A method for analyzing the carrying capacity and grid connection of distributed power sources

Abstract

The present invention discloses a distributed power supply capacity and grid connection analysis method, which belongs to the field of power grid technology, and includes the following steps: S1: obtaining the operating data of the distributed power supply, and constructing a distributed power supply learning model according to the operating data of the distributed power supply; S2: obtaining the operating data of the power grid, and constructing a power grid learning model according to the operating data of the power grid; S3: simulating, analyzing and evaluating the power grid learning model and the distributed power supply learning model, and making optimization management and control decisions according to the analysis and evaluation results. The present invention solves the existing problem that the distributed power supply capacity and grid connection status cannot be monitored and analyzed and evaluated in real time, the distributed power supply grid connection security and stability are low, and the distributed power supply cannot be efficiently and safely connected to the grid. The present invention can monitor and analyze the distributed power supply capacity and grid connection status in real time, improve the distributed power supply grid connection security and stability, and realize the efficient and safe grid connection operation of the distributed power supply.

Description

Technical Field

[0001] The present invention relates to the technical field of power grids, and in particular to a method for analyzing the carrying capacity and grid connection of distributed power sources. Background Art

[0002] With the continuous development of renewable energy technology, distributed power generation, as a new type of energy access method, has attracted more and more attention. Among them, distributed power generation is distributed at the user end, connected to the 35kV and below voltage level power grid, and mainly consumed locally, including solar energy, natural gas, biomass energy, wind energy, hydropower, hydrogen energy, geothermal energy, ocean energy, comprehensive resource utilization power generation and energy storage, etc.

[0003] The Chinese patent with publication number CN117977694A discloses a distributed power cluster control method, including the following steps: S1: collecting distributed power data based on distributed power cluster control; S2: processing the distributed power data to determine the distributed power characterization data based on the distributed power cluster control; S3: comparing and analyzing the distributed power characterization data to determine the distributed power analysis results based on the distributed power cluster control; S4: intelligently controlling the distributed power analysis results based on the distributed power cluster control to determine the distributed power cluster control method based on the distributed power cluster control; the distributed power can be effectively clustered and the distributed power cluster control effect can be improved; however, the patent has the following defects:

[0004] Existing distributed power sources may have insufficient carrying capacity when connected to the power grid, and cannot perform real-time monitoring, analysis and evaluation of the distributed power source carrying capacity and grid connection status, resulting in low security and stability of distributed power source grid connection, and unable to achieve efficient and safe grid-connected operation of distributed power sources. Summary of the invention

[0005] The purpose of the present invention is to provide a distributed power supply carrying capacity and grid-connected analysis method, which can perform real-time monitoring and analysis and evaluation of the distributed power supply carrying capacity and grid-connected status, improve the safety and stability of distributed power supply grid-connected operation, and realize efficient and safe grid-connected operation of distributed power supply, thereby solving the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A distributed power supply carrying capacity and grid connection analysis method comprises the following steps:

[0008] S1: Obtain the operating data of the distributed power source and build a distributed power source learning model based on the operating data of the distributed power source;

[0009] S2: Obtain the operation data of the power grid and build a power grid learning model based on the operation data of the power grid;

[0010] S3: Conduct simulation analysis and evaluation on the power grid learning model and the distributed power generation learning model, and make distributed power generation capacity and grid connection optimization management and control decisions based on the distributed power generation capacity and grid connection analysis and evaluation results.

[0011] Preferably, in S1, the operation data of the distributed power source is obtained by performing the following operations:

[0012] Monitor the output power of distributed power sources and determine the power parameters of distributed power sources;

[0013] Monitor the output current of the distributed power supply and determine the current parameters of the distributed power supply;

[0014] Monitor the output voltage of the distributed power supply and determine the voltage parameters of the distributed power supply;

[0015] The operation data of the distributed power source is determined based on the power parameters, current parameters and voltage parameters of the distributed power source.

[0016] Preferably, in S1, obtaining the operating data of the distributed power source further includes:

[0017] Real-time monitoring of the acquisition time of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter;

[0018] According to the acquisition moments of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter, the data acquisition time difference between the distributed power supply power parameter and the distributed power supply current parameter, the data acquisition time difference between the distributed power supply current parameter and the distributed power supply voltage parameter, and the data acquisition time difference between the distributed power supply power parameter and the distributed power supply voltage parameter;

[0019] Taking the data acquisition time difference between the distributed power supply power parameter and the distributed power supply current parameter as the first time difference data;

[0020] Using the data acquisition time difference between the distributed power supply current parameter and the distributed power supply voltage parameter as second time difference data;

[0021] Using the data acquisition time difference between the distributed power supply power parameter and the distributed power supply voltage parameter as third time difference data;

[0022] The data difference stability evaluation coefficient is obtained by using the first time difference data, the second time difference data and the third time difference data; wherein the data difference stability evaluation coefficient is obtained by the following formula:

[0023] ;

[0024] Wherein, W represents the data difference stability evaluation coefficient; n represents the number of data collection times corresponding to the distributed power supply power parameter, distributed power supply current parameter and distributed power supply voltage parameter; T c01i , T c02i and T c03i They respectively represent the first time difference data, the second time difference data and the third time difference data corresponding to the i-th data collection; w represents the compensation coefficient, and the compensation coefficient is obtained by the following formula:

[0025] ;

[0026] Where w represents the compensation coefficient; P max01 and P min01 They respectively represent the occurrence ratio of the first time difference data being the maximum value and the occurrence ratio of the first time difference data being the minimum value in the data collection process that has been experienced; P max02 and P min02 They respectively represent the occurrence ratio of the second time difference data being the maximum value and the occurrence ratio of the second time difference data being the minimum value in the data collection process that has been experienced; P max03 and P min03 They respectively represent the occurrence ratio of the third time difference data being the maximum value and the occurrence ratio of the third time difference data being the minimum value in the data collection process that has been experienced;

[0027] Comparing the data difference stability evaluation coefficient with a preset evaluation coefficient threshold;

[0028] When the data difference stability evaluation coefficient is lower than a preset evaluation coefficient threshold, the data collection operation status of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter is evaluated and abnormality is determined.

