A real-time monitoring method and system for new energy power

Abstract

The application relates to a real-time monitoring method and system for new energy power, relates to the technical field of new energy power system monitoring and control, constructs an early warning model, can accurately capture the mutation point of power change, improves the prediction accuracy of switching time, provides early warning for the normal operation of power equipment, solves the problem that new energy power is greatly affected by the environment, output power is intermittent, and the state switching time cannot be accurately predicted, based on the predicted switching time, obtains the past intermittent duration in a plurality of past monitoring periods, quantizes the stability of the intermittent duration, obtains the predicted switching duration, and provides data support for the duration of switching to the standby power source according to the law and duration of the intermittent power of new energy power.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of new energy power system monitoring and control technology, and particularly relates to a real-time monitoring method and system for new energy power. BACKGROUND

[0002] With the increasing proportion of new energy power (such as solar energy, wind energy, etc.) in the power system, real-time monitoring and management of new energy power becomes increasingly important. However, due to the significant influence of environmental factors (such as light intensity, wind speed changes, etc.) on the power generation principle of new energy power, the output power of new energy power has obvious intermittency, which not only increases the difficulty of dispatching the power system, but also may threaten the normal operation of power equipment.

[0003] In the prior art, new energy power is greatly affected by the environment, and the intermittency of the output power makes it difficult to accurately predict the state switching time, which not only affects the dispatching efficiency of the power system, but also may cause damage to power equipment or interruption of power supply due to inaccurate prediction. Due to the volatility of the intermittent duration of new energy power, the prior art often has difficulty in giving reliable basis when predicting the switching duration. This may lead to problems such as unstable power supply or equipment overload during actual switching due to inaccurate prediction of switching duration. SUMMARY

[0004] The present application aims to provide a real-time monitoring method and system for new energy power to solve at least one of the above-mentioned prior art problems.

[0005] In a first aspect, a real-time monitoring method for new energy power includes:

[0006] In the past monitoring period, the output power of new energy power is analyzed, the past intermittent phenomenon is identified, and a reference intermittent change curve is obtained;

[0007] In the real-time monitoring period, the output power of new energy power is analyzed, compared with the reference intermittent change curve of the past multiple intermittent phenomena, and the current new energy power intermittent risk degree is evaluated;

[0008] If the power intermittent risk is large, the real-time analysis of the real-time monitored power output is performed to obtain a warning reference slope, and a warning model is constructed to obtain a predicted switching time;

[0009] Based on the predicted switching time, the past intermittent duration in the past monitoring period is obtained and analyzed to obtain a predicted switching duration, and the new energy power switching is completed.

[0010] In a second aspect, a real-time monitoring system for new energy power includes:

[0011] The output power of new energy power is analyzed in the past monitoring period, past intermittent phenomena are identified, and a reference intermittent change curve is obtained;

[0012] The output power of new energy power is analyzed in the past monitoring period, past intermittent phenomena are identified, and a reference intermittent change curve is obtained;

[0013] The output power of new energy power is analyzed in the past monitoring period, past intermittent phenomena are identified, and a reference intermittent change curve is obtained;

[0014] The output power of new energy power is analyzed in the past monitoring period, past intermittent phenomena are identified, and a reference intermittent change curve is obtained;

[0015] The beneficial effects of the present application are:

[0016] 1、The output power of new energy power is analyzed in the past monitoring period, past intermittent phenomena are identified, and a reference intermittent change curve is obtained, the real-time power change curve in the real-time monitoring period is combined and compared with the reference intermittent change curve, the overall matching degree of real-time power characteristics and historical intermittent mode is quantified through two dimensions of change trend similarity and change amplitude similarity, the monitoring accuracy of new energy power output power is improved, and data support is provided for subsequent power warning;

