Terminal performance determination method and device, storage medium and electronic equipment

Abstract

The invention discloses a terminal performance determination method and device, a storage medium and electronic equipment. The method comprises the following steps: determining an initial capability fingerprint of a target terminal; performing fault diagnosis on the preset power grid fault scene by using the target terminal to obtain a target diagnosis result; determining a target index value of a performance index of the target terminal based on the target diagnosis result; determining a performance level of the target terminal based on the target index value and the initial capability fingerprint; based on the performance grade and the target index value, determining a performance result of the target terminal, the performance result being used for indicating whether the performance of the target terminal is qualified; and determining the target performance of the target terminal in the preset power grid fault scene based on the initial capability fingerprint, the target index value, the performance grade and the performance result. According to the invention, the technical problem that the performance determination result of the terminal is not accurate in the prior art is solved.

Description

Technical Field

[0001] This application relates to the field of power systems, and more specifically, to a method, apparatus, storage medium, and electronic device for determining the performance of a terminal. Background Technology

[0002] With the continuous improvement of power system intelligence, a large number of various types of intelligent terminals have been deployed on the distribution and consumption side. These terminals exhibit significant heterogeneity in hardware configuration, communication capabilities, software versions, and environmental adaptability, making quantitative, fair, and comparable performance evaluation increasingly complex and crucial. Especially for the critical function of fault diagnosis, terminal performance directly impacts the overall operational efficiency and safety of the power system. Current methods for determining terminal performance, which classify terminals according to model or hardware specifications and then compare performance within each category based on "fault diagnosis accuracy," result in biased and uninterpretable performance results. Therefore, these technologies suffer from inaccurate terminal performance determination results.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method, apparatus, storage medium, and electronic device for determining the performance of a terminal, so as to at least solve the technical problem of inaccurate terminal performance determination results in related technologies.

[0005] According to one aspect of the embodiments of this application, a method for determining the performance of a terminal is provided, comprising: determining an initial capability fingerprint of a target terminal, wherein the initial capability fingerprint is used to quantitatively describe the performance characteristics of the target terminal; performing fault diagnosis on a preset power grid fault scenario using the target terminal to obtain a target diagnosis result; determining a target index value for the performance index of the target terminal based on the target diagnosis result; determining a performance level of the target terminal based on the target index value and the initial capability fingerprint, wherein the performance level is used to quantify the performance level of the target terminal; determining a performance result of the target terminal based on the performance level and the target index value, wherein the performance result is used to indicate whether the performance of the target terminal is qualified; and determining the target performance of the target terminal in the preset power grid fault scenario based on the initial capability fingerprint, the target index value, the performance level, and the performance result.

[0006] According to another aspect of the embodiments of this application, a terminal performance determination apparatus is provided, comprising: an initial capability fingerprint determination module, configured to determine an initial capability fingerprint of a target terminal, wherein the initial capability fingerprint is used to quantitatively describe the performance characteristics of the target terminal; a target diagnosis result determination module, configured to perform fault diagnosis on a preset power grid fault scenario using the target terminal to obtain a target diagnosis result; a target index value determination module, configured to determine a target index value of the performance index of the target terminal based on the target diagnosis result; a performance level determination module, configured to determine a performance level of the target terminal based on the target index value and the initial capability fingerprint, wherein the performance level is used to quantify the performance level of the target terminal; a performance result determination module, configured to determine a performance result of the target terminal based on the performance level and the target index value, wherein the performance result is used to indicate whether the performance of the target terminal is qualified; and a target performance determination module, configured to determine the target performance of the target terminal in the preset power grid fault scenario based on the initial capability fingerprint, the target index value, the performance level, and the performance result.

[0007] According to another aspect of the embodiments of this application, a non-volatile storage medium is provided, which stores a plurality of instructions adapted for a terminal performance determination method to be loaded by a processor and executed at any one of them.

[0008] According to another aspect of the embodiments of this application, an electronic device is provided, including: one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the terminal performance determination methods.

[0009] According to another aspect of the embodiments of this application, a computer program product is provided, which, when executed on a data processing device, is a program adapted to perform the steps of a terminal performance determination method.

[0010] In this embodiment, the following steps are taken: First, an initial capability fingerprint of the target terminal is determined, whereby the initial capability fingerprint is used to quantitatively describe the performance characteristics of the target terminal. Then, the target terminal is used to perform fault diagnosis on a preset power grid fault scenario to obtain a target diagnosis result. Based on the target diagnosis result, a target index value for the target terminal's performance indicators is determined. Next, based on the target index value and the initial capability fingerprint, the performance level of the target terminal is determined, whereby the performance level is used to quantify the performance level of the target terminal. Finally, based on the performance level and the target index value, the performance result of the target terminal is determined, whereby the performance result indicates whether the target terminal's performance is qualified. Finally, based on the initial capability fingerprint, target index value, performance level, and performance result, the target performance of the target terminal in the preset power grid fault scenario is determined. This achieves the technical effect of improving the accuracy of the target performance determination result, thereby solving the technical problem of inaccurate terminal performance determination results in related technologies. Attached Figure Description

[0011] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart of a method for determining the performance of a terminal according to an embodiment of this application; Figure 2 This is a schematic diagram of an optional power heterogeneous terminal capability fingerprint hierarchical evaluation system provided according to an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an optional terminal capability profiling module provided according to an embodiment of this application; Figure 4 This is a schematic diagram of an optional evaluation and hierarchical module provided according to an embodiment of this application; Figure 5 This is a flowchart of an optional terminal performance determination method provided according to an embodiment of this application; Figure 6 This is a schematic diagram of an optional terminal performance determination device provided according to an embodiment of this application. Detailed Implementation

[0012] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0013] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0014] For ease of description, the following explains some of the nouns or terms used in the embodiments of this application: Schema refers to the data structure or database framework design, which defines how data is organized, including data types, fields, tables, and the relationships between tables.

[0015] According to an embodiment of this application, a method embodiment for determining the performance of a terminal is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0016] Figure 1 This is a flowchart of a terminal performance determination method according to an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps: Step S102: Determine the initial capability fingerprint of the target terminal, wherein the initial capability fingerprint is used to quantitatively describe the performance characteristics of the target terminal. It is understandable that obtaining the initial capability fingerprint of the target terminal is crucial, encompassing aspects such as sampling and computing capabilities, time synchronization and communication quality, electromagnetic compatibility and power supply stability, and software operating environment. By acquiring this initial capability fingerprint, key support is provided for the dynamic monitoring and comprehensive evaluation of the target terminal's performance, thereby improving the accuracy and practicality of the target performance determination results.