[0029] Preferably, when the data difference stability evaluation coefficient is lower than a preset evaluation coefficient threshold, the data collection operation status of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter is evaluated and abnormal determination is performed, including:

[0030] When the data difference stability evaluation coefficient is lower than a preset evaluation coefficient threshold, extracting the acquisition time of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter;

[0031] Determine the first fluctuation parameter corresponding to the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter according to the acquisition time of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter in combination with the first fluctuation acquisition model;

[0032] The model structure of the first fluctuation acquisition model is as follows:

[0033] ;

[0034] Among them, B 01 represents the first fluctuation parameter corresponding to the distributed power supply power parameter, distributed power supply current parameter or distributed power supply voltage parameter obtained by the first fluctuation acquisition model; n represents the number of data collection times corresponding to the distributed power supply power parameter, distributed power supply current parameter and distributed power supply voltage parameter; T i represents the data collection time corresponding to the distributed power source power parameter, distributed power source current parameter or distributed power source voltage parameter during the i-th data collection; T i-1 represents the data collection time corresponding to the distributed power source power parameter, distributed power source current parameter or distributed power source voltage parameter during the i-1th data collection; T e Indicates the maximum allowed amplitude duration between two adjacent acquisition moments; P t Indicates the proportion of the maximum value of the collection time fluctuation of the distributed power supply power parameter, the distributed power supply current parameter or the distributed power supply voltage parameter in the n data collections that have been experienced;

[0035] Compare the first fluctuation parameters corresponding to the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter with a preset first fluctuation parameter threshold; extract the distributed power supply power parameter, the distributed power supply current parameter and / or the distributed power supply voltage parameter corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold;

[0036] According to the number of distributed power supply power parameters, distributed power supply current parameters and / or distributed power supply voltage parameters corresponding to the first fluctuation parameter that exceeds the preset first fluctuation parameter threshold, it is determined whether there is an abnormality in the data collection operation status of the distributed power supply power parameters, distributed power supply current parameters and distributed power supply voltage parameters.

[0037] Preferably, determining whether there is an abnormality in the data collection operation state of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter according to the number of the distributed power supply power parameter, the distributed power supply current parameter and / or the distributed power supply voltage parameter corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold, respectively, includes:

[0038] When the number of distributed power supply power parameters, distributed power supply current parameters or distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold is one, an abnormal alarm is directly issued for the data collection operation status of the distributed power supply power parameters, distributed power supply current parameters or distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold;

[0039] When the number of distributed power supply power parameters, distributed power supply current parameters or distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold is multiple, the time difference data of the distributed power supply power parameters, distributed power supply current parameters and distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold is used to obtain the second fluctuation parameter; wherein the second fluctuation parameter is obtained by the following formula:

[0040] ;

[0041] Among them, B 01 represents the second fluctuation parameter; m represents the number of distributed power supply power parameters, distributed power supply current parameters or distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold; B 01j represents the first fluctuation parameter corresponding to the distributed power supply power parameter, the distributed power supply current parameter or the distributed power supply voltage parameter corresponding to the jth first fluctuation parameter exceeding the preset first fluctuation parameter threshold; T cpj represents the average value of the time difference data involved in the distributed power supply power parameter, distributed power supply current parameter or distributed power supply voltage parameter corresponding to the jth first fluctuation parameter exceeding the preset first fluctuation parameter threshold; T e Indicates the maximum allowed amplitude duration between two adjacent acquisition moments;

[0042] When the second fluctuation parameter exceeds a preset second fluctuation parameter threshold, an abnormal alarm is issued for the data collection operation status of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter.

[0043] Preferably, in S1, a distributed power supply learning model is constructed according to the operation data of the distributed power supply, and the following operations are performed:

[0044] Obtaining the operating data of distributed power sources;

[0045] Divide the operating data of distributed power sources;

[0046] Determine a distributed power supply training set and a distributed power supply test set;

[0047] Select the appropriate model architecture based on the distributed power generation capacity and grid-connected analysis requirements;

[0048] Based on the distributed power training set, train the selected appropriate model architecture;

[0049] Determine the distributed power learning model;

[0050] Based on the distributed power supply test set, the performance of the distributed power supply learning model is tested;

[0051] Determine the performance test results based on the distributed power learning model;

[0052] Conduct in-depth mining and relevant analysis on the performance test results based on the distributed power learning model;

[0053] Determine the optimal adjustment plan based on the distributed power supply learning model;

[0054] Optimize and adjust the distributed power learning model based on the optimization adjustment plan;

[0055] Determine the optimal distributed power learning model.

[0056] Preferably, in S2, the operation data of the power grid is obtained, and the following operations are performed:

[0057] Monitor the operation status of the power grid and determine the power grid status parameters;

[0058] Monitor the operating environment of the power grid and determine the power grid environmental parameters;

[0059] Monitor the operation market of the power grid and determine the power grid market parameters;

[0060] The operation data of the power grid is determined based on the power grid status parameters, environmental parameters and market parameters.

[0061] Preferably, in S2, a power grid learning model is constructed according to the operation data of the power grid, and the following operations are performed:

[0062] Obtaining the operation data of the power grid;

[0063] Divide the operation data of the power grid;

[0064] Determine a power grid training set and a power grid test set;

[0065] Select the appropriate model architecture based on the distributed power generation capacity and grid-connected analysis requirements;

[0066] Based on the power grid training set, train the selected appropriate model architecture;

[0067] Determine the grid learning model;

[0068] Based on the power grid test set, the performance of the power grid learning model is tested;

[0069] Determine performance test results based on the power grid learning model;

[0070] Conduct in-depth mining and relevant analysis on the performance test results based on the power grid learning model;

[0071] Determine the optimal adjustment plan based on the power grid learning model;

[0072] Optimize and adjust the power grid learning model based on the optimization adjustment plan;

[0073] Determine the optimal power grid learning model.

