Artificial intelligence data acquisition method for smart power grid

Abstract

The invention discloses an artificial intelligence data acquisition method for an intelligent power grid, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring intelligent power grid data through an artificial intelligence data acquisition model; calculating a data security risk assessment value according to the smart grid data; comparing the data security risk assessment value with a preset threshold value; if the data security risk assessment value is not smaller than a preset threshold value, checking or eliminating potential safety hazard elements of the smart power grid data; and if the data security risk assessment value is smaller than a preset threshold value, inputting the acquired smart grid data into the artificial intelligence data acquisition model again for training so as to realize optimization of the artificial intelligence data acquisition model. According to the invention, the artificial intelligence model is adopted to carry out data acquisition on the smart power grid, and the acquired data is subjected to security verification, so that the efficiency and accuracy of data acquisition of the smart power grid are improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence data collection method for a smart grid. Background Art

[0002] Smart grid is the intelligence of power grid, also known as "Grid 2.0". It is built on the basis of integrated, high-speed two-way communication network. Through the application of advanced sensing and measurement technology, advanced equipment technology, advanced control methods and advanced decision support system technology, it realizes the goals of reliable, safe, economical, efficient, environmentally friendly and safe use of power grid. Its main features include self-healing, motivating and protecting users, resisting attacks, providing power quality that meets user needs, allowing access to various forms of power generation, launching electricity market and optimizing and efficient operation of assets.

[0003] The existing smart grid data collection generally only performs data reading operations such as manual meter reading, which wastes manpower and time, and does not verify the security of the grid, and cannot guarantee the accuracy of meter reading data. Based on this, the present invention proposes an artificial intelligence data collection method for smart grids. Summary of the invention

[0004] The present invention provides an artificial intelligence data collection method for a smart grid, comprising:

[0005] Collect smart grid data through artificial intelligence data collection models;

[0006] Calculate data security risk assessment values ​​based on smart grid data;

[0007] Compare the data security risk assessment value with the preset threshold;

[0008] If the data security risk assessment value is not less than the preset threshold, the security risk factors of the smart grid data are checked or eliminated;

[0009] If the data security risk assessment value is less than the preset threshold, the collected smart grid data will be input into the artificial intelligence data collection model again for training to achieve the optimization of the artificial intelligence data collection model.

[0010] The method for collecting artificial intelligence data for a smart grid as described above, wherein the method for constructing the artificial intelligence data collection model comprises the following sub-steps:

[0011] Collect historical smart grid data;

[0012] Extract features from the collected data to form a smart grid feature data set;

[0013] Use smart grid feature data sets to train artificial intelligence data acquisition models.

[0014] An artificial intelligence data collection method for smart grid as described above, wherein the smart grid data includes basic grid data and grid security data, the basic grid data includes electric energy data, voltage data, current data, and power load data, and the grid security data includes grid equipment status data, grid system performance data, grid health operation parameter data, and grid communication data.

[0015] As described above, an artificial intelligence data collection method for smart grids is used, wherein the artificial intelligence data collection model is trained using a smart grid feature data set, specifically: multiple sub-data models are selected, and multiple sub-classification models are used to comprehensively construct an artificial intelligence data collection model.

[0016] The method for collecting artificial intelligence data for smart grid as described above, wherein the potential safety hazard elements of smart grid data are checked or eliminated, specifically including:

[0017] Start the safety hazard investigation procedure; formulate a detailed investigation plan and determine the scope, objectives and methods of the investigation;

[0018] Formulate elimination measures based on the analysis results of potential safety hazards;

[0019] Implement corresponding measures step by step according to the formulated elimination measures plan.

