Data link self-healing method based on situation awareness and fuzzy decision and related equipment

Abstract

The application discloses a data link self-healing method based on situation awareness and fuzzy decision and related equipment, and relates to the technical field of power data link management. The method comprises the following steps: acquiring situation awareness data of a power grid data link; the situation awareness data comprises link state data, service attribute data and fault information data; based on the situation awareness data, a target membership function of a preset evaluation index is constructed; the preset evaluation index comprises consistency recovery rate, self-healing response delay, link resource occupancy rate and service adaptation degree; based on the situation awareness data, a dynamic weight calculation model of the preset evaluation index is constructed; according to the target membership function and the dynamic weight calculation model, a fuzzy comprehensive evaluation value of a candidate self-healing strategy is acquired; according to the fuzzy comprehensive evaluation value, a target self-healing strategy is selected from the candidate self-healing strategy; and the target self-healing strategy is executed on the power grid data link, so that the self-healing of the power grid data link is realized. The application can improve the decision precision of data link management and can be widely applied to the technical field of power data link management.

Description

Technical Field

[0001] This invention relates to the field of power data link management technology, and in particular to a data link self-healing method and related equipment based on situational awareness and fuzzy decision-making. Background Technology

[0002] In the context of the power grid's granular data silo model, the data transmission, interaction, and supply scenarios across business systems are becoming increasingly complex. Data link consistency failures (such as packet loss, format incompatibility, and data missing) directly impact the continuity of power services and the security of data assets. Data link self-healing technology has become a core support for ensuring the digital operation of the power grid. However, existing data link self-healing solutions generally lack deep adaptation to the characteristics of power data link services (such as the real-time requirements of dispatch data and multi-service semantic adaptation) and dynamic operating states (such as link load fluctuations and differences in fault levels), making it difficult to meet the actual needs of multi-objective collaborative self-healing in the power grid. Summary of the Invention

[0003] In view of this, the main objective of the embodiments of the present invention is to provide a data link self-healing method and related equipment based on situational awareness and fuzzy decision-making, in order to solve at least one of the problems of the prior art. The present invention can improve the decision-making accuracy of data link management.

[0004] To achieve the above objectives, one aspect of this invention provides a data link self-healing method based on situational awareness and fuzzy decision-making, the method comprising: Acquire situational awareness data of the power grid data link; the situational awareness data includes link status data, service attribute data, and fault information data; Based on the situational awareness data, a target membership function for preset evaluation indicators is constructed; the preset evaluation indicators include consistency recovery rate, self-healing response latency, link resource utilization rate, and service adaptability. Based on the situational awareness data, a dynamic weight calculation model for the preset evaluation indicators is constructed. Based on the target membership function and the dynamic weight calculation model, obtain the fuzzy comprehensive evaluation value of the candidate self-healing strategy; Based on the fuzzy comprehensive evaluation value, a target self-healing strategy is selected from the candidate self-healing strategies; The target self-healing strategy is executed on the power grid data link to achieve self-healing of the power grid data link.

[0005] In some embodiments, constructing the target membership function of the preset evaluation index based on the situational awareness data includes the following steps: Preset the initial effective threshold for the first membership degree and the saturation threshold for the first membership degree; Based on the first effective membership threshold and the first membership saturation threshold, a first ascending half-trapezoidal membership function for the consistency recovery rate is constructed. Based on the business attribute data, a second membership saturation threshold, a first membership failure threshold, a third membership saturation threshold, and a second membership failure threshold are preset for core business scenarios. Based on the second membership saturation threshold, the first membership failure threshold, the third membership saturation threshold, and the second membership failure threshold, a first decreasing half-trapezoidal membership function for the self-healing response delay is constructed. Preset the saturation threshold for the fourth membership degree and the failure threshold for the third membership degree; Based on the fourth membership degree saturation threshold and the third membership degree failure threshold, a second descending half-trapezoidal membership degree function for the link resource occupancy rate is constructed. Preset the effective threshold for the second membership degree and the saturation threshold for the fifth membership degree; Based on the second effective membership threshold and the fifth membership saturation threshold, the second ascending half-trapezoidal membership function of the business adaptability is constructed.

[0006] In some embodiments, constructing a dynamic weight calculation model for the preset evaluation index based on the situational awareness data includes the following steps: The business type labels in the business attribute data are quantified to construct a business priority factor; Obtain the average of link bandwidth utilization and computing power occupancy in the link status data, and construct the link load factor; The scope and severity of the fault impact in the fault information data are quantified to construct a fault level factor; Based on the business priority factor and the fault level factor, a first weighted calculation model for the consistency recovery rate is constructed. Based on the business priority factor and the fault level factor, a second weight calculation model for the self-healing response delay is constructed. Based on the link load factor, a third weight calculation model for the link resource utilization rate is constructed; Based on the business priority factor, a fourth weight calculation model for the business adaptability is constructed.

[0007] In some embodiments, obtaining the fuzzy comprehensive evaluation value of the candidate self-healing strategy based on the target membership function and the dynamic weight calculation model includes the following steps: Based on the fault information data, multiple candidate self-healing strategies that match the current fault type are selected from the pre-built candidate self-healing strategy library. Obtain the first actual quantitative value of the consistency recovery rate, the second actual quantitative value of the self-healing response latency, the third actual quantitative value of the link resource utilization rate, and the fourth actual quantitative value of the service adaptability corresponding to the candidate self-healing strategy. Based on the target membership function, the first actual quantization value, the second actual quantization value, the third actual quantization value, and the fourth actual quantization value, obtain the first membership value of the consistency recovery rate, the second membership value of the self-healing response delay, the third membership value of the link resource occupancy rate, and the fourth membership value of the service adaptability. Based on the dynamic weight calculation model, the first membership value, the second membership value, the third membership value, and the fourth membership value, the fuzzy comprehensive evaluation value of the candidate self-healing strategy is obtained.