[0074] Preferably, in S3, simulation analysis and evaluation are performed on the power grid learning model and the distributed power source learning model, and the following operations are performed:

[0075] Obtain real-time operation data of distributed power sources;

[0076] Input the real-time operation data of distributed power sources into the optimal distributed power source learning model;

[0077] Based on the optimal distributed power learning model, the real-time operation data of distributed power is simulated and analyzed;

[0078] Determine the analysis results of distributed power generation capacity;

[0079] Obtain real-time operation data of the power grid;

[0080] Input the real-time operation data of the power grid into the optimal power grid learning model;

[0081] Based on the optimal grid learning model, simulate and analyze the real-time operation data of the grid;

[0082] Determine the distributed power generation capacity and grid-connected analysis and evaluation results.

[0083] Preferably, in S3, the real-time operation data of the distributed power source and the real-time operation data of the power grid are obtained, and the following operations are performed:

[0084] Obtain real-time operation data of distributed power sources and power grids;

[0085] Based on the sequential retrieval method, the real-time operation data of the distributed power source and the real-time operation data of the power grid are retrieved;

[0086] Check the consistency of real-time operation data of distributed power sources and real-time operation data of power grid;

[0087] Check whether the real-time operation data of the distributed power source and the real-time operation data of the power grid meet the requirements according to the reasonable value range and mutual relationship of each variable in the real-time operation data of the distributed power source and the real-time operation data of the power grid;

[0088] Remove inconsistent data that is beyond the normal range, logically unreasonable or contradictory in the real-time operation data of distributed power sources and the real-time operation data of the power grid;

[0089] Process invalid and missing values ​​of real-time operation data of distributed power sources and power grids;

[0090] Remove invalid and missing data that are of no value to the distributed power generation capacity and grid connection analysis from the real-time operation data of the distributed power generation and the real-time operation data of the power grid;

[0091] Determine the real-time operation data of distributed power sources and power grids that are valuable for distributed power generation capacity and grid connection analysis.

[0092] Preferably, in S3, an optimization management and control decision is made according to the evaluation results, and the following operations are performed:

[0093] Obtain the distributed power generation capacity and grid connection analysis and evaluation results;

[0094] Conduct in-depth exploration and relevant analysis on the distributed power generation capacity and grid connection analysis and evaluation results;

[0095] Determine the distributed power generation capacity and grid-connection optimization management and control decisions;

[0096] Based on the distributed power generation carrying capacity and grid-connected optimization management and control decisions, the distributed power generation carrying capacity and grid-connected conditions are optimized and controlled to enable the distributed power generation to operate efficiently and safely in grid-connected mode.

[0097] Compared with the prior art, the present invention has the following beneficial effects:

[0098] The present invention obtains the operating data of distributed power sources and constructs a distributed power source learning model according to the operating data of the distributed power sources; obtains the operating data of the power grid and constructs a power grid learning model according to the operating data of the power grid; based on the power grid learning model and the distributed power source learning model, simulation analysis and evaluation are performed on the real-time operating data of the power grid and the real-time operating data of the distributed power sources, and the distributed power source carrying capacity and grid-connected analysis and evaluation results are determined; distributed power source carrying capacity and grid-connected optimization management and control decisions are made according to the distributed power source carrying capacity and grid-connected analysis and evaluation results; based on the distributed power source carrying capacity and grid-connected optimization management and control decisions, the distributed power source carrying capacity and grid-connected conditions are optimized and controlled; real-time monitoring, analysis and evaluation of the distributed power source carrying capacity and grid-connected conditions can be performed, the distributed power source grid-connected safety and stability can be improved, and efficient and safe grid-connected operation of the distributed power sources can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] Figure 1 The present invention is a flow chart of the distributed power supply carrying capacity and grid connection analysis method. DETAILED DESCRIPTION

[0100] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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.

[0101] In order to solve the existing problem that the distributed power generation capacity and grid connection status cannot be monitored, analyzed and evaluated in real time, resulting in low security and stability of distributed power generation grid connection, and the inability to achieve efficient and safe grid connection operation of distributed power generation, please refer to Figure 1 , this embodiment provides the following technical solutions:

[0102] A distributed power supply carrying capacity and grid connection analysis method comprises the following steps:

[0103] S1: Obtain the operating data of the distributed power source and build a distributed power source learning model based on the operating data of the distributed power source;

[0104] In this embodiment, as a preferred technical solution of the present invention, the operation data of the distributed power source is obtained by performing the following operations:

[0105] Monitor the output power of distributed power sources and determine the power parameters of distributed power sources;

[0106] Monitor the output current of the distributed power supply and determine the current parameters of the distributed power supply;

[0107] Monitor the output voltage of the distributed power supply and determine the voltage parameters of the distributed power supply;

[0108] The operation data of the distributed power source is determined based on the power parameters, current parameters and voltage parameters of the distributed power source.

[0109] Specifically, in S1, obtaining the operating data of the distributed power source also includes:

[0110] Real-time monitoring of the acquisition time of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter;

[0111] According to the acquisition moments of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter, the data acquisition time difference between the distributed power supply power parameter and the distributed power supply current parameter, the data acquisition time difference between the distributed power supply current parameter and the distributed power supply voltage parameter, and the data acquisition time difference between the distributed power supply power parameter and the distributed power supply voltage parameter;

[0112] Taking the data acquisition time difference between the distributed power supply power parameter and the distributed power supply current parameter as the first time difference data;

[0113] Using the data acquisition time difference between the distributed power supply current parameter and the distributed power supply voltage parameter as second time difference data;

[0114] Using the data acquisition time difference between the distributed power supply power parameter and the distributed power supply voltage parameter as third time difference data;

[0115] The data difference stability evaluation coefficient is obtained by using the first time difference data, the second time difference data and the third time difference data; wherein the data difference stability evaluation coefficient is obtained by the following formula:

[0116] ;

[0117] Wherein, W represents the data difference stability evaluation coefficient; n represents the number of data collection times corresponding to the distributed power supply power parameter, distributed power supply current parameter and distributed power supply voltage parameter; T c01i , T c02i and T c03i They respectively represent the first time difference data, the second time difference data and the third time difference data corresponding to the i-th data collection; w represents the compensation coefficient, and the compensation coefficient is obtained by the following formula:

[0118] ;

[0119] Where w represents the compensation coefficient; P max01 and Pmin01 They respectively represent the occurrence ratio of the first time difference data being the maximum value and the occurrence ratio of the first time difference data being the minimum value in the data collection process that has been experienced; P max02 and P min02 They respectively represent the occurrence ratio of the second time difference data being the maximum value and the occurrence ratio of the second time difference data being the minimum value in the data collection process that has been experienced; P max03 and P min03 They respectively represent the occurrence ratio of the third time difference data being the maximum value and the occurrence ratio of the third time difference data being the minimum value in the data collection process that has been experienced;

[0120] Comparing the data difference stability evaluation coefficient with a preset evaluation coefficient threshold;

[0121] When the data difference stability evaluation coefficient is lower than a preset evaluation coefficient threshold, the data collection operation status of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter is evaluated and abnormality is determined.

[0122] The technical effect of the above technical solution is: by real-time monitoring of the power, current and voltage parameters of the distributed power source and their acquisition time, the data acquisition time difference between these parameters (i.e., the first time difference, the second time difference and the third time difference) can be accurately calculated. This real-time monitoring and precise calculation ensures the timeliness and accuracy of the data, and provides a reliable basis for subsequent data analysis and evaluation.

[0123] The calculated time difference data (first time difference, second time difference and third time difference) is used in combination with the compensation coefficient to calculate the data difference stability evaluation coefficient (W) through a specific formula. This evaluation coefficient comprehensively considers the distribution characteristics of the data acquisition time difference and the occurrence rate of extreme situations, so as to comprehensively evaluate the stability and reliability of the data.

[0124] The introduction of the compensation coefficient (w) is an important innovation. It is dynamically adjusted according to the occurrence ratio of the maximum and minimum values ​​of the time difference data, making the data difference stability evaluation coefficient more in line with the actual situation and improving the accuracy and robustness of the evaluation. This adaptive compensation mechanism helps to reduce misjudgments caused by extreme data and improves the stability and reliability of the system.

[0125] By comparing the calculated data difference stability evaluation coefficient with the preset evaluation coefficient threshold, the evaluation and abnormality determination of the distributed power supply power, current and voltage parameter data collection operation status can be realized. Once the data difference stability evaluation coefficient is found to be lower than the preset threshold, it means that there may be data collection abnormality or unstable equipment operation status, so that timely measures can be taken to repair or adjust to ensure the normal operation of the distributed power system.

[0126] This technical solution reduces the possibility of manual intervention and misjudgment through automated data monitoring, analysis and evaluation processes, and improves the efficiency of system maintenance and management. At the same time, it also provides strong data support for fault diagnosis and performance optimization of distributed power systems.

[0127] In summary, this technical solution effectively improves the accuracy of distributed power system data acquisition and the reliability of stability assessment through real-time monitoring, precise calculation, adaptive compensation and abnormality judgment, providing a strong guarantee for the normal operation and efficient management of the system.

[0128] Specifically, when the data difference stability evaluation coefficient is lower than a preset evaluation coefficient threshold, the data collection operation status of the distributed power supply power parameter, the distributed power supply current parameter, and the distributed power supply voltage parameter is evaluated and abnormal determination is performed, including:

[0129] When the data difference stability evaluation coefficient is lower than a preset evaluation coefficient threshold, extracting the acquisition time of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter;

[0130] Determine the first fluctuation parameter corresponding to the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter according to the acquisition time of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter in combination with the first fluctuation acquisition model;

[0131] The model structure of the first fluctuation acquisition model is as follows:

[0132] ;

[0133] Among them, B 01 represents the first fluctuation parameter corresponding to the distributed power supply power parameter, distributed power supply current parameter or distributed power supply voltage parameter obtained by the first fluctuation acquisition model; n represents the number of data collection times corresponding to the distributed power supply power parameter, distributed power supply current parameter and distributed power supply voltage parameter; T i represents the data collection time corresponding to the distributed power source power parameter, distributed power source current parameter or distributed power source voltage parameter during the i-th data collection; T i-1 represents the data collection time corresponding to the distributed power source power parameter, distributed power source current parameter or distributed power source voltage parameter during the i-1th data collection; T e Indicates the maximum allowed amplitude duration between two adjacent acquisition moments; P tIndicates the proportion of the maximum value of the collection time fluctuation of the distributed power supply power parameter, the distributed power supply current parameter or the distributed power supply voltage parameter in the n data collections that have been experienced;

[0134] Compare the first fluctuation parameters corresponding to the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter with a preset first fluctuation parameter threshold; extract the distributed power supply power parameter, the distributed power supply current parameter and / or the distributed power supply voltage parameter corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold;

[0135] According to the number of distributed power supply power parameters, distributed power supply current parameters and / or distributed power supply voltage parameters corresponding to the first fluctuation parameter that exceeds the preset first fluctuation parameter threshold, it is determined whether there is an abnormality in the data collection operation status of the distributed power supply power parameters, distributed power supply current parameters and distributed power supply voltage parameters.

[0136] The technical effect of the above technical solution is: when the data difference stability evaluation coefficient is lower than the preset evaluation coefficient threshold, the technical solution further analyzes the acquisition time of the distributed power source power parameter, current parameter and voltage parameter, and uses the first fluctuation acquisition model to determine the first fluctuation parameters of these parameters. This method can more accurately capture the fluctuation of data in the time series, thereby more effectively identifying potential abnormal or unstable states.

[0137] The first fluctuation acquisition model takes into account the number of data collection times (n), the data collection time (Ti and Ti-1), the preset maximum allowable amplitude duration between two adjacent collection times (Te), and the proportion of the maximum value of the three parameters in the collection time fluctuation (Pt). The introduction of these factors makes the model more dynamic and adaptable, and can automatically adjust the judgment criteria according to different situations, thereby improving the accuracy of anomaly detection.

