A power grid data analysis method and device

Abstract

The application provides a power grid data analysis method and device, and belongs to the field of power grid data analysis. According to historical analysis results, the change rate of the current analysis result is determined as the degree of influence on the analysis result, and the data is classified according to the change rate, and important data with greater influence on the analysis result is determined. Further, the order of magnitude is determined to determine the order of magnitude influence type data and important sensitive type data. The fine classification of the data influence type helps the user to deeply understand the specific influence mode and degree of different data on the power grid data analysis result, and provides more targeted basis for subsequent data processing and decision-making. In the massive data, the fine classification of the data influence type helps to quickly identify important data with greater influence on the analysis result, and the analysis personnel can preferentially focus on and process these key data without spending a lot of time on unimportant data, thereby improving the analysis efficiency.

Description

Technical Field

[0001] This invention relates to the field of power grid data analysis technology, and in particular to a power grid data analysis method and apparatus. Background Technology

[0002] Power grid data analysis refers to the process of collecting, organizing, processing, and analyzing various data generated in the power grid system to obtain information and knowledge about the power grid's operating status, performance indicators, and development trends. Its purpose is to optimize the planning, construction, operation, and maintenance of the power grid, improve its reliability and economy, and ensure the safe, stable, and efficient supply of electricity. For example, power grid data analysis can include power grid investment benefit data analysis and renewable energy power grid planning data analysis.

[0003] Existing power grid data analysis technologies primarily rely on basic benefit analysis of large amounts of stored data. However, this approach has limitations; it merely interprets the surface of the data and fails to fully uncover its intrinsic value. Specifically, while existing technological frameworks can perform data analysis tasks, they struggle to quickly locate key information when faced with massive amounts of data, thus impacting the efficiency and accuracy of the analysis. Summary of the Invention

[0004] This invention provides a power grid data analysis method and apparatus to address the problems of low efficiency and accuracy in existing power grid data analysis methods.

[0005] In a first aspect, the present invention provides a power grid data analysis method, comprising: Obtain the current input data, as well as historical input data and their corresponding historical analysis results; Based on the current input data, the current analysis results of the power grid are obtained; Based on the historical analysis results, determine the rate of change of the current analysis results; If the rate of change is greater than a preset value, the current input data is determined to be important data; If the current input data is important data, and the difference in magnitude between the current input data and the historical input data is greater than a preset threshold, then the current input data is determined to be data with a magnitude impact. If the current input data is important data, and the difference in magnitude between the current input data and the historical input data is no greater than a preset threshold, then the current input data is determined to be important and sensitive data. Power grid data analysis is conducted based on the aforementioned impactful and sensitive data.

[0006] In one possible implementation, determining the rate of change of the current analysis result based on the historical analysis results includes: The historical analysis results and the current analysis results are sorted in chronological order to determine the previous analysis result of the current analysis result; Based on the previous analysis results and the current analysis results, the rate of change of the current analysis results is determined.

[0007] In one possible implementation, determining the rate of change of the current analysis result based on the previous analysis result and the current analysis result includes: The rate of change of the current analysis results is determined based on the following formula. in, This indicates the current analysis results. This indicates the result of the previous analysis.

[0008] In one possible implementation, prior to conducting power grid data analysis based on the aforementioned impactful and sensitive data, the following steps are also included: The data with significant impact and the data with important sensitivity are classified and stored separately. The data with significant impact is compressed before storage, and the data with important sensitivity is encrypted before storage.

[0009] In one possible implementation, prior to acquiring the current input data, the method further includes: Obtain the number of times the primary target data was accessed during the historical analysis process; If the number of accesses to the first target data exceeds a set threshold, then the first target data is determined to be frequently used data.

[0010] In one possible implementation, after determining that the first target data is frequently used data, the method further includes: The frequently used data is transferred to a high-speed storage medium, wherein the read / write speed of the high-speed storage medium is higher than that of the storage medium before the frequently used data was transferred.