[0017] 2、If the power intermittent risk is large, the real-time analysis of the real-time monitored power output power is carried out, the warning model is constructed, so that the mutation point of power change can be accurately captured, the accuracy of the predicted switching time is improved, the normal operation of the power equipment is provided with warning, the new energy power is greatly affected by the environment, the output power has intermittence, it is difficult to accurately predict the state switching time, based on the predicted switching time, the past intermittent duration in multiple past monitoring periods is obtained, and the stability of the quantized intermittent duration is analyzed, the predicted switching duration is obtained, and data support is provided for the duration of switching to standby power according to the intermittent law and duration of new energy power. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1 is a step flow chart of a real-time monitoring method for new energy power of the present application;

[0020] Figure 2 is a schematic diagram of a real-time monitoring system for new energy power of the present application. DETAILED DESCRIPTION

[0021] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0022] Embodiment one

[0023] As shown in the figure, the real-time monitoring method for new energy power provided by the embodiments of the present application specifically includes the following steps: Figure 1

[0024] Step one: In the past monitoring period, the output power of new energy power is analyzed, the past intermittent phenomenon is identified, and the reference intermittent change curve is obtained;

[0025] In some embodiments, the past monitoring period is equally divided into several past monitoring time points;

[0026] Among them, the interval length between adjacent past monitoring time points after division is equal;

[0027] The past output power corresponding to each past monitoring time point is obtained, and the difference value of the past power is obtained by difference processing with the rated output power of new energy;

[0028] The past power difference value is compared with the past power difference threshold value, and the process is as follows:

[0029] If the past power difference value is greater than the past power difference threshold value, it means that the past output power at the analyzed past monitoring time point is greatly different from the rated output power of new energy, which is a suspected past intermittent time point;

[0030] If the past power difference is less than or equal to the past power difference threshold value, it means that the past output power at the analyzed past monitoring time point is less different from the rated output power of new energy, which is a normal power time point;

[0031] The suspected past intermittent time points are counted, and the suspected past intermittent time points are sorted according to the time sequence corresponding to the suspected past intermittent time points, and a suspected past intermittent sequence is constructed;

[0032] ​extract a suspected previous intermittent time point at a suspected previous intermittent sequence head and a suspected previous intermittent time point at a suspected previous intermittent sequence tail respectively, and obtain a time period between the suspected previous intermittent time point at the suspected previous intermittent sequence head and the suspected previous intermittent time point at the suspected previous intermittent sequence tail as a suspected previous intermittent time period;

[0033] The suspected previous intermittent time period includes all suspected previous intermittent points within a suspected previous intermittent sequence.

[0034] The standard deviation of the previous difference value corresponding to each suspected previous intermittent time point in the suspected previous intermittent time period is calculated, and a previous difference standard deviation value is output.

[0035] If the previous difference standard deviation value is less than or equal to the previous difference standard deviation threshold value, it indicates that the previous output power and the new energy rated output power have a large difference in the suspected previous intermittent time period, and are relatively stable, and it is determined that the previous intermittent phenomenon occurs in the suspected previous intermittent time period.

[0036] If the previous difference standard deviation value is greater than the previous difference standard deviation threshold value, it indicates that the previous output power and the new energy rated output power have a large difference in the suspected previous intermittent time period, and are relatively unstable, and it is determined that the previous intermittent phenomenon does not occur in the suspected previous intermittent time period.

[0037] The X-axis is time, the Y-axis is power, the previous output power corresponding to each previous monitoring time point in the previous monitoring period is input into a two-dimensional coordinate system, and a previous power change curve is constructed.

[0038] The starting point coordinates of the previous power change curve and the local previous power change curve between the suspected previous intermittent time point at the suspected previous intermittent sequence head are intercepted as a reference intermittent change curve.

[0039] Step 2: In the real-time monitoring period, the output power of the new energy power is analyzed, compared with the reference intermittent change curve that appears multiple times with the previous intermittent phenomenon, and whether the current new energy power has intermittent risk is evaluated.

[0040] In some embodiments, the real-time monitoring period is equally divided into a plurality of real-time monitoring time points.

[0041] The interval length between adjacent real-time monitoring time points is equal, and the real-time monitoring period is divided in the same way as the previous monitoring period.

[0042] In the real-time monitoring period, the real-time output power corresponding to each real-time monitoring time point is obtained, the X-axis is time, the Y-axis is power, and a real-time power change curve is constructed.