[0008] In some embodiments, selecting a target self-healing strategy from the candidate self-healing strategies based on the fuzzy comprehensive evaluation value includes the following steps: From the multiple candidate self-healing strategies, select the effective strategies whose fuzzy comprehensive evaluation value is greater than or equal to a preset threshold; From the effective strategies, the effective strategy with the largest fuzzy comprehensive evaluation value is selected as the target self-healing strategy; If the difference between the fuzzy comprehensive evaluation values ​​of multiple effective strategies is less than the preset tolerance, then the effective strategy with the largest first membership value is taken as the target self-healing strategy.

[0009] In some embodiments, after executing the target self-healing strategy on the power grid data link, the method further includes the following steps: Collect actual effect data after the target self-healing strategy is executed; Based on the actual effect data, the target membership function, the dynamic weight calculation model, and the candidate self-healing strategy library are updated.

[0010] To achieve the above objectives, another aspect of this invention proposes a data link self-healing device based on situational awareness and fuzzy decision-making, the device comprising: The situation awareness module is used to acquire situation awareness data of the power grid data link; the situation awareness data includes link status data, service attribute data, and fault information data. The first fuzzy decision module is used to construct a target membership function of preset evaluation indicators based on the situational awareness data; the preset evaluation indicators include consistency recovery rate, self-healing response latency, link resource utilization rate, and service adaptability. The second fuzzy decision module is used to construct a dynamic weight calculation model for the preset evaluation index based on the situational awareness data. The third fuzzy decision module is used to obtain the fuzzy comprehensive evaluation value of the candidate self-healing strategy based on the target membership function and the dynamic weight calculation model. The fourth fuzzy decision module is used to select a target self-healing strategy from the candidate self-healing strategies based on the fuzzy comprehensive evaluation value. The self-healing strategy execution module is used to execute the target self-healing strategy on the power grid data link to achieve self-healing of the power grid data link.

[0011] To achieve the above objectives, another aspect of the present invention provides an electronic device, the electronic device including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method described above.

[0012] To achieve the above objectives, another aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0013] To achieve the above objectives, another aspect of the present invention provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions to cause the computer device to perform the aforementioned method.

[0014] The embodiments of the present invention include at least the following beneficial effects: The present invention provides a data link self-healing method and related equipment based on situational awareness and fuzzy decision-making. This scheme acquires situational awareness data of the power grid data link, including link status data, service attribute data, and fault information data, ensuring the comprehensiveness and relevance of data collection; based on the situational awareness data, a target membership function of preset evaluation indicators is constructed, providing a unified dimension input basis for subsequent comprehensive evaluation; the preset evaluation indicators include consistency recovery rate, self-healing response delay, link resource occupancy rate, and service adaptability; based on the situational awareness data, a dynamic weight calculation model of the preset evaluation indicators is constructed, ensuring that the weight settings match the situational awareness data in real time, improving the accuracy and scenario adaptability of fuzzy decision-making; according to the target membership function and the dynamic weight calculation model, the fuzzy comprehensive evaluation value of candidate self-healing strategies is obtained, providing a precise decision basis for the execution of self-healing strategies; according to the fuzzy comprehensive evaluation value, a target self-healing strategy is selected from the candidate self-healing strategies, improving the decision-making accuracy of data link management; the target self-healing strategy is executed on the power grid data link to achieve power grid data link self-healing. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of the data link self-healing method based on situational awareness and fuzzy decision-making provided in the embodiments of the present invention; Figure 2 This is a schematic diagram of a closed-loop architecture for data link self-healing based on situational awareness and fuzzy decision-making provided in an embodiment of the present invention. Figure 3 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this invention; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this invention as detailed in the appended claims.

[0018] It should be noted that although functional modules are divided in the system diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first / S100" and "second / S200" in the specification, claims, and the foregoing drawings may be used herein to describe various concepts, but unless specifically stated otherwise, these concepts are not limited by these terms. These terms are used only to distinguish one concept from another. For example, first information may also be referred to as second information without departing from the scope of the embodiments of the invention, and similarly, second information may also be referred to as first information. Depending on the context, the words "if" or "when" as used herein may be interpreted as "when," "in response to a determination," or "in the event of a determination."

[0019] The terms “at least one,” “multiple,” “each,” “any,” etc., used in this invention, “at least one” includes one, two, or more than two; “multiple” includes two or more than two; “each” refers to each of the corresponding multiple; and “any” refers to any one of the multiple.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0021] Before providing a detailed description of the embodiments of the present invention, some of the nouns and terms involved in the embodiments of the present invention will be explained first. The nouns and terms involved in the embodiments of the present invention are subject to the following interpretations.

[0022] The Trapezoidal Membership Function (Trapmf) is a commonly used membership function in fuzzy logic and fuzzy control systems. Its shape resembles a trapezoid and is determined by four parameters. These parameters correspond to the four inflection points of the trapezoid, defining the width of the base and top of the trapezoid.

[0023] "Electricity bill collection" refers to ensuring the safe, complete, and efficient collection of electricity fees or the safe use of electricity through scientific management and technological means, so as to ensure that every electricity fee or every unit of electricity is accurately credited or used safely.

[0024] Currently, the problems with data link self-healing technology in the power grid "granular recovery" scenario include: a single self-healing objective, focusing only on consistency restoration and ignoring multi-objective coordination such as real-time performance, resource consumption, and business adaptation, leading to a disconnect between the solution and actual power business needs; a lack of a quantitative evaluation system adapted to the characteristics of power data, with indicator design failing to take into account both power grid business semantics and link operation rules, resulting in a lack of objective measurement basis for self-healing effectiveness; and statically set indicator weights, which cannot respond to dynamic scenarios such as data link load fluctuations and changes in business priorities, resulting in insufficient flexibility and adaptability of the self-healing strategy.