[0138] The solution not only evaluates the individual fluctuations of the power parameters, current parameters, and voltage parameters of the distributed power supply, but also comprehensively determines whether there are any abnormalities in the data collection operation status by comparing the first fluctuation parameters of these parameters with the preset thresholds and counting the number of parameters that exceed the thresholds. This multi-dimensional evaluation method can more comprehensively reflect the actual status of the system and reduce misjudgments and missed judgments.

[0139] By real-time monitoring and evaluation of the data collection operation status, once an abnormal or unstable situation is found, the early warning mechanism can be triggered immediately to notify relevant personnel to take timely measures to repair or adjust. This helps to reduce the impact of system failures on production operations and improve the reliability and stability of the system.

[0140] By continuously monitoring and evaluating the operating status of data collection, data quality issues such as missing data, errors, or abnormal fluctuations can be discovered and corrected in a timely manner. This helps improve data quality and provide more accurate and reliable information support for subsequent data analysis and decision-making.

[0141] The automated anomaly detection and evaluation process reduces the workload of manual intervention and inspection, allowing system maintenance personnel to focus more on handling actual problems and optimizing system performance. At the same time, accurate analysis and judgment based on data also improves the pertinence and effectiveness of maintenance work.

[0142] In summary, this technical solution realizes accurate monitoring and abnormal judgment of the operating status of distributed power supply data acquisition by introducing the first fluctuation acquisition model and multi-dimensional evaluation method, improves the reliability and stability of the system, optimizes data quality management, and improves the efficiency of system maintenance.

[0143] Specifically, determining whether there is an abnormality in the data collection operation state of the distributed power supply power parameter, the distributed power supply current parameter, and the distributed power supply voltage parameter according to the number of the distributed power supply power parameter, the distributed power supply current parameter, and / or the distributed power supply voltage parameter corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold, includes:

[0144] When the number of distributed power supply power parameters, distributed power supply current parameters or distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold is one, an abnormal alarm is directly issued for the data collection operation status of the distributed power supply power parameters, distributed power supply current parameters or distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold;

[0145] When the number of distributed power supply power parameters, distributed power supply current parameters or distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold is multiple, the time difference data of the distributed power supply power parameters, distributed power supply current parameters and distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold is used to obtain the second fluctuation parameter; wherein the second fluctuation parameter is obtained by the following formula:

[0146] ;

[0147] Among them, B 01 represents the second fluctuation parameter; m represents the number of distributed power supply power parameters, distributed power supply current parameters or distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold; B 01jrepresents the first fluctuation parameter corresponding to the distributed power supply power parameter, the distributed power supply current parameter or the distributed power supply voltage parameter corresponding to the jth first fluctuation parameter exceeding the preset first fluctuation parameter threshold; T cpj represents the average value of the time difference data involved in the distributed power supply power parameter, distributed power supply current parameter or distributed power supply voltage parameter corresponding to the jth first fluctuation parameter exceeding the preset first fluctuation parameter threshold; T e Indicates the maximum allowed amplitude duration between two adjacent acquisition moments;

[0148] When the second fluctuation parameter exceeds a preset second fluctuation parameter threshold, an abnormal alarm is issued for the data collection operation status of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter.

[0149] The technical effect of the above technical solution is: the solution adopts different abnormality determination strategies according to the number of parameters exceeding the preset first fluctuation parameter threshold. When only one parameter exceeds the threshold, the data collection operation status of the parameter is directly alarmed, which helps to quickly locate and deal with a single problem. When multiple parameters exceed the threshold, the second fluctuation parameters of these parameters are further calculated to more comprehensively evaluate the stability of the system.

[0150] When multiple parameters exceed the first fluctuation parameter threshold, the solution uses the time difference data corresponding to these parameters to calculate the second fluctuation parameter. This method not only takes into account the fluctuation amplitude of the parameters, but also combines the time factor, which can more accurately reflect the changing trend and stability of the system status.

[0151] By introducing a second fluctuation parameter and its threshold determination, the solution improves the ability to detect abnormal system conditions. Even when multiple parameters fluctuate at the same time, comprehensive analysis can be used to determine whether an abnormality actually exists, thus avoiding false alarms caused by fluctuations in a single parameter.

[0152] The first fluctuation parameter threshold and the second fluctuation parameter threshold in the scheme are both presettable, which provides users with the flexibility to adjust the judgment criteria according to actual needs. Users can set appropriate thresholds according to the specific situation and operation requirements of the system to achieve the best anomaly detection effect.

[0153] Once an abnormal state is detected, the solution will immediately trigger the abnormal alarm mechanism and notify relevant personnel to take timely measures to deal with it. This efficient abnormality handling process helps reduce the impact of system failures on production operations and improve the reliability and stability of the system.

[0154] By continuously monitoring the data collection operation status and determining abnormalities, the solution helps to promptly discover and correct data quality issues. This not only improves the accuracy and reliability of data, but also provides more powerful support for subsequent data analysis and decision-making.

[0155] In summary, this technical solution achieves comprehensive monitoring and accurate judgment of the operating status of distributed power supply data acquisition through refined abnormal judgment logic, comprehensive time difference data analysis, enhanced abnormal detection capability, flexible threshold setting and efficient abnormal handling process, optimizes data quality management, and improves the reliability and stability of the system.

[0156] In this embodiment, as a preferred technical solution of the present invention, a distributed power supply learning model is constructed according to the operation data of the distributed power supply, and the following operations are performed:

[0157] Obtaining the operating data of distributed power sources;

[0158] Divide the operating data of distributed power sources;

[0159] Determine a distributed power supply training set and a distributed power supply test set;

[0160] Select the appropriate model architecture based on the distributed power generation capacity and grid-connected analysis requirements;

[0161] Based on the distributed power training set, train the selected appropriate model architecture;

[0162] Determine the distributed power learning model;

[0163] Based on the distributed power supply test set, the performance of the distributed power supply learning model is tested;

[0164] Determine the performance test results based on the distributed power learning model;

[0165] Conduct in-depth mining and relevant analysis on the performance test results based on the distributed power learning model;

[0166] Determine the optimal adjustment plan based on the distributed power supply learning model;

[0167] Optimize and adjust the distributed power learning model based on the optimization adjustment plan;

[0168] Determine the optimal distributed power learning model.