[0043] The real-time power change curve is divided into a plurality of real-time change sub-curves according to the local real-time power change curve between adjacent real-time monitoring time points;

[0044] The slope of each real-time change sub-curve is obtained through a slope calculation formula, and summation mean calculation is performed to obtain a real-time change slope;

[0045] Similarly, the reference intermittent change curve is divided into a plurality of reference change sub-curves according to the local reference intermittent change curve between adjacent past monitoring time points;

[0046] The slope of each reference change sub-curve is obtained through a slope calculation formula, and summation mean calculation is performed to obtain a reference change slope;

[0047] The real-time change slope and the reference change slope are taken as a change trend comparison group;

[0048] All peak point coordinates and trough point coordinates on the real-time power change curve are extracted, and the distance between adjacent peak point coordinates and trough point coordinates (or the distance between adjacent trough point coordinates and peak point coordinates) is obtained through a coordinate point distance formula, as a unit real-time change amplitude;

[0049] All unit real-time change amplitudes are subjected to mean value processing, and a real-time change amplitude mean value is output;

[0050] Similarly, all peak point coordinates and trough point coordinates on the reference intermittent change curve are extracted, and the distance between adjacent peak point coordinates and trough point coordinates (or the distance between adjacent trough point coordinates and peak point coordinates) is obtained through a coordinate point distance formula, as a unit reference change amplitude;

[0051] All unit reference change amplitudes are subjected to mean value processing, and a reference change amplitude mean value is output;

[0052] The real-time change amplitude mean value and the reference change amplitude mean value are taken as a change amplitude comparison group;

[0053] The change trend comparison group and the change amplitude comparison group are respectively input into a Euclidean distance calculation formula, and a comparison similarity value is output ;

[0054] Specifically, the Euclidean distance calculation formula is: wherein, and represent the real-time change slope and the reference change slope in the change trend comparison group, respectively; and represent the real-time change amplitude mean value and the reference change amplitude mean value in the change amplitude comparison group, respectively;

[0055] ​It can be understood that the comparison of the similarity values represents the following meanings:

[0056] Meaning one: in the comparison dimension, the similarity of the overall change trend of the real-time power change curve and the overall change trend of the reference intermittent change curve, and the similarity of the overall change amplitude of the real-time change curve and the overall change amplitude of the reference intermittent change curve are compared, so as to quantize the similarity by numerical value, provide objective judgment basis for real-time monitoring of new energy power system, and assist operation and maintenance personnel to respond to abnormalities in time;

[0057] Meaning two: from the mathematical essence, the change curve and the change amplitude are respectively regarded as coordinate points in a two-dimensional space, and the "space distance" of real-time data and historical reference data is calculated by using Euclidean distance. If the distance is closer, it means that the similarity of the real-time power change characteristics and the historical intermittent phenomenon is higher, and the intermittent risk is higher. If the distance is farther, it means that the similarity of the real-time power change characteristics and the historical intermittent phenomenon is lower, and the intermittent risk is lower;

[0058] The multiple comparison similarity values are compared in size, and the reference intermittent change curve corresponding to the minimum comparison similarity value is extracted as the target reference curve;

[0059] The past intermittent time period on the target reference curve is extracted, and the time length corresponding to the past intermittent time period is obtained. The time length is compared with the time length of the past monitoring period to calculate the ratio, and the past intermittent time length ratio is output;

[0060] In the past intermittent time period, the past power difference value corresponding to each past intermittent time point is obtained, and the past power difference value is processed by mean value. The past power difference value is compared with the rated output power of new energy to calculate the ratio, and the past difference ratio is output;

[0061] The past intermittent time length ratio and the past difference ratio are multiplied to calculate the intermittent risk value;

[0062] The intermittent risk value is compared with the intermittent risk threshold value, and the process is as follows:

[0063] If the intermittent risk value is greater than the intermittent risk threshold value, it means that the intermittent risk is high, and a large intermittent probability signal is generated;

