Safety evaluation system for comprehensive platform of photovoltaic power plant

Abstract

The invention provides a photovoltaic power plant comprehensive platform safety evaluation system, and belongs to the technical field of photovoltaic power plant safety. The system comprises a data acquisition module which is used for determining a data source of a target to obtain original data and storing the original data into a corresponding data lake; the data processing module formulates a data processing rule according to the type of the original data, and preprocesses the original data of any data lake to obtain standard data; the data space module is used for screening the standard data of any data lake to obtain key data and constructing a data space model; according to the encryption module, data space models of different data source providers are mutually encrypted through encryption protocol design, and the data space models complete a data calculation task in a calculation model; and the sharing module is used for adding noise of preset parameters when the data results of all the data sources are published, obtaining an overall data set and displaying statistical characteristics of the overall data set. The integrity and authenticity of the data are ensured, and the safety evaluation result is more accurate and reliable.

Description

Technical Field

[0001] The present invention relates to the technical field of security assessment, and particularly to a comprehensive security assessment system for a photovoltaic power plant. Background Art

[0002] At present, many photovoltaic power plants have started to apply big data technology, and the security of data has become increasingly important. It is necessary to protect the security of the data of photovoltaic power plants and customer information, and ensure the integrity and compliance of the operation of photovoltaic power plants. Usually, the trusted data space directly processes multi-party data and then returns it to the data provider. This method makes the data cumbersome and cannot guarantee the security of the data.

[0003] Therefore, the present invention proposes a comprehensive security assessment system for a photovoltaic power plant, which can ensure the integrity and authenticity of data, and make the security assessment results more accurate and reliable. Summary of the Invention

[0004] The present invention provides a comprehensive security assessment system for a photovoltaic power plant, which is used to obtain the original data of the data source of the data provider through an interface, perform data processing to generate a corresponding data space model, and finally summarize and encrypt for overall analysis, and finally display the statistical characteristics of the overall data set, but the individual information of the data results cannot be identified and displayed.

[0005] On the one hand, the present invention provides a comprehensive security assessment system for a photovoltaic power plant, including:

[0006] Data acquisition module: Determine the data source of the target, use the interface to obtain the original data of all data sources, and store the original data in the data lakes corresponding to different data sources;

[0007] Data processing module: Formulate data processing rules according to the type of original data, and preprocess the original data of any data lake to obtain standard data;

[0008] Data space module: Screen the standard data of any data lake according to the key data rules to obtain key data, and construct a data space model according to the basic parameters of the key data;

[0009] Encryption module: Through the design of encryption protocols, the data space models provided by different data source providers are encrypted with each other, and all data space models complete data calculation tasks in the calculation model to obtain corresponding data results;

[0010] Sharing module: When the data results of all data sources are published, add noise with preset parameters to obtain an overall data set and display the statistical characteristics of the overall data set, but the individual information of the data results cannot be identified and displayed.

[0011] On the other hand, the data acquisition module includes:

[0012] Data source unit: Determine the data source to be connected according to business requirements and data analysis objectives;

[0013] Interface unit: Configure the corresponding API client parameters according to the data sources of all data sources; Build an interface for the corresponding data source based on the API client parameters, connect the data source to the interface of the corresponding data source, and obtain the original data of the interface of the data source.

[0014] On the other hand, the data collection module further includes:

[0015] Data cleaning unit: Preprocess the original data of the interface of any data source obtained, screen and remove useless dirty data to obtain the original data of the data source;

[0016] Data lake construction unit: Preset the data lake directory interface for the data source according to the data type characteristics of the data source, and construct a data lake;

[0017] Data storage unit: Use a data upload tool to upload the original data of the data source to the corresponding data lake.

[0018] On the other hand, the data processing module includes:

[0019] First data rule unit: Analyze the format of the original data of any data lake, determine the final conversion format for standardizing different formats of data, and generate a first data processing rule; The original data of the data lake includes formatted data and unformatted data;

[0020] Second data rule unit: Obtain the data type and data structure of the original data of the data lake, and match the unit rule corresponding to the original data according to the data type - data structure - unit rule mapping table. All unit rules constitute the second data processing rule of the data source.