[0020] The present invention also provides an artificial intelligence data acquisition system for a smart grid, comprising:

[0021] A collection module for collecting smart grid data through an artificial intelligence data collection model;

[0022] The security verification module is used to calculate the data security risk assessment value based on the smart grid data; compare the data security risk assessment value with the preset threshold; if the data security risk assessment value is not less than the preset threshold, check or eliminate the security risk factors of the smart grid data; if the data security risk assessment value is less than the preset threshold, trigger the model optimization module;

[0023] The model optimization module is used to input the collected smart grid data into the artificial intelligence data acquisition model again for training to achieve the optimization of the artificial intelligence data acquisition model.

[0024] As described above, an artificial intelligence data acquisition system for a smart grid, wherein the construction of the artificial intelligence data acquisition model includes: collecting historical smart grid data; performing feature extraction on the collected data to form a smart grid feature data set; and using the smart grid feature data set to train the artificial intelligence data acquisition model.

[0025] An artificial intelligence data acquisition system for a smart grid as described above, wherein the smart grid data includes basic grid data and grid security data, the basic grid data includes electric energy data, voltage data, current data, and power load data, and the grid security data includes grid equipment status data, grid system performance data, grid health operation parameter data, and grid communication data.

[0026] As described above, an artificial intelligence data acquisition system for smart grids is used, wherein the artificial intelligence data acquisition model is trained using a smart grid feature data set, specifically by selecting multiple sub-data models and using multiple sub-classification models to comprehensively construct an artificial intelligence data acquisition model.

[0027] As described above, an artificial intelligence data collection system for smart grids, in which safety hazard elements of smart grid data are checked or eliminated, specifically includes: starting a safety hazard check procedure; formulating a detailed check plan to determine the scope, objectives and methods of the check; formulating elimination measures based on the analysis results of safety hazards; and gradually implementing corresponding measures according to the formulated elimination measures plan.

[0028] The beneficial effects achieved by the present invention are as follows: the present invention adopts an artificial intelligence model to collect data from the smart grid, and performs security verification on the collected data, thereby improving the efficiency and accuracy of smart grid data collection. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0030] Figure 1 This is a flow chart of an artificial intelligence data collection method for smart grids provided in Example 1 of the present application. DETAILED DESCRIPTION

[0031] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0032] Embodiment 1

[0033] like Figure 1As shown, the present application provides an artificial intelligence data collection method for a smart grid, the method comprising the following steps:

[0034] Step S1, the data collection center collects smart grid data through the current artificial intelligence data collection model.

[0035] Specifically, the method for constructing the artificial intelligence data acquisition model includes the following sub-steps:

[0036] Step S11, collecting historical power grid basic data and historical power grid security data;

[0037] When constructing an artificial intelligence data acquisition model, it is necessary to use historical acquisition data to train the model. The historical acquisition data includes historical grid basic data and historical grid security data collected simultaneously when collecting grid basic data. Grid basic data includes but is not limited to electric energy data, voltage data, current data, power load data, etc. Grid security data includes but is not limited to grid equipment status data, grid system performance data, grid health operation parameter data, grid communication data, etc.

[0038] Step S12, extracting features from the collected data to form a smart grid feature data set;

[0039] Specifically, the embodiment of the present application forms multiple smart grid feature data sets based on historical power grid basic data and power grid security data, including a main set consisting of historical power grid basic data and historical power grid safety data, a secondary set one consisting of historical power grid basic data and power grid equipment status data, a secondary set two consisting of historical power grid basic data and power grid system performance data, a secondary set three consisting of historical power grid basic data and power grid health operation parameter data, and a secondary set four consisting of historical power grid basic data and power grid communication data.

[0040] Step S13, training multiple sub-data collection models using the smart grid feature data set;

[0041] The training sub-data collection module specifically includes the following sub-steps:

[0042] S131. Selecting the corresponding optimal artificial intelligence model according to the attributes of each secondary set;

[0043] Specifically, the sub-data collection model includes but is not limited to a neural network model, a decision tree model, a support vector machine model, a clustering model, a reinforcement learning model, a deep learning model, a Bayesian model, a genetic algorithm model, a fuzzy logic model, a random deep forest learning model, etc. Different secondary set attributes are trained using different artificial intelligence models, which can improve the training accuracy of the data for the model.