[0064] If the intermittent risk value is less than or equal to the intermittent risk threshold value, the intermittent risk is low, and a small intermittent probability signal is generated;

[0065] The specific implementation of the embodiment is: in the previous monitoring period, the output power of new energy power is analyzed, the previous intermittent phenomenon is identified, and a reference intermittent change curve is obtained; the real-time power change curve in the real-time monitoring period is combined and compared with the reference intermittent change curve; through two dimensions of change trend similarity and change amplitude similarity, the overall matching degree of real-time power characteristics and historical intermittent mode is quantified, the monitoring accuracy of new energy power output power is improved, and data support is provided for subsequent power warning.

[0066] Embodiment two

[0067] Step three: if the power intermittent risk is large, the real-time analysis is performed on the real-time monitored power output power, the warning model is constructed, and the predicted switching time is obtained;

[0068] In some embodiments, on the real-time power change curve, the slopes of adjacent real-time change sub-curves are respectively input into the Euclidean distance formula, and the real-time sub-slope difference value is output ;

[0069] Specifically, the Euclidean distance formula is: , wherein, represents the slope of the first real-time change sub-curve on the real-time power change curve, represents the slope of the first real-time change sub-curve on the real-time power change curve, and n represents the total number of real-time change sub-curves on the real-time power change curve.

[0070] It should be noted that the purpose of using the Euclidean distance formula is:

[0071] The Euclidean distance is essentially the straight-line distance between two points in a multi-dimensional space. By mathematical formula, the abstract "slope difference" is converted into a specific measurable value, which not only captures the mutation of local adjacent slopes (such as sharp turning between two sub-curves), but also evaluates the fluctuation degree of the entire curve by statistics of all adjacent slope distance values, provides key feature parameters (such as the position of the turning point and the slope change amplitude) for subsequent real-time output power warning, and improves the accuracy of the predicted switching time;

[0072] If the real-time sub-slope difference value is greater than the real-time sub-slope threshold value, it means that the slope difference of all adjacent real-time change sub-curves on the real-time power change curve is large, and a large sub-slope difference signal is generated;

[0073] If the real-time sub-slope difference value is less than or equal to the real-time sub-slope threshold value, it means that the slope difference of all adjacent real-time change sub-curves on the real-time power change curve is small, and a small sub-slope difference signal is generated;

[0074] If the sub-slope difference large signal is generated, the slopes of all real-time change sub-curves on the real-time power change curve are compared in size, the maximum slope of the real-time change sub-curve is extracted as the early warning reference slope;

[0075] If the sub-slope difference small signal is generated, the slopes of all real-time change sub-curves on the real-time power change curve are processed by mean value, and the early warning reference slope is output;

[0076] The end point coordinates on the real-time power change curve are obtained, and the early warning model is constructed in combination with the early warning reference slope, and the early warning model equation is obtained: , wherein, The early warning reference slope is represented as b, and b is represented as a constant;

[0077] The intermittent output power value is input into the early warning model equation, and the predicted switching time is output;

[0078] It should be noted that the meaning of the predicted switching time is: based on the real-time power change curve and the early warning model, the time point when the new energy power system switches from the current state to another state (such as from normal power supply to standby power supply, from full load operation to power limiting mode, etc.) is predicted. Due to the influence of the environment, intermittent periods will occur, so it is necessary to switch the new energy power output to ensure that the power equipment can operate normally;

[0079] Step four: based on the predicted switching time, the past intermittent duration in a plurality of past monitoring periods is obtained and analyzed to obtain the predicted switching duration, and the new energy power switching is completed;

[0080] In some embodiments, the duration corresponding to the past intermittent period in a past monitoring period is obtained as the past intermittent duration;

[0081] It should be noted that the past intermittent period is the time length corresponding to the past intermittent phenomenon when the past intermittent period is judged in the past monitoring period;

[0082] All past intermittent durations in the past monitoring period are counted and input into the coefficient of variation formula to output the past intermittent stable value ;

[0083] Specifically, the coefficient of variation formula is: , wherein, is the standard deviation of all past intermittent durations in the past monitoring period, is the mean value of all past intermittent durations in the past monitoring period;

[0084] The variance of the past intermittent stability values corresponding to all past monitoring periods is calculated, and an intermittent duration stability value is output;

[0085] It can be explained that the meaning represented by the intermittent duration stability value is that, in the time dimension, the intermittent duration stability value reflects the fluctuation of the intermittent duration of the new energy power system in multiple past monitoring periods, and from the data perspective, the stability of the intermittent duration can be quantified, providing data support for the duration of switching to the standby power source according to the intermittent rules and duration of the new energy power.