[0021] On the other hand, the data processing module further includes:

[0022] Data processing unit: Process any data in the data lake according to the first data processing rule and the second data processing rule. Specifically:

[0023] Among them, d i represents the first unit data after the i-th data is processed by the first data rule, n represents that there are n data in the data lake, x i represents the i-th data of the original data of the data lake, x min represents the minimum value of the original data of the data lake, x max represents the maximum value of the original data of the data lake, x avgrepresents the mean of the original data in the data lake, σi represents the absolute difference between the variance of the i-th data and the original data in the data lake, and ln represents the logarithmic function;

[0024] Match the first result with the second data processing rule, match the corresponding unit rule and process the first unit data to obtain the second unit data. All the second unit data constitute the standard data of the data lake and are stored in the corresponding data lake.

[0025] On the other hand, the data space module includes:

[0026] Key data indicator unit: Based on the business requirements of any data lake prototype data source, obtain the key data indicators of the data lake, and obtain the standard thresholds of the key data indicators according to the historical records in the expert database;

[0027] Screening unit: According to the key data indicators and the standard thresholds of the key data indicators, formulate the key data rules of the data lake, and formulate the data screening steps. Based on the key data rules and the data screening steps, obtain the key data from the standard data of the data lake;

[0028] Data space model unit: Create the basic parameters of dimensions and metrics in the data space model according to the key data indicators corresponding to the key data, build the foundation of the data architecture, and then load the key data rules into the data architecture to form the data space model.

[0029] On the other hand, the encryption module includes:

[0030] Encryption unit: According to the secure multi-party computing protocol, split the data into multiple parts, and then use the SMC encryption technology to encrypt the data space models provided by different data sources, and transmit the data results of the data space model to the computing model;

[0031] Computing unit: According to the preset data calculation task, add a key to decrypt the combined data result of all data source providers to obtain the original combined data, and run the preset data calculation task on the original combined data to obtain the original data result;

[0032] Data distribution unit: According to the data source id of any original unit data in the original data result, return this data to the corresponding data source provider.

[0033] On the other hand, the sharing module includes:

[0034] Display parameter unit: Extract the data statistical characteristics of the preset original data result to obtain the display parameters;

[0035] Noise unit: Select the noise addition mechanism to obtain the noise distribution parameters according to the privacy requirements and data statistical characteristics;

[0036] Publication unit: Add the display parameters and noise distribution parameters to the original data result to generate an overall data set, and display the statistical characteristics of the overall data set, but the individual information of the original data result cannot be displayed in an identifiable manner;

[0037] Review unit: Review the published overall data set, determine whether the accuracy of noise addition and statistical characteristics meets the preset, obtain feedback, and adjust the noise parameters according to the feedback.

[0038] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0039] The present invention provides a comprehensive safety assessment system for a photovoltaic power plant, which is used to obtain the original data of the data source of the data provider through an interface, generate a corresponding data space model through data processing, and finally summarize and encrypt for overall analysis, and finally display the statistical characteristics of the overall data set, but the individual information of the data result cannot be displayed in an identifiable manner. Description of the Drawings

[0040] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0041] Figure 1 It is a schematic structural diagram of a comprehensive safety assessment system for a photovoltaic power plant provided by an embodiment of the present invention. Detailed Embodiments

[0042] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0043] Embodiment 1:

[0044] As Figure 1 shown, a comprehensive safety assessment system for a photovoltaic power plant provided by an embodiment of the present invention includes:

[0045] Data acquisition module: Determine the data sources of the targets, use the interface to obtain the original data of all data sources, and store the original data in the data lakes corresponding to different data sources;

[0046] Data Processing Module: Formulate data processing rules according to the original data type, and preprocess the original data of any data lake to obtain standard data;

[0047] Data Space Module: Screen the standard data of any data lake according to the key data rules to obtain key data, and construct a data space model based on the basic parameters of the key data;

[0048] Encryption Module: Through encryption protocol design, the data space models of different data source providers are encrypted with each other, and all data space models complete data calculation tasks in the calculation model to obtain corresponding data results;

[0049] Sharing Module: When the data results of all data sources are published, add noise with preset parameters to obtain the overall data set and display the statistical characteristics of the overall data set, but the individual information of the data results cannot be displayed in an identifiable manner.

[0050] In this embodiment, the data source refers to the system from which the original data is obtained, including: different databases, application programs, sensors, log files, or other data storage systems.

[0051] In this embodiment, the interface refers to the interface used for data interaction in a system or application program.

[0052] In this embodiment, the original data is the unprocessed data directly obtained from the data source.

[0053] In this embodiment, the data lake is a system that stores a large amount of original data and stores data from different data sources in the original format.

[0054] In this embodiment, the original data type is the specific format or category of the data obtained by the data acquisition module.

[0055] In this embodiment, the data processing rules are the operations and standards for converting the original data into standard data.