[0044] S132. Input the main set and each secondary set into the corresponding optimal artificial intelligence model respectively, and train to obtain multiple sub-data collection models.

[0045] Step S14, constructing an artificial intelligence data acquisition model based on multiple sub-data acquisition models.

[0046] Specifically, using the formula The estimated weight set of the sub-data model is {η1, η2, η3...η T}, through each sub-data model {ν1(x), ν2(x), ν3(x)...ν T (x)} and its corresponding weight set {μ1, μ2, μ3...μ T} combination to determine the final artificial intelligence data acquisition model: Among them, ξ is the constructed artificial intelligence data acquisition model, T represents the number of sub-data models, η t represents the weight value corresponding to the sub-data model, ν t (x) represents the t-th sub-data model, ψ t represents the optimization coefficient of the t-th sub-data model, n t is the number of iterations of the t-th sub-data model, H t is the degree of fit of the t-th sub-data model to the input features. The optimization coefficient is optimized and updated with each security data collected. The artificial intelligence data collection model obtained by the above training is used to collect smart grid data.

[0047] Return to see Figure 1 , Step S2, the data acquisition center calculates the data security risk assessment value based on the smart grid data.

[0048] In the embodiment of the present application, after the current data is collected using the artificial intelligence data collection model, it is necessary to determine whether the collected data is safe data based on the grid security data in the collected smart grid data, which specifically includes the following sub-steps:

[0049] Step S21, perform anomaly detection on smart grid data and calculate anomaly risk value.

[0050] Specifically, the calculation formula of abnormal risk value is:

[0051]

[0052] Where F represents the calculated abnormal risk value; ξ u represents the abnormal risk characteristic value, βi represents the abnormal risk impact weight; γ represents the total number of abnormal risk categories; τ u represents the weight factor of the u-th abnormal risk; q urepresents the number of the u-th abnormal risk; s u Represents the danger value of the u-th anomaly.

[0053] Step S22, calculating the safety factor component value according to the abnormal risk value, and dividing the safety status level according to the safety factor component value;

[0054] Specifically, the calculation formula for the safety factor component value is:

[0055] Among them, R is the calculated safety factor component value, F u represents abnormal risk value; Y w is the wth safety factor of the sub-data model, including hardware equipment safety factor, smart grid system software safety factor, and network security level. The value of n ranges from 1 to n, where n is the total number of safety factors. is the impact weight of the nth security factor on the security of the sub-data model.

[0056] Step S23, calculating the safety risk assessment value according to the safety factor component value.

[0057] Specifically, the security risk assessment value calculation formula is:

[0058]

[0059] Among them, SI represents the security risk assessment value; θ1 is the influence weight of node characteristics on the security assessment value; θ2 is the influence weight of abnormal data on the security assessment value; e i is the data anomaly characteristic value of the security node of the ith sub-data model; h ρi represents the fluctuation factor of the abnormal data of the ith operating characteristic of the monitored ρth processor; L ρi It represents the continuous abnormal value of the i-th continuous operation characteristic abnormal data of the monitored ρ-th processor; the value of i ranges from 1 to N, where N represents the total number of types of abnormal data of the operation characteristics of the data training model; Rpim represents the standard value for security risk formulation; R is the component value of the security factor;

[0060] Step S3, compare the data security risk assessment value and the preset threshold value. If the data security risk assessment value is not less than the preset threshold value, check or eliminate the potential safety hazard elements of the smart grid data. Otherwise, execute step S4.

[0061] Specifically, the data security risk assessment value and the preset threshold are compared. The data security risk assessment value is calculated through the previous steps and represents the security risk level of smart grid data; the preset threshold is a threshold set according to security policies and requirements to determine whether the data security risk is acceptable.

[0062] If the data security risk assessment value is greater than the preset threshold, perform the following operations to troubleshoot or eliminate security risk factors.