[0025] In view of this, embodiments of the present invention provide a data link self-healing method and related equipment based on situational awareness and fuzzy decision-making, such as... Figure 2 As shown, this solution uses a closed-loop architecture centered on "situational awareness—indicator quantification—dynamic weight calculation—fuzzy decision-making—self-healing execution and feedback optimization." Addressing the dynamic characteristics and multi-objective requirements of data link consistency failures in the power grid's "granular data storage" system, it achieves precise generation and efficient implementation of the optimal self-healing strategy through the coordinated operation of multiple core modules. Specifically, the situational awareness module provides real-time and reliable basic data support for the entire solution; the multi-dimensional indicator system establishes a scientific basis for the quantitative evaluation of self-healing effects; the dynamic weight calculation model dynamically adjusts the weights of each indicator by acquiring the latest link status, business attributes, and fault level data in real time, adapting to the dynamic changes in the power grid's granular data storage data link; fuzzy decision-making solves the strategy optimization problem under multi-objective conflicts through membership function quantification, dynamic weight allocation, and a comprehensive evaluation model; and the self-healing strategy execution and feedback optimization module realizes strategy implementation and iterative optimization throughout the entire process.

[0026] Figure 1 This is an optional flowchart of a data link self-healing method based on situational awareness and fuzzy decision-making provided in an embodiment of the present invention. Figure 1 The method may include, but is not limited to, steps S100 to S600: Step S100: Obtain situational awareness data of the power grid data link; the situational awareness data includes link status data, service attribute data, and fault information data. Step S200: Based on situational awareness data, construct the target membership function of preset evaluation indicators; the preset evaluation indicators include consistency recovery rate, self-healing response latency, link resource utilization rate, and service adaptability. Step S300: Based on situational awareness data, construct a dynamic weight calculation model for preset evaluation indicators; Step S400: Obtain the fuzzy comprehensive evaluation value of the candidate self-healing strategy based on the target membership function and the dynamic weight calculation model. Step S500: Select the target self-healing strategy from the candidate self-healing strategies based on the fuzzy comprehensive evaluation value. Step S600: Execute the target self-healing strategy on the power grid data link to achieve self-healing of the power grid data link.

[0027] In step S100 of some embodiments, considering the characteristics of multi-service integration and dynamic fluctuations in the power grid granular data link, a comprehensive perception system covering links, services, and faults is constructed. This system acquires link status data, service attribute data, and fault information data of the power grid data link, ensuring the comprehensiveness and relevance of data collection. Optionally, for the link status data dimension, the focus is on core data transmission indicators, selecting bandwidth utilization, computing power utilization, packet loss rate, and transmission delay as key perception items to directly reflect the link's operating load and transmission quality, providing basic data for subsequent resource utilization evaluation. For the service attribute data dimension, combined with the differentiated needs of power grid services, different service types such as scheduling data, metering data, and operation and maintenance data are identified, the priority of core and non-core services is distinguished, and data semantic tags such as equipment ID, voltage unit, and timestamp format are labeled to meet the quantitative requirements of service adaptability indicators. For the fault information data dimension, specific fault types such as packet loss, format incompatibility, and data missing are captured, the impact of a single service system or the scope of cross-system impact is defined, and first-level, second-level, and third-level fault levels are classified to provide a basis for prioritizing self-healing strategies.

[0028] In some optional embodiments, data link holographic sensing technology, log parsing interfaces, and multi-service system linkage mechanisms are integrated to achieve real-time synchronous acquisition of multi-source situational awareness data. For example, holographic sensing technology is used to monitor dynamic parameters of link transmission in real time; log parsing interfaces are used to extract relevant records such as format specifications and field matching during data flow; and linkage with business platforms such as scheduling systems and metering systems is used to obtain details of business attributes and original fault triggering information, ensuring the real-time nature and integrity of the collected data.

[0029] Optionally, to address potential issues in the collected data such as extreme outliers caused by link fluctuations, differences in multi-source data formats, and timestamp asynchronization, standardized preprocessing was performed on the situational awareness data. For example, the 3α data cleaning principle was used to remove extreme outliers from the link status data, avoiding interference with the weight allocation logic; normalization was used to convert indicators with different dimensions, such as latency in milliseconds and bandwidth utilization percentage, to the 0-1 range, providing a unified quantitative basis for subsequent membership calculations; and a timestamp alignment algorithm was used to achieve temporal synchronization of multi-source data, ensuring the spatiotemporal correlation of link status, service attributes, and fault information. Ultimately, a structured, highly reliable perception result was output, providing solid support for the accurate operation of multi-dimensional indicator quantification and fuzzy decision-making algorithms.

[0030] In some embodiments, to achieve scientific quantification and multi-objective optimization of the self-healing scheme for data link consistency faults in power grid granular data collection, this paper draws on the comprehensive evaluation approach of multiple indicators for distribution network self-healing, combines data link transmission characteristics with the core business needs of the power grid, and follows the principles of relevance, quantifiability, and adaptability to construct a multi-dimensional evaluation indicator system covering consistency effect, real-time performance, economy, and business adaptability, providing a comprehensive and accurate quantitative basis for fuzzy decision-making. Optionally, based on this multi-dimensional evaluation indicator system, the following preset evaluation indicators can be constructed: (1) Consistency Recovery Rate: The consistency recovery rate is used as the core evaluation indicator, directly reflecting the effectiveness of the self-healing scheme in restoring data link consistency. It is defined as the ratio of the total amount of data that conforms to the power grid data consistency standard after self-healing to the total amount of data affected by the fault, covering key judgment dimensions such as field integrity, numerical accuracy, and semantic compatibility. The quantitative formula for the consistency recovery rate is: Consistency Recovery Rate = (Amount of data conforming to the consistency standard / Total amount of data affected by the fault) × 100%. Ensuring that the data after self-healing can meet the core requirements of subsequent applications of various power grid businesses is the basic premise for measuring the effectiveness of the self-healing scheme.

[0031] (2) Self-healing response delay: Self-healing response delay focuses on the real-time requirements of the self-healing process and is defined as the total time from the detection and identification of the fault to the complete execution of the self-healing process and the restoration of the data link to normal transmission status. In combination with the differentiated characteristics of power grid services, strict timing thresholds are set for core services such as scheduling data, and quasi-strict timing thresholds are set for non-core services such as historical statistical data. By distinguishing the timing standards of different service types, the real-time requirements of various services are adapted to avoid the impact of self-healing delay on the normal operation of core power grid services.

