Power grid load supervision data processing system based on cloud computing

Abstract

The invention discloses a power grid load supervision data processing system based on cloud computing, which belongs to the technical field of power grid load supervision and comprises a demand analysis module, a demand processing module, an acquisition module, a storage module and a data analysis module. The demand analysis module is used for carrying out load demand analysis and establishing a demand statistical table; the demand processing module is used for performing demand processing analysis according to the demand statistical table, and determining a data analysis mode and an adaptive acquisition mode corresponding to the load analysis demand; the acquisition module acquires load data in a power grid in real time; the storage module is used for storing the load data and classifying the load data according to load analysis requirements to obtain requirement monitoring data; the data analysis module is used for carrying out data analysis and carrying out distributed processing on load analysis requirements according to analysis grades; and analyzing the demand monitoring data according to the data analysis mode to obtain a load monitoring result.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid load supervision, and in particular is a power grid load supervision data processing system based on cloud computing. Background Art

[0002] With the rapid development of power systems and the continuous advancement of smart grid construction, power grid load data processing technology has become one of the key technologies to ensure the safe, stable and efficient operation of power grids. However, the existing power grid load data processing system still has certain shortcomings; for example, the existing technology has certain delays in data acquisition, transmission and processing, resulting in insufficient real-time processing results. This may affect the real-time dispatching and operation decisions of the power grid. At the same time, due to the huge amount and complexity of data, the existing technology may consume a lot of computing resources and time in the data processing process. This reduces the efficiency of data processing and may limit the scope of application of power grid load data processing technology.

[0003] Therefore, in order to efficiently process the power grid load supervision data, it has become a problem that needs to be solved urgently; based on this, the present invention provides a power grid load supervision data processing system based on cloud computing. Summary of the invention

[0004] In order to solve the problems existing in the above solutions, the present invention provides a power grid load supervision data processing system based on cloud computing.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A cloud computing-based power grid load supervision data processing system includes a demand analysis module, a demand processing module, a collection module, a storage module and a data analysis module;

[0007] The demand analysis module is used to perform load demand analysis, determine a number of load analysis requirements of the user for power grid load supervision, and establish a demand statistics table according to the load analysis requirements;

[0008] The analysis level of the load analysis demand is determined in real time according to the demand statistics table, and the analysis level is marked accordingly in the demand statistics table.

[0009] Furthermore, the method for determining the load analysis requirement includes:

[0010] Establishing a demand reserve library, wherein the demand reserve library is used to store potential demands and demand background ranges corresponding to the potential demands;

[0011] A background judgment model is established, and the expression of the background judgment model is:

[0012]

[0013] Where: (BD, si) is the input data, BD is the power grid background, si is the demand background range of the corresponding potential demand in the demand reserve, i represents the corresponding potential demand in the demand reserve, i=1, 2, ..., n, n is the number of potential demands in the demand reserve; BD→si means that the power grid background belongs to the demand background range of the corresponding potential demand; the output data is the background matching value BQ(BD, si), the background matching value is 1 or 0;

[0014] Identify the user's power grid background, analyze the power grid background and demand reserve through the background judgment model, and obtain the background matching value of the corresponding potential demand;

[0015] The potential demand with a background matching value of 1 is marked as a recommended demand, and a recommendation information table is established according to the recommended demand; the recommendation information table is displayed to the user to determine the load analysis demand.

[0016] Furthermore, the method for determining the analysis level of the corresponding load analysis demand in real time according to the demand statistics table is:

[0017] The platform presets each analysis level and the level value range corresponding to the analysis level; sets the corresponding benchmark level value for the load analysis demand in the demand statistics table;

[0018] Acquire demand-related data of the load analysis demand in real time, analyze the demand-related data in real time through a preset grade adjustment model, and obtain a grade adjustment value of the load analysis demand;

[0019] The level positioning value of the corresponding load analysis requirement is calculated in real time according to the level calculation formula. The level calculation formula is:

[0020] DZ=DC+DLt;

[0021] Where: DZ is the level positioning value; DC is the reference level value; DLt is the level adjustment value at the corresponding time, and t is the time;

[0022] The analysis level of the load analysis requirement is determined in real time according to the level positioning value and the level value range.

[0023] The demand processing module is used to perform demand processing analysis according to the demand statistics table, and determine the data analysis method and adaptive collection method corresponding to the load analysis demand.