[0086] If the intermittent duration stability value is less than or equal to the intermittent duration stability threshold, it indicates that the past intermittent duration in multiple past periods is relatively stable, and an intermittent duration stability signal is generated.

[0087] If the intermittent duration stability value is greater than the intermittent duration stability threshold, it indicates that the past intermittent duration in multiple past periods is relatively volatile, and an intermittent duration fluctuation signal is generated.

[0088] If the intermittent duration stability signal is generated, the past intermittent stability values corresponding to all past monitoring periods are processed by mean value, and a predicted switching duration is output.

[0089] If the intermittent duration fluctuation signal is generated, the maximum past intermittent duration corresponding to each past monitoring period is extracted and processed by mean value, and a predicted switching duration is output.

[0090] The specific implementation scheme of the embodiment is that if the power intermittent risk is large, the real-time analysis of the real-time monitored power output is performed, and a warning model is constructed, so that the mutation point of power change can be accurately captured, the accuracy of the predicted switching time is improved, the normal operation of the power equipment is warned, and the problems that the new energy power is greatly affected by the environment, the output power is intermittent, and the state switching time is difficult to accurately predict are solved. Based on the predicted switching time, the past intermittent duration in multiple past monitoring periods is obtained, the stability of the quantified intermittent duration is obtained, and the predicted switching duration is obtained, which provides data support for the duration of switching to the standby power source according to the intermittent rules and duration of the new energy power.

[0091] Embodiment three

[0092] As shown in Figure 2 The real-time monitoring system for new energy power provided by the embodiment of the application includes the following modules:

[0093] Past monitoring analysis module: in the past monitoring period, the output power of the new energy power is analyzed, the past intermittent phenomenon is identified, and a reference intermittent change curve is obtained.

[0094] The comparison risk assessment module: in the real-time monitoring period, the output power of new energy power is analyzed, compared with the reference intermittent change curve of the intermittent phenomenon appearing for many times in the past, and the current new energy power intermittent risk degree is evaluated;

[0095] The switching time prediction module: if the power intermittent risk is large, the real-time analysis is carried out on the real-time monitored power output, the early warning reference slope is obtained, the early warning model is constructed, and the predicted switching time is obtained;

[0096] The switching time prediction module: based on the predicted switching time, the past intermittent duration in the past monitoring period is obtained and analyzed, the predicted switching time is obtained, and the new energy power switching is completed.

[0097] The above formulas are all dimensionless values, and the formulas are obtained by collecting a large amount of data to simulate the recent real situation, and the preset parameters in the formula are set by the person skilled in the art according to the actual situation.

[0098] The above describes one embodiment of the application in detail, but the content described is only the preferred embodiment of the application, and cannot be considered as limiting the scope of the application. Any equivalent changes and improvements made according to the scope of the application should still belong to the patent coverage range of the application.