[0169] It should be noted that by acquiring the operating data of distributed power sources and building a distributed power source learning model based on the operating data of distributed power sources, it is convenient for subsequent simulation analysis of the real-time operating data of distributed power sources based on the distributed power source learning model, and the analysis results of the distributed power source carrying capacity can be quickly determined, and the distributed power source carrying capacity can be monitored in real time.

[0170] S2: Obtain the operation data of the power grid and build a power grid learning model based on the operation data of the power grid;

[0171] In this embodiment, as a preferred technical solution of the present invention, the operation data of the power grid is obtained by performing the following operations:

[0172] Monitor the operation status of the power grid and determine the power grid status parameters;

[0173] Monitor the operating environment of the power grid and determine the power grid environmental parameters;

[0174] Monitor the operation market of the power grid and determine the power grid market parameters;

[0175] The operation data of the power grid is determined based on the power grid status parameters, environmental parameters and market parameters.

[0176] In this embodiment, as a preferred technical solution of the present invention, a power grid learning model is constructed according to the operation data of the power grid, and the following operations are performed:

[0177] Obtaining the operation data of the power grid;

[0178] Divide the operation data of the power grid;

[0179] Determine a power grid training set and a power grid test set;

[0180] Select the appropriate model architecture based on the distributed power generation capacity and grid-connected analysis requirements;

[0181] Based on the power grid training set, train the selected appropriate model architecture;

[0182] Determine the grid learning model;

[0183] Based on the power grid test set, the performance of the power grid learning model is tested;

[0184] Determine performance test results based on the power grid learning model;

[0185] Conduct in-depth mining and relevant analysis on the performance test results based on the power grid learning model;

[0186] Determine the optimal adjustment plan based on the power grid learning model;

[0187] Optimize and adjust the power grid learning model based on the optimization adjustment plan;

[0188] Determine the optimal power grid learning model.

[0189] It should be noted that by acquiring the operating data of the power grid and building a power grid learning model based on the operating data of the power grid, it is convenient for the subsequent simulation analysis of the real-time operating data of the power grid based on the power grid learning model, and the distributed power generation capacity and grid-connected analysis and evaluation results can be quickly determined, and the distributed power generation capacity and grid-connected conditions can be analyzed and evaluated in real time.

[0190] S3: Conduct simulation analysis and evaluation on the power grid learning model and the distributed power generation learning model, and make distributed power generation capacity and grid connection optimization management and control decisions based on the distributed power generation capacity and grid connection analysis and evaluation results.

[0191] In this embodiment, as a preferred technical solution of the present invention, simulation analysis and evaluation are performed on the power grid learning model and the distributed power source learning model, and the following operations are performed:

[0192] Obtain real-time operation data of distributed power sources;

[0193] Input the real-time operation data of distributed power sources into the optimal distributed power source learning model;

[0194] Based on the optimal distributed power learning model, the real-time operation data of distributed power is simulated and analyzed;

[0195] Determine the analysis results of distributed power generation capacity;

[0196] Obtain real-time operation data of the power grid;

[0197] Input the real-time operation data of the power grid into the optimal power grid learning model;

[0198] Based on the optimal grid learning model, simulate and analyze the real-time operation data of the grid;

[0199] Determine the distributed power generation capacity and grid-connected analysis and evaluation results.

[0200] In this embodiment, as a preferred technical solution of the present invention, the real-time operation data of the distributed power source and the real-time operation data of the power grid are obtained, and the following operations are performed:

[0201] Obtain real-time operation data of distributed power sources and power grids;

[0202] Based on the sequential retrieval method, the real-time operation data of the distributed power source and the real-time operation data of the power grid are retrieved;

[0203] Check the consistency of real-time operation data of distributed power sources and real-time operation data of power grid;

[0204] Check whether the real-time operation data of the distributed power source and the real-time operation data of the power grid meet the requirements according to the reasonable value range and mutual relationship of each variable in the real-time operation data of the distributed power source and the real-time operation data of the power grid;

[0205] Remove inconsistent data that is beyond the normal range, logically unreasonable or contradictory in the real-time operation data of distributed power sources and the real-time operation data of the power grid;

[0206] Process invalid and missing values ​​of real-time operation data of distributed power sources and power grids;

[0207] Remove invalid and missing data that are of no value to the distributed power generation capacity and grid connection analysis from the real-time operation data of the distributed power generation and the real-time operation data of the power grid;

[0208] Determine the real-time operation data of distributed power sources and power grids that are valuable for distributed power generation capacity and grid connection analysis.

[0209] In this embodiment, as a preferred technical solution of the present invention, S3, according to the evaluation results, makes an optimized management and control decision, and performs the following operations:

[0210] Obtain the distributed power generation capacity and grid connection analysis and evaluation results;

[0211] Conduct in-depth exploration and relevant analysis on the distributed power generation capacity and grid connection analysis and evaluation results;

[0212] Determine the distributed power generation capacity and grid-connection optimization management and control decisions;

[0213] Based on the distributed power generation carrying capacity and grid-connected optimization management and control decisions, the distributed power generation carrying capacity and grid-connected conditions are optimized and controlled to enable the distributed power generation to operate efficiently and safely in grid-connected mode.

[0214] It should be noted that based on the results of the distributed power generation capacity and grid-connection analysis and evaluation, distributed power generation capacity and grid-connection optimization management and control decisions are made, and the distributed power generation capacity and grid-connection situation are optimized and controlled based on the distributed power generation capacity and grid-connection optimization management and control decisions, so that the distributed power generation can be efficiently and safely connected to the grid and operate, which can improve the safety and stability of distributed power generation access to the power grid and reduce the risk of power outages caused by distributed power generation failures.