[0011] In one possible implementation, prior to the acquisition of the number of accesses to the first target data during the historical analysis process, the method further includes: Use data tracking software to monitor data interactions during the data analysis process; When data is accessed in the data storage module during data analysis, the data tracking software captures and records the data accessed and the frequency of the access.

[0012] In one possible implementation, after determining that the first target data is frequently used data, the method further includes: Acquire the second target data accessed during the historical analysis process; If the type of the second target data is the same as the type of the first target data, then the second target data is determined to be high-frequency data, wherein the first target data is high-frequency data; The second target data is transferred to a high-speed storage medium.

[0013] In one possible implementation, before determining that the second target data is high-frequency data if the type of the second target data is the same as the type of the first target data, the method further includes: The second target data is input into a pre-trained data type model to obtain the type of the second target data, wherein the data type model is trained based on multiple first target data, and the first target data is frequently used data; Determine whether the type of the second target data is the same as the type of the first target data.

[0014] In a second aspect, the present invention provides a power grid data analysis device, comprising: The acquisition module is used to acquire the current input data, as well as the historical input data and their corresponding historical analysis results; The module is used to obtain the current analysis result of the power grid based on the current input data; The determination module is used to determine the rate of change of the current analysis result based on the historical analysis results; The judgment module is used to determine the current input data as important data if the rate of change is greater than a preset value; The first determination module is used to determine that the current input data is data with a magnitude impact if the current input data is important data and the difference in magnitude between the current input data and the historical input data is greater than a preset threshold. The second determination module is used to determine that the current input data is important and sensitive data if the current input data is important data and the difference in magnitude between the current input data and the historical input data is not greater than a preset threshold. The analysis module is used to perform power grid data analysis based on the aforementioned impactful and sensitive data.

[0015] This invention provides a method and apparatus for power grid data analysis. The invention determines the rate of change of the current analysis results based on historical analysis results, using this rate as the degree of influence on the analysis results, and classifies the data accordingly to identify important data that has a significant impact on the analysis results. Furthermore, it classifies data based on magnitude of influence and data that is of significant sensitivity. This refined classification of data impact types helps users to deeply understand the specific ways and degrees that different data affect the power grid data analysis results, providing a more targeted basis for subsequent data processing and decision-making. In massive amounts of data, this refined classification of data impact types helps to quickly identify important data that has a significant impact on the analysis results. Analysts can prioritize and process these key data instead of spending a lot of time on unimportant data, thereby improving the efficiency of the analysis. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is an application scenario diagram of the power grid data analysis method provided in the embodiments of the present invention; Figure 2 This is a flowchart illustrating the implementation of the power grid data analysis method provided in this embodiment of the invention. Figure 3 This is a schematic diagram of the power grid data analysis system provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the power grid data analysis device provided in an embodiment of the present invention. Detailed Implementation

[0018] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0019] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0020] Figure 1 This diagram illustrates an application scenario of the power grid data analysis method provided in an embodiment of the present invention. For example... Figure 1As shown, this invention proposes a power grid data analysis system. For example, it could be a multi-level power grid investment benefit data analysis system. Power grid investment benefit data analysis refers to a comprehensive, systematic, and scientific analysis and evaluation of the economic benefits of power grid investment projects. This process involves collecting, organizing, and analyzing data from multiple stages, including power grid construction, operation, and maintenance. A multi-level power grid investment benefit data analysis system can efficiently process and analyze large amounts of power grid investment data, providing strong data support for power companies. Furthermore, a multi-level power grid investment benefit data analysis system may include a data storage module and a data analysis module.

[0021] For example, the data storage module is used to store multi-level power grid data, while the data analysis module performs benefit analysis on the stored data.

[0022] While existing technical frameworks can perform data analysis tasks, they lack a data classification and processing mechanism during the analysis process. Due to the lack of effective classification methods, the system struggles to quickly locate key information when faced with massive amounts of data, thus affecting the efficiency and accuracy of the analysis.

[0023] This invention provides a power grid data analysis method that identifies and classifies massive amounts of data to distinguish key data, thereby solving the problems of low efficiency and accuracy in existing power grid data analysis methods.