[0017] Optionally, the target terminals mentioned above may include, but are not limited to, smart meters, data collectors, edge industrial control computers, protection devices, IoT sensors, etc.

[0018] In one optional embodiment, determining the initial capability fingerprint of the target terminal includes: acquiring the initial performance parameters of the target terminal; standardizing the performance parameters to obtain the target performance parameters of the target terminal; and representing the target performance parameters as a vector to obtain the initial capability fingerprint.

[0019] It is understandable that the initial performance parameters of the target terminal are obtained, such as sampling rate and bit width, computing and memory resources, time synchronization method and jitter, communication protocol and quality, power supply and electromagnetic compatibility level, software and firmware information, etc. These initial performance parameters may have different dimensions and numerical ranges, requiring standardization to obtain the target terminal's target performance parameters. This eliminates the influence of dimensions, allowing for comparison and analysis of the initial performance parameters on a unified scale. Standardization can include data cleaning, outlier handling, dimension conversion, and data normalization. For example, there may be multiple time synchronization methods, which need to be converted into a unified indicator of time synchronization accuracy; the diversity of communication protocols also needs to be converted into quantitative indicators such as communication rate and packet loss rate for easier subsequent analysis. The target performance parameters are then represented as vectors to obtain the initial capability fingerprint of the target terminal. By standardizing and vectorizing the initial performance parameters of the target terminal, the resulting initial capability fingerprint can improve the accuracy of the target terminal's target performance determination.

[0020] Step S104: Use the target terminal to perform fault diagnosis on the preset power grid fault scenario and obtain the target diagnosis result; It is understandable that using a target terminal to diagnose a preset power grid fault scenario yields a target diagnostic result, which includes information such as fault prediction category, confidence level, and timestamp. By directly testing the target terminal's fault diagnosis performance under the preset power grid fault scenario, the diagnostic accuracy, response speed, and resource utilization efficiency of the target terminal can be accurately reflected, thereby more accurately determining its performance level under specific tasks and improving the accuracy of the target performance determination results.

[0021] In an optional embodiment, before using the target terminal to perform fault diagnosis on a preset power grid fault scenario and obtain the target diagnosis result, the method further includes: determining the initial power grid scenario, initial load condition, and initial fault type of the power grid, wherein the initial power grid scenario is used to describe the operating state and environmental conditions of the power grid; performing time alignment on the initial power grid scenario, initial load condition, and initial fault type to obtain the target power grid scenario, target load condition, and target fault type of the power grid; and determining the preset power grid fault scenario based on the target power grid scenario, target load condition, and target fault type.

[0022] It is understandable that before using the target terminal to diagnose a preset power grid fault scenario, it is necessary to construct the preset power grid fault scenario. First, the initial power grid scenario, initial load condition, and initial fault type are determined. These initial power grid scenario, initial load condition, and initial fault type are then time-aligned to ensure they are synchronized on the timeline, avoiding fault diagnosis errors caused by time differences. This yields the target power grid scenario, target load condition, and target fault type. Based on the target power grid scenario, target load condition, and target fault type, the preset power grid fault scenario is constructed for subsequent fault diagnosis by the target terminal. By thoroughly determining the initial power grid scenario, initial load condition, and initial fault type and performing time alignment, the generated preset power grid fault scenario more closely resembles the actual operating environment of the power grid, improving the accuracy and reliability of the target diagnosis results.

[0023] Optionally, the initial power grid scenario may include, but is not limited to, the operating parameters of the power grid such as voltage, current, frequency, and power, as well as external environmental factors such as weather, temperature, and humidity; the initial load condition may include, but is not limited to, peak load, average load, and load type; and the initial fault type may include, but is not limited to, short circuit, overload, and ground fault.

[0024] Step S106: Based on the target diagnostic results, determine the target index values ​​for the performance indicators of the target terminal. It is understandable that target performance metrics are calculated based on the target diagnostic results output by the target terminal. These performance metrics may include, but are not limited to, weighted / balanced accuracy, diagnostic latency and early detection rate, confidence calibration error, and resource and cost metrics. Determining target performance metrics based on target diagnostic results not only improves the accuracy of target terminal performance determination results but also enhances the comprehensiveness, reliability, and robustness of the performance determination results.

[0025] Optionally, the performance metrics of the target terminal can go beyond a single accuracy rate, covering weighted / balanced accuracy, diagnostic latency and early detection rate, confidence and calibration, end-side resource consumption, and perturbation robustness, etc., and unify the calculation and aggregation criteria to ensure that the results are comparable and reproducible across terminals, scenarios, and time periods.

[0026] Step S108: Based on the target index value and the initial capability fingerprint, determine the performance level of the target terminal, wherein the performance level is used to quantify the performance level of the target terminal. It is understandable that the performance level of a target terminal is determined based on its initial capability fingerprint and the target indicator values ​​obtained during fault diagnosis. Combining the target indicator values ​​and the initial capability fingerprint to determine the performance level of the target terminal more accurately reflects its true performance level, ensuring the accuracy of subsequent performance determinations.

[0027] In one optional embodiment, determining the performance level of the target terminal based on the target index value and the initial capability fingerprint includes: performing dimensionality reduction processing on the initial capability fingerprint based on the target index value to obtain the target capability fingerprint of the target terminal; and determining the performance level based on the target index value and the target capability fingerprint.

[0028] It is understandable that, based on the target indicator values ​​obtained during fault diagnosis of the target terminal, the initial capability fingerprint is dimensionality-reduced to obtain the target capability fingerprint of the target terminal. The target capability fingerprint includes the key performance features in the initial capability fingerprint that have the greatest impact on the target indicator values. Performance features that are irrelevant or redundant to the target indicator values ​​are removed from the initial capability fingerprint to improve the accuracy and efficiency of performance level determination. Based on the target indicator values ​​and the target capability fingerprint, the performance level of the target terminal is determined. Dimensionality reduction of the initial capability fingerprint can significantly reduce data dimensionality, accelerate the determination of performance results, and also remove irrelevant performance features, avoiding the influence of "noise" on the performance result determination process, thereby improving the accuracy and reliability of the target performance determination results.