[0215] Therefore, by obtaining the operating data of distributed power sources, a distributed power source learning model is constructed according to the operating data of distributed power sources; by obtaining the operating data of the power grid, a power grid learning model is constructed according to the operating data of the power grid; based on the power grid learning model and the distributed power source learning model, the real-time operating data of the power grid and the real-time operating data of the distributed power sources are simulated, analyzed and evaluated to determine the distributed power source carrying capacity and grid-connected analysis and evaluation results; based on the distributed power source carrying capacity and grid-connected analysis and evaluation results, distributed power source carrying capacity and grid-connected optimization management and control decisions are made; based on the distributed power source carrying capacity and grid-connected optimization management and control decisions, the distributed power source carrying capacity and grid-connected situation are optimized and controlled; the distributed power source carrying capacity and grid-connected situation can be monitored, analyzed and evaluated in real time, the safety and stability of distributed power source access to the power grid can be improved, the risk of power outages caused by distributed power source failures can be reduced, and efficient and safe grid-connected operation of distributed power sources can be realized.

[0216] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0217] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for analyzing the carrying capacity and grid connection of distributed power sources, characterized in that: The steps include: S1: Obtain the operating data of the distributed power source and build a distributed power source learning model based on the operating data of the distributed power source; S2: Obtain the operation data of the power grid and build a power grid learning model based on the operation data of the power grid; S3: Conduct simulation analysis and evaluation on the power grid learning model and distributed power learning model, and make distributed power carrying capacity and grid connection optimization management and control decisions based on the distributed power carrying capacity and grid connection analysis and evaluation results; In S1, the operation data of the distributed power source is obtained, and further includes: Real-time monitoring of the acquisition time of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter; According to the acquisition moments of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter, the data acquisition time difference between the distributed power supply power parameter and the distributed power supply current parameter, the data acquisition time difference between the distributed power supply current parameter and the distributed power supply voltage parameter, and the data acquisition time difference between the distributed power supply power parameter and the distributed power supply voltage parameter; Taking the data acquisition time difference between the distributed power supply power parameter and the distributed power supply current parameter as the first time difference data; Using the data acquisition time difference between the distributed power supply current parameter and the distributed power supply voltage parameter as second time difference data; Using the data acquisition time difference between the distributed power supply power parameter and the distributed power supply voltage parameter as third time difference data; The data difference stability evaluation coefficient is obtained by using the first time difference data, the second time difference data and the third time difference data; wherein the data difference stability evaluation coefficient is obtained by the following formula: ； Wherein, W represents the data difference stability evaluation coefficient; n represents the number of data collection times corresponding to the distributed power supply power parameter, distributed power supply current parameter and distributed power supply voltage parameter; T c01i , T c02i and T c03i They respectively represent the first time difference data, the second time difference data and the third time difference data corresponding to the i-th data collection; w represents the compensation coefficient, and the compensation coefficient is obtained by the following formula: ； Where w represents the compensation coefficient; P max01 and P min01 They respectively represent the occurrence ratio of the first time difference data being the maximum value and the occurrence ratio of the first time difference data being the minimum value in the data collection process that has been experienced; P max02 and P min02 They respectively represent the occurrence ratio of the second time difference data being the maximum value and the occurrence ratio of the second time difference data being the minimum value in the data collection process that has been experienced; P max03 and P min03 They respectively represent the occurrence ratio of the third time difference data being the maximum value and the occurrence ratio of the third time difference data being the minimum value in the data collection process that has been experienced; Comparing the data difference stability evaluation coefficient with a preset evaluation coefficient threshold; When the data difference stability evaluation coefficient is lower than a preset evaluation coefficient threshold, the data collection operation status of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter is evaluated and abnormality is determined.

2. A distributed power source carrying capacity and grid connection analysis method according to claim 1, characterized in that: In S1, the operation data of the distributed power source is obtained, and the following operations are performed: Monitor the output power of distributed power sources and determine the power parameters of distributed power sources; Monitor the output current of the distributed power supply and determine the current parameters of the distributed power supply; Monitor the output voltage of the distributed power supply and determine the voltage parameters of the distributed power supply; The operation data of the distributed power source is determined based on the power parameters, current parameters and voltage parameters of the distributed power source.

3. A distributed power source carrying capacity and grid connection analysis method according to claim 2, characterized in that: When the data difference stability evaluation coefficient is lower than the preset evaluation coefficient threshold, the data collection operation status of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter is evaluated and abnormal determination is performed, including: When the data difference stability evaluation coefficient is lower than a preset evaluation coefficient threshold, extracting the acquisition time of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter; Determine the first fluctuation parameter corresponding to the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter according to the acquisition time of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter in combination with the first fluctuation acquisition model; The model structure of the first fluctuation acquisition model is as follows: ； Among them, B 01 represents the first fluctuation parameter corresponding to the distributed power supply power parameter, distributed power supply current parameter or distributed power supply voltage parameter obtained by the first fluctuation acquisition model; n represents the number of data collection times corresponding to the distributed power supply power parameter, distributed power supply current parameter and distributed power supply voltage parameter; T i represents the data collection time corresponding to the distributed power source power parameter, distributed power source current parameter or distributed power source voltage parameter during the i-th data collection; T i-1 represents the data collection time corresponding to the distributed power source power parameter, distributed power source current parameter or distributed power source voltage parameter during the i-1th data collection; T e Indicates the maximum allowed amplitude duration between two adjacent acquisition moments; P t Indicates the proportion of the maximum value of the collection time fluctuation of the distributed power supply power parameter, the distributed power supply current parameter or the distributed power supply voltage parameter in the n data collections that have been experienced; Compare the first fluctuation parameters corresponding to the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter with a preset first fluctuation parameter threshold; extract the distributed power supply power parameter, the distributed power supply current parameter and / or the distributed power supply voltage parameter corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold; According to the number of distributed power supply power parameters, distributed power supply current parameters and / or distributed power supply voltage parameters corresponding to the first fluctuation parameter that exceeds the preset first fluctuation parameter threshold, it is determined whether there is an abnormality in the data collection operation status of the distributed power supply power parameters, distributed power supply current parameters and distributed power supply voltage parameters.