[0032] (3) Link resource utilization rate: The link resource utilization rate is used as an economic evaluation indicator to assess the degree of link resource consumption during the self-healing process. The link resource utilization rate is defined as the ratio of the actual bandwidth and computing power resources occupied during the self-healing process to the total available link resources. The quantitative formula is: Link resource utilization rate = (self-healing occupied resources / total available link resources) × 100%. The setting of this indicator can avoid excessive occupation of link resources during the self-healing process, which may lead to obstruction of other service transmissions, and achieve a dynamic balance between the self-healing repair effect and resource consumption.

[0033] (4) Business Adaptability: Business adaptability focuses on the special characteristics of power grid business scenarios and is defined as the degree of fit between the self-healing solution and power grid business rules and data semantic specifications. It is quantified through data semantic matching. Specifically, it combines the power grid business semantic tag library and makes a comprehensive judgment from the dimensions of equipment identification consistency, data unit compatibility, timestamp synchronization, and business logic compliance. The adaptability is taken as the highest value when it fully complies with the power grid business specifications, and as the lowest value when there are incompatibilities in key semantics. This ensures that the self-healing solution can not only achieve data consistency restoration, but also accurately adapt to the specific application needs of different businesses such as scheduling, metering, and operation and maintenance.

[0034] In some optional embodiments, a dynamic adaptation mechanism is set up simultaneously in the multi-dimensional evaluation index system to support the flexible expansion of index types, adjustment of quantitative formula parameters and threshold ranges based on new power grid business scenarios such as new energy grid-connected data transmission. This ensures that the index system can continuously adapt to the business expansion and technology upgrade needs of the data link, and improves the long-term applicability and scenario coverage of the entire self-healing technology solution.

[0035] In step S200 of some embodiments, in order to achieve unified quantification and fuzzy decision adaptation of multi-dimensional evaluation indicators, based on the physical meaning, advantages and disadvantages trend and power grid granular data link scenario characteristics of each preset evaluation indicator, and referring to the mapping logic of "indicator-membership function" in the distribution network self-healing algorithm, targeted target membership functions are designed for the four types of preset evaluation indicators: consistency recovery rate, self-healing response delay, link resource occupancy rate and service adaptability. The original quantified values ​​of each indicator are converted into fuzzy membership values ​​in the range [0,1], providing a unified dimension input basis for subsequent comprehensive evaluation.

[0036] In some embodiments, step S200 may include, but is not limited to, steps S210 to S280: Step S210: Preset the first effective threshold for membership degree and the first saturation threshold for membership degree; Step S220: Construct the first ascending half-trapezoidal membership function of consistency recovery rate based on the first effective membership threshold and the first membership saturation threshold; Step S230: Based on the business attribute data, pre-set the second membership saturation threshold, the first membership failure threshold, the third membership saturation threshold, and the second membership failure threshold in the core business scenario; Step S240: Construct a first half-trapezoidal membership function for self-healing response delay based on the second membership saturation threshold, the first membership failure threshold, the third membership saturation threshold, and the second membership failure threshold. Step S250: Preset the fourth membership degree saturation threshold and the third membership degree failure threshold; Step S260: Based on the fourth membership degree saturation threshold and the third membership degree failure threshold, construct the second decreasing half-trapezoidal membership degree function for link resource occupancy. Step S270: Preset the second membership degree initial effective threshold and the fifth membership degree saturation threshold; Step S280: Construct the second ascending half-trapezoidal membership function of business adaptability based on the second membership degree initial effective threshold and the fifth membership degree saturation threshold.

[0037] In steps S210 to S220 of some embodiments, the consistency recovery rate is a preset evaluation index where a higher rate is better. The closer the consistency recovery rate is to the target value, the closer the membership degree corresponding to the consistency recovery rate is to 1. Therefore, an ascending half-trapezoidal membership function is used to construct the target membership function of the consistency recovery rate, i.e., the first ascending half-trapezoidal membership function. For example, combining the power grid data consistency requirements with the actual achievability of the project, the key parameter of the function is preset: the first effective threshold for the membership degree. First membership saturation threshold The corresponding first semi-trapezoidal membership function The expression is as follows: ; In the formula, This is the first actual quantitative value of the consistency recovery rate, with a value range of [0, 100%]; The first membership value corresponds to the consistency recovery rate, and its value ranges from [0,1]. When the consistency recovery rate is below 98%, the self-healing effect is deemed unqualified, and the membership value is 0. When the recovery rate is between 98% and 99.5%, the membership value increases linearly with the recovery rate. When the recovery rate reaches 99.5% or above, the membership value saturates to 1, and the self-healing effect is deemed optimal.

[0038] In steps S230 to S240 of some embodiments, the self-healing response delay is a preset evaluation index where lower is better. The smaller the value of the self-healing response delay is than the threshold, the closer the membership degree corresponding to the self-healing response delay is to 1. Therefore, a reduced half-trapezoidal membership function is used to construct the target membership function of the self-healing response delay, i.e., the first reduced half-trapezoidal membership function. For example, considering the differentiated characteristics of power grid services, function parameters are set according to the service priorities in the service attribute data. The service priorities can be divided into core services and non-core services. In the core service scenario, the second membership saturation threshold... First membership failure threshold In non-core business scenarios, the third membership degree saturation threshold Second membership failure threshold The corresponding first descending semi-trapezoidal membership function The expression is as follows: ; In the formula, This is the second actual quantification value of the self-healing response delay, in units of ; For business priority, when At that time, corresponding to the core business, when At that time, it corresponds to non-core business; This is the second membership value corresponding to the self-healing response delay, with a value range of [0,1]. When the self-healing response delay does not exceed the saturation threshold, the membership is 1, indicating optimal real-time performance; when the delay is between the saturation threshold and the failure threshold, the membership decreases linearly with the delay; when the delay reaches or exceeds the failure threshold, the membership is 0, indicating that the real-time performance does not meet business requirements.