[0029] Optionally, principal component analysis (PCA), feature selection, and cluster analysis can be used to reduce the dimensionality of the initial capability fingerprint to obtain the target capability fingerprint. PCA uses linear transformation to find the principal components in the initial capability fingerprint—those features that best explain the data variance—thus achieving dimensionality reduction. Feature selection, based on correlation analysis, mutual information, or other statistical methods, selects the subset of features most closely related to the target index value from the initial capability fingerprint as the target capability fingerprint. Cluster analysis first performs preliminary clustering of the initial capability fingerprint of the target terminal, and then reduces dimensionality by selecting the most representative performance features within each cluster to obtain the target capability fingerprint.

[0030] Optionally, the performance level of the target terminal can be determined as follows: First, based on the needs and standards of the power system, target values ​​are set for each performance indicator. These target values ​​may be dynamically adjusted as the application scenario and time progress. Next, using the dimensionality-reduced target capability fingerprint, a hierarchical structure is generated or updated, and corresponding indicator thresholds are set for each level. This threshold can be fixed or dynamically adjusted based on an adaptive function of the target capability fingerprint to ensure consistency in the evaluation benchmarks of terminal devices at the same level. Finally, the performance level of the target terminal is determined based on the target indicator values ​​and its level in the hierarchical structure. Machine learning models such as decision trees, Bayesian classifiers, or support vector machines can be used to automatically determine the performance level of the target terminal.

[0031] Step S110: Based on the performance level and target index value, determine the performance result of the target terminal, wherein the performance result is used to indicate whether the performance of the target terminal is qualified. It is understandable that the performance of a target terminal is evaluated based on its performance level and target indicator values ​​to obtain a performance result indicating whether the target terminal's performance is up to standard. Determining the performance result of a target terminal based on its performance level and target indicator values ​​enables accurate, flexible, and dynamic performance evaluation, providing strong technical support for the selection, operation optimization, and supervision of heterogeneous power terminals.

[0032] In one optional embodiment, determining the performance result of the target terminal based on the performance level and the target indicator value includes: determining the indicator threshold of the performance indicator based on the performance level; comparing the target indicator value with the indicator threshold to obtain a comparison result; and determining the performance result based on the comparison result.

[0033] The performance results of the target terminal are understood to be determined as follows: First, based on the performance level of the target terminal, a threshold value for the performance indicator is determined. Next, the target indicator value is compared with the threshold value, and the comparison result is obtained. Finally, based on the comparison result, the performance result of the target terminal is determined. By determining the indicator threshold value based on the performance level and comparing it with the target indicator value, the accuracy of the performance result can be ensured, and a fair comparison between terminal devices of the same performance level can also be achieved.

[0034] Optionally, when the aforementioned performance indicators are not unique, the performance result of the target terminal is determined as follows: First, based on the performance level of the target terminal, threshold values ​​corresponding to multiple performance indicators are determined, and the values ​​of each target indicator are compared with their corresponding threshold values ​​to obtain multiple comparison results that correspond one-to-one with the multiple performance indicators. Then, based on the above multiple comparison results, the performance result of the target terminal is determined.

[0035] Optionally, for performance indicators where a larger value is better, if the comparison result shows that the target indicator value is greater than or equal to the corresponding indicator threshold, the performance result is considered acceptable for the target terminal; otherwise, the performance result is considered unacceptable for the target terminal. For performance indicators where a smaller value is better, if the comparison result shows that the target indicator value is less than or equal to the corresponding indicator threshold, the performance result is considered acceptable for the target terminal; otherwise, the performance result is considered unacceptable for the target terminal.

[0036] Optionally, if the performance indicators are not unique, the performance result of the target terminal is considered to be qualified only if the comparison results corresponding to multiple performance indicators all indicate that the performance sub-result of the target terminal is qualified under that performance indicator; if there is any performance sub-result corresponding to any performance indicator that the performance sub-result of the target terminal is unqualified under that performance indicator, then the performance result of the target terminal is considered to be unqualified.

[0037] Step S112: Based on the initial capability fingerprint, target index value, performance level, and performance results, determine the target performance of the target terminal in the preset power grid fault scenario.

[0038] It is understandable that by integrating the initial capability fingerprint, target index values, performance level, and performance results of the target terminal, the target performance of the target terminal in a preset power grid fault scenario can be obtained. By comprehensively considering the initial capability fingerprint, target index values, performance level, and performance results of the target terminal, the accuracy and comprehensiveness of the obtained target performance can be ensured.

[0039] In an optional embodiment, where the target performance also includes the robustness characteristics of the target terminal, the method further includes: injecting any disturbance of the target type into a preset power grid fault scenario to obtain any disturbance power grid fault scenario; performing fault diagnosis on any disturbance power grid fault scenario using the target terminal to obtain any disturbance diagnosis result; determining any target disturbance index value of the performance index based on any disturbance diagnosis result; determining multiple target disturbance index values ​​obtained by the target terminal after injecting multiple disturbances by using the method of determining any target disturbance index value, wherein the disturbance types of the multiple disturbances are all target types, and the disturbance intensities of the multiple disturbances are different, and the multiple disturbances correspond one-to-one with the multiple target disturbance index values; and determining the robustness characteristics of the target terminal under the disturbance of the target type based on the multiple target disturbance index values.

[0040] It is understood that, when the target performance also includes the robustness characteristics of the target terminal, the robustness characteristics of the target terminal are determined in the following way: First, any disturbance of the target type is injected into a preset power grid fault scenario to obtain a power grid fault scenario with any disturbance. Second, the target terminal is used to perform fault diagnosis on any power grid fault scenario with any disturbance to obtain a fault diagnosis result for any disturbance. Next, based on the fault diagnosis result for any disturbance, the target disturbance index value of the performance index of the target terminal after injecting any disturbance is calculated. By determining the above-mentioned target disturbance index value, multiple target disturbance index values ​​are determined after injecting multiple disturbances of the target type into the target terminal respectively, and the robustness characteristics of the target terminal's performance index under the disturbance of the target type are determined based on the multiple target disturbance index values. By performing fault diagnosis on the target terminal under diverse disturbance scenarios and collecting its performance under different disturbance intensities, the robustness of the terminal can be evaluated more comprehensively and accurately, avoiding the evaluation bias caused by determining robustness characteristics based on a single fault diagnosis, and improving the reliability of the robustness characteristic determination results.

[0041] In one optional embodiment, the robustness characteristics of a target terminal under target type perturbations are determined based on multiple target perturbation index values, including: determining the performance drop curve of the target terminal's performance index based on multiple target perturbation index values; determining the performance drop critical point of the target terminal's performance index based on the performance drop curve; and determining the robustness characteristics based on the performance drop curve and the performance drop critical point.