4. A distributed power supply carrying capacity and grid connection analysis method according to claim 3, characterized in that: According to the number of distributed power supply power parameters, distributed power supply current parameters and / or distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold, respectively determining whether the data collection operation status of the distributed power supply power parameters, the distributed power supply current parameters and the distributed power supply voltage parameters is abnormal, including: When the number of distributed power supply power parameters, distributed power supply current parameters or distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold is one, an abnormal alarm is directly issued for the data collection operation status of the distributed power supply power parameters, distributed power supply current parameters or distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold; When the number of distributed power supply power parameters, distributed power supply current parameters or distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold is multiple, the time difference data of the distributed power supply power parameters, distributed power supply current parameters and distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold is used to obtain the second fluctuation parameter; wherein the second fluctuation parameter is obtained by the following formula: ； Among them, B 01 represents the second fluctuation parameter; m represents the number of distributed power supply power parameters, distributed power supply current parameters or distributed power supply voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold; B 01j represents the first fluctuation parameter corresponding to the distributed power supply power parameter, the distributed power supply current parameter or the distributed power supply voltage parameter corresponding to the jth first fluctuation parameter exceeding the preset first fluctuation parameter threshold; T cpj represents the average value of the time difference data involved in the distributed power supply power parameter, distributed power supply current parameter or distributed power supply voltage parameter corresponding to the jth first fluctuation parameter exceeding the preset first fluctuation parameter threshold; T e Indicates the maximum allowed amplitude duration between two adjacent acquisition moments; When the second fluctuation parameter exceeds a preset second fluctuation parameter threshold, an abnormal alarm is issued for the data collection operation status of the corresponding distributed power supply power parameter, distributed power supply current parameter and distributed power supply voltage parameter.

5. A distributed power source carrying capacity and grid connection analysis method according to claim 4, characterized in that: In S1, a distributed power supply learning model is constructed according to the operation data of the distributed power supply, and the following operations are performed: Obtaining the operating data of distributed power sources; Divide the operating data of distributed power sources; Determine a distributed power supply training set and a distributed power supply test set; Select the appropriate model architecture based on the distributed power generation capacity and grid-connected analysis requirements; Based on the distributed power training set, train the selected appropriate model architecture; Determine the distributed power learning model; Based on the distributed power supply test set, the performance of the distributed power supply learning model is tested; Determine the performance test results based on the distributed power learning model; Conduct in-depth mining and relevant analysis on the performance test results based on the distributed power learning model; Determine the optimal adjustment plan based on the distributed power supply learning model; Optimize and adjust the distributed power learning model based on the optimization adjustment plan; Determine the optimal distributed power learning model.

6. A distributed power source carrying capacity and grid connection analysis method according to claim 5, characterized in that: In S2, the operation data of the power grid is obtained, a power grid learning model is constructed according to the operation data of the power grid, and the following operations are performed: Monitor the operation status of the power grid and determine the power grid status parameters; Monitor the operating environment of the power grid and determine the power grid environmental parameters; Monitor the operation market of the power grid and determine the power grid market parameters; Among them, based on the grid state parameters, environmental parameters and market parameters, the operation data of the grid is determined; Divide the operation data of the power grid; Determine a power grid training set and a power grid test set; Select the appropriate model architecture based on the distributed power generation capacity and grid-connected analysis requirements; Based on the power grid training set, train the selected appropriate model architecture; Determine the grid learning model; Based on the power grid test set, the performance of the power grid learning model is tested; Determine performance test results based on the power grid learning model; Conduct in-depth mining and relevant analysis on the performance test results based on the power grid learning model; Determine the optimal adjustment plan based on the power grid learning model; Optimize and adjust the power grid learning model based on the optimization adjustment plan; Determine the optimal power grid learning model.

7. A distributed power source carrying capacity and grid connection analysis method according to claim 6, characterized in that: In S3, simulation analysis and evaluation are performed on the power grid learning model and the distributed power source learning model, and the following operations are performed: Obtain real-time operation data of distributed power sources; Input the real-time operation data of distributed power sources into the optimal distributed power source learning model; Based on the optimal distributed power learning model, the real-time operation data of distributed power is simulated and analyzed; Determine the analysis results of distributed power generation capacity; Obtain real-time operation data of the power grid; Input the real-time operation data of the power grid into the optimal power grid learning model; Based on the optimal grid learning model, simulate and analyze the real-time operation data of the grid; Determine the distributed power generation capacity and grid-connected analysis and evaluation results.

8. A distributed power source carrying capacity and grid connection analysis method according to claim 7, characterized in that: In S3, the real-time operation data of the distributed power source and the real-time operation data of the power grid are obtained, and the following operations are performed: Obtain real-time operation data of distributed power sources and power grids; Based on the sequential retrieval method, the real-time operation data of the distributed power source and the real-time operation data of the power grid are retrieved; Check the consistency of real-time operation data of distributed power sources and real-time operation data of power grid; Check whether the real-time operation data of the distributed power source and the real-time operation data of the power grid meet the requirements according to the reasonable value range and mutual relationship of each variable in the real-time operation data of the distributed power source and the real-time operation data of the power grid; Remove inconsistent data that is beyond the normal range, logically unreasonable or contradictory in the real-time operation data of distributed power sources and the real-time operation data of the power grid; Process invalid and missing values ​​of real-time operation data of distributed power sources and power grids; Remove invalid and missing data that are of no value to the distributed power generation capacity and grid connection analysis from the real-time operation data of the distributed power generation and the real-time operation data of the power grid; Determine the real-time operation data of distributed power sources and power grids that are valuable for distributed power generation capacity and grid connection analysis.

9. A distributed power source carrying capacity and grid connection analysis method according to claim 8, characterized in that: In S3, an optimization management and control decision is made according to the evaluation results, and the following operations are performed: Obtain the distributed power generation capacity and grid connection analysis and evaluation results; Conduct in-depth exploration and relevant analysis on the distributed power generation capacity and grid connection analysis and evaluation results; Determine the distributed power generation capacity and grid-connection optimization management and control decisions; Based on the distributed power generation carrying capacity and grid-connected optimization management and control decisions, the distributed power generation carrying capacity and grid-connected conditions are optimized and controlled to enable the distributed power generation to operate efficiently and safely in grid-connected mode.

Images