An intelligent self-regulating power concentrator

Abstract

The present invention relates to the technical field of concentrators, and in particular to an intelligent self-regulating power concentrator, comprising: a data acquisition module, a storage processing module, a data analysis module, an analysis and regulation module, and a remote management module, wherein the data acquisition module acquires electrical parameters and meter readings of power grid nodes; the storage processing module adds a timestamp and stores data, and generates a time domain image of power grid data; the data analysis module determines data fluctuation characterization parameters and analysis categories according to the time domain image; the analysis and regulation module selects a data analysis method according to the analysis category, predicts load changes and detects anomalies; and the remote management module sends instructions to a master station according to the analysis method. The present invention classifies the collected power grid information before analysis, reduces unnecessary data duplication processes, and improves the working efficiency of the power concentrator.

Description

Technical Field

[0001] The present invention relates to the technical field of concentrators, and in particular to an intelligent self-regulating power concentrator. Background Art

[0002] A concentrator device is a central connection point device that connects terminals, computers or communication equipment. It becomes the central point where cables converge. In areas with dense terminal density, in order to reduce communication lines, the terminal is usually connected to the concentrator first, and then the concentrator is connected to the computer's communication controller through a high-speed line. The concentrator has the function of a statistical time division multiplexer, which can smooth the data streams input by various terminals; it has buffer storage and intelligent capabilities. When the concentrator is overloaded, it can input information for caching and queuing; it has communication control software, which can perform data stream multiplexing and demultiplexing and execute transmission control procedures to enhance signal functions.

[0003] Chinese patent application publication number: CN105006135A discloses a remote automatic meter reading concentrator system, including a smart electric energy meter, a data collector, a power line modem 2, a low-voltage power grid, a power line modem 1, a concentrator, a modem 2, a data communication network, a modem 1, and a remote server meter reading center. The data collector is embedded in the smart electric meter to automatically collect, process and send the power consumption information and charging information of the monitored power-consuming equipment. The data collector converts the collected power consumption data into a data format suitable for power carrier transmission through the power line modem 2 and outputs and transmits it through the low-voltage power grid; the data transmitted by the low-voltage power grid carrier is converted into a data format through the power line modem, and the format-converted data is transmitted to the concentrator; it can be seen that the remote automatic meter reading concentrator system has the following problems: the collected power information is not classified and is directly and repeatedly acquired, resulting in the power concentrator collecting unnecessary data, resulting in a waste of computing power. Summary of the invention

[0004] To this end, the present invention provides an intelligent self-regulating power concentrator to overcome the problem in the prior art that the collected power information is not classified and directly acquired repeatedly, resulting in the power concentrator collecting unnecessary data and causing a waste of computing power.

[0005] To achieve the above object, the present invention provides an intelligent self-regulating power concentrator, comprising:

[0006] A data acquisition module is used to continuously collect grid data from each node in the grid. The grid data includes electrical parameters and meter readings. The electrical parameters include voltage, current, power and power factor.

[0007] A storage processing module, which is connected to the data acquisition module, is used to add time stamps to the data of each node of the power grid and store them accordingly, and draw a number of time domain images of power grid data according to the storage status of the data;

[0008] A data analysis module, connected to the storage processing module, for determining data fluctuation characterization parameters according to each of the power grid data time domain images, and determining a data analysis category according to the data fluctuation characterization parameters;

[0009] An analysis and adjustment module, which is respectively connected to the data analysis module, the storage processing module and the data acquisition module, and is used to determine a data analysis method according to the data analysis category, including:

[0010] Directly analyze the current power grid data, predict load changes based on the analysis results, and determine whether there are any abnormalities;

[0011] Or, determining the missing discrete parameters according to the stored power grid data to determine the data missing type, so as to determine the data processing method, performing data analysis on the processed power grid data, predicting the load change according to the analysis result, and judging whether there is an abnormality;

[0012] The remote management module is connected to the analysis and adjustment module and determines the content of the instruction sent to the main station according to the data analysis method.

[0013] Furthermore, the frequency at which the storage processing module adds the timestamp is the same as the frequency at which the data acquisition module acquires the power grid data;

[0014] If the data acquisition module fails to successfully collect data, the data corresponding to the current timestamp will be recorded as 0.

[0015] Furthermore, the data analysis module determines the data fluctuation characterization parameter according to formula (1),

[0016]

[0017] In formula (1), K is the parameter characterizing data fluctuation, n1 is the total number of non-zero power grid data, n0 is the total number of timestamps, ki is the i-th power grid sub-data, k0 is the mean value of the current type of power grid data, and i is an integer greater than 0.

