A cross-layer power grid data status comprehensive evaluation system and method

Abstract

The present invention discloses a cross-layer power grid data state comprehensive evaluation system, which includes a data conversion module that extracts power grid power consumption data through a source database, performs corresponding format conversion on the power grid power consumption data according to a preset data format, and synchronizes the corresponding data packet to the database; a data verification module that calculates the data value of each data packet in the database according to a verification algorithm to obtain a corresponding verification value, and performs consistency verification on the verification value and the additional verification value of the data packet; an exception handling module that is used to automatically correct the abnormal data and perform consistency verification again. If the consistency verification still fails, a data correction strategy is recommended and the data value is corrected; a state comprehensive evaluation module that performs a data comprehensive evaluation of the power grid operation state according to the data value of the corrected data packet. The present invention improves the reliability of data synchronization, enhances the automation of data verification, and improves the accuracy of fault warning.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid data processing, and in particular to a cross-layer power grid data state comprehensive evaluation system and method. Background Art

[0002] With the continuous development of power grid systems and the acceleration of intelligentization, higher requirements are placed on the processing, analysis and early warning capabilities of power grid data. In existing technologies, power grid data processing usually relies on traditional database systems and data processing methods, using machine learning and artificial intelligence technologies to analyze power grid data to predict faults, optimize resource allocation and improve power grid efficiency.

[0003] However, when processing cross-layer power grid data, these methods often have problems such as difficulty in data migration and synchronization, low data verification efficiency, and insufficient and inaccurate fault warning. Especially when it comes to data interaction between domestic and foreign databases, the differences in data format, storage method, and synchronization mechanism further increase the complexity of data processing. In addition, most of the existing data verification methods rely on manually defined verification rules and lack intelligent exception handling mechanisms, which makes it difficult to promptly and effectively handle abnormal data found during the data verification process.

[0004] Therefore, it is a technical problem that needs to be solved urgently to invent a cross-layer power grid data status comprehensive evaluation system, improve the reliability of data synchronization, enhance the automation of data verification, and realize the intelligent processing of abnormal data. Summary of the invention

[0005] The purpose of the present invention is to provide a cross-layer power grid data status comprehensive evaluation system and method, which can improve the reliability, real-time and efficiency of data synchronization, enhance the automation and intelligence of data verification, improve the accuracy and timeliness of fault warning, and realize intelligent processing and continuous optimization of abnormal data.

[0006] To achieve this purpose, the present invention designs a cross-layer power grid data status comprehensive evaluation system, which includes:

[0007] The data conversion module extracts the power grid power consumption data from the source database, performs corresponding format conversion on various types of data in the extracted power grid power consumption data according to the correspondence between various types of data and data formats in the preset power grid power consumption data, and synchronizes the data packets corresponding to various types of data after format conversion to the database, each data packet includes a data value and an additional check value;

[0008] The data verification module is used to calculate the data value of each data packet in the database according to the verification algorithm to obtain the corresponding verification value, and perform consistency verification on the verification value calculated corresponding to the data value of each data packet and the additional verification value of the corresponding data packet;

[0009] The exception handling module is used to mark the data value of the data packet corresponding to the consistency check as abnormal data when the consistency check fails, correct the abnormal data according to the preset automatic correction rules, and perform consistency check again on the calculated check value corresponding to the data value of the corrected data packet and the additional check value of the corresponding data packet. If the consistency check of the corrected data packet still fails, the corresponding intelligent data correction algorithm is used according to the identified reason for the failure of the check to recommend a data correction strategy to the corrected data packet, and the data value of the data packet is corrected according to the data correction strategy;

[0010] The comprehensive status evaluation module performs a comprehensive data evaluation of the power grid operation status according to the data values ​​of the corrected data packets.

[0011] Preferably, the additional check value is calculated by converting various types of data in the power grid power consumption data into corresponding formats according to a check algorithm.

[0012] Preferably, the data verification module includes a verification algorithm module, a rule definition module and a verification engine module, wherein the verification algorithm module is used to provide an algorithm interface for other modules to call for data verification; the rule definition module is used to store and manage user-defined verification rules for use by the verification engine; the verification engine module is used to generate a verification report based on the verification results, including successfully verified data and failed verified data and the reasons for the failed verification.