[0024] Furthermore, the method for performing demand processing analysis according to the demand statistics table includes:

[0025] The platform establishes an analysis algorithm library and a collection reserve library. The analysis algorithm library is used to store data analysis methods applicable to corresponding load analysis requirements; the collection reserve library is used to store adaptive collection methods applicable to corresponding data analysis methods;

[0026] Identify the load analysis requirements in the demand statistics table, perform simulation analysis on the load analysis requirements based on the analysis algorithm library and the collection reserve library, and determine the data analysis method and adaptive collection method of the load analysis requirements.

[0027] Furthermore, the method for simulating and analyzing the load analysis requirements based on the analysis algorithm library and the acquisition reserve library includes:

[0028] Identify the existing data analysis methods and adaptive collection method combinations according to the analysis algorithm library and the collection reserve library, mark them as reserve combinations, and add corresponding load analysis requirement tags to the reserve combinations;

[0029] Establishing a condition reserve library, the condition reserve library is used to store analysis condition data, the analysis condition data includes a benchmark accuracy and a benchmark estimation method;

[0030] Matching corresponding reserve combinations according to the load analysis requirements, and matching corresponding analysis condition data from the condition reserve library according to the reserve combinations and the load analysis requirements;

[0031] The reserve combination is screened according to the analysis condition data to determine a target analysis combination, and the data analysis method and adaptive collection method of the load analysis requirement are determined according to the target analysis combination.

[0032] Furthermore, the method for establishing the conditional reserve library includes:

[0033] Acquire historical load monitoring data of the user, classify the historical load monitoring data according to the load analysis requirements, and form load material data of the load analysis requirements;

[0034] Performing simulation analysis on the load material data according to the reserve combination to obtain the simulation accuracy and simulation usage duration of the reserve combination for the load analysis requirement; and setting a duration estimation method according to the simulation usage duration;

[0035] The simulation accuracy is marked as the benchmark accuracy, the duration estimation method is marked as the benchmark estimation method, the benchmark accuracy and the benchmark estimation method are integrated into analysis condition data, and the analysis condition data is marked with corresponding reserve combination and load analysis requirement labels; a condition reserve library is established according to the analysis condition data.

[0036] Furthermore, the method of screening the reserve portfolio according to the analysis condition data includes:

[0037] Identify the reserve portfolio and analysis condition data corresponding to the load analysis requirement, identify the benchmark accuracy and benchmark prediction method corresponding to the analysis condition data, and determine the corresponding predicted usage duration according to the benchmark prediction method;

[0038] Identify the analysis level of the load analysis requirement according to the requirement statistical table;

[0039] Conduct a comparative analysis on the corresponding reserve portfolio according to the screening and comparison formula to obtain the corresponding comparison and screening value. The screening and comparison formula is:

[0040]

[0041] In the formula: SE is the comparison and screening value; b1 and b2 are both proportionality coefficients, and the value range is 0 < b1 ≤ 1, 0 < b2 ≤ 1. The proportionality coefficients are determined according to the analysis level; GD1 and GD2 are the benchmark accuracies of the two reserve portfolios for comparison respectively; YT1 and YT2 are the predicted usage durations of the two reserve portfolios for comparison respectively;

[0042] Screen the reserve portfolio corresponding to the load analysis requirement according to the comparison and screening value to determine the target analysis portfolio.

[0043] The acquisition module acquires load data, determines the adaptive acquisition method for the load analysis requirement, and acquires the load data in the power grid in real time according to the adaptive acquisition method;

[0044] The storage module is used to store the load data, classify the load data according to the load analysis requirement, and obtain the demand monitoring data;

[0045] The data analysis module is used to conduct data analysis, identify the analysis level of the load analysis requirement, and perform distributed processing on the load analysis requirement according to the analysis level; analyze the demand monitoring data according to the data analysis method of the load analysis requirement to obtain the load monitoring result.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] By introducing cloud computing technology, the present invention can utilize the powerful computing power and distributed processing mechanism of the cloud to effectively shorten the delay time of data collection, transmission and processing. This ensures the instant update and rapid response of power grid load data, provides strong support for the real-time dispatch and operation decision-making of the power grid, and thus significantly improves the safety and stability of power grid operation. By optimizing the data processing flow and improving the processing efficiency, the present invention provides strong support for the intelligent management of the power grid. Real-time and accurate data processing results can provide key information for the automation control, fault prediction, energy efficiency management, etc. of the power grid, and promote the development of the power grid in a more intelligent and efficient direction. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] 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 of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0050] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] like Figure 1 As shown, a cloud computing-based power grid load supervision data processing system includes a demand analysis module, a demand processing module, a collection module, a storage module and a data analysis module;

[0052] The demand analysis module is used to perform load demand analysis, determine various load analysis requirements of users for power grid load supervision, such as the change law of power grid load, load forecasting and other load analysis requirements, and establish a demand statistics table according to the determined load analysis requirements;

[0053] The analysis level of the corresponding load analysis demand is determined in real time according to the demand statistics table, and the obtained analysis level is marked accordingly in the demand statistics table.