[0063] Step S31, start the safety hazard investigation procedure; formulate a detailed investigation plan, and determine the scope, objectives and methods of the investigation.

[0064] Specifically, it may include inspections of various components, network connections, data storage and transmission of smart grid systems.

[0065] Step S32, formulating elimination measures;

[0066] Specifically, according to the analysis results of security risks, corresponding elimination measures are formulated. This may include repairing system vulnerabilities, updating security configurations, strengthening access control, encrypting sensitive data, etc., to reduce security risks.

[0067] Step S33, implementing elimination measures;

[0068] Specifically, according to the formulated elimination measures plan, corresponding measures are gradually implemented to ensure the effectiveness and timeliness of the measures, and necessary tests and verifications are carried out to ensure that the safety hazards are properly resolved.

[0069] Step S4, the collected smart grid security data is input into the artificial intelligence data acquisition model again for training to optimize the model.

[0070] Specifically, the previously calculated AI model performance goodness values ​​are passed as input to the AI ​​data acquisition model. By combining these performance goodness values ​​with the model's training data, the model can learn and adjust its parameters to improve its performance in data acquisition tasks. In this way, the AI ​​data acquisition model can be continuously optimized and improved to improve the accuracy, efficiency, and reliability of its data acquisition. This helps improve the performance of the model in practical applications, enabling it to process and analyze data more effectively, and provide better support and decision-making basis for related tasks.

[0071] Embodiment 2

[0072] Embodiment 2 of the present invention provides an artificial intelligence data acquisition system for a smart grid, comprising:

[0073] A collection module for collecting smart grid data through an artificial intelligence data collection model;

[0074] The security verification module is used to calculate the data security risk assessment value based on the smart grid data; compare the data security risk assessment value with the preset threshold; if the data security risk assessment value is not less than the preset threshold, check or eliminate the security risk factors of the smart grid data; if the data security risk assessment value is less than the preset threshold, trigger the model optimization module;

[0075] The model optimization module is used to input the collected smart grid data into the artificial intelligence data acquisition model again for training to achieve the optimization of the artificial intelligence data acquisition model.

[0076] Specifically, the method for constructing the artificial intelligence data acquisition model includes the following sub-steps:

[0077] Collect historical power grid basic data and historical power grid security data;

[0078] When constructing an artificial intelligence data acquisition model, it is necessary to use historical acquisition data to train the model. The historical acquisition data includes historical grid basic data and historical grid security data collected simultaneously when collecting grid basic data. Grid basic data includes but is not limited to electric energy data, voltage data, current data, power load data, etc. Grid security data includes but is not limited to grid equipment status data, grid system performance data, grid health operation parameter data, grid communication data, etc.

[0079] Extract features from the collected data to form a smart grid feature data set;

[0080] Specifically, the embodiment of the present application forms multiple smart grid feature data sets based on historical power grid basic data and power grid security data, including a main set consisting of historical power grid basic data and historical power grid safety data, a secondary set one consisting of historical power grid basic data and power grid equipment status data, a secondary set two consisting of historical power grid basic data and power grid system performance data, a secondary set three consisting of historical power grid basic data and power grid health operation parameter data, and a secondary set four consisting of historical power grid basic data and power grid communication data.

[0081] Using smart grid characteristic data sets to train multiple sub-data collection models;

[0082] The training sub-data collection module specifically includes:

[0083] According to the attributes of each secondary set, select the corresponding optimal artificial intelligence model;

[0084] Specifically, the sub-data collection model includes but is not limited to a neural network model, a decision tree model, a support vector machine model, a clustering model, a reinforcement learning model, a deep learning model, a Bayesian model, a genetic algorithm model, a fuzzy logic model, a random deep forest learning model, etc. Different secondary set attributes are trained using different artificial intelligence models, which can improve the training accuracy of the data for the model.

[0085] The main set and each secondary set are input into the corresponding optimal artificial intelligence model respectively, and multiple sub-data collection models are trained to obtain.

