application models, and fully utilize various key technologies.

[0003] In the future, the metaverse will become a parallel space to the physical world in which people work and live. During its synchronous operation and interaction with the physical world, a quantitative evaluation method is needed to assess how digital twins in the virtual world simulate physical entities and the quality of their simulation. However, physical entities are complex and dynamically changing, making it difficult to evaluate their capabilities in a fixed way. Therefore, exploring a capability evaluation method for digital twin systems used in metaverse applications is particularly important.

[0004] Since the 1960s, researchers in this field have been studying the problem of system capability assessment, and after many years of development, they have achieved considerable research results. Commonly used capability assessment methods can be divided into the following four categories:

[0005] One method is the expert evaluation method, which involves constructing a system capability evaluation index system based on extensive expert opinions, and obtaining the index weights through comprehensive evaluation by multiple experts. This evaluation method can evaluate and predict indicators that are difficult to quantify due to a lack of data, but it inevitably leads to a certain degree of subjectivity and bias in the evaluation and prediction results.

[0006] The second method is the analytical method. This method leverages its effectiveness in overcoming estimation errors caused by coarse quantization to compare the performance of systems with uniform quantization resolution. Furthermore, it can utilize the Analytic Hierarchy Process (AHP) and its extensions to evaluate system capabilities. Essentially, this method calculates capability evaluation indicators by establishing mathematical models. It is computationally simple and easy to understand and apply. However, its drawbacks include limited factors considered during model construction, overly abstract results, and a lack of objectivity in the system.

[0007] Thirdly, there is the simulation method, which includes representative methods such as capability evaluation based on system dynamics models or artificial neural networks, as well as evaluation methods based on multi-agent and automatic control system theories. This evaluation method simulates the actual operation or development process of the system, but it suffers from high system complexity and weak representation of the connection relationships between nodes.

[0008] Fourth is network analysis, which compensates for the shortcomings of agent-based modeling and other methods in modeling system information interaction. It abstracts various entities in complex systems into nodes and various connections into links, which can better reflect the interaction relationships between nodes. However, existing network analysis methods are difficult to simulate the dynamic nature of existing networks and the ever-changing structure of digital twins, resulting in less than ideal capability analysis results. Summary of the Invention

[0009] In view of the above analysis, the embodiments of the present invention aim to provide a network comprehensive capability assessment method and system based on digital twins, so as to solve the problem that the assessment effect of existing network comprehensive capability assessment methods is not ideal.

[0010] On the one hand, the present invention provides a method for evaluating the comprehensive capabilities of a network based on a digital twin, comprising:

[0011] Map network entities to a network digital twin system and obtain all capability states of the network digital twin system;

[0012] Based on all the capability states of the network digital twin system, a system state transition probability matrix is ​​constructed;

[0013] Based on the system state transition probability matrix, the steady-state capability evaluation value and transient capability evaluation value of the network digital twin system are obtained;

[0014] Based on the performance indicators of the network digital twin system, obtain the task completion capability value of the network digital twin system;

[0015] Based on the steady-state capability evaluation value, transient capability evaluation value, and task completion capability value of the network digital twin system, the comprehensive network capability evaluation result of the network entity is obtained.

[0016] Based on the above solution, the present invention also makes the following improvements:

[0017] Furthermore, all capability states of the network digital twin system include:

[0018] Capability Status 0: All nodes in the network digital twin system are in good condition, and all functions of the network digital twin system are functioning normally.

[0019] Capability Status 1: In the network digital twin system, one node is in a fault state, but the network digital twin system can still meet certain functional requirements;

[0020] Capability state j: j nodes in the network digital twin system are in a fault state, but the network digital twin system can still meet certain functional requirements; 1≤j≤s-1;

[0021] Capability status s: There are s or more nodes in the network digital twin system that are in a fault state. The network digital twin system is in a fault state and cannot meet any functional requirements; s represents the total number of faulty nodes when the network digital twin system completely loses its function.

[0022] Furthermore, the system state transition probability matrix Q is:

[0023]

[0024] Where, λ i = (mi)λ, where m represents the total number of nodes in the network digital twin system; i = 0, 1, ..., s-1; λ and μ represent the failure rate and repair rate of each node in the network digital twin system, respectively.