[0039] In steps S250 to S260 of some embodiments, the link resource occupancy rate is a preset evaluation index where lower is better. The lower the link resource occupancy rate is than the constraint threshold, the closer the membership degree corresponding to the link resource occupancy rate is to 1. Therefore, a reduced half-trapezoidal membership function is used to construct the target membership function of the link resource occupancy rate, i.e., the second reduced half-trapezoidal membership function. For example, combined with the link resource carrying capacity, a key parameter of the function is set: the fourth membership degree saturation threshold. Third membership failure threshold The corresponding second descending semi-trapezoidal membership function The expression is as follows: ; In the formula, This is the third actual quantitative value of the link resource utilization rate, with a value range of [0, 100%]. This is the third membership value corresponding to the link resource occupancy rate, with a value range of [0,1]. When the occupancy rate does not exceed 20%, the membership degree is 1, indicating optimal resource consumption; when the occupancy rate is between 20% and 30%, the membership degree decreases linearly with the occupancy rate; when the occupancy rate reaches 30% or above, the membership degree is 0, indicating excessive resource consumption, which will affect the normal transmission of other services.

[0040] In steps S270 to S280 of some embodiments, the service adaptability is a preset evaluation index where higher is better. The closer the service adaptability value is to 1, the closer the corresponding membership degree is to 1. Therefore, an ascending half-trapezoidal membership function is used to construct the target membership function of the service adaptability, i.e., the second ascending half-trapezoidal membership function. For example, in conjunction with the semantic matching requirements of power grid services, the key parameter of the function is set as: the initial effective threshold of the second membership degree. Fifth membership saturation threshold The corresponding second semi-trapezoidal membership function The expression is as follows: ; In the formula, This is the fourth actual quantitative value of business adaptability, with a value range of [0,1]. This is the fourth membership value corresponding to the business adaptability, with a value range of [0,1]. When the adaptability is below 0.7, it is determined that the self-healing solution is incompatible with the business specifications, and the membership is 0; when the adaptability is between 0.7 and 0.9, the membership increases linearly with the adaptability; when the adaptability reaches 0.9 or above, the membership saturates to 1, and it is determined that the self-healing solution fully adapts to the power grid business requirements.

[0041] In step S300 of some embodiments, in order to solve the problem that traditional fixed weight allocation cannot adapt to the dynamic characteristics of the power grid granular data link, the embodiments of the present invention are based on the design concept of linking indicator weights with scenario requirements. According to the real-time situational awareness data output by the situational awareness module, a closed-loop linkage mechanism of "sensing data - influencing factors - weight adjustment" is constructed to realize the dynamic weight allocation of four types of preset evaluation indicators: consistency recovery rate, self-healing response delay, link resource occupancy rate, and service adaptability. This ensures that the weight settings are matched with the link status, service requirements, and fault scenarios in real time, thereby improving the accuracy of fuzzy decision-making and scenario adaptability.

[0042] In some embodiments, step S300 may include, but is not limited to, steps S310 to S370: Step S310: Quantify the business type labels in the business attribute data and construct a business priority factor; Step S320: Obtain the average value of link bandwidth utilization and computing power occupancy rate in the link status data, and construct the link load factor. Step S330: Quantify the scope and severity of the fault impact in the fault information data and construct a fault level factor; Step S340: Construct the first weight calculation model for consistency recovery rate based on the business priority factor and the fault level factor; Step S350: Construct a second weight calculation model for self-healing response delay based on the business priority factor and the fault level factor. Step S360: Construct a third weighted calculation model for link resource utilization rate based on the link load factor; Step S370: Construct a fourth weight calculation model for business adaptability based on the business priority factor.

[0043] In steps S310 to S330 of some embodiments, based on the three types of core data collected by the situational awareness module—link status data, service attribute data, and fault information data—three major weighting factors are extracted and standardized and quantified to provide objective input basis for weight calculation.

[0044] In step S310 of some embodiments, a business priority factor is constructed by quantifying the business type label in the business attribute data. For example, the business priority factor of core business (business with extremely high requirements for real-time performance and consistency) is assigned a value of 1.0, and the business priority factor of non-core business (business with lower requirements for timeliness) is assigned a value of 0.6, thereby accurately distinguishing the differentiated needs of different businesses for self-healing objectives.

[0045] In step S320 of some embodiments: the link load factor is calculated based on the average of the link bandwidth utilization and computing power occupancy rate in the link state data. The quantification formula is as follows: ; In the formula, The value range is [0.3, 1.0], and the higher the link load, the better. The larger the value, the more important the resource consumption constraint is in self-healing decision-making; This represents the actual load on the link. This represents the maximum load on the link.

[0046] In step S330 of some embodiments, the fault level factor is quantified according to the fault impact range and severity in the fault information data. For example, a fault severity factor of 1.0 is assigned to Level 1 faults (affecting cross-system operations and core business operations), a fault severity factor of 0.8 is assigned to Level 2 faults (affecting a single business system but not other businesses), and a fault severity factor of 0.5 is assigned to Level 3 faults (local data anomalies, with no impact on business operations). Quantifying the scope and severity of fault impact guides the self-healing priority.

[0047] In steps S340 to S370 of some embodiments, based on the logic of setting basic weights based on engineering practice in the distribution network self-healing algorithm, and combined with the three major influencing factors of business priority factor, link load factor, and fault level factor, a dynamic weight calculation model for four types of preset evaluation indicators can be constructed. For example, the expression of the first weight calculation model is: ; The expression for the second weight calculation model is: ; The expression for the third weight calculation model is: ; The expression for the fourth weight calculation model is: ; In the formula, Initial weights for consistency recovery rate; The initial weights for delaying the self-healing response; The initial weight for link resource utilization; Initial weights are assigned to business adaptability. The basic weight coefficients in each formula (0.3, 0.25, 0.2, etc.) are calibrated based on engineering practice experience of power grid data link self-healing. Dynamic adjustment of weights is achieved through the product of influence factors: when the core business encounters a Level 1 fault, , ,at this time , This highlights the core decision-making importance of consistency recovery and real-time performance; when the link state is that the link load is saturated ( )hour, This strengthens the weight of resource consumption constraints in decision-making, preventing the self-healing process from excessively consuming resources and affecting other businesses.