[0056] In this embodiment, the preprocessing is the process of converting the original data into standard data, including data cleaning, data conversion, and data integration.

[0057] In this embodiment, the standard data is the data after preprocessing, which conforms to the unified format and quality standards.

[0058] In this embodiment, the key data rules are the data standards used to screen and identify the data important for business analysis.

[0059] In this embodiment, the key data refers to the important data set screened from the standard data in the data space module.

[0060] In this embodiment, the basic parameters refer to the core data attributes or metrics used when constructing the data space model.

[0061] In this embodiment, the data space model integrates the standard data extracted from different data sources according to specific rules and parameters to form a unified model that can be further processed and analyzed.

[0062] In this embodiment, the encryption protocol is a standardized method for protecting data security, which ensures that data is not accessed by unauthorized parties during transmission, storage, or processing through encryption technology.

[0063] In this embodiment, the computational model is a mathematical or algorithmic framework for processing and analyzing data.

[0064] In this embodiment, the data calculation task refers to the process of processing and analyzing the encrypted data space model in the computational model.

[0065] In this embodiment, the data result refers to the final output data obtained after calculating the encrypted data space model in the computational model.

[0066] In this embodiment, the preset parameters refer to the parameters used in the sharing module to add noise to protect individual data privacy, including the type, intensity, and distribution rules of the noise.

[0067] In this embodiment, the noise refers to the random perturbation added to the data result to protect individual information privacy.

[0068] In this embodiment, the overall data set refers to the comprehensive data set obtained by combining the calculation results of all data sources.

[0069] In this embodiment, the statistical characteristics refer to the numerical characteristics that describe the overall distribution and trend of the data set, such as mean, variance, standard deviation, median, and quantiles.

[0070] The working principle and beneficial effects of the above technical solution are as follows: Through the data collection, processing, encryption, and sharing modules, data privacy protection and secure sharing are achieved. Encryption and noise addition technologies protect data privacy, standardized processing improves data processing efficiency, meets compliance requirements, and supports cross-data source collaboration and flexible applications.

[0071] Embodiment 2:

[0072] Based on the above Embodiment 1, the data collection module includes:

[0073] Data source unit: Determine the data source to be targeted according to business requirements and data analysis objectives;

[0074] Interface Unit: Configure corresponding API client parameters according to the data sources of all data sources; build an interface for the corresponding data source based on the API client parameters, connect the data source to the interface of the corresponding data source, and obtain the original data of the interface of the data source.

[0075] In this embodiment, business requirements refer to the data and information required to achieve specific business goals or solve specific problems.

[0076] In this embodiment, the data analysis objective refers to the specific purpose hoped to be achieved through data analysis activities.

[0077] In this embodiment, the data source refers to the original source from which the data is obtained.

[0078] In this embodiment, API client parameters are used to configure and manage the settings of API requests, including: API keys, endpoints, request methods, request headers, etc.

[0079] The working principle and beneficial effects of the above technical solution are: realizing data docking through the data source unit and the interface unit, and configuring API parameters to obtain the original data. This method improves the accuracy and efficiency of data acquisition, ensures the reliability of the data source, and provides a basis for subsequent analysis.

[0080] Embodiment 3:

[0081] Based on the above Embodiment 2, the data acquisition module further includes:

[0082] Data Cleaning Unit: Preprocess the original data of the interface of any data source obtained, screen and remove useless dirty data to obtain the original data of the data source;

[0083] Data Lake Construction Unit: Preset the data lake directory interface of the data source according to the data type characteristics of the data source, and construct a data lake;

[0084] Data Storage Unit: Use a data upload tool to upload the original data of the data source to the corresponding data lake.

[0085] In this embodiment, useless dirty data refers to the incorrect, incomplete or irrelevant data existing in the data set.

[0086] In this embodiment, data type characteristics refer to the characteristics and structures of the data, including: data format, data type, data distribution, etc.

[0087] In this embodiment, the directory interface is used to define and manage the storage and organizational structure of data in the data lake.

[0088] In this embodiment, the data upload tool is a tool for transferring data from a source system to a data lake or other storage systems, including tools such as Apache Nifi, AWS Glue, and Azure Data Factory.

[0089] The working principle and beneficial effects of the above technical solution are as follows: By processing and removing useless data through the data cleaning unit, the cleaned data is uploaded to the constructed data lake, improving data quality and storage structure, and ensuring efficient data management and subsequent analysis.