[0042] It is understandable that, based on multiple target perturbation index values, a performance drop curve is plotted for the target terminal's performance indicators under target-type perturbations. This performance drop curve shows the trend of the target terminal's performance index values ​​decreasing as the perturbation intensifies. Simultaneously, based on this performance drop curve, the performance drop critical point of the target terminal's performance indicators is determined, i.e., the inflection point where the rate of decrease in performance index values ​​significantly accelerates. Determining the performance drop critical point helps to accurately identify at which perturbation level the target terminal's performance indicators begin to show significant performance degradation. Based on the performance drop curve and the performance drop critical point, the robustness characteristics of the target terminal's performance indicators under target-type perturbations are determined. By analyzing the specific performance of the target terminal under different perturbation intensities and constructing performance drop curves and performance drop critical points, the actual robustness of the target terminal under target-type perturbations can be reflected more accurately, improving the comprehensiveness and accuracy of the target performance determination results.

[0043] Optionally, the robustness characteristics of the target terminal's performance indicators under target-type disturbances can be determined using the aforementioned method. This method identifies the robustness characteristics of the target terminal's performance indicators under various types of disturbances, and correlates the performance drop of the target terminal's performance indicators with the initial capability fingerprint of the target terminal. This allows for the identification of the attribution summaries of the main influencing factors affecting the target terminal's performance indicators, i.e., the main disturbance types causing the decline in performance indicator values. This provides a basis for terminal selection, parameter tuning, and on-site management. When performance indicators are not unique, this method can also be used to determine the attribution summaries of the main influencing factors corresponding to multiple performance indicators, improving the comprehensiveness and reliability of the target terminal's performance determination results.

[0044] Optionally, the types of disturbances injected may include, but are not limited to, communication packet loss, clock drift, electromagnetic interference, and quantization noise. To reflect the uncertainties and disturbances in real-world scenarios, a unified robustness assessment framework can be defined to determine the robustness characteristics of the target terminal. Under standardized disturbances such as communication packet loss, clock drift, electromagnetic interference, and quantization noise, performance degradation curves and performance degradation critical points are output. Furthermore, a correlation analysis is performed between performance degradation and initial capability fingerprints to determine the attribution summary of the main influencing factors of the target terminal's performance indicators, thereby providing a basis for terminal selection, parameter tuning, and on-site management.

[0045] Optionally, based on the above embodiments, a hierarchical evaluation method and system for the capability fingerprint of heterogeneous power terminals can be proposed. This system comprises a terminal capability profiling module, a scenario generation module, a reference truth value module, a diagnostic execution module, an evaluation and hierarchical module, and a certificate / report module, all interconnected through a standardized data interface. The terminal capability profiling module generates versioned initial capability fingerprints; the scenario generation module combines operating condition, load, and fault databases and generates test scenarios (i.e., preset power grid fault scenarios) based on time alignment rules; the diagnostic execution module outputs target diagnostic results in the tested target terminal or its equivalent environment; the evaluation and hierarchical module calculates target index values ​​for multi-dimensional performance indicators and determines the performance level and index thresholds of the target terminal to obtain the performance results of the target terminal; the certificate / report module outputs the target performance results in machine-readable certificate form, supporting querying and verification.

[0046] Optionally, the terminal capability profiling module may include, but is not limited to, a data acquisition unit, an encoding unit, and a consistency verification unit. The data acquisition unit is used to acquire multi-dimensional initial performance parameters related to the target terminal's performance. The encoding unit is used to standardize and vectorize the data according to a preset schema to form a fixed-length initial capability fingerprint and record version information. The consistency verification unit is used to generate a summary and verification information for the initial capability fingerprint to support cross-batch and cross-organizational mutual recognition and auditing.

[0047] Optionally, the evaluation and stratification module may include, but is not limited to, an index calculation unit, an embedding generation unit, a stratification generation unit, a threshold determination unit, and a robustness analysis unit. The index calculation unit calculates the target index value of the multidimensional performance index according to a unified standard. The embedding generation unit, while maintaining interpretability, maps the initial capability fingerprint to a capability embedding space that is more correlated with the performance index, achieving dimensionality reduction of the initial capability fingerprint to obtain the target capability fingerprint. The stratification generation unit generates a stratified structure according to the criterion of "significant inter-stratum differences and controlled intra-stratum variance," merges and stabilizes strata with insufficient samples or abnormal fluctuations, and determines the performance level of the target terminal based on the stratified structure. The threshold determination unit expresses the index threshold as an adaptive function of the performance level or a family of stratified thresholds (i.e., index thresholds corresponding to different levels) and outputs the performance results of the target terminal with confidence information. The robustness analysis unit outputs performance drop curves and performance drop critical points under standardized perturbations such as communication packet loss, time drift, electromagnetic interference, and quantization noise, and forms an attribution summary of the main influencing factors of the performance index.

[0048] Optionally, the power heterogeneous terminal capability fingerprint hierarchical evaluation system can support closed-loop operation. When indicator drift or version change trigger conditions are detected, it can automatically initiate a re-evaluation and update the certificate, so that the target performance results of the target terminal remain valid as the environment and software version evolve.

[0049] Through the above steps S102 to S112, the goal is to determine the target index value of the target terminal's performance indicators by determining the initial capability fingerprint of the target terminal and combining the target diagnosis result obtained by the target terminal in the fault diagnosis of the preset power grid fault scenario, thereby determining the target performance of the target terminal. This achieves the technical effect of improving the accuracy of the target performance determination result of the target terminal, and solves the technical problem of inaccurate terminal performance determination results in related technologies.

[0050] Based on the above embodiments and optional embodiments, this application proposes an implementation method for an optional terminal performance determination method. This implementation method can be understood as a hierarchical evaluation method and system for capability fingerprinting of heterogeneous power terminals, used to accurately determine the target performance of a target terminal.

[0051] The power distribution side is rapidly introducing various types of intelligent terminal devices (such as smart meters, data collectors, edge industrial control computers, protection devices, and IoT (Internet of Things) sensors) for fault detection, anomaly identification, and operational optimization. These terminals exhibit significant heterogeneity in areas such as sampling frequency and quantization bit width, time synchronization methods and clock stability, communication protocols and link quality, computing power and memory, EMI (Electromagnetic Interference) levels and power supply fluctuations, and software / firmware versions. This heterogeneity directly impacts the availability and usability of fault data, thereby affecting the accuracy, timeliness, and reliability of fault diagnosis. In the context of large-scale deployment and cross-regional interconnection, operators and regulators not only need to ensure the accuracy of algorithms in a single scenario but also need to ensure comparable evaluations and auditable conclusions across terminals, scenarios, and time periods to support access reviews, operational verification, and continuous optimization.