Claims

1. A method for real-time monitoring of new energy power, characterized in that, The method comprises the following steps: In the past monitoring period, the output power of new energy power is analyzed, the past intermittent phenomenon is identified, and the reference intermittent change curve is obtained; In the real-time monitoring period, the output power of new energy power is analyzed, and compared with the reference intermittent change curve of the past intermittent phenomenon, the risk degree of current new energy power intermittent is evaluated; The identification process of the past intermittent phenomenon is as follows: The past monitoring period is equally divided into several past monitoring time points; The past output power corresponding to each past monitoring time point is obtained, and the difference value of the past output power and the new energy rated output power is processed to obtain the past power difference value, if it is greater than the past power difference threshold value, it is a suspected past intermittent time point; Sort the suspected past intermittent time points in time sequence to construct a suspected past intermittent sequence, and the time period between the first suspected past intermittent time point and the tail of the suspected past intermittent time point is regarded as the suspected past intermittent time period; The standard deviation of the past power difference value corresponding to each suspected past intermittent time point in the suspected past intermittent time period is calculated, and the past difference standard deviation value is output, if the past difference standard deviation value is less than or equal to the past difference standard deviation threshold value, the past intermittent phenomenon occurs; The output power of new energy power is analyzed, and compared with the reference intermittent change curve of the past intermittent phenomenon, the process is as follows: The real-time monitoring period is equally divided into several real-time monitoring time points, the real-time output power corresponding to each real-time monitoring time point is obtained, the real-time power change curve is constructed, and is divided to obtain a plurality of real-time change sub-curves, and the slope of the real-time change sub-curve is obtained, and the mean value is processed to output the real-time change slope; The reference intermittent change curve is divided to obtain a plurality of reference change sub-curves, and the slope of the reference change sub-curve is obtained, and the mean value is processed to output the reference change slope; The real-time change slope and the reference change slope are combined into a change trend comparison group; All peak point coordinates and valley point coordinates on the real-time power change curve and all peak point coordinates and valley point coordinates on the reference intermittent change curve are extracted, the unit real-time change amplitude and the unit reference change amplitude are obtained through the coordinate point distance formula, and the mean value of the real-time change amplitude and the mean value of the reference change amplitude are obtained through the mean value processing; The real-time change amplitude mean value and the reference change amplitude mean value are combined into a change amplitude comparison group; The change trend comparison group and the change amplitude comparison group are respectively input into the Euclidean distance calculation formula, and the comparison similarity value is output; If the power intermittent risk is large, the real-time analysis of the real-time monitored power output is carried out to obtain the early warning benchmark slope, and the early warning model is constructed to obtain the predicted switching time; Based on the predicted switching time, the past intermittent time length in the past monitoring period is obtained, and is analyzed to obtain the predicted switching time length, and the new energy power switching is completed.

2. The method for real-time monitoring of new energy power according to claim 1, characterized in that, The process of evaluating the risk degree of current new energy power intermittent is as follows: The reference intermittent change curve corresponding to the minimum comparison similarity value is extracted as the target reference curve; Extract the past intermittent period on the target reference curve, obtain the time length corresponding to the past intermittent period, and calculate the ratio of the past intermittent time length to the past monitoring period time length, and output the past intermittent time length ratio; In the past intermittent period, the mean value of the past power difference value corresponding to each past intermittent time point is obtained, and the ratio of the past power difference value to the new energy rated output power is calculated, and the past difference ratio is output; The past intermittent time length ratio and the past difference ratio are multiplied to obtain the intermittent risk value, and if the intermittent risk value is greater than the intermittent risk threshold, the intermittent probability large signal is generated.

3. The method for real-time monitoring of new energy power according to claim 1, characterized in that, The acquisition method of the early warning reference slope is: In the real-time power change curve, the slopes of adjacent real-time change sub-curves are input into the Euclidean distance formula, and the real-time sub-slope difference value is output; If the real-time sub-slope difference value is greater than the real-time sub-slope threshold, a sub-slope difference large signal is generated, and the slopes of all real-time change sub-curves on the real-time power change curve are compared, and the maximum slope of the real-time change sub-curve is extracted as the early warning reference slope; If the real-time sub-slope difference value is less than or equal to the real-time sub-slope threshold, a sub-slope difference small signal is generated, and the slopes of all real-time change sub-curves on the real-time power change curve are averaged to obtain the early warning reference slope.

4. The method for real-time monitoring of new energy power according to claim 1, characterized in that, The early warning model construction process is as follows: The terminal point coordinates on the real-time power change curve are acquired, a warning model is constructed in combination with the warning reference slope, and a warning model equation y j = K j X + b is obtained, wherein K j represents the warning reference slope, and b represents a constant.