[0024] Figure 2 A flowchart illustrating the implementation of a power grid data analysis method provided in this embodiment of the invention is described in detail below: Step 201: Obtain the current input data, as well as the historical input data and their corresponding historical analysis results.

[0025] Step 202: Based on the current input data, obtain the current analysis results of the power grid.

[0026] For example, the power grid data analysis system also includes an analysis result recording module. The analysis result recording module interfaces with the data analysis module. When the data analysis module searches for data in the data storage module and performs calculations and analysis, the analysis result recording module records each analysis result that occurs and stores the analysis result data.

[0027] Furthermore, the specific method by which the analysis result recording module records the calculation results of the data analysis module is as follows: Step 1: Set up a data interface to connect the data analysis module and the analysis result recording module, so that each analysis result output by the data analysis module can be captured in real time through this data interface.

[0028] It's worth noting that the data interface settings, in addition to supporting common HTTP / HTTPS protocols, can also consider supporting protocols such as WebSocket and gRPC to adapt to data transmission needs in different scenarios. Furthermore, by introducing message queues (such as Kafka and RabbitMQ) as an intermediate layer, asynchronous communication between the data analysis module and the analysis result recording module can be achieved. This reduces the coupling between systems, improving system scalability and stability. Besides common JSON and XML formats, more complex data formats (such as Avro and Protobuf) or binary formats can also be supported to meet the needs of large data volumes and high-performance transmission. In summary, it can meet the interface protocol requirements, satisfy the needs of various usage scenarios, asynchronous processing mechanisms, and the transmission requirements of various data types, greatly improving overall usability.

[0029] Step 2: After receiving the analysis results, the analysis result recording module stores them in the distributed database MongoDB. Simultaneously, it performs data validation to ensure data integrity and accuracy. Based on the data volume and access frequency, it shards the MongoDB database to improve data read / write performance and scalability. Furthermore, it configures replica sets to guarantee high availability and fault tolerance.

[0030] Step 203: Determine the rate of change of the current analysis results based on the historical analysis results.

[0031] For example, the power grid data analysis system also includes a processing terminal. The processing terminal is used to process the analysis result data, arrange the analysis result data in sequence according to the analysis order of various categories by the data analysis module, and then calculate the rate of change of adjacent analysis result data.

[0032] In one possible implementation, determining the rate of change of the current analysis result based on historical analysis results includes: Sort the historical and current analysis results in chronological order to determine the previous analysis result of the current analysis result; Based on the results of the previous analysis and the current analysis, determine the rate of change of the current analysis results.

[0033] It's important to note that arranging the analysis results in order can be achieved using timestamps. For example, add a timestamp field to each analysis result, recording the time the data was generated. The timestamp can be represented in the format "year-month-day-hour-minute-second". Then, sort the data based on the timestamp field to obtain a dataset arranged in the order of analysis. Sorting can be implemented using sorting functions in programming languages ​​or the ORDER BY statement in a database.

[0034] In one possible implementation, determining the rate of change of the current analysis result based on the previous analysis result and the current analysis result includes: determining the rate of change of the current analysis result based on the following formula, in, This indicates the current analysis results. This indicates the result of the previous analysis.

[0035] For example, when calculating the rate of change of the analysis results data, assume there is a sequence of data: A1, A2, A3, ..., An, where An represents the nth analysis result data. The above formula can be used to calculate the relative degree of change between two adjacent data points and express it as a percentage.

[0036] Step 204: If the rate of change is greater than the preset value, the current input data is determined to be important data.

[0037] For example, when the rate of change is greater than a set threshold, the data input to the data analysis module that produces the analysis result is considered important data.

[0038] The threshold for the rate of change set here can also be set according to the situation. For example, it can be the average of all rates of change. When the rate of change is greater than the average, it indicates that it is important data.

[0039] Step 205: If the current input data is important data and the difference in magnitude between the current input data and the historical input data is greater than a preset threshold, then the current input data is determined to be data with a magnitude impact.

[0040] Step 206: If the current input data is important data and the difference in magnitude between the current input data and the historical input data is no greater than a preset threshold, then the current input data is determined to be important and sensitive data.