[0025] Furthermore, obtaining the steady-state capability evaluation value of the network digital twin system includes:

[0026] Solve the steady-state equilibrium equation Q during the operation of the network digital twin system. T When π = 0, the limiting distribution π is obtained; where π = [π0, π1, ..., π]. j ,…,π s ] T , π j Let represent the steady-state probability of the j-th capability state;

[0027] The steady-state probabilities of all available states in all capability states are summarized to form the steady-state capability evaluation value of the network digital twin system;

[0028] The available states in the capability states include capability state 0 to capability state s-1.

[0029] Furthermore, the steady-state capability evaluation value E of the network digital twin system ss :

[0030]

[0031] in,

[0032]

[0033] Furthermore, the transient capability evaluation value E of the network digital twin system I :

[0034]

[0035] Among them, l j (t) represents the transient probability when the network digital twin system is in the j-th available state, and t represents time;

[0036]

[0037]

[0038] Furthermore, based on the performance indicators of the network digital twin system, the task completion capability value of the network digital twin system is obtained, including:

[0039] Based on the performance indicators of the network digital twin system, the task completion capability values ​​of the network digital twin system in each available state are obtained;

[0040] Based on the task completion capability value and transient probability of the network digital twin system in each available state, the task completion capability value of the network digital twin system is obtained.

[0041] Furthermore, the task completion capability value A of the network digital twin system is:

[0042]

[0043] Among them, c j This represents the task completion capability value of the network digital twin system when it is in an available state j.

[0044] Furthermore, the network comprehensive capability evaluation result of the network entity is the product of the steady-state capability evaluation value, transient capability evaluation value, and task completion capability value of the network digital twin system.

[0045] On the other hand, the present invention also provides a network comprehensive capability evaluation system based on digital twins, comprising:

[0046] The capability status acquisition module is used to map network entities into a network digital twin system and acquire all capability statuses of the network digital twin system.

[0047] The system state transition probability matrix construction module is used to construct the system state transition probability matrix based on all capability states of the network digital twin system.

[0048] The evaluation value acquisition module is used to acquire the steady-state capability evaluation value and transient capability evaluation value of the network digital twin system based on the system state transition probability matrix; it is also used to acquire the task completion capability value of the network digital twin system based on the performance indicators of the network digital twin system.

[0049] The network comprehensive capability assessment module is used to obtain the network comprehensive capability assessment result of the network entity based on the steady-state capability evaluation value, transient capability evaluation value, and task completion capability value of the network digital twin system.

[0050] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0051] The network comprehensive capability assessment method and evaluation system based on digital twins provided by this invention have the following beneficial effects:

[0052] This invention analyzes all capability states of a network digital twin system, constructs a system state transition probability matrix, and obtains corresponding steady-state and transient capability evaluation values ​​based on it. Furthermore, by analyzing the primary and secondary indicators of the network digital twin system, it obtains the task completion capability value of the network digital twin system. Finally, by integrating the steady-state capability evaluation value, transient capability evaluation value, and task completion capability value, it obtains the network comprehensive capability evaluation result of the network digital twin system. This result reflects the network comprehensive capability of the network digital twin system, possesses strong dynamics, and can effectively reflect the changes in the comprehensive capability of network entities and the network digital twin system over time.

[0053] In this invention, the above-described technical solutions can be combined with each other to achieve more preferred combinations. Other features and advantages of this invention will be set forth in the following description, and some advantages may become apparent from the description or be learned by practicing the invention. The objects and other advantages of this invention can be realized and obtained from what is particularly pointed out in the description and drawings. Attached Figure Description

[0054] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts.

[0055] Figure 1 This is a flowchart of the network comprehensive capability evaluation method based on digital twins provided in Embodiment 1 of the present invention;

[0056] Figure 2 This is a state transition diagram of the network digital twin system provided in Embodiment 1 of the present invention;

[0057] Figure 3A schematic diagram of the network comprehensive capability evaluation results of the network digital twin system provided in Embodiment 1 of the present invention;

[0058] Figure 4 This is a schematic diagram of the network comprehensive capability assessment system based on digital twins provided in Embodiment 1 of the present invention. Detailed Implementation

[0059] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0060] A specific embodiment of the present invention discloses a method for evaluating the comprehensive capabilities of a network based on a digital twin, the flowchart of which is shown below. Figure 1 As shown, it includes the following steps:

[0061] Step S1: Map the network entities into a network digital twin system and obtain all capability states of the network digital twin system;

[0062] In this embodiment, the nodes and links in the network entity are mapped to the corresponding nodes and links in the network digital twin system, and the failure rate and repair rate of the nodes in the network digital twin system are kept consistent with the failure rate and repair rate of the corresponding nodes in the network entity.

