CN118659448B - A method for analyzing the carrying capacity and grid connection of distributed power sources - Google Patents

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

Distributed power supply bearing capacity and grid-connected analysis method

Technical Field

The invention relates to the technical field of power grids, in particular to a distributed power supply bearing capacity and grid connection analysis method.

Background

With the continuous development of renewable energy technology, a distributed power supply is increasingly attracting attention as a novel energy access mode. The distributed power supply is distributed at a user side, is connected with a power grid with the voltage level of 35kV or below, is mainly consumed in situ, and comprises solar energy, natural gas, biomass energy, wind energy, water energy, hydrogen energy, geothermal energy, ocean energy, comprehensive utilization of resources, power generation, energy storage and the like.

The Chinese patent with the publication number of CN117977694A discloses a distributed power supply cluster control method, which comprises the following steps of S1, collecting distributed power supply data based on distributed power supply cluster control, S2, processing the distributed power supply data to determine distributed power supply characterization data based on distributed power supply cluster control, S3, comparing and analyzing the distributed power supply characterization data to determine a distributed power supply analysis result based on distributed power supply cluster control, S4, performing intelligent control on the distributed power supply analysis result based on distributed power supply cluster control to determine a distributed power supply cluster control method based on distributed power supply cluster control, and effectively performing cluster control on distributed power supplies to improve the distributed power supply cluster control effect, wherein the patent has the following defects:

The problem of insufficient bearing capacity of the existing distributed power supply can occur when the existing distributed power supply is connected to a power grid, and the bearing capacity and the grid-connected condition of the distributed power supply cannot be monitored, analyzed and evaluated in real time, so that the grid-connected safety and stability of the distributed power supply are low, and the efficient and safe grid-connected operation of the distributed power supply cannot be realized.

Disclosure of Invention

The invention aims to provide a distributed power supply bearing capacity and grid connection analysis method which can monitor, analyze and evaluate the distributed power supply bearing capacity and grid connection conditions in real time, improve the grid connection safety and stability of the distributed power supply, realize the efficient and safe grid connection operation of the distributed power supply and solve the problems in the background technology.

In order to achieve the above purpose, the present invention provides the following technical solutions:

a distributed power bearing capacity and grid connection analysis method comprises the following steps:

s1, acquiring operation data of a distributed power supply, and constructing a distributed power supply learning model according to the operation data of the distributed power supply;

S2, acquiring operation data of a power grid, and constructing a power grid learning model according to the operation data of the power grid;

And S3, carrying out simulation analysis and evaluation on the power grid learning model and the distributed power supply learning model, and making a distributed power supply bearing capacity and grid connection optimization management and control decision according to the distributed power supply bearing capacity and grid connection analysis and evaluation results.

Preferably, in the step S1, operation data of the distributed power supply is obtained, and the following operations are performed:

Monitoring the output power of the distributed power supply to determine the power parameters of the distributed power supply;

Monitoring the output current of the distributed power supply to determine the current parameter of the distributed power supply;

Monitoring the output voltage of the distributed power supply to determine the voltage parameter of the distributed power supply;

the operation data of the distributed power supply is determined based on the distributed power supply power parameter, the current parameter and the voltage parameter.

Preferably, in the step S1, the obtaining operation data of the distributed power supply further includes:

Monitoring the acquisition time of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter in real time;

Acquiring a data acquisition time difference between the distributed power supply power parameter and the distributed power supply current parameter, a data acquisition time difference between the distributed power supply current parameter and the distributed power supply voltage parameter and a data acquisition time difference between the distributed power supply power 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;

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

Taking the data acquisition time difference between the distributed power supply current parameter and the distributed power supply voltage parameter as second time difference data;

taking the data acquisition time difference between the distributed power supply power parameter and the distributed power supply voltage parameter as third time difference data;

obtaining a data difference stability evaluation coefficient 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:

;

The method comprises the steps of obtaining a data difference stability evaluation coefficient, wherein W represents the data difference stability evaluation coefficient, n represents the data acquisition times corresponding to a distributed power parameter, a distributed power current parameter and a distributed power voltage parameter, T _c01i、T_c02i and T _c03i respectively represent first time difference data, second time difference data and third time difference data corresponding to the data acquisition of the ith time, W represents a compensation coefficient, and the compensation coefficient is obtained through the following formula:

;

Wherein w represents a compensation coefficient, P _max01 and P _min01 represent an occurrence ratio of the first time difference data being the maximum value and an occurrence ratio of the first time difference data being the minimum value, respectively, during the data acquisition process, P _max02 and P _min02 represent an occurrence ratio of the second time difference data being the maximum value and an occurrence ratio of the second time difference data being the minimum value, respectively, during the data acquisition process, P _max03 and P _min03 represent an occurrence ratio of the third time difference data being the maximum value and an occurrence ratio of the third time difference data being the minimum value, respectively;

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

And when the data difference stability evaluation coefficient is lower than a preset evaluation coefficient threshold value, evaluating and judging abnormality of the data acquisition running states of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter.