[0041] For example, the power grid data analysis system also includes a determination module. This module determines the cause of the important data. Specifically, based on the magnitude of the data, important data that significantly alters the analysis results of the data analysis module is categorized into magnitude-influenced data and important-sensitive data. Magnitude-influenced data refers to data with a large magnitude, resulting in a large rate of change in the analysis results generated by the data analysis module. Important-sensitive data, on the other hand, is data with a moderate magnitude but a significant impact. For instance, assuming the input data type is the construction of power grid lines, and the input data is 10,000, while other data are mostly 100 or several hundred, then the 10,000 can be considered significantly larger than the other data, belonging to the magnitude-influenced data category. As another example, assuming in a certain data type, such as the number of base stations invested in and constructed, the input data is 10, but other data of the same type are not significantly different from 10, such as 8, 11, 9, and 7, then this data can be considered important-sensitive data, causing a significant change in the model's output results despite a small change in magnitude.

[0042] It's important to note that "moderate magnitude" is not an absolute concept, but rather relative to the entire dataset or a specific analytical scenario. Generally, moderately sized data refers to data whose numerical values ​​are close to the average or median of the dataset. This "close" also has a predetermined threshold, such as plus or minus ten percent of the median.

[0043] It should also be noted that the comparisons here can be divided into direct comparisons: directly comparing the absolute values ​​of the data. For example, in numerical analysis, if the absolute value of a data point is much larger than that of other data points, it is usually considered to be of a larger magnitude.

[0044] Relative value comparison: Comparing data to a benchmark or average value. For example, if a data point exceeds the average of a dataset or a preset threshold, it may be considered to be of a large magnitude.

[0045] Proportional comparison: Calculate the proportion or percentage of a data point relative to the entire dataset. If the proportion or percentage of a certain data point is significantly higher than that of other data points, then it may be considered to be of a large magnitude.

[0046] For different types of data, it is necessary to compare them with data of the same type. For example, if we have the following data that need to be analyzed by the data analysis module, such as the length of the power grid erected per unit time (1000 meters) and the power of the installed transformer equipment, then these data only need to be compared with data of the same type, and cannot be compared with each other.

[0047] Step 207: Perform power grid data analysis based on data with significant impact and important sensitive data.

[0048] It should be noted that in massive amounts of data, fine-grained classification of data impact types helps to quickly identify important data that has a significant impact on the analysis results. Analysts can prioritize and process these key data instead of spending a lot of time on unimportant data, thereby improving the efficiency of the analysis.

[0049] In one possible implementation, before conducting power grid data analysis based on magnitude-impact data and important sensitive data, the following steps are also included: classifying and storing the magnitude-impact data and important sensitive data, wherein the magnitude-impact data is compressed before storage, and the important sensitive data is encrypted before storage.

[0050] For example, the power grid data analysis system also includes a categorized storage module. This module stores important data in an enterprise-level database. It also compresses data with significant impact and encrypts sensitive data. For instance, the enterprise database includes, but is not limited to, relational databases and cloud databases.

[0051] It's important to note that critical and sensitive data typically contains core corporate secrets, user privacy, and other sensitive information, significantly impacting power grid data analysis results. Leakage or unauthorized access to this data could cause severe losses to both the company and users; therefore, encryption is recommended for storage. Data with massive impact requires compression rather than encryption primarily because, while important, its large volume means it's usually only used in subsequent statistical analysis or long-term data archiving. This type of data is often related to significant events or long-term investments, such as records of large-scale equipment investments. It's not accessed in real-time or frequently, but may have extremely high value in statistical analysis years later. The main purpose of compressing this type of data is to reduce its storage space footprint, thereby saving storage costs. Since this data typically doesn't involve real-time transactions or the risk of sensitive information leakage, encryption is not a primary consideration. Instead, compression technology can effectively reduce storage requirements without sacrificing data integrity, facilitating future data analysis and historical record preservation.