[0013] Preferably, the exception handling module cleans, denoises, and standardizes the exception data and performs feature extraction, extracts key features from the exception data, and uses these features as input to the machine learning model to learn the relationship between the exception data and the correction strategy. The intelligent data correction algorithm is used to recommend the data correction strategy based on the preprocessed exception data, and the data value of the corrected data packet is finally checked for consistency, and the correction record is made after the final consistency check passes.

[0014] Preferably, the modified and confirmed data of the exception handling module is fed back to the data verification module, and the verification rules in the data verification module are checked and evaluated. If there are loopholes, necessary adjustments and optimizations will be made to the verification rules.

[0015] Preferably, the exception handling module performs a consistency check on the data value of the corrected data packet and the additional check value of the corresponding data packet. If the check passes, the corresponding data is synchronized to the database, and the abnormal data is regularly monitored to obtain the number and type of abnormal data, analyze and record the causes of the abnormal data and the correction effects.

[0016] Preferably, the comprehensive evaluation specifically includes data quality evaluation, abnormal state evaluation, and comprehensive index evaluation;

[0017] Data quality assessment ensures that there are no missing values ​​by checking the integrity of the data values ​​of the revised data packet; data quality assessment also verifies the accuracy of the data values ​​of the revised data packet by comparing historical data or reference standard values; data quality assessment verifies the real-time nature of the data values ​​of the revised data packet to reflect the current status of the power grid;

[0018] Abnormal status assessment monitors the data values ​​of the corrected data packets in real time according to the set assessment model, identifying abnormal data and corresponding abnormal trends;

[0019] Comprehensive index evaluation sets comprehensive indexes according to evaluation requirements, including power grid stability index, energy efficiency index, and reliability index. The evaluation indexes are used to evaluate the data value of the revised data packet to evaluate the power grid data status.

[0020] Preferably, it also includes a log recording module, which is used to record the correction records of data values ​​and log information during the synchronization process.

[0021] Beneficial effects of the present invention:

[0022] The present invention provides a cross-layer power grid data status comprehensive evaluation system, which solves the data synchronization difficulties caused by differences in data transmission data formats, storage methods and synchronization mechanisms between databases, improves the reliability of data synchronization, and improves data verification efficiency by adding an intelligent exception handling mechanism, solving the problem of fault warnings not being timely and accurate enough. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a structural schematic diagram of the present invention;

[0024] Figure 2 It is an implementation flow chart of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments:

[0027] Example 1

[0028] A cross-layer grid data status comprehensive evaluation system, such as Figure 1 As shown, it includes:

[0029] The data conversion module extracts the power grid power consumption data from the source database, performs corresponding format conversion on various types of data in the extracted power grid power consumption data according to the correspondence between various types of data and data formats in the preset power grid power consumption data, and synchronizes the data packets corresponding to various types of data after format conversion to the database, each data packet includes a data value and an additional check value;

[0030] The data verification module is used to calculate the data value of each data packet in the database according to the verification algorithm to obtain the corresponding verification value, and perform consistency verification on the verification value calculated corresponding to the data value of each data packet and the additional verification value of the corresponding data packet;

[0031] The exception handling module is used to mark the data value of the data packet corresponding to the consistency check as abnormal data when the consistency check fails, correct the abnormal data according to the preset automatic correction rules, and perform consistency check again on the calculated check value corresponding to the data value of the corrected data packet and the additional check value of the corresponding data packet. If the consistency check of the corrected data packet still fails, the corresponding intelligent data correction algorithm is used according to the identified reason for the failure of the check to recommend a data correction strategy to the corrected data packet, and the data value of the data packet is corrected according to the data correction strategy;

[0032] The comprehensive status evaluation module performs a comprehensive data evaluation of the power grid operation status according to the data values ​​of the corrected data packets.

[0033] In the above technical solution, power grid data including current, voltage, power, load, equipment status, etc. are extracted through the source database, and the conversion rules are based on the general needs of data processing and the format requirements of the database, including but not limited to data type conversion, such as integer to floating point; data unit conversion, such as from kilowatt to megawatt; data format adjustment, such as the unification of timestamp format.