[0018] Furthermore, the data analysis module determines the data analysis category according to the data fluctuation characterization parameter.

[0019] If the data fluctuation characterization parameter meets the preset analysis condition, the data analysis category of the current power grid data is determined to be indirect analysis;

[0020] If the data fluctuation characterization parameter does not meet the preset analysis condition, the data analysis category of the current power grid data is determined to be direct analysis.

[0021] Among them, the preset analysis condition is that the data fluctuation characterization parameter is greater than the preset fluctuation parameter or the data fluctuation characterization parameter is equal to 0.

[0022] Furthermore, the analysis and adjustment module determines the data analysis method according to the data analysis category.

[0023] If the data analysis category is indirect analysis, the missing discrete parameter is determined according to the stored power grid data to determine the data missing type, so as to determine the data adjustment method, perform data analysis on the adjusted power grid data, predict the load change according to the analysis result, and determine whether there is an abnormality;

[0024] If the data analysis category is direct analysis, data analysis is directly performed on the current meter reading, load changes are predicted based on the analysis results, and it is determined whether there is an abnormality.

[0025] Furthermore, the analysis and adjustment module determines the missing discrete parameter according to formula (2):

[0026]

[0027] In formula (2), c represents the missing discrete parameter, n0 is the total number of timestamps, ki is the i-th power grid sub-data, k0 is the mean value of the current power grid sub-data, and i is an integer greater than 0.

[0028] Furthermore, the analysis and adjustment module determines the missing discrete parameter according to the stored power grid data to determine the data missing type.

[0029] If the missing discrete parameter is greater than the preset missing discrete parameter, the current data missing type is determined to be discrete data missing;

[0030] If the missing discrete parameter is less than or equal to the preset missing discrete parameter and greater than the standard missing discrete parameter, the current data missing type is determined to be continuous data missing.

[0031] Furthermore, the data processing method of the analysis and adjustment module for processing the power grid data according to the data missing type includes:

[0032] If the analysis and adjustment module determines that the current data missing type is discrete data missing, then reacquire the corresponding power grid data according to the power grid data type corresponding to the timestamp of the data record being 0;

[0033] If the analysis and adjustment module determines that the current data missing type is continuous data missing, the power grid data in the timestamp set with data records of 0 are removed to perform analysis based on the remaining power grid data.

[0034] Furthermore, the analysis and adjustment module determines whether there is an abnormality based on the predicted load change result.

[0035] If the predicted load change result exceeds the standard change result, it is determined that there is an abnormality at the load end and remote management is required;

[0036] If the predicted load change result does not exceed the standard change result, it is determined that there is no abnormality at the load end and no remote management is required.

[0037] Furthermore, the remote management module also includes an instruction sending unit for implementing remote control content.

[0038] Compared with the prior art, the beneficial effect of the present invention lies in that the data acquisition module can continuously collect grid data of each node of the grid, including electrical parameters and meter readings, to realize real-time monitoring of the grid status and data acquisition; the storage and processing module adds timestamps to the collected data and stores them, can effectively manage and organize the data, and generate a time domain image of the grid data according to the storage situation, which is convenient for subsequent analysis and visualization; the data analysis module determines the data fluctuation characterization parameters according to the time domain image of the grid data, and then determines the data analysis category; the analysis and adjustment module can select a suitable data analysis method according to the data analysis category, including directly analyzing the meter readings or determining the missing parameters according to the stored data and adjusting them, so as to predict load changes and detect abnormal situations, which is helpful to find problems in advance and take corresponding measures; the remote management module can determine the content of the instructions sent to the main station according to the data analysis method, realize remote management and control of the power grid system, and improve the flexibility and response speed of the system; the present invention classifies the collected power grid information before analysis, reduces unnecessary data duplication processes, and improves the working efficiency of the power concentrator.

[0039] Furthermore, in the present invention, the frequency at which the storage and processing module adds timestamps to data is the same as the frequency at which the data acquisition module collects power grid data, thereby ensuring the synchronization of the timestamp and the power grid data; when the data acquisition module fails to successfully collect data, the storage and processing module records the data corresponding to the current timestamp as 0, thereby ensuring the integrity and continuity of the data, so that the stored data has certain reliability and availability; by recording the timestamp data corresponding to the data that has not been successfully collected as 0, the storage and processing module can promptly identify the moment when the data collection is abnormal, providing a basis for subsequent data analysis and anomaly detection, and helping the system to respond to and handle abnormal situations in a timely manner.