[0052] This invention determines the rate of change of the current analysis results based on historical analysis results, using this rate as a measure of the degree of influence on the analysis results. Data is then categorized to identify important data that significantly impacts the analysis results. Furthermore, data with magnitude-based impact and important sensitive data are identified based on their order of magnitude. This refined classification of data impact types helps users gain a deeper understanding of the specific ways and degrees different data affect the power grid data analysis results, providing a more targeted basis for subsequent data processing and decision-making. In massive datasets, this refined classification of data impact types helps quickly identify important data that significantly impacts the analysis results. Analysts can prioritize and process these key data, avoiding spending excessive time on unimportant data, thereby improving analysis efficiency.

[0053] In one possible implementation, before acquiring the current input data, the method further includes: acquiring the number of times the first target data was accessed during the historical analysis process; if the number of times the first target data was accessed is greater than a set threshold, then the first target data is determined to be frequently used data.

[0054] In one possible implementation, after determining that the first target data is frequently used data, the method further includes: transferring the frequently used data to a high-speed storage medium, wherein the read / write speed of the high-speed storage medium is higher than the read / write speed of the storage medium before the frequently used data is transferred.

[0055] For example, the categorized storage module is used to store frequently accessed data in a fast-response storage medium, such as a high-speed storage medium. For example, high-speed storage media include, but are not limited to, SSDs (Solid State Drives), in-memory databases, and caches.

[0056] It's important to note that high-frequency data refers to data that is frequently accessed and updated. This data is crucial for system responsiveness and performance. By storing high-frequency data in fast-response storage media (such as SSDs, in-memory databases, and caches), data access speed can be significantly improved, thereby enhancing overall system performance. Frequently used data is directly categorized and stored in fast-response storage media so that it can be quickly retrieved during subsequent data analysis, improving overall analysis efficiency.

[0057] In one possible implementation, before obtaining the number of times the first target data was accessed during the historical analysis process, the method further includes: using data tracking software to monitor data interactions during the data analysis process; when data in the data storage module is accessed during the data analysis process, the data tracking software captures and records the data and frequency of the access.

[0058] For example, data tracking software Elasticsearch is used to monitor data interactions between the data analytics module and the data storage module. When the data analytics module requests access to data in the data storage module, the data tracking software captures and records the data and frequency of this access.

[0059] Furthermore, a counter can be configured in the data tracking software to record the number of times each data item is searched.

[0060] For example, the power grid data analysis system also includes a frequency recording module. Leveraging Elasticsearch's distributed search and analysis capabilities, the frequency recording module can quickly process large numbers of data access requests, ensuring that every data interaction is accurately captured, providing a reliable data source for subsequent data analysis.

[0061] The frequency recording module periodically (e.g., every hour) analyzes the lookup frequency of each data item. When the lookup frequency of a data item exceeds a preset threshold, it is automatically marked as frequently used data. The threshold can be set to a value that is used more than 10 times when the data analysis module analyzes the data in the data storage module. This threshold can be adjusted according to actual conditions, such as based on the median or variance of the number of times all data items are used. The setting should be tailored to the specific circumstances.

[0062] It should also be noted that the frequency recording module can also introduce data classification and tag management functions, which makes it easier for system administrators to manage and optimize data. By adding classification tags to data items, system administrators can more intuitively understand the attributes and uses of the data, thereby formulating more accurate data optimization strategies.

[0063] In one possible implementation, after determining that the first target data is frequently used data, the method further includes: acquiring second target data accessed during historical analysis; if the type of the second target data is the same as the type of the first target data, then determining that the second target data is frequently used data, wherein the first target data is frequently used data; and transferring the second target data to a high-speed storage medium.

[0064] For example, the power grid data analysis system may also include an optimization module. After the frequency recording module marks a piece of data as high-frequency usage data, the optimization module can directly transfer it to a fast-response storage medium for storage when storing high-frequency usage data of this type in subsequent transactions.

[0065] Furthermore, data type models can be built to identify frequently used data. The model building process will be introduced below.

[0066] Step 1: Preprocess the high-frequency usage data through the optimization module. After completing the preprocessing step, extract features from the high-frequency usage data.