[0063] It should be emphasized that the capability assessment method in this embodiment is based on the Markov birth-death process. Therefore, the following conditions must be met when implementing this method:

[0064] (1) All nodes in the network digital twin system are of the same type;

[0065] Here, "nodes of the same type" specifically refers to nodes in a network digital twin system having the same level and function.

[0066] (2) All links in the network digital twin system are working normally;

[0067] (3) During the operation of the network digital twin system, when a node fails, the node's function can be restored through supplementation or backup replacement, and the probability of repairing a single node is μ, and the probability of repairing within Δt time is μΔt.

[0068] (4) During the operation of the network digital twin system, within a very small time interval, there is only one node that fails or is repaired;

[0069] (5) When some nodes of the network digital twin system fail, the network digital twin system completely loses its functional capabilities, and from then on, no node continues to fail.

[0070] In step S1, assume that the network digital twin system consists of m nodes. When the number of faulty nodes is s (0 < s ≤ m), the network digital twin system completely loses its function; that is, s represents the total number of faulty nodes when the network digital twin system completely loses its function. Then, in the task preparation and execution phase, all the ability states of the network digital twin system include the following situations:

[0071] Ability state 0: All nodes in the network digital twin system are in good condition, and all functions of the network digital twin system can be realized normally;

[0072] Ability state 1: One node in the network digital twin system is in a faulty state, and the network digital twin system can still meet certain functional requirements;

[0073] Ability state 2: Two nodes in the network digital twin system are in faulty states, and the network digital twin system can still meet certain functional requirements; ...

[0075] Ability state j: j nodes in the network digital twin system are in faulty states, and the network digital twin system can still meet certain functional requirements; 1 ≤ j ≤ s - 1; ...

[0077] Ability state s - 1: s - 1 nodes in the network digital twin system are in faulty states, and the network digital twin system can still meet certain functional requirements;

[0078] Ability state s: s or more nodes in the network digital twin system are in faulty states, and the entire network digital twin system is in a faulty state and cannot meet any functional requirements.

[0079] Step S2: Based on all the ability states of the network digital twin system, construct a system state transition probability matrix;

[0080] Specifically, step S2 includes:​​​​​​​​Assume that the state transition process X(t) of the network digital twin system satisfies {X(t), t≥0}, and is a homogeneous Markov process with continuous time and finite states, with a state space I={0,1,2,3,···,s}. Assume that the failure rate and repair rate of each node in the network digital twin system are λ and μ, respectively. Then, the state transition probability p from capability state i to capability state j is... ij (t) satisfies:

[0084] (1) When j = i + 1 and i = 0, 1, ..., s - 1, p ij (t)=p i→i+1 (t)=λ i t+o(t);

[0085] Where, λ i = (mi)λ, where t represents time and o(t) represents an infinitesimal number;

[0086] At this point, the capability state changes from i to i+1, indicating that a faulty node has been added to the network digital twin system;

[0087] (2) When j = i-1 and i = 1,...,s, p ij (t)=p i→i→1 (t)=μt+o(t);

[0088] At this point, the capability state transitions from i to i-1, indicating that a node in the network digital twin system has been repaired.

[0089] (3) When j = i and i = 0,...,s, p ij (t)=p i→i (t)=(λ i +μ)t+o(t);

[0090] At this point, the capability state changes from i to i, indicating that the network digital twin system has one node failure and another node repair within an infinitesimally small time frame.

[0091] (4) When |ij|≥2 and i,j=0,...,s, p ij (t)=p i→j (t) = o(t);

[0092] Since there is exactly one node that fails or recovers within a very small time interval, |ij|≥2, p ij (t) is a value with extremely small probability, denoted as o(t).