[0054] In one embodiment, the user may determine each load analysis requirement by himself / herself and upload the determined load analysis requirement.

[0055] In one embodiment, in order to facilitate users to completely and quickly determine various load analysis requirements, the following method is used for analysis, including:

[0056] The platform conducts real-time demand statistics in the field of power grid management, determines various analytical requirements in the field of power grid management that fall within the scope of power grid load monitoring, marks them as potential requirements, and sets the demand background range according to the power grid background of the corresponding potential requirements. The demand background range is used to indicate under what circumstances the power grid monitoring background will have the potential demand, and statistical analysis can be performed according to the corresponding power grid background with the potential demand;

[0057] Organize various potential demands and demand background ranges to establish a demand reserve library; and update the demand reserve library in real time according to data updates to ensure the comprehensiveness of the demands.

[0058] A background judgment model is established. The background judgment model is used to judge whether the current power grid background belongs to the corresponding demand background range. The expression of the background judgment model is:

[0059]

[0060] Where: (BD, si) is the input data, BD is the power grid background, si is the demand background range of the corresponding potential demand in the demand reserve, i represents the corresponding potential demand in the demand reserve, i=1, 2, ..., n, n is the number of potential demands in the demand reserve; BD→si means that the power grid background belongs to the demand background range of the corresponding potential demand; the output data is the background matching value BQ(BD, si), the background matching value is 1 or 0;

[0061] Identify the user's power grid background, analyze the power grid background and demand reserve through the background judgment model, and obtain the background matching value of the corresponding potential demand;

[0062] The potential demand with a background matching value of 1 is marked as a recommended demand, and a recommendation information table is established according to the recommended demand, and the introduction information of the corresponding recommended demand can be supplemented in the recommended information table; the recommended information table is displayed to the user, and the user selects the corresponding recommended demand as the load analysis demand.

[0063] In one embodiment, a method for determining the analysis level of a corresponding load analysis demand in real time according to a demand statistics table is as follows: the analysis level is determined using an existing method, and the analysis level is determined according to the timeliness requirement of the corresponding load analysis demand. The platform party presets a number of analysis levels and corresponding level introduction information according to platform resources. Different analysis levels subsequently correspond to different service resources and timeliness, such as computing resources (such as CPU, memory), storage resources, network resources, etc.; subsequent users can set the corresponding analysis level according to actual needs to meet the analysis requirements, and perform manual adjustments when the analysis level needs to be adjusted.

[0064] In one embodiment, the method for determining the analysis level of the corresponding load analysis demand in real time according to the demand statistics table is:

[0065] The platform presets each analysis level and the level value range corresponding to the analysis level, such as 0-20 for the first level and 21-40 for the second level. The platform sets the specific range according to the actual situation.

[0066] The user sets the corresponding benchmark level value for each load analysis requirement. For example, if the user sets a load analysis requirement to the second level, the corresponding benchmark level value can be set in the range of 21-40 according to the degree difference. The platform can also assist the user in setting the value.

[0067] Obtain demand-related data for each load analysis demand in real time. Demand-related data refers to data related to whether the load analysis demand has timeliness changes. For example, if a certain power grid abnormality requires timely analysis of a certain load analysis demand, the corresponding demand-related data is collected to adjust the benchmark level value;

[0068] The demand-related data is analyzed in real time through a preset level adjustment model to obtain the level adjustment value of the corresponding load analysis demand;

[0069] The level positioning value of the corresponding load analysis requirement is calculated in real time according to the level calculation formula. The level calculation formula is:

[0070] DZ=DC+DLt;

[0071] Where: DZ is the level positioning value; DC is the reference level value; DLt is the level adjustment value at the corresponding time, and t is the time;

[0072] The analysis level of the corresponding load analysis requirement is determined based on the level positioning value and the level value range of each analysis level.