[0067] Preprocessing may include data cleaning (removing invalid or erroneous data), data formatting (converting data to a uniform format), and data normalization (scaling data to the same scale). After preprocessing, feature extraction is performed. These features can be structural features of the data (such as field types, table structures, etc.) or content features (such as keywords in text, objects in images, etc.).

[0068] Step 2: Divide the extracted features into training dataset and validation dataset. Then, use the training dataset to build a model. After the model is built, use the validation dataset to validate the model.

[0069] It is important to note that the choice and construction of the model depends on the type and characteristics of the data. For example, for structured data, rule-based methods or machine learning algorithms (such as decision trees, support vector machines, etc.) can be used to build the model; for unstructured data, such as text or images, natural language processing (NLP) or computer vision techniques can be used to extract features and build the model.

[0070] After the model is built, during subsequent data storage, the data is input into the trained model, and the data type is determined based on the model's output. Then, the optimization module directly stores the frequently used data of the same type into a fast-response storage medium.

[0071] In one possible implementation, if the type of the second target data is the same as the type of the first target data, before determining that the second target data is high-frequency data, the method further includes: inputting the second target data into a pre-trained data type model to obtain the type of the second target data, wherein the data type model is trained based on multiple first target data, and the first target data is high-frequency data; and determining whether the type of the second target data is the same as the type of the first target data.

[0072] Figure 3 This is a schematic diagram of the power grid data analysis system provided in an embodiment of the present invention; see attached diagram. Figure 3This invention discloses a multi-level power grid investment benefit data analysis system, comprising: a data analysis module, a data storage module, a frequency recording module, an analysis result recording module, a processing terminal, a judgment module, a classification storage module, and an optimization module. The system centrally stores power grid investment benefit data through the data storage module, and the data analysis module performs benefit analysis on it. The frequency recording module records the number of data searches and marks frequently used data. The analysis result recording module records and stores each analysis result. The processing terminal processes the analysis result data, and the judgment module distinguishes between data with significant impact and important sensitive data. The classification storage module stores high-frequency data on a high-speed storage medium, stores important data in an enterprise-level database, compresses and stores data with significant impact, and encrypts and stores important sensitive data.

[0073] The following comprehensive embodiment illustrates the application process of the power grid data analysis method provided by the present invention: First, data is collected from multiple data sources and stored in the data storage module. Then, the data analysis module extracts data from the data storage module according to a pre-defined analysis logic and sequence, performing analysis and processing to generate a series of analysis results. These results are captured in real-time and transmitted to the analysis result recording module. This module utilizes a data interface to ensure the timeliness and integrity of the data and stores it in the distributed database MongoDB, while performing rigorous data validation to guarantee accuracy and consistency. In the analysis result recording module, the processing terminal sorts the analysis results according to the analysis order of the data analysis module.

[0074] Next, the processing terminal calculates the rate of change between adjacent analysis results to identify data fluctuations. When the rate of change of a certain analysis result exceeds a preset threshold, the data is marked as important data (data with significant impact or important and sensitive data), indicating that it may represent a significant change or anomaly. Simultaneously, to identify high-frequency data, the system may perform further statistical analysis on the analysis results, such as calculating the frequency of data occurrences or counting the number of times a data value repeats within a certain period. Through this method, the system can identify data that occurs frequently or has significant repetition; this data is considered high-frequency data.

[0075] Finally, the system will comprehensively determine which data is high-frequency and which is important based on the rate of change and frequency of occurrence of the analysis results. This information will be used to support business decisions, trigger alarm mechanisms, or perform further business logic processing, thereby helping organizations better understand and utilize their data resources.

[0076] The multi-level power grid data analysis method provided by this invention has the following beneficial effects: 1. Through the collaborative work of the data analysis module, frequency recording module, and processing terminal, the system can accurately analyze the importance of data. The frequency recording module records the number of times data is searched and marks frequently used data; the processing terminal calculates the rate of change of adjacent analysis results to determine important data, thereby ensuring that key data receives timely attention and effective processing.