[0093] The state transition diagram of a network digital twin system is as follows: Figure 2 As shown.

[0094] Step S22: Construct the system state transition probability matrix based on the system state transition probabilities;

[0095] In constructing the system state transition probability matrix based on the system state transition probabilities, the influence of time needs to be eliminated first. Also, since o(t) is an infinitesimal number, it is approximately 0 here, and its influence is not considered during matrix construction. Therefore, the baseline state transition probability p for the transition from capability state i to capability state j... ij satisfy:

[0096] (1) When j = i + 1 and i = 0, 1, ..., s - 1, p ij =λ i ;

[0097] (2) When j = i-1 and i = 1,...,s, p ij =μ;

[0098] (4) When j = i and i = 0,...,s, p ij =λ i +μ;

[0099] (4) When |ij|≥2 and i,j=0,...,s, p ij =0;

[0100] According to the homogeneous Markov process, the system state transition probability matrix must satisfy the following condition:

[0101] The sum of the elements in each row of the system state transition probability matrix is ​​0, the diagonal elements are negative or 0, and the remaining elements are greater than or equal to 0.

[0102] Therefore, the system state transition probability matrix Q is constructed as follows:

[0103]

[0104] Step S3: Based on the system state transition probability matrix, obtain the steady-state capability evaluation value and transient capability evaluation value of the network digital twin system;

[0105] Specifically, step S3 includes:

[0106] Step S31: Based on the system state transition probability matrix, obtain the steady-state capability evaluation value of the network digital twin system;

[0107] The probability of a system being normally available in steady state characterizes the probability that a network digital twin system will complete its tasks in a normal state in steady state. It reflects the readiness of the network digital twin system for use, and its value is related to factors such as the failure rate, repair rate, and the degree of backup redundancy of nodes in the system.

[0108] For a homogeneous Markov birth-death process {X(t), t≥0} that is continuous in time and finite in state, with state space I={0,1,2,3,···,s}, if the process is ergodic, then a limiting distribution exists.

[0109] The limiting distribution π can characterize the probability distribution matrix of the steady-state operation of the network digital twin system, π=[π0,π1,π2,…,π s ] T The limiting distribution π satisfies the steady-state equilibrium equation of the system:

[0110] Q T π = 0

[0111] Decomposing the above formula reveals the following relationship:

[0112]

[0113] By iteratively applying term by term, we can obtain:

[0114]

[0115] And because We can obtain:

[0116]

[0117]

[0118] The steady-state capability evaluation value of a network digital twin system is the probability that the network digital twin system is in a steady state. It is the sum of the steady-state probabilities of the available states {0,1,2,3,...,s-1} out of s+1 possible states. That is, the steady-state capability evaluation value E of the network digital twin system. ss :

[0119]

[0120] Step S32: Based on the system state transition probability matrix, obtain the transient capability evaluation value of the network digital twin system;

[0121] The transient capability evaluation of a network digital twin system is a measure of the system's state at a given instant during operation, given that the system's state at the start of a task is known.

[0122] To evaluate the transient capability of a network digital twin system, it is necessary to first calculate the probability that the system is transiently available. The probability of the network digital twin system being in a transiently available state during operation can be obtained using the Komogorov progression equation. The Komogorov progression equation expressed using the aforementioned mathematical model is as follows:

[0123] L′(t)=L(t)Q (2)

[0124] Where L(t) and L′(t) represent the transient probability matrices for completing the specified task under available conditions at two different time points; where,

[0125] L(t) = [l0(t), l1(t), ..., l s (t)],

[0126] L′(t)=[l0′(t),l1′(t),…,l s ′(t)];

[0127] The above matrix equations can be multiplied and extracted to obtain a system of simultaneous equations:

[0128]

[0129] Assume that all nodes are in normal working state at the start of the task, i.e., l0(0) = 1; j (0)=0,j=1,2,…,s-1. By performing a Laplace transform on the above system of equations and solving it, we can obtain the transient probabilities of the network digital twin system in each available state {0,1,2,3,…,s-1}:

[0130]

[0131]

[0132]

[0133]

[0134] Assume the network digital twin system is in a normal, usable state during the time interval (0, t), meaning it can be used to complete the task. Transient capability is the sum of the transient probabilities of the system being in a usable state during the execution of the specified task. That is, the transient capability evaluation value E of the network digital twin system. I :

[0135]

[0136] Step S4: Based on the performance indicators of the network digital twin system, obtain the task completion capability value of the network digital twin system;

[0137] In this embodiment, the concept of a task completion capability vector for a network digital twin system is proposed. This vector reflects the capability of the network digital twin system to complete task objectives and is characterized by a weighted value of a certain type of performance index or multiple types of performance indexes.