[0034] In the above technical solution, the purpose of converting and synchronizing data according to the required format is to ensure that the format of the data transmitted to the database is consistent with the format of the data in the database, which is convenient for subsequent processing and storage. Through format conversion, the organization and access efficiency of data can be optimized, and the reliability of data synchronization can be improved.

[0035] In the above technical solution, the additional check value is calculated by converting the format of various types of data in the power grid power consumption data into corresponding data according to the check algorithm.

[0036] In the above technical solution, the data verification module includes a verification algorithm module, a rule definition module and a verification engine module, wherein the verification algorithm module is used to provide an algorithm interface for other modules to call for data verification; the rule definition module is used to store and manage user-defined verification rules for use by the verification engine; the verification engine module is used to generate a verification report based on the verification results, including successfully verified data and failed verification data and the reasons for failed verification.

[0037] In the above technical solution, the rule definition module provides a user-friendly interface or configuration tool, allowing users to define and configure verification rules; defines a series of verification rules according to business rules and data format requirements, such as cross-reference verification in financial data, data length verification, and data type verification; uses regular expressions, SQL query statements or coding languages ​​(such as JavaScript) to implement these verification rules.

[0038] In the above technical solution, the data verification module calls the verification algorithm module and the rule definition module to verify the data packet.

[0039] In the above technical solution, the specific verification process of the consistency check is: first determine the object and scope of the check, and clarify the specific content of the data or system implementation that needs to be checked; then use certain algorithms or methods, such as protocol consistency testing, cyclic redundancy check (CRC), etc. to check the verification object. These algorithms or methods can detect errors or inconsistencies that may exist in the data or system implementation; in the protocol consistency test, the test system will generate a set of test sequences for the implementation under test (IUT) according to the specification, and observe whether the external behavior of the implementation under test conforms to the description of the specification. By comparing the actual output with the expected output, it can be determined whether the implementation under test meets the consistency requirements; if the verification result shows that the data or system implementation is inconsistent with the predetermined standard or specification, it is necessary to take corresponding measures to correct it to ensure the consistency of the data or system implementation.

[0040] In the above technical solution, an error occurs during data transmission, resulting in the inconsistency between the calculated check value corresponding to the data value of the data packet and the additional check value of the corresponding data packet. Errors such as bit flipping, data packet loss, differences in initial values, differences in processing order, etc. will cause the check value to be inconsistent with the additional check value.

[0041] In the above technical solution, the calculated check value corresponding to the data value of the data packet is reused and compared with the additional check value of the data packet to see if they are consistent. Its function is to generate a reference value for verifying the integrity of the data. Through the check value and the additional check value, it is determined whether an error has occurred in the data transmission process and whether the data has been correctly received.

[0042] In the above technical solution, the algorithm for calculating the data check value uses hash algorithms such as MD5 and SHA to check the data to ensure the uniqueness and integrity of the data. The hash values ​​generated by these algorithms are highly unique, and any slight data change will cause the hash value to change; parity check, BCC XOR check and other algorithms have certain advantages in terms of calculation simplicity, resource occupation, applicable scenarios and error detection capabilities. In different scenarios, the system selects the corresponding algorithm according to the needs. The specific application of the algorithm is as follows:

[0043] Parity calculation method: add a check bit at the end of the data so that the number of "1"s in the data including the check bit meets the predetermined parity rule (odd or even). After receiving the data, the database will perform the same parity check to verify whether an error occurred during the data transmission process. Parity check is applied to simple data transmission situations where error detection is not required.

[0044] BCC XOR check calculation method: All bytes in a data block are bit-wise XORed to generate a check character. If the check character does not match the actual calculated one, it indicates that an error may have occurred in data transmission. BCC check is used in scenarios that require efficient real-time check.

[0045] MD5 calculation method: convert data of any length into a fixed-length hash value, perform multiple rounds of processing on the input data based on bit operations, logical operations, and modulo operations to generate the final hash value, which is used to encrypt or sign sensitive information;

[0046] SHA calculation method: Divide the original message into blocks of fixed length, and combine it with the shared key to generate a fixed-length message digest using a series of logical algorithms.