[0077] 2. Through a judgment module and a classification storage module, the system can classify this data into data with significant impact and data of high importance and sensitivity. This classification not only helps in understanding the characteristics and impact of the data, but also enables the data to be stored in appropriate storage media. For example, high-frequency data can be stored in fast-response storage media, while important data can be stored in an enterprise-level database, greatly improving the speed and efficiency of subsequent data access.

[0078] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0079] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0080] Figure 4 A schematic diagram of the power grid data analysis device provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below: like Figure 4 As shown, the power grid data analysis device 4 includes: The acquisition module 41 is used to acquire the current input data, as well as the historical input data and their corresponding historical analysis results; Module 42 is used to obtain the current analysis results of the power grid based on the current input data; Module 43 is used to determine the rate of change of the current analysis result based on historical analysis results; The judgment module 44 is used to determine the current input data as important data if the rate of change is greater than a preset value; The first determination module 45 is used to determine that the current input data is data with a magnitude impact if the current input data is important data and the difference in magnitude between the current input data and the historical input data is greater than a preset threshold. The second determination module 46 is used to determine that the current input data is important and sensitive data if the current input data is important data and the difference in magnitude between the current input data and the historical input data is no greater than a preset threshold. Analysis module 47 is used for power grid data analysis based on data with significant impact and important sensitive data.

[0081] This invention determines the rate of change of the current analysis results based on historical analysis results, using this rate as a measure of the degree of influence on the analysis results. Data is then categorized based on this rate of change to identify key data that significantly impacts the analysis results. Furthermore, data with magnitude-based impact and sensitive data are categorized based on their order of magnitude. This refined classification of data impact types helps users gain a deeper understanding of the specific ways and degrees different data affect the power grid data analysis results, providing a more targeted basis for subsequent data processing and decision-making. In massive datasets, this refined classification of data impact types helps quickly identify key data that significantly impacts the analysis results. Analysts can prioritize and process these critical data points instead of spending excessive time on unimportant data, thereby improving analysis efficiency.

[0082] In one possible implementation, determining the rate of change of the current analysis result based on historical analysis results includes: Sort the historical and current analysis results in chronological order to determine the previous analysis result of the current analysis result; Based on the results of the previous analysis and the current analysis, determine the rate of change of the current analysis results.

[0083] In one possible implementation, determining the rate of change of the current analysis result based on the previous analysis result and the current analysis result includes: The rate of change of the current analysis results is determined based on the following formula. in, This indicates the current analysis results. This indicates the result of the previous analysis.

[0084] In one possible implementation, prior to power grid data analysis based on data with significant impact and important sensitive data, the following steps are also included: Data with significant impact and important sensitive data are classified and stored separately. Data with significant impact is compressed before storage, while important sensitive data is encrypted before storage.

[0085] In one possible implementation, before obtaining the current input data, the following is also included: Obtain the number of times the primary target data was accessed during the historical analysis process; If the number of accesses to the first target data exceeds a set threshold, then the first target data is determined to be frequently used data.

[0086] In one possible implementation, after determining that the first target data is frequently used data, the following is also included: Frequently used data is transferred to high-speed storage media, where the read and write speeds of the high-speed storage media are higher than those of the original storage media.

[0087] In one possible implementation, before obtaining the number of accesses to the first target data during the historical analysis process, the following is also included: Use data tracking software to monitor data interactions during the data analysis process; When data is accessed in the data storage module during data analysis, the data tracking software captures and records the data accessed and the frequency of the access.

[0088] In one possible implementation, after determining that the first target data is frequently used data, the following is also included: Acquire the second target data accessed during the historical analysis process; If the type of the second target data is the same as the type of the first target data, then the second target data is determined to be high-frequency data, wherein the first target data is high-frequency data. The second target data is transferred to a high-speed storage medium.

[0089] In one possible implementation, if the type of the second target data is the same as the type of the first target data, before determining that the second target data is frequently used data, the following steps are also included: The second target data is input into a pre-trained data type model to obtain the type of the second target data. The data type model is trained based on multiple first target data, which are frequently used data. Determine whether the type of the second target data is the same as the type of the first target data.