[0138] Specifically, the task completion capability vector C of the network digital twin system can be represented as: [c0,c1,…,c j ,…,c s ]. Among them, c j This represents the task completion capability value of the network digital twin system when it is in an available state j, where each c... j This corresponds to one or more types of system performance indicators, where j = 0, 1, ..., s-1. s c is the probability that the network digital twin system will complete its task objective when it is in a faulty state. s =0.

[0139] Specifically, the task completion capability value of the network digital twin system in each available state is obtained by performing the following operations:

[0140] Step S41: Obtain the primary indicators of the network digital twin system in each available state, as well as the secondary indicators under each primary indicator;

[0141] For example, the performance metrics include several primary metrics, and each primary metric includes several secondary metrics.

[0142] Step S42: Based on the values ​​of the secondary indicators under each primary indicator, obtain the weight of each primary indicator; specifically:

[0143] Step S421: Normalize the values ​​of the secondary indicators of the network digital twin system in each available state to obtain the normalized values ​​of the corresponding secondary indicators.

[0144] Step S422: Obtain the weight of each secondary indicator based on the normalized values ​​of all secondary indicators under the same primary indicator;

[0145] Step S422: Based on the weights of all secondary indicators under each primary indicator, obtain the weight of each primary indicator.

[0146] The implementation process of step S42 is explained as follows:

[0147] For example, capability evaluation indicators can be categorized into multiple types and hierarchical levels based on system availability states. In the j = 0, 1, ..., s-1 availability states, multiple types and hierarchical levels are defined. Thus, the following system performance indicators are defined:

[0148] (1) Primary indicators

[0149] The k-th primary metric for the j-th available state is represented by c. jk c jk The importance of a network digital twin system in the capability evaluation process is determined by its weight ω.jk Characterization; where k ranges from 1 to K, and K represents the total number of categories of the primary indicator.

[0150] (2) Secondary indicators

[0151] The v-th secondary indicator under the k-th primary indicator in the j-th available state is represented by c. jkv c jkv The importance of a network digital twin system in the capability evaluation process is determined by its weight ω. jkv Characterization; where v ranges from 1 to V, and V represents the total number of categories of secondary indicators under the current primary indicator.

[0152] Because various indicators have different units of measurement, they are normalized before being weighted to assess the overall system capability. jkv The normalized value is r jkv .

[0153]

[0154] In the process of solving for the weights of the first-level normalized indicators, it is first necessary to calculate the entropy value of the weights of the first-level indicator system based on the second-level indicators it contains; where the entropy value of the weight of the k-th first-level indicator in the j-th available state is:

[0155]

[0156] Based on the entropy value of each primary indicator, the amount of information contained in each indicator can be obtained, and the weight can be determined according to the amount of information contained. Therefore, the weights of the primary indicators can be calculated; where the weight ω of the k-th primary indicator in the j-th available state is... jk for:

[0157]

[0158] Step S43: Based on the weights of all primary and secondary indicators, obtain the task completion capability value of the network digital twin system in the corresponding available state.

[0159] Specifically, the task completion capability value c of the network digital twin system when it is in an available state j. j for:

[0160]

[0161] For example, the performance metrics and their values ​​for a network entity in capability state 0 are shown in Table 1:

[0162] Table 1 Performance indicators and their values ​​when network entities are in capability state 0

[0163]

[0164] At this point, the task completion capability value when capability state 0 can be obtained in the following way:

[0165] Calculation of secondary indicator weights:

[0166] ω 011 =0.403, ω 012 =0.254, ω 013 =0.343

[0167] ω 021 =0.204, ω 022 =0.222, ω 023 =0.278, ω 024 =0.296

[0168] Entropy calculation:

[0169] H 01 =0.984, H 02 =0.992

[0170] Primary indicator weights:

[0171] ω 01 =0.651, ω 02 =0.349

[0172] Task completion ability value when ability status is 0

[0173] c0 = 0.797

[0174] Similarly, the task completion capability value of the system in other states can be calculated, and then the overall task completion capability value of the system can be obtained.