[0040] Furthermore, in the present invention, by determining the data analysis category according to the data fluctuation characterization parameters, the system can dynamically select the analysis method according to the characteristics of the data, thereby achieving flexible adaptation to different situations and improving the applicability and performance of the system; and the system predicts load changes based on the analysis results and determines whether there are anomalies. It has strong anomaly detection and prediction capabilities, which helps to timely discover and handle abnormal situations and improve the stability and reliability of the system.

[0041] Furthermore, in the present invention, by analyzing the parameters characterizing data fluctuations, the current data missing type can be accurately determined, and subsequent processing can be carried out in a targeted manner; different processing methods are adopted according to different types of data missing. For continuous data missing, the corresponding power grid data is reacquired; for discrete data missing, the corresponding image segments in the timestamp set with data records of 0 are eliminated. This flexible processing method can more effectively deal with different types of data missing; the coefficient of variation c in probability statistics is introduced into data analysis, and continuous missing and intermittent missing are distinguished, so that data interpolation or processing methods can be selected more accurately, thereby improving the accuracy and reliability of data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a schematic diagram of the structure of an intelligent self-regulating power concentrator according to an embodiment of the present invention;

[0043] Figure 2 A logic diagram for determining data parsing categories for an embodiment of the present invention;

[0044] Figure 3 A logic diagram for determining data missing types for an embodiment of the present invention;

[0045] Figure 4 This is a logic diagram for determining whether there is an abnormality at the load end according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0047] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0048] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the term "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0049] See also Figure 1 As shown, it is a schematic diagram of the structure of an intelligent self-regulating power concentrator according to an embodiment of the present invention. The present invention provides an intelligent self-regulating power concentrator, including:

[0050] A data acquisition module is used to continuously collect grid data from each node in the grid. The grid data includes electrical parameters and meter readings. The electrical parameters include voltage, current, power and power factor.

[0051] A storage processing module, which is connected to the data acquisition module, is used to add time stamps to the data of each node of the power grid and store them accordingly, and draw a number of time domain images of power grid data according to the storage status of the data;

[0052] A data analysis module, connected to the storage processing module, for determining data fluctuation characterization parameters according to each of the power grid data time domain images, and determining a data analysis category according to the data fluctuation characterization parameters;

[0053] An analysis and adjustment module, which is respectively connected to the data analysis module, the storage processing module and the data acquisition module, and is used to determine a data analysis method according to the data analysis category, including:

[0054] Directly analyze the current meter readings, predict load changes based on the analysis results, and determine whether there are any abnormalities;

[0055] Or, determining the missing discrete parameters according to the stored power grid data to determine the data missing type, so as to determine the data processing method, performing data analysis on the processed power grid data, predicting the load change according to the analysis result, and judging whether there is an abnormality;

[0056] The remote management module is connected to the analysis and adjustment module and determines the content of the instruction sent to the main station according to the data analysis method.

[0057] In this embodiment, the power grid data is acquired according to the power data collector, and the concentrator can acquire and concentrate the power grid data collected by multiple collectors. This is the basic function of the concentrator and is not specifically limited or further described here;

[0058] In implementation, the present invention does not limit the specific structures of the storage processing module, the data analysis module, the analysis and adjustment module, and the remote management module, which may be composed of logic components, including a field programmable processor, a computer, and a microprocessor in the computer;

[0059] The storage processing module can add a timestamp through any programming software and code in the logic component, and no specific limitation is made here.

[0060] The data acquisition module can continuously collect grid data of each node of the grid, including electrical parameters and meter readings, to realize real-time monitoring of the grid status and data acquisition; the storage processing module adds timestamps to the collected data and stores them, can effectively manage and organize the data, and generates a time domain image of the grid data according to the storage situation, which is convenient for subsequent analysis and visualization; the data analysis module determines the data fluctuation characterization parameters according to the time domain image of the grid data, and then determines the data analysis category; the analysis and adjustment module can select a suitable data analysis method according to the data analysis category, including directly analyzing the meter readings or determining the missing parameters according to the stored data and adjusting them, so as to predict load changes and detect abnormal situations, which is helpful to find problems in advance and take corresponding measures; the remote management module can determine the content of the instructions sent to the main station according to the data analysis method, realize remote management and control of the grid system, and improve the flexibility and response speed of the system; the present invention classifies the collected grid information before analysis, reduces unnecessary data duplication processes, and improves the working efficiency of the power concentrator.