[0047] In the above technical solution, by checking the consistency of the check value and the additional check value, errors that may occur during data transmission or storage can be discovered and corrected in a timely manner, thereby reducing losses caused by data transmission.

[0048] In the above technical solution, the exception handling module cleans, denoises and standardizes the abnormal data and performs feature extraction, extracts key features from the abnormal data, and these features will be used as inputs to the machine learning model to learn the relationship between the abnormal data and the correction strategy. The intelligent data correction algorithm is used to recommend the data correction strategy based on the preprocessed abnormal data, and the data value of the corrected data packet is finally checked for consistency, and the correction record is made after the final consistency check passes.

[0049] In the above technical solution, the abnormal data refers to data that has significant deviations from normal data or does not conform to expected rules in the comprehensive evaluation and fault warning system of power grid data status; these data may be generated due to transmission errors, equipment failures, human operational errors or other reasons; in the system, abnormal data are usually identified and captured by the data verification module, thereby triggering the relevant functions of the exception handling module.

[0050] In the above technical solution, the automatic correction rules predefine a series of error patterns and corresponding correct forms according to business logic and data characteristics, namely, automatic correction rules. When the system detects that the input data conforms to a certain error pattern, it will automatically replace it with the corresponding correct form, thereby achieving the purpose of correction; these rules may include common spelling errors, grammatical errors, format errors, etc., and their corresponding correct forms. For example, the system may preset spelling rules such as automatically correcting "teh" to "the" and correcting "tehse" to "these"; or grammatical rules such as correcting "Me" to "I" and abbreviating "they are" to "they're". In addition, it also includes correction rules such as professional terminology and format specifications for specific fields or applications. When the user enters data, the system will automatically scan and match these preset rules. Once a matching error pattern is found, it will immediately replace and correct it, thereby ensuring the accuracy and consistency of the output data.

[0051] In the above technical scheme, the specific implementation method of recommending data correction strategy through intelligent data correction algorithm is: using the error detection module in the intelligent data correction algorithm, such as rule-based detection or model-based detection, to identify errors or anomalies in the data; classifying the detected errors according to type, such as format errors, range errors, logical errors, etc.; finally, based on the severity and impact of the assessed errors, determining which errors need to be corrected first.

[0052] Among them, the model-based correction strategy uses machine learning algorithms to train the correction model. The model can learn the normal patterns and error patterns of the data. When a new error is detected, the model can recommend an appropriate correction strategy based on the learned knowledge. This strategy is suitable for situations where the data volume is large, the error types are diverse, and it is difficult to preset rules. The intelligent data correction algorithm is a hybrid model algorithm that can use machine learning algorithms to identify new anomaly types and rule algorithms to process known error types. When recommending data correction strategies, the hybrid model algorithm can flexibly select the most suitable correction method based on the specific situation.

[0053] In the above technical solution, for abnormal data that cannot be automatically corrected or intelligently recommended for correction, a manual review interface is provided to allow the user to manually correct the abnormal data and record the correction process.

[0054] In the above technical solution, both the automatic correction and the manual correction require a correction confirmation step to ensure that the corrected data is accurate.

[0055] In the above technical solution, the data modified and confirmed by the exception handling module is fed back to the data verification module, and a specific verification module is selected to ensure the integrity, accuracy and consistency of the data. A series of checks and verifications are performed on the data to ensure that there are no errors or tampering during the transmission, storage and processing of the data; the verification rules in the data verification module are then checked and evaluated. If there are loopholes, necessary adjustments and optimizations will be made to the verification rules.

[0056] In the above technical scheme, the situations in which the verification rules have loopholes include the verification rules being incomplete, the verification rules being too strict, the verification rules having logical errors, the verification rules failing to be updated in time, and other problems. Among them, when the verification rules fail to cover all possible data error types, the loophole exists in that the verification rules are incomplete; the verification rules being too strict may cause legal data to be misjudged as erroneous data, which is the situation in which the verification rules are too strict; when the verification rules themselves have logical errors or contradictions, it will cause inaccurate data verification results, which is the situation in which the verification rules have logical errors; with the continuous development and changes of the power grid system, new data error types may appear, and the old verification rules may not be able to adapt to these new error types. If the verification rules are not updated in time, these new errors cannot be effectively detected and corrected. The situation in which the verification rules have loopholes is that the verification rules fail to be updated in time.