[0090] Embodiment 4:

[0091] Based on the above Embodiment 1, the data processing module includes:

[0092] The first data rule unit: Analyze the format of the original data of any data lake, determine the final conversion format for standardizing data in different formats, and generate the first data processing rule; the original data of the data lake includes formatted data and unformatted data;

[0093] The second data rule unit: Obtain the data type and data structure of the original data of the data lake, and according to the data type - data structure - unit rule mapping table, match the unit rule corresponding to the original data, and all unit rules constitute the second data processing rule of the data source.

[0094] In this embodiment, standardization is a process of converting data from different sources or formats into a unified format or structure during data processing.

[0095] In this embodiment, the final conversion format is the unified format into which the original data is converted during data processing.

[0096] In this embodiment, the first data processing rule is to analyze the format of the original data in the data lake and standardize these different formats of data into a unified final conversion format.

[0097] In this embodiment, formatted data refers to data that has been organized and structured according to certain rules, including: tables, delimiters, SQL data, etc.

[0098] In this embodiment, unformatted data refers to data without a clear structure or fixed format, including: text files, multimedia data, social media data, etc.

[0099] In this embodiment, the data structure refers to the organization method and storage form of data in computer memory.

[0100] In this embodiment, the data type - data structure - unit rule mapping table refers to a table of the mapping relationship between the data type and the unit rule corresponding to the data structure.

[0101] In this embodiment, the unit rule is the specific conversion and processing rule for each data unit in the data processing process.

[0102] In this embodiment, the second data processing rule is a set of detailed data processing and conversion rules formulated based on the analysis result of the first data rule unit and the data type - data structure - unit rule mapping table.

[0103] The working principle and beneficial effects of the above technical solution are as follows: The first data rule unit standardizes the data format, and the second data rule unit matches the data type and structure to generate a processing rule, ensuring data consistency and structurization, and improving the accuracy and efficiency of processing.

[0104] Embodiment 5:

[0105] Based on the above Embodiment 4, the data processing module further includes:

[0106] A data processing unit: processes any data in the data lake according to the first data processing rule and the second data processing rule. Specifically:

[0107] where, d i represents the first unit data after the i-th data is processed by the first data rule, n represents that there are n data in the data lake in total, x i represents the i-th data of the original data in the data lake, x min represents the minimum value of the original data in the data lake, x max represents the maximum value of the original data in the data lake, x avg represents the mean value of the original data in the data lake, σi represents the absolute difference between the i-th data and the variance of the original data in the data lake, and ln represents the logarithmic function;

[0108] Match the first result with the second data processing rule, match the corresponding unit rule and process the first unit data to obtain the second unit data. All the second unit data constitute the standard data of the data lake and are stored in the corresponding data lake.

[0109] In this embodiment, the first unit data refers to the data result after being processed by the first data processing rule.

[0110] In this embodiment, the second unit data is the first unit data after being processed by the second data processing rule.

[0111] The working principle and beneficial effects of the above technical solution are as follows: The data processing unit processes the data in the data lake according to rules to generate standardized data. By calculating the absolute difference of variances and matching the processing rules, data consistency and accuracy are ensured, and the efficiency of data management and analysis is improved.

[0112] Example 6:

[0113] Based on the above Example 1, the data space module includes:

[0114] Key data indicator unit: Based on the business requirements of any data lake prototype data source, obtain the key data indicators of the data lake, and obtain the standard thresholds of the key data indicators according to the historical records in the expert database;

[0115] Screening unit: According to the key data indicators and the standard thresholds of the key data indicators, formulate the key data rules of the data lake, and formulate data screening steps, and obtain key data from the standard data of the data lake based on the key data rules and data screening steps;

[0116] Data space model unit: Create the dimension and measure basic parameters in the data space model according to the key data indicators corresponding to the key data, build the foundation of the data architecture, and then load the key data rules into the data architecture to form the data space model.

[0117] In this embodiment, the business requirements refer to the specific goals and requirements in the data lake system, including: key data indicators, standard thresholds, data space models, etc.

[0118] In this embodiment, the key data indicators usually include sales amount, user growth rate, inventory turnover rate, etc.

[0119] In this embodiment, the historical records in the expert database are databases that store the past experience and suggestions of experts, and the records include: the key data indicators and their standard thresholds determined under similar business requirements.

[0120] In this embodiment, the standard threshold is a reference value used to evaluate whether the key data indicator meets the expected standard.

[0121] In this embodiment, the data screening step refers to the process of selecting, cleaning, and processing data in the data lake based on the key data rules.