[0073] In one embodiment, the level adjustment model is established based on existing intelligent technology, such as based on a neural network such as a CNN network or a DNN network. The platform sets a corresponding training set for training. The training set includes input data and output data. The input data is the demand-related data of the corresponding load analysis requirements; the output data is the level adjustment value, which is analyzed by the level adjustment model after successful training.

[0074] The demand processing module is used to perform demand processing analysis according to the demand statistics table, and determine the data analysis method and adaptive collection method corresponding to the corresponding load analysis demand.

[0075] The data analysis method is a specific analysis method that meets the load analysis requirements, such as traditional statistical methods, machine learning algorithms, deep learning models and other related data analysis methods.

[0076] The adaptive collection method is the data collection, processing, transmission and other methods for the data analysis method, which is used to minimize the collection time and improve timeliness.

[0077] In one embodiment, the demand processing analysis is performed according to the demand statistics table, and the analysis can be performed based on an existing method.

[0078] In one embodiment, the method for performing demand processing analysis according to the demand statistics table includes:

[0079] The platform shall establish an analysis algorithm library based on the development of existing technologies. The analysis algorithm library is used to store data analysis methods for corresponding load analysis requirements. The analysis algorithm library shall be regularly updated and maintained, and new algorithms and technologies shall be introduced to ensure the advancement and applicability of the analysis algorithm library.

[0080] A collection reserve library is established based on the analysis algorithm library. The collection reserve library is used to store adaptive collection methods that adapt to corresponding data analysis methods. That is, the load data can be directly analyzed by the data analysis method after collection and processing. The corresponding adaptive collection method is mainly set according to the collection equipment available on site, applicable data processing methods, etc.; data processing refers to the cleaning, integration and formatting of the collected data to meet the analysis requirements of subsequent data analysis methods.

[0081] The analysis algorithm library and collection reserve library are both established by the platform;

[0082] Identify the load analysis requirements in the demand statistics table, simulate and analyze the load analysis requirements based on the analysis algorithm library and the collection reserve library, and determine the data analysis method and adaptive collection method corresponding to the corresponding load analysis requirements.

[0083] In one embodiment, a method for simulating and analyzing load analysis requirements based on an analysis algorithm library and a collection reserve library includes:

[0084] Determine various data analysis methods and adaptive collection method combinations based on the analysis algorithm library and the collection reserve library, mark the corresponding combinations as reserve combinations, and label the reserve combinations with corresponding applicable load analysis demand labels;

[0085] Obtain the user's historical load monitoring data, classify the historical load monitoring data according to the load analysis requirements, form historical load classification data corresponding to the corresponding load analysis requirements, and mark them as load material data, that is, classify them according to what data is needed to analyze the load analysis requirements;

[0086] According to the reserve combination, the corresponding load material data is simulated and analyzed to obtain the corresponding simulation accuracy and simulation usage time; that is, the simulation is performed according to the data analysis method and the adaptive collection method corresponding to the corresponding reserve combination, and the corresponding usage time from collection to analysis, as well as the accuracy of the corresponding simulation results, and a representative simulation accuracy and simulation usage time are determined by simulating multiple groups of data, such as using the average, mode, etc. for statistical analysis; the duration estimation method is set according to the simulated usage time, that is, the corresponding time is subsequently estimated according to the duration evaluation method to use the reserve combination for collection and analysis; a simulation adjustment model is established according to the above process, and the simulation adjustment model is used to adjust the corresponding simulation accuracy and duration estimation method according to the received analysis process data to make it more accurate, and is established using existing technology. For example, it is established based on a neural network such as a CNN network or a DNN network, and the platform establishes a corresponding training set for training, and the training set includes input data and output data, the input data is the analysis process data corresponding to the received corresponding reserve combination and load analysis requirements, and the output data is the adjusted simulation accuracy and duration estimation method;

[0087] The simulation accuracy is marked as the benchmark accuracy, the duration estimation method is marked as the benchmark estimation method, the benchmark accuracy and the benchmark estimation method are integrated into the analysis condition data, and the analysis condition data is labeled with the corresponding reserve combination and load analysis demand tags; the model can be dynamically updated based on the simulation adjustment model later;

[0088] Establish a condition reserve based on the analyzed condition data;

[0089] Match the corresponding reserve combination according to the load analysis requirements, match the corresponding analysis condition data from the condition reserve library according to the reserve combination and the load analysis requirements, screen the reserve combination according to the analysis condition data, determine the target analysis combination, and output the data analysis method and adaptation collection method corresponding to the target analysis combination as the data analysis method and adaptation collection method for the load analysis requirements.