[0057] In view of the loopholes in the above-mentioned verification rules, the following solutions can be adopted for adjustment and optimization: improve the verification rules, conduct a comprehensive review and update of the verification rules to ensure that they can cover all possible data error types, and pay attention to the latest developments and changes in the power grid system, and timely adjust and update the verification rules to adapt to new error types; reasonably set the verification threshold. For the overly strict parts of the verification rules, the verification threshold can be appropriately relaxed to reduce the possibility of legal data being misjudged as erroneous data. At the same time, it is necessary to ensure that the setting of the verification threshold is in line with the actual situation of the power grid system and can effectively detect and correct data errors; correct logical errors, correct the logical errors or contradictions in the verification rules, and ensure the correctness and consistency of the verification rules. This requires careful review and testing of the verification rules to discover and correct the logical errors therein; introduce intelligent verification technology. With the development of artificial intelligence and machine learning technology, it is possible to consider introducing intelligent verification technology to improve the accuracy and efficiency of data verification. For example, machine learning algorithms can be used to train and learn power grid data to automatically identify and correct data errors. This can reduce the possibility of human intervention and misjudgment and improve the automation and intelligence level of data verification.

[0058] In the above technical scheme, checking and evaluating the verification rules in the data verification module is an important part of ensuring the accuracy and stability of the comprehensive evaluation system of the power grid data status. By timely discovering and correcting loopholes in the verification rules and taking corresponding solutions for adjustment and optimization, the accuracy and efficiency of data verification can be further improved, providing strong guarantees for the safe and stable operation of the power grid system.

[0059] In the above technical solution, the exception handling module performs a consistency check on the data value of the corrected data packet and the additional check value of the corresponding data packet. If the check passes, the corresponding data is synchronized to the database, and the abnormal data is monitored regularly to obtain the number and type of abnormal data, analyze and record the causes of the abnormal data and the correction effects.

[0060] In the above technical solution, the core components of the intelligent recommendation system include:

[0061] Feature extraction and preprocessing: Collect and organize historical abnormal data and its correction records to form a training data set, clean, denoise and standardize the data to ensure data quality; extract key features from abnormal data, such as data type, abnormal type, abnormal value range, contextual information, etc. These features will be used as input to the machine learning model to learn the relationship between abnormal data and correction strategies.

[0062] Model prediction and strategy recommendation: Select appropriate machine learning algorithms, such as decision trees, random forests, neural networks, etc., build intelligent recommendation models, and use training data sets to train the models so that they can accurately predict the best correction strategy for given abnormal data; based on the prediction results of the machine learning model, recommend correction strategies for abnormal data that cannot be automatically corrected. The recommended strategies may include specific correction values, correction methods, or correction suggestions.

[0063] User feedback and model optimization: Collect users’ actual application of recommendation strategies and their feedback, and use feedback data to continuously optimize machine learning models to improve the accuracy and reliability of recommendations.

[0064] In the above technical solution, whether it is automatic correction or manual correction, it needs to go through a confirmation process to ensure that the corrected data is accurate.

[0065] In the above technical solution, the specific workflow of the intelligent recommendation system in the exception handling module is as follows: in the data verification process, capture and identify abnormal data that cannot be resolved by automatic correction rules; perform feature extraction and preprocessing on the captured abnormal data to form a data format suitable for machine learning model input; input the preprocessed data into the machine learning model for predictive analysis, and recommend correction strategies for the abnormal data based on the prediction results of the model; users receive the recommended strategies, review and select them based on actual conditions, apply the selected strategies, and correct the abnormal data; collect users' application status and feedback on the recommended strategies, and use the feedback data to iteratively optimize the machine learning model to improve the accuracy and applicability of the recommendations.