[0090] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0091] Those skilled in the art will recognize that the templates, units, and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0092] If the module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various power grid data analysis method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0093] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A power grid data analysis method, characterized in that, include: Obtain the current input data, as well as historical input data and their corresponding historical analysis results; Based on the current input data, the current analysis results of the power grid are obtained; Based on the historical analysis results, determine the rate of change of the current analysis results; If the rate of change is greater than a preset value, the current input data is determined to be important data; If the current input data is important data, and the difference in magnitude between the current input data and the historical input data is greater than a preset threshold, then the current input data is determined to be data with a magnitude impact. If the current input data is important data, and the difference in magnitude between the current input data and the historical input data is no greater than a preset threshold, then the current input data is determined to be important and sensitive data. Power grid data analysis is conducted based on the aforementioned impactful and sensitive data.

2. The power grid data analysis method according to claim 1, characterized in that, Based on the historical analysis results, the rate of change of the current analysis results is determined as follows: The historical analysis results and the current analysis results are sorted in chronological order to determine the previous analysis result of the current analysis result; Based on the previous analysis results and the current analysis results, the rate of change of the current analysis results is determined.

3. The power grid data analysis method according to claim 2, characterized in that, Based on the previous analysis results and the current analysis results, the rate of change of the current analysis results is determined by: The rate of change of the current analysis results is determined based on the following formula. in, This indicates the current analysis results. This indicates the result of the previous analysis.

4. The power grid data analysis method according to claim 1, characterized in that, Before conducting power grid data analysis based on the aforementioned impactful and sensitive data, the following steps are also included: The data with significant impact and the data with important sensitivity are classified and stored separately. The data with significant impact is compressed before storage, and the data with important sensitivity is encrypted before storage.

5. The power grid data analysis method according to claim 1, characterized in that, Before obtaining the current input data, the method further includes: Obtain the number of times the primary target data was accessed during the historical analysis process; If the number of accesses to the first target data exceeds a set threshold, then the first target data is determined to be frequently used data.

6. The power grid data analysis method according to claim 5, characterized in that, After determining that the first target data is frequently used data, the method further includes: The frequently used data is transferred to a high-speed storage medium, wherein the read / write speed of the high-speed storage medium is higher than that of the storage medium before the frequently used data was transferred.

7. The power grid data analysis method according to claim 5, characterized in that, Before the process of obtaining the number of accesses to the first target data during the historical analysis, the method further includes: Use data tracking software to monitor data interactions during the data analysis process; When data is accessed in the data storage module during data analysis, the data tracking software captures and records the data accessed and the frequency of the access.

8. The power grid data analysis method according to claim 7, characterized in that, After determining that the first target data is frequently used data, the method further includes: Acquire the second target data accessed during the historical analysis process; If the type of the second target data is the same as the type of the first target data, then the second target data is determined to be high-frequency data, wherein the first target data is high-frequency data; The second target data is transferred to a high-speed storage medium.

9. The power grid data analysis method according to claim 8, characterized in that, If the type of the second target data is the same as the type of the first target data, then before determining that the second target data is high-frequency data, the process further includes: The second target data is input into a pre-trained data type model to obtain the type of the second target data, wherein the data type model is trained based on multiple first target data, and the first target data is frequently used data; Determine whether the type of the second target data is the same as the type of the first target data.

10. A power grid data analysis device, characterized in that, include: The acquisition module is used to acquire the current input data, as well as the historical input data and their corresponding historical analysis results; The module is used to obtain the current analysis result of the power grid based on the current input data; The determination module is used to determine the rate of change of the current analysis result based on the historical analysis results; The judgment module is used to determine the current input data as important data if the rate of change is greater than a preset value; The first determination module is used to determine that the current input data is data with a magnitude impact if the current input data is important data and the difference in magnitude between the current input data and the historical input data is greater than a preset threshold. The second determination module is used to determine that the current input data is important and sensitive data if the current input data is important data and the difference in magnitude between the current input data and the historical input data is not greater than a preset threshold. The analysis module is used to perform power grid data analysis based on the aforementioned impactful and sensitive data.

Images