[0052] In related technologies, determining terminal performance often focuses on the algorithm or individual device. Firstly, fixed datasets or laboratory-based assessment models are used to report overall accuracy or F1 scores. Secondly, coarse-grained grouping and comparison are performed based on terminal device model / protocol or a small number of hardware specifications. Thirdly, pass / fail judgments are made on-site using empirical or standardized thresholds, lacking a fair approach coupled with the actual capabilities of the terminal. Fourthly, robustness characteristics are typically described qualitatively as "whether it resists interference" or through single-point comparisons, lacking standardized disturbance injection and continuous performance drop curve characterization. Fifthly, assessment results are often stored as PDF (Portable Document Format) reports, lacking machine-readable certificates and lifecycle update mechanisms, making it difficult to support cross-unit mutual recognition and automated review.

[0053] The relevant technologies suffer from the following main shortcomings. First, the evaluation criteria are inconsistent, often using "overall accuracy" to replace comprehensive quality, failing to incorporate performance indicators such as weighted / balanced accuracy, diagnostic latency and early detection rate, confidence calibration error, and resource and cost metrics. Furthermore, there is a lack of structured modeling for differences in terminal hardware and links, leading to unfair comparisons of results across devices / sites. Second, the reproduction of pre-set power grid fault scenarios is weakly aligned with ground truth, lacking standardized modeling and time synchronization within the "scenario-load-fault" (i.e., initial power grid scenario-initial load condition-initial fault type) framework, making it difficult to extrapolate laboratory conclusions (i.e., target diagnostic results) to the field. Third, a "one-size-fits-all" threshold is used, ignoring differences in terminal capabilities. First, it is prone to mistakenly eliminating low-performance / weak network devices and also to condoning potential problems of high-performance devices, making it difficult to achieve fair judgment and optimal resource allocation. Second, robustness testing lacks standardization and interpretability, and lacks continuous characterization and capability dimension attribution of "disturbance injection → performance drop curve → performance drop critical point", making it difficult to guide terminal selection and governance. Third, it generally ignores uncertainty, and the assessment only provides point estimates without confidence boundaries, resulting in unauditable conclusions and high review costs. Fourth, it lacks machine-readable certificates and lifecycle closure, and cannot automatically review and update with the evolution of environment, firmware or model versions, making it difficult to support the engineering requirements of on-network access, operational review and cross-domain mutual recognition.

[0054] To address the aforementioned issues, a hierarchical evaluation method and system for capability fingerprinting of heterogeneous power terminals is proposed, offering the following advantages: Centered on the "initial capability fingerprint of the terminal," the system standardizes and encodes initial performance parameters affecting diagnostic quality into fixed-length vectors, optionally carrying uncertainty, thus obtaining the initial capability fingerprint. Evaluation is conducted under a unified framework aligned with the truth value in a three-dimensional "scenario-load-fault" environment. Capability embedding related to performance indicators and separability-driven hierarchical classification (i.e., determining the performance level of the target terminal) are introduced, achieving scientific binning that ensures "comparability within the same layer and differentiation between layers." The qualification criteria are represented as an adaptive function of indicator thresholds or a hierarchical family of indicator thresholds, avoiding a one-size-fits-all approach. Standardized perturbation injection outputs performance drop curves and performance drop thresholds, forming a capability attribution summary to guide governance. Finally, a machine-readable evaluation certificate carries the target terminal's target performance results, triggering a re-evaluation to achieve a closed-loop lifecycle.

[0055] The aforementioned hierarchical evaluation method and system for capability fingerprinting of heterogeneous power terminals abstracts the initial performance parameters of the target terminal, such as sampling and computing capabilities, time synchronization and communication quality, electromagnetic compatibility and power supply stability, and software operating environment, into standardized vectors to obtain the initial capability fingerprint of the target terminal, which serves as a common language for subsequent performance evaluation and comparison. Based on this, combined with the three-dimensional scenario of "scenario-load-fault" and the aligned truth system, a reproducible and horizontally comparable diagnostic quality evaluation is carried out to determine the target performance of the target terminal.

[0056] The power heterogeneous terminal capability fingerprint hierarchical evaluation system consists of a terminal capability profiling module, a scenario generation module, a reference truth value module, a diagnostic execution module, an evaluation and hierarchical module, and a certificate / report module, all interconnected through a standardized data interface. The terminal capability profiling module generates versioned initial capability fingerprints; the scenario generation module combines operating condition, load, and fault databases and generates test scenarios (i.e., preset power grid fault scenarios) based on time alignment rules; the diagnostic execution module outputs target diagnostic results on the tested target terminal or its equivalent environment; the evaluation and hierarchical module calculates target index values ​​for multi-dimensional performance indicators and determines the performance level and index thresholds of the target terminal, obtaining the performance results of the target terminal; the certificate / report module outputs the target performance results in machine-readable certificate format, supporting querying and verification.

[0057] To reflect the uncertainties and interferences in real-world scenarios, a unified robustness assessment framework is defined to determine the robustness characteristics of the target terminal. Under standardized disturbances such as packet loss, clock drift, electromagnetic interference, and quantization noise, performance degradation curves and performance degradation critical points are output. Furthermore, a correlation analysis is performed between performance degradation and initial capability fingerprints to determine the attribution summary of the main influencing factors of the target terminal's performance indicators. This provides a basis for terminal selection, parameter tuning, and on-site management.

[0058] The performance metrics of the target terminal go beyond a single accuracy rate, covering weighted / balanced accuracy, diagnostic latency and early detection rate, confidence and calibration, edge resource consumption, and perturbation robustness, etc., and unifying the calculation and aggregation criteria to ensure the comparability and retestability of results across terminals, scenarios, and time periods. The target performance results of the target terminal are carried by a machine-readable certificate, including an initial capability fingerprint digest, hierarchical labels (i.e., the performance level labels of the target terminal), performance metrics and target metric values, metric threshold function versions and metric thresholds, robustness digests (i.e., robustness features), and signatures, which is beneficial for access review, operational verification, and regulatory mutual recognition.

[0059] The power heterogeneous terminal capability fingerprint hierarchical evaluation system supports closed-loop operation. When indicator drift or version change trigger conditions are detected, it automatically initiates a re-evaluation and updates the certificate, so that the target performance results of the target terminal remain valid as the environment and software version evolve.