[0061] Specifically, the frequency of adding the timestamp by the storage processing module is the same as the frequency of collecting the power grid data by the data collection module;

[0062] If the data acquisition module fails to successfully collect data, the data corresponding to the current timestamp will be recorded as 0.

[0063] In implementation, the timestamp maintains a one-to-one correspondence with each power grid data, that is, when the data acquisition module normally acquires data, the timestamp is normally added to the data. If the data acquisition module fails to acquire the power grid data normally at a certain data acquisition moment, the storage and processing module stores the data corresponding to the timestamp as 0.

[0064] In the present invention, the frequency at which the storage and processing module adds timestamps to data is the same as the frequency at which the data acquisition module acquires power grid data, thereby ensuring the synchronization of the timestamp and the power grid data; when the data acquisition module fails to successfully acquire data, the storage and processing module records the data corresponding to the current timestamp as 0, thereby ensuring the integrity and continuity of the data, so that the stored data has certain reliability and availability; by recording the timestamp data corresponding to the data that has not been successfully acquired as 0, the storage and processing module can promptly identify the moment when the data acquisition is abnormal, thereby providing a basis for subsequent data analysis and anomaly detection, and helping the system to respond to and handle abnormal situations in a timely manner.

[0065] See also Figure 2 As shown, it is a logic diagram for determining the data analysis category in an embodiment of the present invention. The data analysis module determines the data fluctuation characterization parameter according to formula (1).

[0066]

[0067] In formula (1), K is the parameter characterizing data fluctuation, n1 is the total number of non-zero power grid data, n0 is the total number of timestamps, ki is the i-th power grid sub-data, k0 is the mean value of the power grid sub-data, and i is an integer greater than 0.

[0068] In implementation, It is rounded down, that is, when n1 / n0≥0.7, [n1 / n0+0.3] takes the value of 1, indicating that the data missing rate of the current power grid data time domain image is within the allowable range. Similarly, when n1 / n0<0.7, [n1 / n0+0.3] takes the value of 0, K=0, indicating that the data missing rate of the current power grid data time domain image is not within the allowable range and the amount of data missing is too high.

[0069] In this embodiment, the power grid sub-data corresponds to electrical parameters and meter readings.

[0070] Specifically, the data analysis module determines the data analysis category according to the data fluctuation characterization parameter.

[0071] If the data fluctuation characterization parameter meets the preset analysis condition, the data analysis category of the current power grid data is determined to be indirect analysis;

[0072] If the data fluctuation characterization parameter does not meet the preset analysis condition, the data analysis category of the current power grid data is determined to be direct analysis.

[0073] Among them, the preset analysis condition is that the data fluctuation characterization parameter is greater than the preset fluctuation parameter or the data fluctuation characterization parameter is equal to 0.

[0074] In this embodiment, the preset fluctuation parameter K0 is obtained in advance, wherein the time domain image of the power grid data in the same time period on several dates is obtained as a sample, and the average value ΔK of the power grid data difference of the historical power grid data time domain image in each time period is solved, and K0 is set to ΔK×g, g represents the offset coefficient, 1.25<g<1.35.

[0075] It is understandable that due to regional and seasonal differences, the representativeness of similar data of power grid data with large date intervals is less than that of similar data of power grid data with small date intervals, so the time interval of historical data samples is set to be less than two weeks.

[0076] In the present invention, by determining the data analysis category according to the data fluctuation characterization parameters, the system can dynamically select the analysis method according to the characteristics of the data, realize flexible adaptation to different situations, and improve the applicability and performance of the system; and the system predicts load changes according to the analysis results and determines whether there are anomalies. It has strong anomaly detection and prediction capabilities, which helps to timely discover and handle abnormal situations and improve the stability and reliability of the system.

[0077] Specifically, the analysis and adjustment module determines the data analysis method according to the data analysis category.

[0078] If the data analysis category is indirect analysis, the missing discrete parameter is determined according to the stored power grid data to determine the data missing type, so as to determine the data adjustment method, perform data analysis on the adjusted power grid data, predict the load change according to the analysis result, and determine whether there is an abnormality;

[0079] If the data analysis category is direct analysis, data analysis is directly performed on the current meter reading, load changes are predicted based on the analysis results, and it is determined whether there is an abnormality.

[0080] See also Figure 3 As shown, it is a logic diagram for determining the type of missing data according to an embodiment of the present invention. The analysis and adjustment module determines the missing discrete parameter according to formula (2).