[0048] In some embodiments, to satisfy the constraint condition of "the sum of weights is 1" in fuzzy comprehensive evaluation, the initial weights calculated above are normalized, as shown in the following formula: ; ; ; ; In the formula, The target weight for consistency recovery rate; The target weight for the self-healing response delay; Assign target weights to link resource utilization rates; The target weights for business adaptability are set. By normalizing the initial weights, it can be ensured that the sum of the weights of the four categories of indicators is strictly equal to 1, which meets the mathematical logic requirements of fuzzy decision-making.

[0049] In some optional embodiments, the weight update mechanism is synchronized with the situational awareness data acquisition cycle, with an update cycle set at 50ms. By acquiring the latest link status, service attributes, and fault level data in real time, the weights of each indicator are dynamically adjusted. When there is a sudden change in link load, a service type switch, or a fault level upgrade, an emergency weight update process is triggered, skipping the regular cycle and directly calculating the new weights. This ensures the timeliness and adaptability of weight adjustments, perfectly adapting to the dynamic changes in the power grid granular data link.

[0050] In some embodiments, based on common fault types in the power grid granular data link and combined with proven self-healing methods from engineering practice, a structured candidate self-healing strategy library is pre-built to ensure that the strategies cover major fault scenarios and are executable. For example, the candidate self-healing strategy library includes three sub-strategies for packet loss faults: incremental retransmission strategy, backup link switching strategy, and redundant data retrieval strategy; for format incompatibility faults: real-time format conversion strategy, power grid business semantic mapping strategy, and interface adaptation parameter adjustment strategy; for data missing faults: source data completion strategy, related data derivation strategy, and historical backup data recovery strategy; and for data tampering faults: digital signature verification and repair strategy, source data hash comparison and retransmission strategy, and business logic verification and correction strategy. Each sub-strategy has a pre-defined execution process, applicable conditions, and resource requirements, providing a foundation for subsequent indicator quantification.

[0051] In step S400 of some embodiments, a complete evaluation model of "strategy library - index quantification - comprehensive scoring - optimal selection" is constructed by combining the multiple fault types and multiple self-healing strategies of the power grid particle warehousing data link, so as to realize the scientific selection of self-healing strategies under multiple objective constraints and provide accurate decision-making basis for self-healing execution.

[0052] In some embodiments, step S400 may include, but is not limited to, steps S410 to S440: Step S410: Based on the fault information data, select multiple candidate self-healing strategies that match the current fault type from the pre-built candidate self-healing strategy library. Step S420: Obtain the first actual quantitative value of the consistency recovery rate, the second actual quantitative value of the self-healing response latency, the third actual quantitative value of the link resource utilization rate, and the fourth actual quantitative value of the service adaptability corresponding to the candidate self-healing strategy. Step S430: Based on the target membership function, the first actual quantization value, the second actual quantization value, the third actual quantization value, and the fourth actual quantization value, obtain the first membership value of consistency recovery rate, the second membership value of self-healing response delay, the third membership value of link resource occupancy rate, and the fourth membership value of service adaptability. Step S440: Based on the dynamic weight calculation model, the first membership value, the second membership value, the third membership value, and the fourth membership value, obtain the fuzzy comprehensive evaluation value of the candidate self-healing strategy.

[0053] In step S410 of some embodiments, the current fault type is obtained based on the fault information data acquired in real time. Based on the current fault type, the pre-built candidate self-healing strategy library is queried to filter out multiple candidate self-healing strategies that match the current fault type.

[0054] In step S420 of some embodiments, for each matched candidate self-healing strategy, a first actual quantitative value of consistency recovery rate, a second actual quantitative value of self-healing response latency, a third actual quantitative value of link resource utilization, and a fourth actual quantitative value of service adaptability are obtained for each candidate self-healing strategy.

[0055] In step S430 of some embodiments, substituting the first actual quantized value into the first ascending half-trapezoidal membership function yields the first membership value of the consistency recovery rate; substituting the second actual quantized value into the first descending half-trapezoidal membership function yields the second membership value of the self-healing response delay; substituting the third actual quantized value into the second descending half-trapezoidal membership function yields the third membership value of the link resource occupancy rate; and substituting the fourth actual quantized value into the second ascending half-trapezoidal membership function yields the fourth membership value of the service adaptability.

[0056] In step S440 of some embodiments, substituting the first membership value into the first weight calculation model yields the initial weight for consistency recovery rate; substituting the second membership value into the second weight calculation model yields the initial weight for self-healing response delay; substituting the third membership value into the third weight calculation model yields the initial weight for link resource utilization; and substituting the fourth membership value into the fourth weight calculation model yields the initial weight for service adaptability. Normalizing the initial weights of each preset evaluation indicator yields the target weights for consistency recovery rate, self-healing response delay, link resource utilization, and service adaptability. Using the target weights of each preset evaluation indicator as coefficients in the comprehensive evaluation value calculation model, and taking the membership values ​​of each preset evaluation indicator as input, a weighted summation method is used to calculate the fuzzy comprehensive evaluation value of the candidate self-healing strategy, as shown in the following formula: ; In the formula, The comprehensive evaluation value of the candidate self-healing strategy ranges from [0,1]. This comprehensive evaluation value calculation model reflects the differences in importance of each evaluation dimension under different scenarios through weight coefficients, quantifies the performance of the strategy in each dimension through membership values, and finally achieves an overall characterization of the strategy's merits and demerits through the comprehensive evaluation value. The closer the fuzzy comprehensive evaluation value is to 1, the more suitable the strategy is for the current fault scenario and link status.

[0057] In step S500 of some embodiments, a two-step optimal strategy screening process is designed to ensure the accuracy and engineering applicability of the screening results. The first step is validity screening, and the second step is optimal screening, to select the strategy that best suits the current fault scenario and link status, thereby improving the decision-making accuracy of data link management.

[0058] In some embodiments, step S500 may include, but is not limited to, steps S510 to S530: Step S510: Select effective strategies from multiple candidate self-healing strategies whose fuzzy comprehensive evaluation value is greater than or equal to a preset threshold. Step S520: Select the effective strategy with the largest fuzzy comprehensive evaluation value from the effective strategies as the target self-healing strategy; Step S530: If the difference between the fuzzy comprehensive evaluation values ​​of multiple effective strategies is less than the preset tolerance, then the effective strategy with the largest first membership value is taken as the target self-healing strategy.