[0066] In the above technical solution, the comprehensive evaluation specifically includes data quality evaluation, abnormal state evaluation, and comprehensive indicator evaluation;

[0067] Data quality assessment ensures that there are no missing values ​​by checking the integrity of the data values ​​of the revised data packet; data quality assessment also verifies the accuracy of the data values ​​of the revised data packet by comparing historical data or reference standard values; data quality assessment verifies the real-time nature of the data values ​​of the revised data packet to reflect the current status of the power grid;

[0068] Abnormal status assessment monitors the data values ​​of the corrected data packets in real time according to the set assessment model, identifying abnormal data and corresponding abnormal trends;

[0069] Comprehensive index evaluation sets comprehensive indexes according to evaluation requirements, including power grid stability index, energy efficiency index, and reliability index. The evaluation indexes are used to evaluate the data value of the revised data packet to evaluate the power grid data status.

[0070] In the above technical solution, a comprehensive evaluation of the power grid data status is achieved based on the integrity, correctness, real-time nature of the data values ​​of the above-mentioned corrected data packets, whether there are abnormal data and the corresponding abnormal trends, and the power grid data status evaluation results.

[0071] In the above technical solution, the evaluation model selects a suitable evaluation model according to the specific situation, such as hierarchical analysis method, fuzzy comprehensive evaluation method, neural network, etc. The evaluation model needs to undergo model training and model verification, wherein the model training needs to use a training set and a verification set to train and verify the evaluation model, and the parameters of the evaluation model are adjusted by inputting the data of the training set so that it can learn the relationship between the input features and the labels. The specific steps of the training process are: according to the structure and type of the evaluation model, the parameters of the evaluation model, such as weights and biases, are initialized; the training data is input into the evaluation model, and the prediction results of the evaluation model are calculated; the difference between the prediction results of the evaluation model and the true labels is compared to obtain the loss value of the evaluation model, and the gradient of the evaluation model parameters is calculated by the chain rule according to the loss value; an optimization algorithm, such as stochastic gradient descent, is used to update the parameters of the evaluation model according to the gradient information to reduce the loss value, and then the samples in the training set are repeatedly iterated until a predetermined stopping condition is reached, such as reaching the maximum number of iterations or the convergence of the loss function;

[0072] Model validation requires using a validation set to judge the performance of the evaluation model during the training process in order to adjust the hyperparameters and structure of the evaluation model. The judgment results on the validation set can help us understand the performance of different models on unseen data, thereby judging the generalization ability of different models. When comparing the performance of different models, we can select the best performing model as the evaluation model. We can also judge the performance of different models under different hyperparameter settings to help find the optimal hyperparameter combination.

[0073] By comparing the performance of different models on the training set and validation set, overfitting can be identified and prevented. For the evaluation model in the real-time monitoring and anomaly identification tasks of power grid data, the training set is used for training and the validation set is used for validation to ensure that the evaluation model has good generalization ability and performance.

[0074] In the above technical solution, the various types of data in the power grid electricity consumption data include current data, voltage data, power data, load data, and equipment status data.

[0075] The above technical solution also includes a log recording module, which is used to record the correction records of data values ​​and log information during the synchronization process.

[0076] In the above technical scheme, the evaluation results of the comprehensive evaluation of the power grid data status are specifically evaluated as follows: check the integrity of the data to ensure that there are no missing values ​​or outliers, evaluate the accuracy of the data, verify the correctness of the data by comparing historical data or reference standard values, evaluate the timeliness of the data, and ensure that the data is real-time or near real-time to reflect the current status of the power grid; use statistical methods or machine learning algorithms to monitor the power grid data status in real time, identify abnormal data or trends, set thresholds or early warning mechanisms, and trigger alarms when data exceeds a preset range to prompt possible problems in the power grid, and evaluate whether the power grid data is operating normally or whether a fault occurs; according to the characteristics of the power grid and evaluation needs, construct a series of comprehensive evaluation indicators, such as power grid stability index, energy efficiency index, and reliability index. These indicators should be able to fully reflect the operating status of the power grid, including safety, economy, reliability, and environmental protection. The power grid data status is comprehensively evaluated through evaluation indicators.