[0081]

[0082] In formula (2), c represents the missing discrete parameter, n0 is the total number of timestamps, ki is the i-th power grid sub-data, k0 is the mean value of the current power grid sub-data, and i is an integer greater than 0.

[0083] Specifically, the analysis and adjustment module determines the missing discrete parameter according to the stored power grid data to determine the data missing type.

[0084] If the missing discrete parameter is greater than the preset missing discrete parameter, the current data missing type is determined to be discrete data missing;

[0085] If the missing discrete parameter is less than or equal to the preset missing discrete parameter and greater than the standard missing discrete parameter, the current data missing type is determined to be continuous data missing.

[0086] In this embodiment, the preset missing discrete parameter is selected in the interval [0.15, 0.25], and the standard missing discrete parameter is the missing discrete parameter corresponding to when all data are missing in a continuous missing state when n1 / n0=0.7.

[0087] In implementation, c takes the form of coefficient of variation in probability statistics. For continuously missing data, although the missing data points may lead to difficulties in analysis, this missing pattern is manifested as the continuous loss of data points in the time series, and its missing pattern is relatively regular. Therefore, when interpolating or processing data, some relatively simple methods (such as linear interpolation, moving average, etc.) can be used to estimate the missing data points or eliminate the impact of missing points. For intermittently missing data, the missing data points are irregular in the time series, and this irregular missing pattern will increase the uncertainty of the data. When processing such data, more complex interpolation methods (such as multiple interpolation, time series analysis, etc.) may be needed to estimate the missing data points. Due to the randomness of missing data, even if interpolation is performed, the reliability of the data may be affected, resulting in an increase in the degree of discreteness;

[0088] Therefore, continuous missing data can be handled by simple interpolation due to their regularity, which has little impact on data reliability. However, intermittent missing data are irregular and require complex interpolation, which increases uncertainty and discreteness and has a greater impact on reliability. It is necessary to clarify the interpolation method and its uncertainty.

[0089] Specifically, the data processing method of the analysis and adjustment module for processing the power grid data according to the data missing type includes:

[0090] If the analysis and adjustment module determines that the current data missing type is discrete data missing, then reacquire the corresponding power grid data according to the power grid data type corresponding to the timestamp of the data record being 0;

[0091] If the analysis and adjustment module determines that the current data missing type is continuous data missing, the corresponding power grid data in the timestamp set with data record of 0 is removed to perform analysis based on the remaining power grid data;

[0092] Among them, the same type of power grid sub-data corresponding to three or more consecutive timestamps in the timestamp set are all 0.

[0093] In the present invention, by analyzing the parameters characterizing data fluctuations, the current data missing type can be accurately determined, and subsequent processing can be carried out in a targeted manner; different processing methods are adopted according to different types of data missing. For continuous data missing, the corresponding power grid data is reacquired; for discrete data missing, the corresponding image segments in the timestamp set with data records of 0 are eliminated. This flexible processing method can more effectively deal with different types of data missing; the coefficient of variation c in probability statistics is introduced into data analysis, and continuous missing and intermittent missing are distinguished, so that data interpolation or processing methods can be selected more accurately, thereby improving the accuracy and reliability of data processing.

[0094] See also Figure 4 As shown, it is a logic diagram for determining whether there is an abnormality at the load end according to an embodiment of the present invention. The analysis and adjustment module determines whether there is an abnormality according to the predicted load change result.

[0095] If the predicted load change result exceeds the standard change result, it is determined that there is an abnormality at the load end and remote management is required;

[0096] If the predicted load change result does not exceed the standard change result, it is determined that there is no abnormality at the load end and no remote management is required.

[0097] In the implementation, the variance result of the power grid data indicates that the power grid data in the current time period is in a stable state, and when the fluctuation degree is small, the mean value of the power grid data in the current time period can be used as the standard change result;

[0098] In this embodiment, from the large amount of collected data, the concentrator needs to select the features most relevant to the power load forecast, such as time (hour, day, season, etc.), economic activity indicators, etc. The concentrator uses statistical or machine learning methods to establish a prediction model; common prediction methods include regression analysis, time series analysis, artificial neural networks, deep learning methods, etc.;

[0099] The concentrator trains the prediction model through historical data and adjusts the model parameters to ensure that the model can accurately capture the changing trend of power load; it uses the trained model to predict future power load and analyze the operation status of the power system. The prediction results can be used for the dispatching, planning and load management of the power system.

[0100] Specifically, the remote management module also includes an instruction sending unit for implementing remote control content.