[0086] Using the formula The estimated weight set of the sub-data model is {η1, η2, η3...η T}, through each sub-data model {ν1(x), ν2(x), ν3(x)...ν T (x)} and its corresponding weight set {μ1, μ2, μ3...μ T} combination to determine the final artificial intelligence data acquisition model: Among them, ξ is the constructed artificial intelligence data acquisition model, T represents the number of sub-data models, η t represents the weight value corresponding to the sub-data model, ν t (x) represents the t-th sub-data model, ψ t represents the optimization coefficient of the t-th sub-data model, n t is the number of iterations of the t-th sub-data model, H t is the degree of fit of the t-th sub-data model to the input features. The optimization coefficient is optimized and updated with each security data collected. The artificial intelligence data collection model obtained by the above training is used to collect smart grid data.

[0087] In the embodiment of the present application, after the current data is collected using the artificial intelligence data collection model, it is necessary to determine whether the collected data is safe data based on the grid security data in the collected smart grid data, specifically including:

[0088] Perform anomaly detection on smart grid data and calculate anomaly risk value.

[0089] Specifically, the calculation formula of abnormal risk value is:

[0090]

[0091] Where F represents the calculated abnormal risk value; ξ u represents the abnormal risk characteristic value, βi represents the abnormal risk impact weight; γ represents the total number of abnormal risk categories; τ u represents the weight factor of the u-th abnormal risk; qu represents the number of the u-th abnormal risk; s u Represents the danger value of the u-th anomaly.

[0092] Calculate the safety factor component value according to the abnormal risk value, and divide the safety status level according to the safety factor component value;

[0093] Specifically, the calculation formula for the safety factor component value is:

[0094] Among them, R is the calculated safety factor component value, F u represents abnormal risk value; Y w is the wth safety factor of the sub-data model, including hardware equipment safety factor, smart grid system software safety factor, and network security level. The value of n ranges from 1 to n, where n is the total number of safety factors. is the impact weight of the nth security factor on the security of the sub-data model.

[0095] Calculate the safety risk assessment value based on the safety factor component values.

[0096] Specifically, the security risk assessment value calculation formula is:

[0097]

[0098] Among them, SI represents the security risk assessment value; θ1 is the influence weight of node characteristics on the security assessment value; θ2 is the influence weight of abnormal data on the security assessment value; e i is the data anomaly characteristic value of the security node of the ith sub-data model; h ρi represents the fluctuation factor of the abnormal data of the ith operating characteristic of the monitored ρth processor; L ρi It represents the continuous abnormal value of the i-th continuous operation characteristic abnormal data of the monitored ρ-th processor; the value of i ranges from 1 to N, where N represents the total number of types of abnormal data of the operation characteristics of the data training model; Rpim represents the standard value for security risk formulation; R is the component value of the security factor;

[0099] Corresponding to the above embodiment, an embodiment of the present invention provides a computer storage medium, including: at least one memory and at least one processor;

[0100] The memory is used to store one or more program instructions;

[0101] A processor is used to run one or more program instructions to execute an artificial intelligence data collection method for smart grid.

[0102] Corresponding to the above-mentioned embodiments, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer storage medium contains one or more program instructions, and the one or more program instructions are used by a processor to execute an artificial intelligence data collection method for a smart grid.

[0103] The embodiments disclosed in the present invention provide a computer-readable storage medium, in which computer program instructions are stored. When the computer program instructions are executed on a computer, the computer executes the above-mentioned artificial intelligence data collection method for smart grids.

[0104] In the embodiment of the present invention, the processor may be an integrated circuit chip having the ability to process signals. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0105] The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The processor reads the information in the storage medium and completes the steps of the above method in combination with its hardware.

[0106] The storage medium may be a memory, which may be, for example, a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory.

[0107] Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.

[0108] The volatile memory may be a random access memory (RAM) which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced synchronous DRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus DRAM (DRRAM).