[0077] In the above technical solution, a threshold or early warning mechanism is set based on the identification of abnormal data or trends. When abnormal data appears or an abnormal trend is predicted, an alarm is issued in time, which solves the problem of fault early warning not being timely and accurate enough.

[0078] In the above technical solution, after obtaining a comprehensive evaluation of the power grid data status, the evaluation results are presented to the user in an intuitive manner, such as charts, reports or dashboards, and decision support is provided based on the evaluation results, such as recommendations on what measures to take to improve the power grid status, optimize resource allocation or improve energy efficiency.

[0079] In the above technical solution, through comprehensive evaluation, the health status of the power grid can be better monitored, potential problems can be discovered and prevented in a timely manner, and the efficiency, accuracy and reliability of data processing can be ensured through modular design. The collaborative work of each module not only improves the automation level of data processing, but also enhances the monitoring and evaluation capabilities of the power grid operation status.

[0080] Example 2

[0081] A comprehensive evaluation method for cross-layer power grid data status, such as Figure 2 As shown, the source database extracts the power grid electricity consumption data, performs corresponding format conversion on the power grid electricity consumption data, and synchronizes the format-converted data packets to the database; verifies the synchronized data to ensure the consistency before and after data transmission; handles abnormal situations found during the verification process; conducts a comprehensive assessment based on the power grid data status and issues a fault warning; and records log information during data synchronization.

[0082] The specific method for comprehensive evaluation of cross-layer power grid data status includes the following steps:

[0083] Extracting power grid electricity consumption data through the source database, performing corresponding format conversion on various types of data in the extracted power grid electricity consumption data according to the correspondence between various types of data and data formats in the preset power grid electricity consumption data, and synchronizing the data packets corresponding to various types of data after the format conversion to the database, each data packet includes a data value and an additional check value;

[0084] The data value of each data packet in the database is calculated according to the verification algorithm to obtain the corresponding verification value, and the data value of each data packet corresponding to the calculated verification value is verified for consistency with the additional verification value of the corresponding data packet;

[0085] When the consistency check fails, the data value of the data packet corresponding to the consistency check is marked as abnormal data, and the abnormal data is corrected according to the preset automatic correction rules, and the data value of the corrected data packet is again checked for consistency with the calculated check value and the additional check value of the corresponding data packet. If the consistency check of the corrected data packet still fails, the corresponding intelligent data correction algorithm is used according to the identified reason for the failure of the check to recommend a data correction strategy to the corrected data packet, and the data value of the data packet is corrected according to the data correction strategy;

[0086] A comprehensive data evaluation of the power grid operation status is performed based on the data values ​​of the corrected data packets.

[0087] Example 3

[0088] A computer program product comprises a computer program, wherein when the computer program is executed by a processor, the steps of the method described in Embodiment 2 are implemented.

[0089] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

Claims

1. A cross-layer power grid data status comprehensive evaluation system, characterized in that: It includes: The data conversion module extracts the power grid power consumption data from the source database, performs corresponding format conversion on various types of data in the extracted power grid power consumption data according to the correspondence between various types of data and data formats in the preset power grid power consumption data, and synchronizes the data packets corresponding to various types of data after format conversion to the database, each data packet includes a data value and an additional check value; The data verification module is used to calculate the data value of each data packet in the database according to the verification algorithm to obtain the corresponding verification value, and perform consistency verification on the verification value calculated corresponding to the data value of each data packet and the additional verification value of the corresponding data packet; The exception handling module is used to mark the data value of the data packet corresponding to the consistency check as abnormal data when the consistency check fails, correct the abnormal data according to the preset automatic correction rules, and perform consistency check again on the calculated check value corresponding to the data value of the corrected data packet and the additional check value of the corresponding data packet. If the consistency check of the corrected data packet still fails, the corresponding intelligent data correction algorithm is used according to the identified reason for the failure of the check to recommend a data correction strategy to the corrected data packet, and the data value of the data packet is corrected according to the data correction strategy; The comprehensive status evaluation module performs a comprehensive data evaluation of the power grid operation status according to the data values ​​of the corrected data packets.