Preferably, when the data difference stability evaluation coefficient is lower than a preset evaluation coefficient threshold, evaluating and abnormality determining the data acquisition operation states of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter includes:

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

Determining first fluctuation parameters corresponding to the distributed power supply power parameters, the distributed power supply current parameters and the distributed power supply voltage parameters according to the acquisition moments of the distributed power supply power parameters, the distributed power supply current parameters and the distributed power supply voltage parameters and combining a first fluctuation acquisition model;

the model structure of the first fluctuation acquisition model is as follows:

;

The method comprises the steps of obtaining a first fluctuation acquisition model, wherein B ₀₁ represents a distributed power parameter, a distributed power current parameter or a first fluctuation parameter corresponding to a distributed power voltage parameter, n represents data acquisition times corresponding to the distributed power parameter, the distributed power current parameter and the distributed power voltage parameter, T _i represents data acquisition time corresponding to the distributed power parameter, the distributed power current parameter or the distributed power voltage parameter when data acquisition is carried out for the ith time, T _i-1 represents data acquisition time corresponding to the distributed power parameter, the distributed power current parameter or the distributed power voltage parameter when data acquisition is carried out for the ith-1 time, T _e represents preset maximum amplitude duration allowed for each two adjacent acquisition time, and P _t represents that the fluctuation of the acquisition time of the distributed power parameter, the distributed power current parameter or the distributed power voltage parameter in the n times of data acquisition is the maximum proportion of three parameter acquisition fluctuation;

Comparing 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; extracting distributed power parameters, distributed power current parameters and/or distributed power voltage parameters corresponding to first fluctuation parameters exceeding the preset first fluctuation parameter threshold;

And respectively judging whether the data acquisition running states of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter are abnormal or not according to the quantity 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.

Preferably, determining whether the data acquisition running states of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter are abnormal according to the quantity 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:

When the number of the distributed power parameters, the distributed power current parameters or the distributed power voltage parameters corresponding to the first fluctuation parameters exceeding the preset first fluctuation parameter threshold is one, abnormal alarm is directly carried out on the data acquisition running state of the distributed power parameters, the distributed power current parameters or the distributed power voltage parameters corresponding to the first fluctuation parameters exceeding the preset first fluctuation parameter threshold;

When the number of the distributed power parameters, the distributed power current parameters or the distributed power voltage parameters corresponding to the first fluctuation parameters exceeding the preset first fluctuation parameter threshold is a plurality of, acquiring a second fluctuation parameter by using time difference data of the distributed power parameters, the distributed power current parameters and the distributed power voltage parameters corresponding to the first fluctuation parameters exceeding the preset first fluctuation parameter threshold, wherein the second fluctuation parameter is acquired by the following formula:

;

Wherein B ₀₁ represents a second fluctuation parameter, m represents a distributed power parameter, a distributed power current parameter or a number of distributed power voltage parameters corresponding to a first fluctuation parameter exceeding the preset first fluctuation parameter threshold, B _01j represents a distributed power parameter, a distributed power current parameter or a first fluctuation parameter corresponding to a first fluctuation parameter exceeding the preset first fluctuation parameter threshold, T _cpj represents a distributed power parameter, a distributed power current parameter or a time difference data average value related to a distributed power voltage parameter corresponding to a first fluctuation parameter exceeding the preset first fluctuation parameter threshold, and T _e represents a preset maximum allowable amplitude duration of each two adjacent acquisition moments;

And when the second fluctuation parameter exceeds a preset second fluctuation parameter threshold, carrying out abnormal alarm on the data acquisition running states of the fixed distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter.

Preferably, in the step S1, a distributed power source learning model is constructed according to operation data of the distributed power source, and the following operations are performed:

acquiring operation data of a distributed power supply;

dividing operation data of the distributed power supply;

determining a distributed power training set and a distributed power testing set;

Selecting a proper model framework according to the distributed power supply bearing capacity and grid connection analysis requirements;

Training the selected proper model architecture based on the distributed power training set;

determining a distributed power supply learning model;

Performing performance test on the distributed power supply learning model based on the distributed power supply test set;

determining a performance test result based on a distributed power supply learning model;

deep mining and correlation analysis are carried out on performance test results based on the distributed power supply learning model;

determining an optimized adjustment scheme based on a distributed power supply learning model;

Optimizing and adjusting the distributed power supply learning model based on an optimizing and adjusting scheme;

And determining an optimal distributed power supply learning model.

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

Monitoring the running state of the power grid, and determining the state parameters of the power grid;

Monitoring the running environment of the power grid, and determining the environment parameters of the power grid;

monitoring the running market of the power grid, and determining the market parameters of the power grid;

The operation data of the power grid is determined based on the power grid state parameters, the environment parameters and the market parameters.

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

acquiring operation data of a power grid;

Dividing the operation data of the power grid;

determining a power grid training set and a power grid testing set;

Selecting a proper model framework according to the distributed power supply bearing capacity and grid connection analysis requirements;

Training the selected proper model architecture based on the power grid training set;

Determining a power grid learning model;

based on the power grid test set, performing performance test on the power grid learning model;

Determining a performance test result based on a power grid learning model;

Deep mining and correlation analysis are carried out on performance test results based on the power grid learning model;

Determining an optimization adjustment scheme based on a power grid learning model;

Optimizing and adjusting the power grid learning model based on an optimizing and adjusting scheme;

And determining an optimal power grid learning model.

Preferably, in the step 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:

Acquiring real-time operation data of a distributed power supply;

inputting real-time operation data of the distributed power supply into an optimal distributed power supply learning model;

based on an optimal distributed power supply learning model, performing simulation analysis on real-time operation data of the distributed power supply;

determining a distributed power supply bearing capacity analysis result;

Acquiring real-time operation data of a power grid;

Inputting real-time operation data of the power grid into an optimal power grid learning model;

based on an optimal power grid learning model, performing simulation analysis on real-time operation data of a power grid;

and determining the distributed power bearing capacity and the grid-connected analysis and evaluation result.