[0059] In step S510 of some embodiments, the fuzzy comprehensive evaluation value is removed. The candidate self-healing strategies, then the fuzzy comprehensive evaluation value Candidate self-healing strategies with a threshold of 0.6 or higher will be considered valid strategies, laying the foundation for further optimal selection. This threshold is set based on the engineering acceptance criteria for power grid data link self-healing. Candidate self-healing strategies with a threshold lower than this threshold are deemed unable to meet basic self-healing requirements, such as inadequate consistency recovery or excessive resource consumption.

[0060] In step S520 of some embodiments, the candidate self-healing strategies (i.e., effective strategies) that have passed the validity screening are evaluated according to the fuzzy comprehensive evaluation value. Sort the strategies in descending order and select the effective strategy with the highest fuzzy comprehensive evaluation value as the optimal self-healing strategy for the current fault scenario and link status, i.e., the target self-healing strategy.

[0061] In step S530 of some embodiments, if there are two or more effective strategies whose fuzzy comprehensive evaluation value difference is less than 0.02, that is, the effective strategies corresponding to these fuzzy comprehensive evaluation value differences less than 0.02 are at the same optimal level, then the first membership value of the core indicator of consistency recovery rate is further compared, and the first membership value is selected. A more effective strategy is to act as a self-healing strategy for the target, thereby ensuring that core needs are met first.

[0062] In step S600 of some embodiments, during the target self-healing strategy execution phase, based on the fault type and link status, the corresponding execution process in the candidate strategy library is automatically invoked, linking the data link transmission components, interface adaptation modules, and business system interfaces to achieve automated triggering of operations such as incremental retransmission, format conversion, and link switching, without manual intervention. During execution, core indicator data such as consistency recovery rate and self-healing response latency are collected in real time and dynamically compared with expected thresholds. If the indicators deviate, emergency adjustments are triggered to ensure execution stability.

[0063] In some embodiments, a dynamic iteration mechanism for the strategy is set up to improve the robustness of the model in complex scenarios. For example, after each execution of the target self-healing strategy on the power grid data link, data on the actual execution effect of the target self-healing strategy based on feedback from the situational awareness module is collected. The difference between the predicted and actual values ​​of the comprehensive evaluation is compared, and the quantitative parameters of the corresponding indicators of the strategy are corrected in reverse. This involves updating the target membership function, the dynamic weight calculation model, and the candidate self-healing strategy library. For example, adjusting the key threshold of the membership function, correcting the basic coefficients of the dynamic weight calculation model, adjusting the actual measured value of the self-healing response delay, and optimizing the judgment threshold of business adaptability. Simultaneously, the applicable conditions and priority weights of the strategy in the candidate strategy library are updated. Through iterative optimization after each round of execution, the evaluation model is continuously optimized with engineering practice, gradually improving the accuracy and adaptability of strategy selection, and continuously enhancing the adaptability of the self-healing strategy to the power grid granular data link scenario, thereby strengthening the engineering practicality and robustness of the solution.

[0064] This invention also provides a data link self-healing device based on situational awareness and fuzzy decision-making, which can implement the above-mentioned data link self-healing method based on situational awareness and fuzzy decision-making. The device includes: The situation awareness module is used to acquire situation awareness data of the power grid data link; the situation awareness data includes link status data, service attribute data, and fault information data. The first fuzzy decision module is used to construct the target membership function of preset evaluation indicators based on situational awareness data. The preset evaluation indicators include consistency recovery rate, self-healing response latency, link resource utilization rate, and business adaptability. The second fuzzy decision module is used to construct a dynamic weight calculation model for preset evaluation indicators based on situational awareness data. The third fuzzy decision module is used to obtain the fuzzy comprehensive evaluation value of the candidate self-healing strategy based on the target membership function and the dynamic weight calculation model. The fourth fuzzy decision module is used to select the target self-healing strategy from the candidate self-healing strategies based on the fuzzy comprehensive evaluation value. The self-healing strategy execution module is used to execute the target self-healing strategy on the power grid data link to achieve self-healing of the power grid data link.

[0065] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0066] This invention also provides an electronic device, which includes a processor and a memory. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including a tablet computer, an in-vehicle computer, or similar device.

[0067] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0068] refer to Figure 3 , Figure 3 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 701 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention. The memory 702 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 702 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 702 and is called and executed by the processor 701. The input / output interface 703 is used to implement information input and output; The communication interface 704 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 705 transmits information between various components of the device (e.g., processor 701, memory 702, input / output interface 703, and communication interface 704); The processor 701, memory 702, input / output interface 703, and communication interface 704 are connected to each other within the device via bus 705.

[0069] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0070] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0071] This invention also provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions to cause the computer device to perform the aforementioned method.

[0072] In summary, the data link self-healing method and related equipment based on situational awareness and fuzzy decision-making according to embodiments of the present invention have the following advantages: 1. The embodiments of the present invention break through the limitations of a single objective by using a multi-dimensional indicator system, integrating consistency recovery, real-time performance, resource consumption and business adaptation evaluation, which aligns with the core needs of power data link operation and avoids "emphasizing recovery while neglecting adaptation" or resource waste.

[0073] 2. The embodiments of the present invention respond in real time to changes in link load, service priority and fault level through a dynamic weight allocation mechanism, which significantly improves the flexibility and scenario adaptability of self-healing decision-making.

[0074] 3. The embodiments of the present invention achieve multi-objective optimal strategy selection through fuzzy comprehensive evaluation and closed-loop optimization mechanism, and balance self-healing success rate, response efficiency and resource utilization rate through quantitative indicators and iterative optimization.

[0075] 4. The embodiments of the present invention form a closed-loop automated solution for the entire process of "perception-decision-execution-feedback", which requires no manual intervention, is adaptable to multiple business scenarios of power grid data granularization, ensures the stability of core business, provides efficient support for data link management and control of new power systems, and can be extended to fields such as centralized data link management in the energy industry and self-healing consistency of industrial data transmission.