2. According to claim 1, a cross-layer power grid data status comprehensive evaluation system is characterized by: The additional check value is calculated by converting various types of data in the power grid power consumption data into corresponding formats according to a check algorithm.

3. According to claim 1, a cross-layer power grid data status comprehensive evaluation system is characterized by: The data verification module includes a verification algorithm module, a rule definition module and a verification engine module, wherein the verification algorithm module is used to provide an algorithm interface for other modules to call for data verification; the rule definition module is used to store and manage user-defined verification rules for use by the verification engine; the verification engine module is used to generate a verification report based on the verification results, including successfully verified data and failed verification data and the reasons for the failed verification.

4. According to claim 1, a cross-layer power grid data status comprehensive evaluation system is characterized by: The exception processing module cleans, denoises, and standardizes the exception data and performs feature extraction, extracts key features from the exception data, and uses these features as input to the machine learning model to learn the relationship between the exception data and the correction strategy. The intelligent data correction algorithm is used to recommend the data correction strategy based on the preprocessed exception data, and the data value of the corrected data packet is finally checked for consistency, and the correction record is made after the final consistency check passes.

5. According to claim 1, a cross-layer power grid data status comprehensive evaluation system is characterized by: The data modified and confirmed by the exception handling module is fed back to the data verification module, and the verification rules in the data verification module are checked and evaluated. If there are loopholes, necessary adjustments and optimizations will be made to the verification rules.

6. The cross-layer grid data status comprehensive evaluation system according to claim 1 is characterized by: The exception handling module performs a consistency check on the data value of the corrected data packet and the additional check value of the corresponding data packet. If the check passes, the corresponding data is synchronized to the database, and the abnormal data is regularly monitored to obtain the number and type of abnormal data, analyze and record the cause of the abnormal data and the correction effect.

7. The cross-layer grid data status comprehensive evaluation system according to claim 1 is characterized by: The comprehensive evaluation specifically includes data quality evaluation, abnormal state evaluation, and comprehensive indicator evaluation; Data quality assessment ensures that there are no missing values ​​by checking the integrity of the data values ​​in the revised data package; data quality assessment also verifies the accuracy of the data values ​​in the revised data package by comparing them with historical data or reference standard values; Data quality evaluates the real-time nature of the data values ​​of the corrected data packets to reflect the current state of the power grid; Abnormal status assessment monitors the data values ​​of the corrected data packets in real time according to the set assessment model, identifying abnormal data and corresponding abnormal trends; Comprehensive index evaluation sets comprehensive indexes according to evaluation requirements, including power grid stability index, energy efficiency index, and reliability index. The evaluation indexes are used to evaluate the data value of the revised data packet to evaluate the power grid data status.

8. The cross-layer grid data status comprehensive evaluation system according to claim 1 is characterized by: It also includes a log recording module, which is used to record the modification records of data values ​​and log information during the synchronization process.

9. A method for comprehensive evaluation of power grid data status across layers, characterized in that: It includes the following steps: Extracting power grid electricity consumption data through the source database, performing corresponding format conversion on various types of data in the extracted power grid electricity consumption data according to the correspondence between various types of data and data formats in the preset power grid electricity consumption data, and synchronizing the data packets corresponding to various types of data after the format conversion to the database, each data packet includes a data value and an additional check value; The data value of each data packet in the database is calculated according to the verification algorithm to obtain the corresponding verification value, and the data value of each data packet corresponding to the calculated verification value is verified for consistency with the additional verification value of the corresponding data packet; When the consistency check fails, the data value of the data packet corresponding to the consistency check is marked as abnormal data, and the abnormal data is corrected according to the preset automatic correction rules, and the data value of the corrected data packet is again checked for consistency with the calculated check value and the additional check value of the corresponding data packet. If the consistency check of the corrected data packet still fails, the corresponding intelligent data correction algorithm is used according to the identified reason for the failure of the check to recommend a data correction strategy to the corrected data packet, and the data value of the data packet is corrected according to the data correction strategy; A comprehensive data evaluation of the power grid operation status is performed based on the data values ​​of the corrected data packets.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in claim 9 are implemented.

Images