Preferably, in the step S3, the following operations are executed by acquiring real-time operation data of the distributed power source and real-time operation data of the power grid:

acquiring real-time operation data of a distributed power supply and real-time operation data of a power grid;

Based on a sequential retrieval method, retrieving real-time operation data of the distributed power supply and real-time operation data of a power grid;

checking the consistency of the real-time operation data of the distributed power supply and the real-time operation data of the power grid;

checking whether the real-time operation data of the distributed power supply and the real-time operation data of the power grid are satisfactory or not according to the reasonable value range and the correlation of each variable in the real-time operation data of the distributed power supply and the real-time operation data of the power grid;

the method comprises the steps of removing inconsistent data which exceeds a normal range, is unreasonable in logic or contradicts in real-time operation data of a distributed power supply and real-time operation data of a power grid;

processing invalid values and missing values of the real-time operation data of the distributed power supply and the real-time operation data of the power grid;

removing invalid data and missing data which are not valuable for the distributed power supply bearing capacity and grid connection analysis in the real-time operation data of the distributed power supply and the real-time operation data of the power grid;

and determining the real-time operation data of the distributed power supply, which are valuable for the distributed power supply bearing capacity and grid connection analysis.

Preferably, in the step S3, an optimization management and control decision is made according to the evaluation result, and the following operations are performed:

acquiring a distributed power supply bearing capacity and a grid-connected analysis evaluation result;

deep mining and relevant analysis are carried out on the distributed power supply bearing capacity and the grid connection analysis and evaluation result;

determining the bearing capacity of the distributed power supply and the grid-connected optimization control decision;

and optimizing and controlling the bearing capacity of the distributed power supply and the grid-connected condition based on the optimizing and controlling decision of the bearing capacity of the distributed power supply and the grid-connected condition, so that the distributed power supply can operate in a high-efficiency and safe grid-connected mode.

Compared with the prior art, the invention has the beneficial effects that:

According to the distributed power supply grid-connected control method, the operation data of the distributed power supply are acquired, the distributed power supply learning model is built according to the operation data of the distributed power supply, the power grid learning model is built according to the operation data of the power grid, the real-time operation data of the power grid and the real-time operation data of the distributed power supply are subjected to simulation analysis and evaluation based on the power grid learning model and the distributed power supply learning model, the distributed power supply bearing capacity and the grid-connected analysis and evaluation result are determined, the distributed power supply bearing capacity and the grid-connected optimization and control decision is formulated according to the distributed power supply bearing capacity and the grid-connected analysis and evaluation result, the distributed power supply bearing capacity and the grid-connected condition are subjected to optimization and control based on the distributed power supply bearing capacity and the grid-connected optimization and control decision, the distributed power supply bearing capacity and the grid-connected condition can be monitored, the grid-connected safety and stability of the distributed power supply can be improved, and high-efficiency and safe grid-connected operation of the distributed power supply can be realized.

Drawings

FIG. 1 is a flow chart of a distributed power supply load capacity and grid-tie analysis method of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

In order to solve the problem that the existing distributed power supply cannot monitor, analyze and evaluate the bearing capacity and the grid-connected condition of the distributed power supply in real time, so that the grid-connected safety and stability of the distributed power supply are low, and the high-efficiency and safe grid-connected operation of the distributed power supply cannot be realized, referring to fig. 1, the embodiment provides the following technical scheme:

a distributed power bearing capacity and grid connection analysis method comprises the following steps:

s1, acquiring operation data of a distributed power supply, and constructing a distributed power supply learning model according to the operation data of the distributed power supply;

in this embodiment, as a preferred technical solution of the present invention, operation data of a distributed power supply is obtained, and the following operations are performed:

Monitoring the output power of the distributed power supply to determine the power parameters of the distributed power supply;

Monitoring the output current of the distributed power supply to determine the current parameter of the distributed power supply;

Monitoring the output voltage of the distributed power supply to determine the voltage parameter of the distributed power supply;

the operation data of the distributed power supply is determined based on the distributed power supply power parameter, the current parameter and the voltage parameter.

Specifically, in the S1, the obtaining operation data of the distributed power supply further includes:

Monitoring the acquisition time of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter in real time;

Acquiring a data acquisition time difference between the distributed power supply power parameter and the distributed power supply current parameter, a data acquisition time difference between the distributed power supply current parameter and the distributed power supply voltage parameter and a data acquisition time difference between the distributed power supply power 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;

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

Taking the data acquisition time difference between the distributed power supply current parameter and the distributed power supply voltage parameter as second time difference data;

taking the data acquisition time difference between the distributed power supply power parameter and the distributed power supply voltage parameter as third time difference data;

obtaining a data difference stability evaluation coefficient 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:

;

The method comprises the steps of obtaining a data difference stability evaluation coefficient, wherein W represents the data difference stability evaluation coefficient, n represents the data acquisition times corresponding to a distributed power parameter, a distributed power current parameter and a distributed power voltage parameter, T _c01i、T_c02i and T _c03i respectively represent first time difference data, second time difference data and third time difference data corresponding to the data acquisition of the ith time, W represents a compensation coefficient, and the compensation coefficient is obtained through the following formula:

;

Wherein w represents a compensation coefficient, P _max01 and P _min01 represent an occurrence ratio of the first time difference data being the maximum value and an occurrence ratio of the first time difference data being the minimum value, respectively, during the data acquisition process, P _max02 and P _min02 represent an occurrence ratio of the second time difference data being the maximum value and an occurrence ratio of the second time difference data being the minimum value, respectively, during the data acquisition process, P _max03 and P _min03 represent an occurrence ratio of the third time difference data being the maximum value and an occurrence ratio of the third time difference data being the minimum value, respectively;

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

And when the data difference stability evaluation coefficient is lower than a preset evaluation coefficient threshold value, evaluating and judging abnormality of the data acquisition running states of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter.

The technical effect of the technical scheme is that the data acquisition time difference (namely the first time difference, the second time difference and the third time difference) between the parameters can be accurately calculated by monitoring the power, the current and the voltage parameters of the distributed power supply and the acquisition time of the parameters in real time. The real-time monitoring and accurate calculation ensures timeliness and accuracy of data, and provides a reliable basis for subsequent data analysis and evaluation.