[0090] In one embodiment, the method for screening a reserve portfolio according to analysis condition data includes:

[0091] Identify the reserve portfolio and analysis condition data corresponding to the load analysis requirement, identify the benchmark accuracy and benchmark estimation method corresponding to the analysis condition data, and estimate the estimated usage duration corresponding to the current load analysis requirement according to the benchmark estimation method, that is, estimate the duration required for collection and analysis according to this reserve portfolio in combination with the current load condition;

[0092] Identify the analysis level of the load analysis requirement according to the requirement statistics table, match the corresponding proportionality coefficients b1 and b2 according to the analysis level, and the value range is 0 < b1 ≤ 1, 0 < b2 ≤ 1. Different analysis levels have different requirements for timeliness, so the proportionality coefficients are different, and are specifically preset by the platform side according to the actual needs of users;

[0093] Conduct a comparative analysis of the corresponding reserve portfolio according to the screening comparison formula to obtain the corresponding comparison and screening value. The screening comparison formula is:

[0094]

[0095] In the formula: SE is the comparison and screening value; b1 and b2 are both proportionality coefficients, and the value range is 0 < b1 ≤ 1, 0 < b2 ≤ 1; GD1 and GD2 are the benchmark accuracies of the two reserve portfolios being compared respectively; YT1 and YT2 are the estimated usage durations of the two reserve portfolios being compared respectively;

[0096] Conduct screening according to the comparison and screening values with each other to determine the target analysis portfolio.

[0097] The acquisition module acquires load data, determines the adaptive acquisition method corresponding to the corresponding load analysis requirement, and acquires the load data in the power grid in real time according to the corresponding adaptive acquisition method, including key parameters such as voltage, current, and power.

[0098] The storage module is used to store the load data acquired by the acquisition module, and classify the load data according to the corresponding load analysis requirement to obtain demand monitoring data;

[0099] The storage module uses cloud storage technology to achieve the storage and management of massive data. Cloud storage has advantages such as elastic scalability, high availability, and low cost, and can meet the growing demand for power grid load data.

[0100] The data analysis module is used to perform data analysis, identify the analysis level corresponding to the load analysis requirements, and distribute the corresponding load analysis requirements according to the analysis level, that is, use distributed processing technology and cloud computing resources to distribute data processing tasks to multiple servers or nodes for parallel execution; dynamically adjust the allocation of cloud computing resources according to data processing requirements to ensure processing speed and efficiency, and use existing technologies to achieve distributed processing; identify the data analysis method for load analysis requirements, analyze the corresponding demand monitoring data according to the data analysis method, and obtain the corresponding load monitoring results.

[0101] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0102] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A cloud computing-based power grid load supervision data processing system, characterized in that: It includes demand analysis module, demand processing module, collection module, storage module and data analysis module; The demand analysis module is used to perform load demand analysis, determine a number of load analysis requirements of the user for power grid load supervision, and establish a demand statistics table according to the load analysis requirements; Determine the analysis level of the load analysis demand in real time according to the demand statistics table, and mark the analysis level in the demand statistics table accordingly; The demand processing module is used to perform demand processing analysis according to the demand statistics table, and determine the data analysis method and adaptive collection method corresponding to the load analysis demand; The acquisition module is used to collect load data, determine the adaptive acquisition method for the load analysis requirements, and collect load data in the power grid in real time according to the adaptive acquisition method; The storage module is used to store the load data and classify the load data according to the load analysis requirements to obtain demand monitoring data; The data analysis module is used to perform data analysis, identify the analysis level of the load analysis requirements, and distribute the load analysis requirements according to the analysis level; analyze the demand monitoring data according to the data analysis method of the load analysis requirements to obtain load monitoring results.

2. A cloud computing-based power grid load supervision data processing system according to claim 1, characterized in that: Methods for determining load analysis requirements include: Establishing a demand reserve library, wherein the demand reserve library is used to store potential demands and demand background ranges corresponding to the potential demands; A background judgment model is established, and the expression of the background judgment model is: Where: (BD, si) is the input data, BD is the power grid background, si is the demand background range of the corresponding potential demand in the demand reserve, i represents the corresponding potential demand in the demand reserve, i=1, 2, ..., n, n is the number of potential demands in the demand reserve; BD→si means that the power grid background belongs to the demand background range of the corresponding potential demand; the output data is the background matching value BQ(BD, si), the background matching value is 1 or 0; Identify the user's power grid background, analyze the power grid background and demand reserve through the background judgment model, and obtain the background matching value of the corresponding potential demand; The potential demand with a background matching value of 1 is marked as a recommended demand, and a recommendation information table is established according to the recommended demand; the recommendation information table is displayed to the user to determine the load analysis demand.