5. The method for real-time monitoring of new energy power according to claim 1, characterized in that, The acquisition method of the prediction switching time is: The intermittent output power value is input into the early warning model equation, and the prediction switching time is output.

6. The method for real-time monitoring of new energy power according to claim 1, characterized in that, Obtain the past intermittent time length in multiple past monitoring periods and analyze the process as follows: Randomly select a past intermittent period in a past monitoring period, obtain the time length corresponding to the past intermittent period as the past intermittent time length, and count all past intermittent time lengths in the past monitoring period and input them into the coefficient of variation formula, output the past intermittent stability value, and perform mean value processing to obtain the intermittent time length stability value.

7. The method for real-time monitoring of new energy power according to claim 1, characterized in that, The acquisition process of the prediction switching time length is as follows: If the intermittent time length stability value is less than or equal to the intermittent time length stability threshold, an intermittent time length stability signal is generated, and the mean value of the past intermittent stability value corresponding to all past monitoring periods is output to obtain the prediction switching time length; If the intermittent time length stability value is greater than the intermittent time length stability threshold, an intermittent time length fluctuation signal is generated, and the maximum past intermittent time length corresponding to each past monitoring period is extracted and averaged to obtain the prediction switching time length.

8. A real-time monitoring system for new energy power, characterized in that, It includes: Past monitoring analysis module: In the past monitoring period, the output power of new energy power is analyzed, the past intermittent phenomenon is identified, and the reference intermittent change curve is obtained; Comparison risk assessment module: In the real-time monitoring period, the output power of new energy power is analyzed, compared with the reference intermittent change curve of past intermittent phenomenon, and the current new energy intermittent risk degree is evaluated; The identification process of the past intermittent phenomenon is as follows: Divide the past monitoring period into several past monitoring time points; Obtain the past output power corresponding to each past monitoring time point, and perform difference processing on the past output power and the new energy rated output power to obtain the past power difference value, and if it is greater than the past power difference threshold, it is a suspected past intermittent time point; Sort the plurality of suspected past intermittent time points in time sequence to construct a suspected past intermittent sequence, and take the time period between the first suspected past intermittent time point and the last suspected past intermittent time point as a suspected past intermittent time period; Calculate the standard deviation of the past power difference value corresponding to each suspected past intermittent time point in the suspected past intermittent time period, output the past difference standard deviation value, and if the past difference standard deviation value is less than or equal to the past difference standard deviation threshold, the past intermittent phenomenon occurs; Analyze the output power of new energy power and compare it with the reference intermittent change curve that appears multiple times, the process is as follows: Divide the real-time monitoring period equally into several real-time monitoring time points, obtain the real-time output power corresponding to each real-time monitoring time point, construct a real-time power change curve, and divide it to obtain multiple real-time change sub-curves, and obtain the slope of the real-time change sub-curves, and perform mean value processing to output the real-time change slope; Divide the reference intermittent change curve to obtain multiple reference change sub-curves, and obtain the slope of the reference change sub-curves, and perform mean value processing to output the reference change slope; Combine the real-time change slope and the reference change slope into a change trend comparison group; Extract all peak point coordinates and trough point coordinates on the real-time power change curve and all peak point coordinates and trough point coordinates on the reference intermittent change curve, obtain the unit real-time change amplitude and the unit reference change amplitude through the coordinate point distance formula, and perform mean value processing respectively to obtain the real-time change amplitude mean and the reference change amplitude mean; Combine the real-time change amplitude mean and the reference change amplitude mean into a change amplitude comparison group; Input the change trend comparison group and the change amplitude comparison group into the Euclidean distance calculation formula respectively, and output the comparison similarity value; Switch time prediction module: if the power intermittent risk is large, the real-time monitored power output is analyzed in real time to obtain a warning benchmark slope, a warning model is constructed, and a predicted switching time is obtained; Switching time prediction module: based on the predicted switching time, obtain the past intermittent time length in multiple past monitoring periods, and analyze to obtain the predicted switching time length, and complete the new energy power switching.

Images