The calculated time difference data (first time difference, second time difference and third time difference) are used to calculate a data difference stability evaluation coefficient (W) by a specific formula in combination with the compensation coefficient. The evaluation coefficient comprehensively considers the distribution characteristic of the data acquisition time difference and the occurrence ratio of extreme cases, so that the stability and the reliability of the data can be comprehensively evaluated.

The introduction of the compensation coefficient (w) is an important innovation point. According to the method, dynamic adjustment is carried out according to the occurrence ratio of the maximum value and the minimum value of the time difference data, so that the stable evaluation coefficient of the data difference is more in line with the actual situation, and the evaluation accuracy and the robustness are improved. The self-adaptive compensation mechanism is beneficial to reducing misjudgment caused by extreme data and improving the stability and reliability of the system.

By comparing the calculated stable evaluation coefficient of the data difference with a preset evaluation coefficient threshold value, the evaluation and the abnormality judgment of the data acquisition running state of the distributed power supply power, current and voltage parameters can be realized. Once the data difference stability evaluation coefficient is found to be lower than a preset threshold value, the situation that data acquisition is abnormal or the running state of equipment is unstable is indicated, so that measures can be taken in time to repair or adjust, and the normal running of a distributed power system is ensured.

According to the technical scheme, through an automatic data monitoring, analyzing and evaluating process, the possibility of manual intervention and misjudgment is reduced, and the efficiency of system maintenance and management is improved. Meanwhile, the method also provides powerful data support for fault diagnosis and performance optimization of the distributed power system.

In summary, the technical scheme effectively improves the accuracy of data acquisition and the reliability of stability assessment of the distributed power system through means of real-time monitoring, accurate calculation, self-adaptive compensation, abnormal judgment and the like, and provides powerful guarantee for normal operation and efficient management of the system.

Specifically, when the data difference stability evaluation coefficient is lower than a preset evaluation coefficient threshold, evaluating and abnormality determining the data acquisition running states of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter, including:

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

Determining first fluctuation parameters corresponding to the distributed power supply power parameters, the distributed power supply current parameters and the distributed power supply voltage parameters according to the acquisition moments of the distributed power supply power parameters, the distributed power supply current parameters and the distributed power supply voltage parameters and combining a first fluctuation acquisition model;

the model structure of the first fluctuation acquisition model is as follows:

;

The method comprises the steps of obtaining a first fluctuation acquisition model, wherein B ₀₁ represents a distributed power parameter, a distributed power current parameter or a first fluctuation parameter corresponding to a distributed power voltage parameter, n represents data acquisition times corresponding to the distributed power parameter, the distributed power current parameter and the distributed power voltage parameter, T _i represents data acquisition time corresponding to the distributed power parameter, the distributed power current parameter or the distributed power voltage parameter when data acquisition is carried out for the ith time, T _i-1 represents data acquisition time corresponding to the distributed power parameter, the distributed power current parameter or the distributed power voltage parameter when data acquisition is carried out for the ith-1 time, T _e represents preset maximum amplitude duration allowed for each two adjacent acquisition time, and P _t represents that the fluctuation of the acquisition time of the distributed power parameter, the distributed power current parameter or the distributed power voltage parameter in the n times of data acquisition is the maximum proportion of three parameter acquisition fluctuation;

Comparing 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; extracting distributed power parameters, distributed power current parameters and/or distributed power voltage parameters corresponding to first fluctuation parameters exceeding the preset first fluctuation parameter threshold;

And respectively judging whether the data acquisition running states of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter are abnormal or not according to the quantity 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.

The technical effect of the technical scheme is that when the stable evaluation coefficient of the data difference is lower than a preset evaluation coefficient threshold, the technical scheme determines first fluctuation parameters of the distributed power parameters, the current parameters and the voltage parameters by further analyzing the acquisition moments of the parameters and utilizing a first fluctuation acquisition model. The method can more accurately capture the fluctuation condition of the data in time sequence, so that potential abnormal or unstable states can be more effectively identified.

The first fluctuation acquisition model takes into account the number of data acquisitions (n), the data acquisition moments (Ti and Ti-1), a preset maximum allowed amplitude duration (Te) per two adjacent acquisition moments, and the proportion (Pt) of the maximum of the three parameters of the fluctuation of the acquisition moments. The introduction of the factors enables the model to have better dynamic adaptability, the judgment standard can be automatically adjusted according to different conditions, and the accuracy of abnormality detection is improved.

The scheme not only evaluates the independent fluctuation conditions of the distributed power supply power parameter, the current parameter and the voltage parameter, but also comprehensively judges whether the data acquisition running state is abnormal or not by comparing the first fluctuation parameter of the parameters with a preset threshold value and counting the parameter quantity exceeding the threshold value. The multidimensional evaluation method can reflect the actual condition of the system more comprehensively, and reduce misjudgment and missed judgment.

By monitoring and evaluating the data acquisition running state in real time, once abnormal or unstable conditions are found, an early warning mechanism can be immediately triggered, and related personnel are informed of timely taking measures to repair or adjust. This helps to reduce the impact of system faults on production operations, improving the reliability and stability of the system.

By continuously monitoring and evaluating the data acquisition operation state, the data quality problem such as data loss, error or abnormal fluctuation can be timely found and corrected. This helps to improve data quality and provides more accurate and reliable information support for subsequent data analysis and decision making.

The automated anomaly detection and assessment process reduces the amount of manual intervention and inspection effort, enabling system maintenance personnel to focus more on handling actual problems and optimizing system performance. Meanwhile, the pertinence and the effectiveness of maintenance work are improved based on accurate analysis and judgment of data.