[0060] Figure 2 This is a schematic diagram of an optional power heterogeneous terminal capability fingerprint hierarchical evaluation system provided in an embodiment of this application, as shown below. Figure 2The power heterogeneous terminal capability fingerprint hierarchical evaluation system shown includes a terminal capability profiling module, a scenario generation module, a reference truth value module, a diagnostic execution module, an evaluation and hierarchical module, and a certificate / report module. The terminal capability profiling module collects and manages the capability elements (i.e., initial performance parameters) of the target terminal under test, forming a standardized initial capability fingerprint vector and its versioned description. The scenario generation module combines the initial power grid scenario, initial load condition, and initial fault type under a unified standard, and generates test scenarios based on time alignment rules. The reference truth value module provides benchmark signals and authoritative criteria, outputting truth values ​​(e.g., fault type, duration, impact range, etc.) consistent with the preset power grid fault scenario and their timestamps. The diagnostic execution module receives test scenario drivers, triggers the fault diagnosis process of the target terminal under test or equivalent environment, and outputs target diagnostic results such as prediction results and time information. The evaluation and stratification module calculates the target index values ​​of performance indicators, generates separability-driven stratification based on the initial capability fingerprint, determines the performance level of the target terminal, and determines the index threshold of the performance indicators based on the performance level using a threshold adaptive mechanism, thereby determining the performance result of the target terminal, and performing robustness analysis on the target terminal to determine its robustness characteristics. The certificate / report module generates machine-readable evaluation certificates and standardized reports (i.e., target performance), and provides query and verification interfaces.

[0061] By establishing a hierarchical evaluation system for the capability fingerprint of heterogeneous power terminals, decoupled from specific algorithms, all participating terminals (such as smart meters, data collectors, edge control computers, protection devices, and IoT sensors) can be uniformly profiled and comparablely evaluated within this framework. Terminal suppliers register their terminal capability information (i.e., initial performance parameters) in the system, including sampling rate and bit width, computing and memory resources, time synchronization method and jitter, communication protocol and quality, power supply and electromagnetic compatibility level, and software and firmware information. The terminal capability profiling module structures and standardizes this capability information, forming an auditable initial capability fingerprint, providing a basis for subsequent hierarchical classification and threshold mapping.

[0062] The scenario generation module organizes fault diagnosis using a "scenario-load-fault" triplet, referencing the truth module to provide a synchronization benchmark, ensuring alignment between the tested channel and the benchmark channel at a preset accuracy. The diagnosis execution module runs the fault diagnosis process on the target terminal side or in an equivalent execution environment, recording target diagnostic results such as fault prediction category, confidence level, and timestamp, which serve as input for the evaluation and stratification module. Based on this, the evaluation and stratification module calculates target index values ​​for performance indicators such as weighted / balanced accuracy, diagnostic latency and early detection rate, confidence calibration error, and resource and cost indicators, and determines robustness characteristics under standardized perturbation injection. It also generates a stratified structure based on the initial capability fingerprint, ensuring "comparable within the same layer and differentiated between layers," determining the performance level of the target terminal, and expressing index thresholds as functions of performance levels to achieve fair judgment of heterogeneous terminals. The certificate / report module carries the target performance as a machine-readable certificate, which includes an initial capability fingerprint digest, hierarchical labels, performance metrics, target metric values, metric threshold function versions and metric thresholds, robustness digests and signatures, and manages the signature and validity period of the certificate to meet the requirements of access review, operational verification and regulatory mutual recognition.

[0063] Figure 3 This is a schematic diagram of the structure of an optional terminal capability profiling module provided according to an embodiment of this application, such as... Figure 3 As shown, the terminal capability profiling module includes a data acquisition unit, an encoding unit, and a consistency verification unit. The data acquisition unit is used to acquire multi-dimensional initial performance parameters related to the target terminal's performance. The encoding unit is used to standardize and vectorize the data according to a preset schema to form a fixed-length initial capability fingerprint and record version information. The consistency verification unit is used to generate a summary and verification information for the initial capability fingerprint to support cross-batch and cross-organizational mutual recognition and auditing.

[0064] Figure 4 This is a schematic diagram of an optional evaluation and hierarchical module provided according to an embodiment of this application, such as... Figure 4As shown, the evaluation and stratification module includes an index calculation unit, an embedding generation unit, a stratification generation unit, a threshold determination unit, and a robustness analysis unit. The index calculation unit calculates the target index value of the multidimensional performance index according to a unified standard. The embedding generation unit maps the initial capability fingerprint to a capability embedding space that is more correlated with the performance index, while maintaining interpretability, thus reducing the dimensionality of the initial capability fingerprint and obtaining the target capability fingerprint. The stratification generation unit generates a stratified structure according to the criterion of "significant inter-stratum differences and controlled intra-stratum variance," merges and stabilizes strata with insufficient samples or abnormal fluctuations, and determines the performance level of the target terminal based on the stratification structure. The threshold determination unit represents the index threshold as an adaptive function of the performance level or a family of stratified thresholds (i.e., index thresholds corresponding to different levels) and outputs the performance results of the target terminal with confidence information. The robustness analysis unit outputs performance drop curves and performance drop critical points under standardized perturbations such as communication packet loss, time drift, electromagnetic interference, and quantization noise, and forms an attribution summary of the main influencing factors of the performance index.

[0065] Figure 5 This is a flowchart of an optional terminal performance determination method provided according to an embodiment of this application, such as... Figure 5 As shown, the steps of the hierarchical evaluation method for capability fingerprinting of heterogeneous power terminals include: Step S1, Initial Capability Fingerprint Generation. Initial performance parameters of the target terminal under test are collected, standardized, and encoded to form an initial capability fingerprint vector and register version information; Step S2: Scenario Construction and Reality Alignment. Based on requirements, combine the initial power grid scenario, initial load condition, and initial fault type from the library, and align them with the reference real values ​​in time to generate the test scenario; Step S3, Diagnostic Execution and Recording. Drive the target terminal under test or its equivalent environment to complete fault diagnosis, and record the target diagnosis results such as predicted output, confidence and time information; Step S4, metric calculation. Calculate target metric values ​​for performance indicators such as weighted / balanced accuracy, diagnostic latency and early detection rate, confidence and calibration, and edge resource consumption based on a unified standard. Step S5, Capability Embedding and Layering. Combining the target metric values, the initial capability fingerprint is mapped to the capability embedding space, generating or updating a separability-driven layered structure, and determining the performance level of the target terminal; Step S6, Threshold Adaptive Determination. Based on the adaptive function of the performance level or the hierarchical threshold family, determine the target terminal's indicator threshold, perform a pass / fail determination, and output the target terminal's performance result with confidence information; Step S7, perturbation robustness test. Repeatedly measure the target perturbation index value of the performance index under standardized perturbation, form the performance drop curve and performance drop critical point description, and output the attribution summary of the main influencing factors of the performance index; Step S8, Certificate Output and Archiving. Generate a machine-readable target performance result containing the initial capability fingerprint digest, hierarchical labels, performance metrics, target metric values, metric threshold function versions and metric thresholds, robustness digest, and signature, and complete the signing and validity management; when the operation monitoring triggers the drift condition, initiate a re-evaluation and certificate update.