[0175] The system's task completion capability value is the sum of the products of the capability value in each available state and the instantaneous probability of being in that state. That is, the task completion capability value A of the network digital twin system is:

[0176]

[0177] Step S5: Based on the steady-state capability evaluation value, transient capability evaluation value, and task completion capability value of the network digital twin system, obtain the network comprehensive capability evaluation result of the network entity.

[0178] The network comprehensive capability assessment result of the network entity is equal to the network comprehensive capability assessment result of the network digital twin system. During operation, the network comprehensive capability assessment result is a comprehensive reflection of the steady-state capability evaluation value, transient capability evaluation value, and task completion capability value of the network digital twin system, reflecting its steady-state operating capability, transient operating capability, and task completion capability. Therefore, in this embodiment, the network comprehensive capability assessment result P of the network digital twin system can be expressed as:

[0179] P = E ss ·E I ·A (9).

[0180] In summary, Embodiment 1 provides a method for evaluating the comprehensive network capabilities based on digital twins. By analyzing all capability states of the network digital twin system, a system state transition probability matrix is ​​constructed, and corresponding steady-state and transient capability evaluation values ​​are obtained accordingly. Furthermore, by analyzing the primary and secondary indicators of the network digital twin system, the task completion capability value of the network digital twin system is obtained. Finally, the steady-state capability evaluation value, transient capability evaluation value, and task completion capability value are integrated to obtain the comprehensive network capability evaluation result of the network digital twin system. This result reflects the comprehensive network capability of the network digital twin system, possesses strong dynamism, and can effectively reflect the changes in the comprehensive capabilities of network entities and the network digital twin system over time.

[0181] Based on the method proposed in this embodiment, a function influence relationship analysis is performed to obtain the impact of changes in each parameter on the overall system capability. A schematic diagram of the network comprehensive capability evaluation results of the network digital twin system is shown below. Figure 3 As shown, in Figure 3 The paper presents the relationship between the overall network capability of a network digital twin system and its failure rate and repair rate. Specifically, as the failure rate increases, the overall network capability decreases; conversely, as the repair rate increases, the overall system capability increases. Furthermore, when the failure rate or repair rate is low, network degradation or expansion occurs more rapidly. Therefore, it is evident that under high repair rate conditions, reducing repair costs is more effective than increasing the repair rate in improving the overall system capability.

[0182] Example 2

[0183] Embodiment 2 of this invention provides a network comprehensive capability assessment system based on digital twins, as shown in the schematic diagram below. Figure 4 As shown, it includes:

[0184] The capability status acquisition module is used to map network entities into a network digital twin system and acquire all capability statuses of the network digital twin system.

[0185] The system state transition probability matrix construction module is used to construct the system state transition probability matrix based on all capability states of the network digital twin system.

[0186] The evaluation value acquisition module is used to acquire the steady-state capability evaluation value and transient capability evaluation value of the network digital twin system based on the system state transition probability matrix; it is also used to acquire the task completion capability value of the network digital twin system based on the performance indicators of the network digital twin system.

[0187] The network comprehensive capability assessment module is used to obtain the network comprehensive capability assessment result of the network entity based on the steady-state capability evaluation value, transient capability evaluation value, and task completion capability value of the network digital twin system.

[0188] The specific implementation process of the system embodiment of the present invention can be found in the above method embodiment, and the system embodiment will not be described again here.

[0189] Since the principles of this system embodiment are the same as those of the above method embodiment, this system also has the corresponding technical effects of the above method embodiment.