In summary, by introducing the first fluctuation acquisition model and the multidimensional evaluation method, the technical scheme realizes accurate monitoring and abnormal judgment of the distributed power supply data acquisition running state, improves the reliability and stability of the system, optimizes the data quality management and improves the system maintenance efficiency.

Specifically, according to the number of the distributed power parameters, the distributed power current parameters and/or the distributed power voltage parameters corresponding to the first fluctuation parameter exceeding the preset first fluctuation parameter threshold, whether the data acquisition running states of the distributed power parameters, the distributed power current parameters and the distributed power voltage parameters are abnormal is determined, including:

When the number of the distributed power parameters, the distributed power current parameters or the distributed power voltage parameters corresponding to the first fluctuation parameters exceeding the preset first fluctuation parameter threshold is one, abnormal alarm is directly carried out on the data acquisition running state of the distributed power parameters, the distributed power current parameters or the distributed power voltage parameters corresponding to the first fluctuation parameters exceeding the preset first fluctuation parameter threshold;

When the number of the distributed power parameters, the distributed power current parameters or the distributed power voltage parameters corresponding to the first fluctuation parameters exceeding the preset first fluctuation parameter threshold is a plurality of, acquiring a second fluctuation parameter by using time difference data of the distributed power parameters, the distributed power current parameters and the distributed power voltage parameters corresponding to the first fluctuation parameters exceeding the preset first fluctuation parameter threshold, wherein the second fluctuation parameter is acquired by the following formula:

;

Wherein B ₀₁ represents a second fluctuation parameter, m represents a distributed power parameter, a distributed power current parameter or a number of distributed power voltage parameters corresponding to a first fluctuation parameter exceeding the preset first fluctuation parameter threshold, B _01j represents a distributed power parameter, a distributed power current parameter or a first fluctuation parameter corresponding to a first fluctuation parameter exceeding the preset first fluctuation parameter threshold, T _cpj represents a distributed power parameter, a distributed power current parameter or a time difference data average value related to a distributed power voltage parameter corresponding to a first fluctuation parameter exceeding the preset first fluctuation parameter threshold, and T _e represents a preset maximum allowable amplitude duration of each two adjacent acquisition moments;

And when the second fluctuation parameter exceeds a preset second fluctuation parameter threshold, carrying out abnormal alarm on the data acquisition running states of the fixed distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter.

The technical effect of the technical scheme is that different abnormality judgment strategies are adopted according to the parameter quantity exceeding the preset first fluctuation parameter threshold value. When only one parameter exceeds the threshold value, the abnormal alarm is directly carried out on the data acquisition running state of the parameter, which is helpful for quickly positioning and processing single problems. And when there are multiple parameters exceeding the threshold, a second fluctuation parameter of the parameters is further calculated to more fully evaluate the stability of the system.

In the case where the plurality of parameters exceeds the first fluctuation parameter threshold, the scheme calculates a second fluctuation parameter using time difference data corresponding to the parameters. The method not only considers the fluctuation range of the parameters, but also combines the time factors, and can reflect the change trend and the stability of the system state more accurately.

By introducing the second fluctuation parameter and the threshold value judgment thereof, the scheme improves the detection capability of the abnormal state of the system. Even when a plurality of parameters fluctuate at the same time, whether abnormality exists really can be determined through comprehensive analysis, and false alarm caused by single parameter fluctuation is avoided.

The first fluctuation parameter threshold value and the second fluctuation parameter threshold value in the scheme are both preset, and flexibility is provided for a user to adjust the judgment standard according to actual requirements. The user can set a proper threshold according to the specific condition and operation requirement of the system so as to achieve the optimal abnormality detection effect.

Once an abnormal state is detected, the scheme can immediately trigger an abnormal alarm mechanism to inform related personnel to take measures in time for processing. The efficient exception handling flow is beneficial to reducing the influence of system faults on production operation and improving the reliability and stability of the system.

By continuously monitoring the data acquisition running state and judging abnormality, the scheme is helpful for timely finding and correcting the data quality problem. The method not only can improve the accuracy and reliability of the data, but also can provide more powerful support for subsequent data analysis and decision-making.

In summary, according to the technical scheme, through refined abnormality determination logic, comprehensive time difference data analysis, enhanced abnormality detection capability, flexible threshold setting and efficient abnormality processing flow, comprehensive monitoring and accurate determination of the distributed power supply data acquisition running state are realized, data quality management is optimized, and reliability and stability of a system are improved.

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

acquiring operation data of a distributed power supply;

dividing operation data of the distributed power supply;

determining a distributed power training set and a distributed power testing set;

Selecting a proper model framework according to the distributed power supply bearing capacity and grid connection analysis requirements;

Training the selected proper model architecture based on the distributed power training set;

determining a distributed power supply learning model;

Performing performance test on the distributed power supply learning model based on the distributed power supply test set;

determining a performance test result based on a distributed power supply learning model;

deep mining and correlation analysis are carried out on performance test results based on the distributed power supply learning model;

determining an optimized adjustment scheme based on a distributed power supply learning model;

Optimizing and adjusting the distributed power supply learning model based on an optimizing and adjusting scheme;

And determining an optimal distributed power supply learning model.

It should be noted that, by acquiring the operation data of the distributed power source, a distributed power source learning model is constructed according to the operation data of the distributed power source, so that the subsequent simulation analysis of the real-time operation data of the distributed power source based on the distributed power source learning model is facilitated, the analysis result of the bearing capacity of the distributed power source can be rapidly determined, and the bearing capacity of the distributed power source can be monitored in real time.