[0122] In this embodiment, the dimension defines different perspectives and classifications of data. For example, in the sales data model, the dimensions may include time, region, and product.

[0123] In this embodiment, the measure is used to quantify and calculate specific aspects of data, such as sales amount, number of transactions, or profit.

[0124] In this embodiment, the data architecture foundation refers to the basic structure and framework required to build a data space model, including: dimensions, metrics, data models, etc.

[0125] The working principle and beneficial effects of the above technical solution are: by obtaining standard thresholds, formulating screening rules, and building a data model, the key data extraction and analysis of the data lake are optimized, and the accuracy and efficiency of data processing are improved.

[0126] Embodiment 7:

[0127] Based on the above Embodiment 1, the encryption module includes:

[0128] Encryption unit: According to the secure multi-party computation protocol, the data is split into multiple parts, and then the data space models of different data source providers are encrypted using SMC encryption technology, and the data space model data results are transmitted to the computation model;

[0129] Computation unit: According to the preset data computation task, add a key to decrypt the combined data result of all data source providers to obtain the original combined data, and run the preset data computation task on the original combined data to obtain the original data result;

[0130] Data distribution unit: According to the data source id of any original unit data in the original data result, return this data to the corresponding data source provider.

[0131] In this embodiment, the secure multi-party computation protocol is an encryption protocol designed to allow multiple participating parties to jointly compute the result of a function without revealing their respective input data.

[0132] In this embodiment, the SMC encryption technology, that is, the encryption technology in secure multi-party computation, includes: secret sharing, homomorphic encryption, and encryption protocol content.

[0133] In this embodiment, the preset data computation task refers to the computation operations or processing steps defined and set in advance in the secure multi-party computation (SMC) framework.

[0134] In this embodiment, the key is used to input in the algorithm for converting plaintext to ciphertext or ciphertext to plaintext to achieve the encryption and decryption processes.

[0135] In this embodiment, the original combined data refers to the data set obtained after merging the data from all different data source providers in the encrypted state.

[0136] In this embodiment, the data source id is an identifier used to uniquely identify and distinguish the data of different data source providers.

[0137] The working principle and beneficial effects of the above technical solution are as follows: SMC technology is used to encrypt data, the computing unit decrypts and processes the data, and finally distributes the results according to the data source ID. This improves data security and processing accuracy.

[0138] Example 8:

[0139] Based on the above Example 7, the sharing module includes:

[0140] Display parameter unit: Extract the data statistical features of the original data results to be preset for display, and obtain the display parameters;

[0141] Noise unit: Select a noise addition mechanism, and obtain the noise distribution parameters according to privacy requirements and data statistical features;

[0142] Publishing unit: Add the display parameters and noise distribution parameters to the original data results to generate an overall data set, display the statistical characteristics of the overall data set, but the individual information of the original data results cannot be identified and displayed;

[0143] Review unit: Review the published overall data set, judge whether the accuracy of noise addition and statistical characteristics meets the preset and obtain feedback, and adjust the noise parameters according to the feedback.

[0144] In this example, the data statistical features refer to a series of indicators that describe and summarize the data set through mathematical methods, including: mean, median, mode, etc.

[0145] In this example, the display parameters refer to the statistics or metric values used to describe and display the key characteristics of these data sets.

[0146] In this example, the noise addition mechanism is a data privacy protection technology that uses noise.

[0147] In this example, the noise distribution parameters refer to a series of parameters used to describe the characteristics of noise during the noise addition process, such as: mean, variance, standard deviation, distribution shape parameters, etc.

[0148] In this example, the feedback refers to the evaluation and improvement suggestions for the review results of the published overall data set, such as: whether the noise is added sufficiently to ensure data privacy, but not too much to affect the overall statistical characteristics of the data.

[0149] The working principle and beneficial effects of the above technical solution are as follows: By extracting data features, adding noise to protect privacy, generating an overall data set that cannot be identified, and finally reviewing the data accuracy, it ensures privacy protection and the effectiveness of statistical information.

[0150] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements 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.

Claims

1. A photovoltaic power plant comprehensive safety assessment system, characterized in that: include: Data collection module: Determine the target data source, use the interface to obtain the original data of all data sources, and store the original data in the data lake corresponding to different data sources; Data processing module: formulates data processing rules according to the original data type, and pre-processes the original data of any data lake to obtain standard data; Data space module: Filter the standard data of any data lake according to key data rules to obtain key data, and build a data space model based on the basic parameters of the key data; Encryption module: Through encryption protocol design, the data space models of different data source providers are encrypted with each other. All data space models complete the data calculation tasks in the calculation model to obtain the corresponding data results. Sharing module: When the data results of all data sources are released, noise with preset parameters is added to obtain the overall data set and display the statistical characteristics of the overall data set, but the individual information of the data results cannot be identified and displayed.