[0190] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0191] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for evaluating the comprehensive capabilities of a network based on a digital twin, characterized in that, include: Map network entities to a network digital twin system and obtain all capability states of the network digital twin system; Based on all the capability states of the network digital twin system, a system state transition probability matrix is ​​constructed; Based on the system state transition probability matrix, the steady-state capability evaluation value and transient capability evaluation value of the network digital twin system are obtained; Based on the performance indicators of the network digital twin system, obtain the task completion capability value of the network digital twin system; Based on the steady-state capability evaluation value, transient capability evaluation value, and task completion capability value of the network digital twin system, the comprehensive network capability evaluation result of the network entity is obtained. Among them, the steady-state capability evaluation value of the network digital twin system is the probability that the network digital twin system is in a steady state, which is the probability that it is in a steady state. Available states in the possible states {0,1,2,3,..., The sum of steady-state probabilities; the transient capability evaluation value is the sum of transient probabilities of the network digital twin system being in an available state during the execution of the specified task; This represents the total number of nodes that fail when the network digital twin system completely loses its functionality; Based on the performance metrics of the network digital twin system, the task completion capability value of the network digital twin system is obtained, including: Based on the performance indicators of the network digital twin system, the task completion capability values ​​of the network digital twin system in each available state are obtained; Based on the task completion capability value and transient probability of the network digital twin system in each available state, the task completion capability value of the network digital twin system is obtained.

2. The network comprehensive capability evaluation method based on digital twins according to claim 1, characterized in that, All capability states of the network digital twin system include: Capability Status 0: All nodes in the network digital twin system are in good condition, and all functions of the network digital twin system are functioning normally. Capability Status 1: In the network digital twin system, one node is in a fault state, but the network digital twin system can still meet certain functional requirements; Ability Status The network digital twin system has Even when one node is in a faulty state, the network digital twin system can still meet certain functional requirements; ; Ability Status The network digital twin system has If one or more nodes are in a fault state, the network digital twin system is in a fault state and cannot meet any functional requirements.

3. The network comprehensive capability evaluation method based on digital twins according to claim 1, characterized in that, The system state transition probability matrix for: （1） in, , This represents the total number of nodes in the network digital twin system; ; , These represent the failure rate and repair rate of each node in the network digital twin system, respectively.

4. The network comprehensive capability evaluation method based on digital twins according to claim 3, characterized in that, The process of obtaining the steady-state capability evaluation value of the network digital twin system includes: Solve the steady-state equilibrium equations during the operation of the network digital twin system. The limiting distribution is obtained. ;in, , Indicates the first Steady-state probability under each capability state; The steady-state probabilities of all available states in all capability states are summarized to form the steady-state capability evaluation value of the network digital twin system; The available states in the capability states include capability state 0 to capability state 0. .

5. The network comprehensive capability evaluation method based on digital twins according to claim 4, characterized in that, The steady-state capability evaluation value of the network digital twin system : （2） in, , 。 6. The network comprehensive capability evaluation method based on digital twins according to claim 5, characterized in that, The transient capability evaluation value of the network digital twin system : （3） in, This indicates that the network digital twin system is at the first stage. The transient probability of each available state. Indicates time; ， ， 。 7. The network comprehensive capability evaluation method based on digital twins according to claim 6, characterized in that, The task completion capability value of the network digital twin system for: （4） in, This indicates that the network digital twin system is in a usable state. The task completion ability value at that time.

8. The method for evaluating network comprehensive capabilities based on digital twins according to any one of claims 1-7, characterized in that, The network entity's comprehensive network capability assessment result is the product of the steady-state capability evaluation value, transient capability evaluation value, and task completion capability value of the network digital twin system.

9. A network comprehensive capability assessment system based on digital twins, characterized in that, The system is implemented based on the network comprehensive capability evaluation method based on digital twins as described in any one of claims 1-8, including: The capability status acquisition module is used to map network entities into a network digital twin system and acquire all capability statuses of the network digital twin system. The system state transition probability matrix construction module is used to construct the system state transition probability matrix based on all capability states of the network digital twin system. The evaluation value acquisition module is used to acquire the steady-state capability evaluation value and transient capability evaluation value of the network digital twin system based on the system state transition probability matrix; it is also used to acquire the task completion capability value of the network digital twin system based on the performance indicators of the network digital twin system. The network comprehensive capability assessment module is used to obtain the network comprehensive capability assessment result of the network entity based on the steady-state capability evaluation value, transient capability evaluation value, and task completion capability value of the network digital twin system.

Images