[0101] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0102] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent self-regulating power concentrator, characterized in that: include: A data acquisition module is used to continuously collect grid data from each node in the grid. The grid data includes electrical parameters and meter readings. The electrical parameters include voltage, current, power and power factor. A storage processing module, which is connected to the data acquisition module, is used to add time stamps to the data of each node of the power grid and store them accordingly, and draw a number of time domain images of power grid data according to the storage status of the data; A data analysis module, connected to the storage processing module, for determining data fluctuation characterization parameters according to each of the power grid data time domain images, and determining a data analysis category according to the data fluctuation characterization parameters; An analysis and adjustment module, which is respectively connected to the data analysis module, the storage processing module and the data acquisition module, and is used to determine a data analysis method according to the data analysis category, including: Directly analyze the current power grid data, predict load changes based on the analysis results, and determine whether there are any abnormalities; Or, determining the missing discrete parameters according to the stored power grid data to determine the data missing type, so as to determine the data processing method, performing data analysis on the processed power grid data, predicting the load change according to the analysis result, and judging whether there is an abnormality; A remote management module, which is connected to the analysis and adjustment module and determines the content of the instruction sent to the main station according to the data analysis method; The frequency of adding the timestamp by the storage processing module is the same as the frequency of collecting the power grid data by the data collection module; If the data acquisition module fails to successfully collect data, the data corresponding to the current timestamp is recorded as 0; The data analysis module determines the data fluctuation characterization parameter according to formula (1), In formula (1), K is the parameter characterizing data fluctuation, n1 is the total number of non-zero power grid data, n0 is the total number of timestamps, ki is the i-th power grid sub-data, k0 is the mean value of the current power grid sub-data, and i is an integer greater than 0; The data analysis module determines the data analysis category according to the data fluctuation characterization parameter, If the data fluctuation characterization parameter meets the preset analysis condition, the data analysis category of the current power grid data is determined to be indirect analysis; If the data fluctuation characterization parameter does not meet the preset analysis condition, the data analysis category of the current power grid data is determined to be direct analysis. Among them, the preset analysis condition is that the data fluctuation characterization parameter is greater than the preset fluctuation parameter or the data fluctuation characterization parameter is equal to 0.

2. The intelligent self-regulating power concentrator according to claim 1, characterized in that: The analysis and adjustment module determines the data analysis method according to the data analysis category. If the data analysis category is indirect analysis, the missing discrete parameter is determined according to the stored power grid data to determine the data missing type, so as to determine the data adjustment method, perform data analysis on the adjusted power grid data, predict the load change according to the analysis result, and determine whether there is an abnormality; If the data analysis category is direct analysis, data analysis is directly performed on the current meter reading, load changes are predicted based on the analysis results, and it is determined whether there is an abnormality.

3. The intelligent self-regulating power concentrator according to claim 2, characterized in that: The analysis and adjustment module determines the missing discrete parameter according to formula (2): In formula (2), c represents the missing discrete parameter, n0 is the total number of timestamps, ki is the i-th power grid sub-data, k0 is the mean value of the current power grid sub-data, and i is an integer greater than 0.

4. The intelligent self-regulating power concentrator according to claim 3, characterized in that: The analysis and adjustment module determines the missing discrete parameter according to the stored power grid data to determine the data missing type. If the missing discrete parameter is greater than the preset missing discrete parameter, the current data missing type is determined to be discrete data missing; If the missing discrete parameter is less than or equal to the preset missing discrete parameter and greater than the standard missing discrete parameter, the current data missing type is determined to be continuous data missing.

5. The intelligent self-regulating power concentrator according to claim 4, characterized in that: The data processing method of the analysis and adjustment module for processing the power grid data according to the data missing type includes: If the analysis and adjustment module determines that the current data missing type is discrete data missing, then reacquire the corresponding power grid data according to the power grid data type corresponding to the timestamp of the data record being 0; If the analysis and adjustment module determines that the current data missing type is continuous data missing, the corresponding power grid data in the timestamp set with data record of 0 is removed to perform analysis based on the remaining power grid data.

6. The intelligent self-regulating power concentrator according to claim 5, characterized in that: The analysis and adjustment module determines whether there is an abnormality based on the predicted load change result. If the predicted load change result exceeds the standard change result, it is determined that there is an abnormality at the load end and remote management is required; If the predicted load change result does not exceed the standard change result, it is determined that there is no abnormality at the load end and no remote management is required.

7. The intelligent self-regulating power concentrator according to claim 6, characterized in that: The remote management module also includes an instruction sending unit for implementing remote control content.

Images