S2, acquiring operation data of a power grid, and constructing a power grid learning model according to the operation data of the power grid;

In this embodiment, as a preferred technical solution of the present invention, operation data of a power grid is obtained, and the following operations are performed:

Monitoring the running state of the power grid, and determining the state parameters of the power grid;

Monitoring the running environment of the power grid, and determining the environment parameters of the power grid;

monitoring the running market of the power grid, and determining the market parameters of the power grid;

The operation data of the power grid is determined based on the power grid state parameters, the environment parameters and the market parameters.

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

acquiring operation data of a power grid;

Dividing the operation data of the power grid;

determining a power grid training set and a power grid testing set;

Selecting a proper model framework according to the distributed power supply bearing capacity and grid connection analysis requirements;

Training the selected proper model architecture based on the power grid training set;

Determining a power grid learning model;

based on the power grid test set, performing performance test on the power grid learning model;

Determining a performance test result based on a power grid learning model;

Deep mining and correlation analysis are carried out on performance test results based on the power grid learning model;

Determining an optimization adjustment scheme based on a power grid learning model;

Optimizing and adjusting the power grid learning model based on an optimizing and adjusting scheme;

And determining an optimal power grid learning model.

By acquiring the operation data of the power grid, a power grid learning model is constructed according to the operation data of the power grid, so that the follow-up simulation analysis of the real-time operation data of the power grid based on the power grid learning model is facilitated, the analysis and evaluation results of the distributed power supply bearing capacity and the grid connection can be rapidly determined, and the real-time analysis and evaluation of the distributed power supply bearing capacity and the grid connection condition can be performed.

And S3, carrying out simulation analysis and evaluation on the power grid learning model and the distributed power supply learning model, and making a distributed power supply bearing capacity and grid connection optimization management and control decision according to the distributed power supply bearing capacity and grid connection analysis and evaluation results.

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

Acquiring real-time operation data of a distributed power supply;

inputting real-time operation data of the distributed power supply into an optimal distributed power supply learning model;

based on an optimal distributed power supply learning model, performing simulation analysis on real-time operation data of the distributed power supply;

determining a distributed power supply bearing capacity analysis result;

Acquiring real-time operation data of a power grid;

Inputting real-time operation data of the power grid into an optimal power grid learning model;

based on an optimal power grid learning model, performing simulation analysis on real-time operation data of a power grid;

and determining the distributed power bearing capacity and the grid-connected analysis and evaluation result.

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

acquiring real-time operation data of a distributed power supply and real-time operation data of a power grid;

Based on a sequential retrieval method, retrieving real-time operation data of the distributed power supply and real-time operation data of a power grid;

checking the consistency of the real-time operation data of the distributed power supply and the real-time operation data of the power grid;

checking whether the real-time operation data of the distributed power supply and the real-time operation data of the power grid are satisfactory or not according to the reasonable value range and the correlation of each variable in the real-time operation data of the distributed power supply and the real-time operation data of the power grid;

the method comprises the steps of removing inconsistent data which exceeds a normal range, is unreasonable in logic or contradicts in real-time operation data of a distributed power supply and real-time operation data of a power grid;

processing invalid values and missing values of the real-time operation data of the distributed power supply and the real-time operation data of the power grid;

removing invalid data and missing data which are not valuable for the distributed power supply bearing capacity and grid connection analysis in the real-time operation data of the distributed power supply and the real-time operation data of the power grid;

and determining the real-time operation data of the distributed power supply, which are valuable for the distributed power supply bearing capacity and grid connection analysis.

In this embodiment, as a preferred technical solution of the present invention, the step S3 of making an optimization management and control decision according to the evaluation result performs the following operations:

acquiring a distributed power supply bearing capacity and a grid-connected analysis evaluation result;

deep mining and relevant analysis are carried out on the distributed power supply bearing capacity and the grid connection analysis and evaluation result;

determining the bearing capacity of the distributed power supply and the grid-connected optimization control decision;

and optimizing and controlling the bearing capacity of the distributed power supply and the grid-connected condition based on the optimizing and controlling decision of the bearing capacity of the distributed power supply and the grid-connected condition, so that the distributed power supply can operate in a high-efficiency and safe grid-connected mode.

The distributed power supply load capacity and grid connection optimization control decision is formulated based on the distributed power supply load capacity and grid connection analysis evaluation result, and the distributed power supply load capacity and grid connection situation are optimally controlled based on the distributed power supply load capacity and grid connection optimization control decision, so that the distributed power supply can be operated in a high-efficiency and safe grid connection mode, the safety and stability of the distributed power supply connected to a power grid can be improved, and the power failure risk caused by the distributed power supply failure is reduced.

Therefore, by acquiring the operation data of the distributed power supply, constructing a distributed power supply learning model according to the operation data of the distributed power supply, acquiring the operation data of the power grid, constructing a power grid learning model according to the operation data of the power grid, carrying out simulation analysis and evaluation on the real-time operation data of the power grid and the real-time operation data of the distributed power supply based on the power grid learning model and the distributed power supply learning model, determining the analysis and evaluation results of the distributed power supply bearing capacity and the grid connection, formulating the distributed power supply bearing capacity and the grid connection optimization and management and control decision according to the analysis and evaluation results of the distributed power supply bearing capacity and the grid connection, carrying out optimization and management and control on the distributed power supply bearing capacity and the grid connection condition based on the distributed power supply bearing capacity and the grid connection optimization and management and control decision, carrying out real-time monitoring and analysis and evaluation on the distributed power bearing capacity and the grid connection condition, improving the safety and stability of the distributed power supply access to the power grid, reducing the power failure risk caused by the distributed power failure, and realizing the efficient and safe grid connection operation of the distributed power supply.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.

Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (9)

1. The distributed power supply bearing capacity and grid connection analysis method is characterized by comprising the following steps of:

s1, acquiring operation data of a distributed power supply, and constructing a distributed power supply learning model according to the operation data of the distributed power supply;

S2, acquiring operation data of a power grid, and constructing a power grid learning model according to the operation data of the power grid;

S3, performing simulation analysis and evaluation on the power grid learning model and the distributed power supply learning model, and making a distributed power supply bearing capacity and grid connection optimization management and control decision according to the distributed power supply bearing capacity and grid connection analysis and evaluation result;

in the step S1, obtaining operation data of the distributed power supply further includes:

Monitoring the acquisition time of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter in real time;

Acquiring a data acquisition time difference between the distributed power supply power parameter and the distributed power supply current parameter, a data acquisition time difference between the distributed power supply current parameter and the distributed power supply voltage parameter and a data acquisition time difference between the distributed power supply power 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;

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

Taking the data acquisition time difference between the distributed power supply current parameter and the distributed power supply voltage parameter as second time difference data;

taking the data acquisition time difference between the distributed power supply power parameter and the distributed power supply voltage parameter as third time difference data;

obtaining a data difference stability evaluation coefficient 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:

;

The method comprises the steps of obtaining a data difference stability evaluation coefficient, wherein W represents the data difference stability evaluation coefficient, n represents the data acquisition times corresponding to a distributed power parameter, a distributed power current parameter and a distributed power voltage parameter, T _c01i、T_c02i and T _c03i respectively represent first time difference data, second time difference data and third time difference data corresponding to the data acquisition of the ith time, W represents a compensation coefficient, and the compensation coefficient is obtained through the following formula:

;

Wherein w represents a compensation coefficient, P _max01 and P _min01 represent an occurrence ratio of the first time difference data being the maximum value and an occurrence ratio of the first time difference data being the minimum value, respectively, during the data acquisition process, P _max02 and P _min02 represent an occurrence ratio of the second time difference data being the maximum value and an occurrence ratio of the second time difference data being the minimum value, respectively, during the data acquisition process, P _max03 and P _min03 represent an occurrence ratio of the third time difference data being the maximum value and an occurrence ratio of the third time difference data being the minimum value, respectively;

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

And when the data difference stability evaluation coefficient is lower than a preset evaluation coefficient threshold value, evaluating and judging abnormality of the data acquisition running states of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter.

2. The method for analyzing the bearing capacity and grid connection of a distributed power supply according to claim 1, wherein in S1, operation data of the distributed power supply is obtained, and the following operations are performed:

Monitoring the output power of the distributed power supply to determine the power parameters of the distributed power supply;

Monitoring the output current of the distributed power supply to determine the current parameter of the distributed power supply;

Monitoring the output voltage of the distributed power supply to determine the voltage parameter of the distributed power supply;

the operation data of the distributed power supply is determined based on the distributed power supply power parameter, the current parameter and the voltage parameter.

3. The method for analyzing the load capacity and the grid connection of the distributed power supply according to claim 2, wherein when the data difference stability evaluation coefficient is lower than a preset evaluation coefficient threshold, evaluating and abnormality determining the data acquisition operation states of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter comprises:

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

Determining first fluctuation parameters corresponding to the distributed power supply power parameters, the distributed power supply current parameters and the distributed power supply voltage parameters according to the acquisition moments of the distributed power supply power parameters, the distributed power supply current parameters and the distributed power supply voltage parameters and combining a first fluctuation acquisition model;

the model structure of the first fluctuation acquisition model is as follows:

;

The method comprises the steps of obtaining a first fluctuation acquisition model, wherein B ₀₁ represents a distributed power parameter, a distributed power current parameter or a first fluctuation parameter corresponding to a distributed power voltage parameter, n represents data acquisition times corresponding to the distributed power parameter, the distributed power current parameter and the distributed power voltage parameter, T _i represents data acquisition time corresponding to the distributed power parameter, the distributed power current parameter or the distributed power voltage parameter when data acquisition is carried out for the ith time, T _i-1 represents data acquisition time corresponding to the distributed power parameter, the distributed power current parameter or the distributed power voltage parameter when data acquisition is carried out for the ith-1 time, T _e represents preset maximum amplitude duration allowed for each two adjacent acquisition time, and P _t represents that the fluctuation of the acquisition time of the distributed power parameter, the distributed power current parameter or the distributed power voltage parameter in the n times of data acquisition is the maximum proportion of three parameter acquisition fluctuation;

Comparing 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; extracting distributed power parameters, distributed power current parameters and/or distributed power voltage parameters corresponding to first fluctuation parameters exceeding the preset first fluctuation parameter threshold;

And respectively judging whether the data acquisition running states of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter are abnormal or not according to the quantity 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.

4. The method for analyzing the carrying capacity and the grid connection of a distributed power supply according to claim 3, wherein determining whether the data collection operation states of the distributed power supply power parameter, the distributed power supply current parameter and the distributed power supply voltage parameter are abnormal according to the quantity 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 value comprises:

When the number of the distributed power parameters, the distributed power current parameters or the distributed power voltage parameters corresponding to the first fluctuation parameters exceeding the preset first fluctuation parameter threshold is one, abnormal alarm is directly carried out on the data acquisition running state of the distributed power parameters, the distributed power current parameters or the distributed power voltage parameters corresponding to the first fluctuation parameters exceeding the preset first fluctuation parameter threshold;

When the number of the distributed power parameters, the distributed power current parameters or the distributed power voltage parameters corresponding to the first fluctuation parameters exceeding the preset first fluctuation parameter threshold is a plurality of, acquiring a second fluctuation parameter by using time difference data of the distributed power parameters, the distributed power current parameters and the distributed power voltage parameters corresponding to the first fluctuation parameters exceeding the preset first fluctuation parameter threshold, wherein the second fluctuation parameter is acquired by the following formula:

;

Wherein B ₀₁ represents a second fluctuation parameter, m represents a distributed power parameter, a distributed power current parameter or a number of distributed power voltage parameters corresponding to a first fluctuation parameter exceeding the preset first fluctuation parameter threshold, B _01j represents a distributed power parameter, a distributed power current parameter or a first fluctuation parameter corresponding to a first fluctuation parameter exceeding the preset first fluctuation parameter threshold, T _cpj represents a distributed power parameter, a distributed power current parameter or a time difference data average value related to a distributed power voltage parameter corresponding to a first fluctuation parameter exceeding the preset first fluctuation parameter threshold, and T _e represents a preset maximum allowable amplitude duration of each two adjacent acquisition moments;

And when the second fluctuation parameter exceeds a preset second fluctuation parameter threshold, carrying out abnormal alarm on the data acquisition running states corresponding to the distributed power parameter, the distributed power current parameter and the distributed power voltage parameter.

5. The method for analyzing the bearing capacity and the grid connection of the distributed power supply according to claim 4, wherein 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:

acquiring operation data of a distributed power supply;

dividing operation data of the distributed power supply;

determining a distributed power training set and a distributed power testing set;

Selecting a proper model framework according to the distributed power supply bearing capacity and grid connection analysis requirements;

Training the selected proper model architecture based on the distributed power training set;

determining a distributed power supply learning model;

Performing performance test on the distributed power supply learning model based on the distributed power supply test set;

determining a performance test result based on a distributed power supply learning model;

deep mining and correlation analysis are carried out on performance test results based on the distributed power supply learning model;

determining an optimized adjustment scheme based on a distributed power supply learning model;

Optimizing and adjusting the distributed power supply learning model based on an optimizing and adjusting scheme;

And determining an optimal distributed power supply learning model.

6. The method for analyzing the bearing capacity and the grid connection of the distributed power supply according to claim 5, wherein in S2, 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:

Monitoring the running state of the power grid, and determining the state parameters of the power grid;

Monitoring the running environment of the power grid, and determining the environment parameters of the power grid;

monitoring the running market of the power grid, and determining the market parameters of the power grid;

Determining operation data of the power grid based on the power grid state parameters, the environment parameters and the market parameters;

Dividing the operation data of the power grid;

determining a power grid training set and a power grid testing set;

Selecting a proper model framework according to the distributed power supply bearing capacity and grid connection analysis requirements;

Training the selected proper model architecture based on the power grid training set;

Determining a power grid learning model;

based on the power grid test set, performing performance test on the power grid learning model;

Determining a performance test result based on a power grid learning model;

Deep mining and correlation analysis are carried out on performance test results based on the power grid learning model;

Determining an optimization adjustment scheme based on a power grid learning model;

Optimizing and adjusting the power grid learning model based on an optimizing and adjusting scheme;

And determining an optimal power grid learning model.

7. The method for analyzing the bearing capacity and the grid connection of the distributed power supply according to claim 6, wherein in S3, the following operations are performed by performing simulation analysis and evaluation on a power grid learning model and a distributed power source learning model:

Acquiring real-time operation data of a distributed power supply;

inputting real-time operation data of the distributed power supply into an optimal distributed power supply learning model;

based on an optimal distributed power supply learning model, performing simulation analysis on real-time operation data of the distributed power supply;

determining a distributed power supply bearing capacity analysis result;

Acquiring real-time operation data of a power grid;

Inputting real-time operation data of the power grid into an optimal power grid learning model;

based on an optimal power grid learning model, performing simulation analysis on real-time operation data of a power grid;

and determining the distributed power bearing capacity and the grid-connected analysis and evaluation result.

8. The method for analyzing the bearing capacity and the grid connection of the distributed power supply according to claim 7, wherein in S3, the following operations are performed by acquiring real-time operation data of the distributed power supply and real-time operation data of a power grid:

acquiring real-time operation data of a distributed power supply and real-time operation data of a power grid;

Based on a sequential retrieval method, retrieving real-time operation data of the distributed power supply and real-time operation data of a power grid;

checking the consistency of the real-time operation data of the distributed power supply and the real-time operation data of the power grid;

checking whether the real-time operation data of the distributed power supply and the real-time operation data of the power grid are satisfactory or not according to the reasonable value range and the correlation of each variable in the real-time operation data of the distributed power supply and the real-time operation data of the power grid;

the method comprises the steps of removing inconsistent data which exceeds a normal range, is unreasonable in logic or contradicts in real-time operation data of a distributed power supply and real-time operation data of a power grid;

processing invalid values and missing values of the real-time operation data of the distributed power supply and the real-time operation data of the power grid;

removing invalid data and missing data which are not valuable for the distributed power supply bearing capacity and grid connection analysis in the real-time operation data of the distributed power supply and the real-time operation data of the power grid;

and determining the real-time operation data of the distributed power supply, which are valuable for the distributed power supply bearing capacity and grid connection analysis.

9. The distributed power supply capacity and grid-tie analysis method according to claim 8, wherein in S3, an optimization management and control decision is made according to the evaluation result, and the following operations are performed:

acquiring a distributed power supply bearing capacity and a grid-connected analysis evaluation result;

deep mining and relevant analysis are carried out on the distributed power supply bearing capacity and the grid connection analysis and evaluation result;

determining the bearing capacity of the distributed power supply and the grid-connected optimization control decision;

and optimizing and controlling the bearing capacity of the distributed power supply and the grid-connected condition based on the optimizing and controlling decision of the bearing capacity of the distributed power supply and the grid-connected condition, so that the distributed power supply can operate in a high-efficiency and safe grid-connected mode.