[0066] The hierarchical evaluation method and system for capability fingerprinting of heterogeneous power terminals has the following advantages: By defining an initial capability fingerprint as a common language, the performance of the same diagnostic algorithm on different terminals can be fairly compared, and the selection and access of terminal equipment from different manufacturers and batches also have an objective basis. The introduction of a three-dimensional scenario-load-fault evaluation paradigm aligned with the true value improves the reproducibility and representativeness of the assessment. This ensures that fault diagnosis and target performance determination no longer rely on a single or ideal operating condition, but generate stable conclusions within a combination space covering key operating conditions and fault types, reducing overfitting and randomness from the source and ensuring that target diagnostic results can be extrapolated to the field. A multi-dimensional performance index system is constructed, including weighted / balanced accuracy, diagnostic latency and early detection rate, confidence and calibration, end-side resource consumption, and disturbance robustness. This elevates "fault diagnosis accuracy" from a single-point indicator to a comprehensive quality profile that is "reliable, timely, and disturbance-resistant." Meanwhile, performance degradation curves and critical points are obtained through standardized communication packet loss, clock drift, and electromagnetic interference injection, guiding terminal equipment selection, parameter tuning, and on-site remediation, shortening the problem localization and optimization iteration cycle. Machine-readable certificates carry the target performance results, including initial capability fingerprint digests, hierarchical tags, performance indicators, target indicator values, indicator threshold function versions and thresholds, robustness summaries, and signatures, ensuring auditable, mutually recognized, and traceable results. Combined with runtime-triggered re-evaluation and certificate update mechanisms, the target terminal's performance is updated in response to changes in the field environment and software versions, reducing operation and maintenance and regulatory costs.

[0067] The above-mentioned optional implementation methods achieve at least the following effects: by acquiring the initial capability fingerprint of the target terminal, key support is provided for the dynamic monitoring and comprehensive evaluation of the target terminal performance, improving the accuracy and practicality of the target performance determination results; based on the performance level and target index value, the performance results of the target terminal are determined, realizing accurate, flexible, and dynamic performance evaluation of the target terminal, providing strong technical support for the selection, operation optimization, and supervision of heterogeneous power terminals; by analyzing the specific performance of the target terminal under different disturbance intensities and constructing performance drop curves and performance drop critical points, the actual robustness of the target terminal under the target type of disturbance can be more accurately reflected, improving the comprehensiveness and accuracy of the target performance determination results.

[0068] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0069] This embodiment also provides a terminal performance determination device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the terms "module" and "device" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0070] According to an embodiment of this application, an apparatus embodiment for implementing a terminal performance determination method is also provided. Figure 6 This is a schematic diagram of a terminal performance determination device according to an embodiment of this application, such as... Figure 6 As shown, the performance determination device for the aforementioned terminal includes an initial capability fingerprint determination module 602, a target diagnostic result determination module 604, a target index value determination module 606, a performance level determination module 608, a performance result determination module 610, and a target performance determination module 612. The device will be described below.

[0071] The initial capability fingerprint determination module 602 is used to determine the initial capability fingerprint of the target terminal, wherein the initial capability fingerprint is used to quantitatively describe the performance characteristics of the target terminal. The target diagnosis result determination module 604 is connected to the initial capability fingerprint determination module 602 and is used to perform fault diagnosis on a preset power grid fault scenario using the target terminal to obtain the target diagnosis result. The target indicator value determination module 606 is connected to the target diagnosis result determination module 604 and is used to determine the target indicator value of the performance indicators of the target terminal based on the target diagnosis result. The performance level determination module 608 is connected to the target index value determination module 606 and is used to determine the performance level of the target terminal based on the target index value and the initial capability fingerprint, wherein the performance level is used to quantify the performance level of the target terminal. The performance result determination module 610 is connected to the performance level determination module 608 and is used to determine the performance result of the target terminal based on the performance level and the target index value. The performance result is used to indicate whether the performance of the target terminal is qualified. The target performance determination module 612, connected to the performance result determination module 610, is used to determine the target performance of the target terminal in a preset power grid fault scenario based on the initial capability fingerprint, target index value, performance level, and performance result.

[0072] In a terminal performance determination device provided in this application embodiment, by setting an initial capability fingerprint determination module 602, a target diagnostic result determination module 604, a target index value determination module 606, a performance level determination module 608, a performance result determination module 610, and a target performance determination module 612, the device aims to determine the target index value of the target terminal's performance index by determining the initial capability fingerprint of the target terminal and combining it with the target diagnostic result obtained by the target terminal in performing fault diagnosis on a preset power grid fault scenario. This, in turn, determines the target performance of the target terminal, thereby improving the accuracy of the target performance determination result and solving the technical problem of inaccurate terminal performance determination results in related technologies.

[0073] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0074] It should be noted that the initial capability fingerprint determination module 602, target diagnostic result determination module 604, target index value determination module 606, performance level determination module 608, performance result determination module 610, and target performance determination module 612 correspond to steps S102 to S112 in the embodiments. The instances and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run in a computer terminal.

[0075] It should be noted that the optional or preferred implementation methods of this embodiment can be found in the relevant descriptions in the embodiments, and will not be repeated here.

[0076] The aforementioned terminal performance determination device may further include a processor and a memory. The initial capability fingerprint determination module 602, the target diagnostic result determination module 604, the target index value determination module 606, the performance level determination module 608, the performance result determination module 610, and the target performance determination module 612 are all stored as program units in the memory. The processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0077] The processor contains a core that retrieves the corresponding program unit from memory. One or more cores may be configured. Memory may include non-persistent memory in computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0078] This application provides a non-volatile storage medium storing a program that, when executed by a processor, implements a method for determining the performance of a terminal.