[0109] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0110] Those skilled in the art will appreciate that in one or more of the above examples, the functions described in the present invention can be implemented using a combination of hardware and software. When software is used, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any media that facilitates the transmission of computer programs from one place to another. Storage media can be any available media that can be accessed by general or special-purpose computers.

[0111] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. An artificial intelligence data collection method for smart grid, characterized in that: include: Collect smart grid data through artificial intelligence data collection models; Calculate data security risk assessment values ​​based on smart grid data; Compare the data security risk assessment value with the preset threshold; If the data security risk assessment value is not less than the preset threshold, the security risk factors of the smart grid data are checked or eliminated; If the data security risk assessment value is less than the preset threshold, the collected smart grid data will be input into the artificial intelligence data collection model again for training to achieve the optimization of the artificial intelligence data collection model.

2. The method for collecting artificial intelligence data for smart grid according to claim 1, characterized in that: The method for constructing the artificial intelligence data acquisition model includes the following sub-steps: Collect historical smart grid data; Extract features from the collected data to form a smart grid feature data set; Use smart grid feature data sets to train artificial intelligence data acquisition models.

3. The method for collecting artificial intelligence data for smart grid according to claim 2, characterized in that: Smart grid data includes basic grid data and grid security data. Basic grid data includes electric energy data, voltage data, current data, and power load data. Grid security data includes grid equipment status data, grid system performance data, grid health operation parameter data, and grid communication data.

4. The method for collecting artificial intelligence data for smart grid according to claim 2, characterized in that: The artificial intelligence data collection model is trained using the smart grid feature data set, specifically: multiple sub-data models are selected, and multiple sub-classification models are used to comprehensively construct the artificial intelligence data collection model.

5. The method for collecting artificial intelligence data for smart grid according to claim 1, characterized in that: Check or eliminate potential security risks of smart grid data, including: Start the safety hazard investigation procedure; formulate a detailed investigation plan and determine the scope, objectives and methods of the investigation; Formulate elimination measures based on the analysis results of potential safety hazards; Implement corresponding measures step by step according to the formulated elimination measures plan.

6. An artificial intelligence data acquisition system for smart grid, characterized in that: include: A collection module for collecting smart grid data through an artificial intelligence data collection model; A security verification module, used to calculate a data security risk assessment value based on smart grid data; Compare the data security risk assessment value with the preset threshold; If the data security risk assessment value is not less than the preset threshold, the security risk factors of the smart grid data are checked or eliminated; If the data security risk assessment value is less than the preset threshold, the model optimization module is triggered; The model optimization module is used to input the collected smart grid data into the artificial intelligence data acquisition model again for training to achieve the optimization of the artificial intelligence data acquisition model.

7. The artificial intelligence data acquisition system for smart grid according to claim 6, characterized in that: The construction of the artificial intelligence data acquisition model includes: collecting historical smart grid data; extracting features from the collected data to form a smart grid feature data set; and training the artificial intelligence data acquisition model using the smart grid feature data set.

8. The artificial intelligence data acquisition system for smart grid according to claim 7, characterized in that: Smart grid data includes basic grid data and grid security data. Basic grid data includes electric energy data, voltage data, current data, and power load data. Grid security data includes grid equipment status data, grid system performance data, grid health operation parameter data, and grid communication data.

9. The artificial intelligence data acquisition system for smart grid according to claim 7, characterized in that: The artificial intelligence data collection model is trained using the smart grid feature data set, specifically: multiple sub-data models are selected, and multiple sub-classification models are used to comprehensively construct the artificial intelligence data collection model.

10. The method for collecting artificial intelligence data for smart grid according to claim 6, characterized in that: Check or eliminate potential safety hazards in smart grid data, including: starting the safety hazard check procedure; formulating a detailed check plan to determine the scope, objectives and methods of the check; formulating elimination measures based on the analysis results of safety hazards; and gradually implementing corresponding measures according to the elimination measures plan.

Images