3. The cloud computing-based power grid load monitoring data processing system according to claim 1, characterized in that: The method for determining the analysis level of the corresponding load analysis demand in real time according to the demand statistics table is: The platform party presets each analysis level and the level value range corresponding to the analysis level; sets the corresponding benchmark level value for the load analysis demand in the demand statistics table; Acquire demand-related data of the load analysis demand in real time, analyze the demand-related data in real time through a preset grade adjustment model, and obtain a grade adjustment value of the load analysis demand; The level positioning value of the corresponding load analysis requirement is calculated in real time according to the level calculation formula. The level calculation formula is: DZ=DC+DLt; Where: DZ is the level positioning value; DC is the reference level value; DLt is the level adjustment value at the corresponding time, and t is the time; The analysis level of the load analysis requirement is determined in real time according to the level positioning value and the level value range.

4. The cloud computing-based power grid load monitoring data processing system according to claim 1, characterized in that: Methods for demand processing analysis based on demand statistics include: The platform establishes an analysis algorithm library and a collection reserve library. The analysis algorithm library is used to store data analysis methods applicable to corresponding load analysis requirements; the collection reserve library is used to store adaptive collection methods applicable to corresponding data analysis methods; Identify the load analysis requirements in the demand statistics table, perform simulation analysis on the load analysis requirements based on the analysis algorithm library and the collection reserve library, and determine the data analysis method and adaptive collection method of the load analysis requirements.

5. The cloud computing-based power grid load supervision data processing system according to claim 4, characterized in that: The methods for simulating and analyzing load analysis requirements based on the analysis algorithm library and the acquisition reserve library include: Identify the existing data analysis methods and adaptive collection method combinations according to the analysis algorithm library and the collection reserve library, mark them as reserve combinations, and add corresponding load analysis requirement tags to the reserve combinations; Establishing a condition reserve library, the condition reserve library is used to store analysis condition data, the analysis condition data includes a benchmark accuracy and a benchmark estimation method; Matching corresponding reserve combinations according to the load analysis requirements, and matching corresponding analysis condition data from the condition reserve library according to the reserve combinations and the load analysis requirements; The reserve combination is screened according to the analysis condition data to determine a target analysis combination, and the data analysis method and adaptive collection method of the load analysis requirement are determined according to the target analysis combination.

6. A cloud computing-based power grid load supervision data processing system according to claim 5, characterized in that: The method of establishing a conditional reserve library includes: Acquire historical load monitoring data of the user, classify the historical load monitoring data according to the load analysis requirements, and form load material data of the load analysis requirements; Performing simulation analysis on the load material data according to the reserve combination to obtain the simulation accuracy and simulation usage duration of the reserve combination for the load analysis requirement; and setting a duration estimation method according to the simulation usage duration; The simulation accuracy is marked as the benchmark accuracy, the duration estimation method is marked as the benchmark estimation method, the benchmark accuracy and the benchmark estimation method are integrated into analysis condition data, and the analysis condition data is marked with corresponding reserve combination and load analysis requirement labels; a condition reserve library is established according to the analysis condition data.

7. The cloud computing-based power grid load supervision data processing system according to claim 5, characterized in that: Methods for screening reserve portfolios based on analytical condition data include: Identify the reserve combination and analysis condition data corresponding to the load analysis demand, identify the benchmark accuracy and benchmark estimation method corresponding to the analysis condition data, and determine the corresponding estimated usage time according to the benchmark estimation method; Identifying the analysis level of the load analysis demand according to the demand statistics table; Compare and analyze the corresponding reserve combinations according to the screening comparison formula to obtain the corresponding comparative screening values; The reserve combinations corresponding to the load analysis requirements are screened according to the comparison screening values ​​to determine a target analysis combination.

8. The cloud computing-based power grid load supervision data processing system according to claim 7, characterized in that: The screening comparison formula is: Where: SE is the comparison and screening value; b1 and b2 are both proportionality coefficients, and the value ranges are 0 < b1 ≤ 1, 0 < b2 ≤ 1, and the proportionality coefficients are determined according to the analysis level; GD1 and GD2 are respectively the benchmark accuracies of two reserve combinations to be compared; YT1 and YT2 are respectively the estimated usage durations of two reserve combinations to be compared.

Images