[0076] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is altered and sub-operations described as part of a larger operation are executed independently.

[0077] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the described functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0078] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0079] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0080] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0081] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0082] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0083] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0084] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A data link self-healing method based on situational awareness and fuzzy decision-making, characterized in that, Includes the following steps: Acquire situational awareness data of the power grid data link; the situational awareness data includes link status data, service attribute data, and fault information data; Based on the situational awareness data, construct a target membership function for a preset evaluation index; The preset evaluation indicators include consistency recovery rate, self-healing response latency, link resource utilization rate, and service adaptability. Based on the situational awareness data, a dynamic weight calculation model for the preset evaluation indicators is constructed. Based on the target membership function and the dynamic weight calculation model, obtain the fuzzy comprehensive evaluation value of the candidate self-healing strategy; Based on the fuzzy comprehensive evaluation value, a target self-healing strategy is selected from the candidate self-healing strategies; The target self-healing strategy is executed on the power grid data link to achieve power grid data link self-healing.

2. The method according to claim 1, characterized in that, The step of constructing the target membership function of the preset evaluation index based on the situational awareness data includes the following steps: Preset the initial effective threshold for the first membership degree and the saturation threshold for the first membership degree; Based on the first effective membership threshold and the first membership saturation threshold, a first ascending half-trapezoidal membership function for the consistency recovery rate is constructed. Based on the business attribute data, a second membership saturation threshold, a first membership failure threshold, a third membership saturation threshold, and a second membership failure threshold are preset for core business scenarios. Based on the second membership saturation threshold, the first membership failure threshold, the third membership saturation threshold, and the second membership failure threshold, a first decreasing half-trapezoidal membership function for the self-healing response delay is constructed. Preset the saturation threshold for the fourth membership degree and the failure threshold for the third membership degree; Based on the fourth membership degree saturation threshold and the third membership degree failure threshold, a second descending half-trapezoidal membership degree function for the link resource occupancy rate is constructed. Preset the effective threshold for the second membership degree and the saturation threshold for the fifth membership degree; Based on the second effective membership threshold and the fifth membership saturation threshold, the second ascending half-trapezoidal membership function of the business adaptability is constructed.

3. The method according to claim 1, characterized in that, The process of constructing a dynamic weight calculation model for the preset evaluation indicators based on the situational awareness data includes the following steps: The business type labels in the business attribute data are quantified to construct a business priority factor; Obtain the average of link bandwidth utilization and computing power occupancy in the link status data, and construct the link load factor; The scope and severity of the fault impact in the fault information data are quantified to construct a fault level factor; Based on the business priority factor and the fault level factor, a first weighted calculation model for the consistency recovery rate is constructed. Based on the business priority factor and the fault level factor, a second weight calculation model for the self-healing response delay is constructed. Based on the link load factor, a third weight calculation model for the link resource utilization rate is constructed; Based on the business priority factor, a fourth weight calculation model for the business adaptability is constructed.

4. The method according to claim 1, characterized in that, The step of obtaining the fuzzy comprehensive evaluation value of the candidate self-healing strategy based on the target membership function and the dynamic weight calculation model includes the following steps: Based on the fault information data, multiple candidate self-healing strategies that match the current fault type are selected from the pre-built candidate self-healing strategy library. Obtain the first actual quantitative value of the consistency recovery rate, the second actual quantitative value of the self-healing response latency, the third actual quantitative value of the link resource utilization rate, and the fourth actual quantitative value of the service adaptability corresponding to the candidate self-healing strategy. Based on the target membership function, the first actual quantization value, the second actual quantization value, the third actual quantization value, and the fourth actual quantization value, obtain the first membership value of the consistency recovery rate, the second membership value of the self-healing response delay, the third membership value of the link resource occupancy rate, and the fourth membership value of the service adaptability. Based on the dynamic weight calculation model, the first membership value, the second membership value, the third membership value, and the fourth membership value, the fuzzy comprehensive evaluation value of the candidate self-healing strategy is obtained.

5. The method according to claim 4, characterized in that, The step of selecting a target self-healing strategy from the candidate self-healing strategies based on the fuzzy comprehensive evaluation value includes the following steps: From the multiple candidate self-healing strategies, select the effective strategies whose fuzzy comprehensive evaluation value is greater than or equal to a preset threshold; From the effective strategies, the effective strategy with the largest fuzzy comprehensive evaluation value is selected as the target self-healing strategy; If the difference between the fuzzy comprehensive evaluation values ​​of multiple effective strategies is less than the preset tolerance, then the effective strategy with the largest first membership value is taken as the target self-healing strategy.

6. The method according to claim 1, characterized in that, After executing the target self-healing strategy on the power grid data link, the method further includes the following steps: Collect actual effect data after the target self-healing strategy is executed; Based on the actual effect data, the target membership function, the dynamic weight calculation model, and the candidate self-healing strategy library are updated.

7. A data link self-healing device based on situational awareness and fuzzy decision-making, characterized in that, include: The situation awareness module is used to acquire situation awareness data from the power grid data link; The situational awareness data includes link status data, service attribute data, and fault information data; The first fuzzy decision module is used to construct a target membership function of preset evaluation indicators based on the situational awareness data; the preset evaluation indicators include consistency recovery rate, self-healing response latency, link resource utilization rate, and service adaptability. The second fuzzy decision module is used to construct a dynamic weight calculation model for the preset evaluation index based on the situational awareness data. The third fuzzy decision module is used to obtain the fuzzy comprehensive evaluation value of the candidate self-healing strategy based on the target membership function and the dynamic weight calculation model. The fourth fuzzy decision module is used to select a target self-healing strategy from the candidate self-healing strategies based on the fuzzy comprehensive evaluation value. The self-healing strategy execution module is used to execute the target self-healing strategy on the power grid data link to achieve self-healing of the power grid data link.

8. An electronic device, characterized in that, Including the processor and memory; The memory is used to store programs; The processor executes the program to implement the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The storage medium stores a program that is executed by a processor to implement the method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 6.

Images