[0079] This application provides an electronic device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: determining an initial capability fingerprint of a target terminal, wherein the initial capability fingerprint is used to quantitatively describe the performance characteristics of the target terminal; performing fault diagnosis on a preset power grid fault scenario using the target terminal to obtain a target diagnosis result; determining a target index value for the target terminal's performance indicators based on the target diagnosis result; determining a performance level of the target terminal based on the target index value and the initial capability fingerprint, wherein the performance level is used to quantify the performance level of the target terminal; determining a performance result of the target terminal based on the performance level and the target index value, wherein the performance result indicates whether the target terminal's performance is qualified; and determining the target performance of the target terminal in the preset power grid fault scenario based on the initial capability fingerprint, target index value, performance level, and performance result. The device in this document can be a server, PC, etc.

[0080] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program comprising the following method steps: determining an initial capability fingerprint of a target terminal, wherein the initial capability fingerprint is used to quantitatively describe the performance characteristics of the target terminal; performing fault diagnosis on a preset power grid fault scenario using the target terminal to obtain a target diagnosis result; determining a target index value for the performance index of the target terminal based on the target diagnosis result; determining a performance level of the target terminal based on the target index value and the initial capability fingerprint, wherein the performance level is used to quantify the performance level of the target terminal; determining a performance result of the target terminal based on the performance level and the target index value, wherein the performance result is used to indicate whether the performance of the target terminal is qualified; and determining the target performance of the target terminal in the preset power grid fault scenario based on the initial capability fingerprint, the target index value, the performance level, and the performance result.

[0081] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0082] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0083] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0084] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0085] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0086] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0087] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0088] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0089] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0090] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for determining the performance of a terminal, characterized in that, include: Determine the initial capability fingerprint of the target terminal, wherein the initial capability fingerprint is used to quantitatively describe the performance characteristics of the target terminal; The target terminal is used to perform fault diagnosis on a preset power grid fault scenario to obtain the target diagnosis result; Based on the target diagnostic results, the target index values ​​of the performance indicators of the target terminal are determined; Based on the target index value and the initial capability fingerprint, the performance level of the target terminal is determined, wherein the performance level is used to quantify the performance level of the target terminal; Based on the performance level and the target index value, the performance result of the target terminal is determined, wherein the performance result is used to indicate whether the performance of the target terminal is qualified; Based on the initial capability fingerprint, the target index value, the performance level, and the performance result, the target performance of the target terminal in the preset power grid fault scenario is determined.

2. The method according to claim 1, characterized in that, The determination of the initial capability fingerprint of the target terminal includes: Obtain the initial performance parameters of the target terminal; The performance parameters are standardized to obtain the target performance parameters of the target terminal; The target performance parameters are represented by vectors to obtain the initial capability fingerprint.

3. The method according to claim 1, characterized in that, Before using the target terminal to perform fault diagnosis on a preset power grid fault scenario and obtain the target diagnosis result, the method further includes: Determine the initial grid scenario, initial load condition, and initial fault type of the power grid, wherein the initial grid scenario is used to describe the operating state and environmental conditions of the power grid; Time alignment is performed on the initial power grid scenario, the initial load condition, and the initial fault type to obtain the target power grid scenario, target load condition, and target fault type of the power grid; Based on the target power grid scenario, the target load condition, and the target fault type, the preset power grid fault scenario is determined.

4. The method according to claim 1, characterized in that, Determining the performance level of the target terminal based on the target indicator value and the initial capability fingerprint includes: Based on the target index value, the initial capability fingerprint is reduced in dimensionality to obtain the target capability fingerprint of the target terminal. The performance level is determined based on the target indicator value and the target capability fingerprint.

5. The method according to claim 1, characterized in that, Determining the performance result of the target terminal based on the performance level and the target indicator value includes: Based on the performance level, determine the threshold values ​​for the performance indicators; The target indicator value is compared with the indicator threshold to obtain the comparison result; Based on the comparison results, the performance results are determined.

6. The method according to any one of claims 1 to 5, characterized in that, If the target performance also includes the robustness features of the target terminal, the method further includes: Inject any disturbance of the target type into the preset power grid fault scenario to obtain any disturbance power grid fault scenario; The target terminal is used to perform fault diagnosis on any of the disturbance power grid fault scenarios to obtain any disturbance diagnosis result; Based on any of the disturbance diagnosis results, determine any target disturbance index value of the performance index; The method of determining any one of the target disturbance index values ​​is used to determine multiple target disturbance index values ​​obtained by the target terminal after injecting multiple disturbances. The disturbance types of the multiple disturbances are all the target type, and the disturbance intensities of the multiple disturbances are different. The multiple disturbances correspond one-to-one with the multiple target disturbance index values. Based on the multiple target disturbance index values, the robustness characteristics of the target terminal under the disturbance of the target type are determined.

7. The method according to claim 6, characterized in that, The step of determining the robustness characteristics of the target terminal under the perturbation of the target type based on the plurality of target perturbation index values ​​includes: Based on the multiple target disturbance index values, determine the performance drop curve of the target terminal's performance index; Based on the performance drop curve, determine the performance drop threshold of the target terminal's performance index; The robustness characteristics are determined based on the performance drop curve and the performance drop critical point.

8. A device for determining the performance of a terminal, characterized in that, include: An initial capability fingerprint determination module is used to determine the initial capability fingerprint of a target terminal, wherein the initial capability fingerprint is used to quantitatively describe the performance characteristics of the target terminal; The target diagnosis result determination module is used to perform fault diagnosis on a preset power grid fault scenario using the target terminal to obtain the target diagnosis result. The target indicator value determination module is used to determine the target indicator value of the performance indicator of the target terminal based on the target diagnostic results. A performance level determination module is used to determine the performance level of the target terminal based on the target indicator value and the initial capability fingerprint, wherein the performance level is used to quantify the performance level of the target terminal; A performance result determination module is used to determine the performance result of the target terminal based on the performance level and the target index value, wherein the performance result is used to indicate whether the performance of the target terminal is qualified; The target performance determination module is used to determine the target performance of the target terminal in the preset power grid fault scenario based on the initial capability fingerprint, the target index value, the performance level, and the performance result.

9. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores multiple instructions, which are adapted to be loaded by a processor and executed by the performance determination method of the terminal according to any one of claims 1 to 7.

10. An electronic device, characterized in that, include: One or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the terminal performance determination method according to any one of claims 1 to 7.

Images