2. A photovoltaic power plant comprehensive safety assessment system according to claim 1, characterized in that: The data acquisition module comprises: Data source unit: determines the target data source according to business needs and data analysis goals; Interface unit: configure corresponding API client parameters according to the data sources of all data sources; build the interface of the corresponding data source based on the API client parameters, connect the data source to the interface of the corresponding data source and obtain the original interface data of the data source.

3. A photovoltaic power plant comprehensive safety assessment system according to claim 2, characterized in that: The data acquisition module further includes: Data cleaning unit: pre-processing the original data of the interface of any data source, filtering and removing useless dirty data, and obtaining the original data of the data source; A data lake construction unit: according to the data type characteristics of the data source, preset the data lake directory interface of the data source and construct the data lake; Data storage unit: Use the data upload tool to upload the original data of the data source to the corresponding data lake.

4. A photovoltaic power plant comprehensive safety assessment system according to claim 1, characterized in that: The data processing module comprises: The first data rule unit is used to analyze the format of the original data of any data lake, determine the final conversion format of data in different formats, and generate the first data processing rule; the original data of the data lake includes formatted data and unformatted data; Second data rule unit: obtains the data type and data structure of the original data of the data lake, matches the unit rules corresponding to the original data according to the data type-data structure-unit rule mapping table, and all unit rules constitute the second data processing rules of the data source.

5. A photovoltaic power plant comprehensive safety assessment system according to claim 4, characterized in that: The data processing module further includes: Data processing unit: processes any data in the data lake according to the first data processing rule and the second data processing rule, specifically: Among them, d i represents the first unit data after the i-th data is processed by the first data rule, n represents the total number of n data in the data lake, x i represents the i-th data of the original data in the data lake, x min represents the minimum value of the original data in the data lake, x max Represents the maximum value of the original data in the data lake, x avg represents the mean of the original data of the data lake, σi represents the absolute difference between the variance of the i-th data and the original data of the data lake, and ln represents a logarithmic function; The first result is matched with the second data processing rule, the corresponding unit rule is matched and the first unit data is processed to obtain the second unit data, and all the second unit data constitute the standard data of the data lake and are stored in the corresponding data lake.

6. A photovoltaic power plant comprehensive safety assessment system according to claim 1, characterized in that: The data space module comprises: Key data indicator unit: based on the business requirements of any data lake prototype data source, obtain the key data indicators of the data lake, and obtain the standard thresholds of the key data indicators according to the historical records of the expert database; Screening unit: formulating key data rules of the data lake and data screening steps according to the key data indicators and standard thresholds of the key data indicators, and obtaining key data from the standard data of the data lake based on the key data rules and data screening steps; Data space model unit: Create dimensions and basic measurement parameters in the data space model according to the key data indicators corresponding to the key data, build the foundation of the data architecture, and then load the key data rules into the data architecture to form the data space model.

7. A photovoltaic power plant comprehensive safety assessment system according to claim 1, characterized in that: The encryption module comprises: Encryption unit: According to the secure multi-party computing protocol, the data is divided into multiple parts, and then the data space models of different data source providers are encrypted using SMC encryption technology, and the data space model data results are passed to the computing model; Computing unit: according to the preset data computing task, adds a key to decrypt the data results after merging all data source providers to obtain the original merged data, runs the preset data computing task on the original merged data, and obtains the original data result; Data distribution unit: according to the data source id of any original unit data of the original data result, returns the original unit data to the corresponding data source provider.

8. A photovoltaic power plant comprehensive safety assessment system according to claim 7, characterized in that: The sharing module includes: Display parameter unit: extracts the data statistical features of the original data results of the preset display and obtains the display parameters; Noise unit: Select the noise addition mechanism and obtain the noise distribution parameters according to the privacy requirements and data statistical characteristics; Publishing unit: Add the display parameters and noise distribution parameters to the original data results to generate an overall data set and display the statistical characteristics of the overall data set, but the individual information of the original data results cannot be identified and displayed; Review unit: Review the overall published data set to determine whether the accuracy of noise addition and statistical characteristics meets the preset requirements and obtain feedback, and adjust the noise parameters based on the feedback.

Images