Method for filling power data of photovoltaic power generation equipment and data monitoring system

Abstract

The application provides a power data filling method of a photovoltaic power generation device and a data monitoring system. The data monitoring system acquires power data and power data of the photovoltaic power generation device at intervals of a set time. The method comprises: performing first fitting filling on original power data acquired within the set time to obtain first power data; analyzing original power data acquired within the set time, determining target points needing power missing value filling, and then sequentially obtaining second power data related to the corresponding target points from the first power data according to each target point, and after sequentially performing second fitting on the second power data to obtain power fitting results, obtaining first filling power values of each target point according to the power fitting results; and filling power missing values of the target points according to the first filling power values. The application improves power filling efficiency and filling accuracy, and can effectively reflect the current operation of the photovoltaic power generation device.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method for filling power data of photovoltaic power generation equipment and a data monitoring system. Background Technology

[0002] In the field of photovoltaic power generation, it is usually necessary to use data monitoring systems to monitor the power generation of photovoltaic power generation equipment. For example, at the end of the day, the photovoltaic power generation data collected the previous day is used to draw power generation curves and power curves to display to users.

[0003] During the data acquisition process for photovoltaic power generation equipment, situations sometimes arise where electricity and power data are unavailable. With significant data gaps, it becomes difficult to directly utilize this data to create curves. Typically, electricity is obtained using a "daily cumulative" method, while power is measured as an "instantaneous value." For example... Figure 1 As shown, at certain times, although the equipment is running and its actual power should be greater than 0, the sampled power value is 0, presenting an abnormal power graph. However, not all power curves with a midpoint of 0 are abnormal; some equipment is actually stopped, such as... Figure 2 The diagram shown is a normal power graph. The main task of filling in missing power values ​​is to... Figure 1 If the power value shown is missing, fill in the missing power points, while avoiding [missing information]. Figure 2 The normal power diagram shown corresponds to a situation where an erroneous operation occurs.

[0004] The relevant photovoltaic (PV) power generation equipment data reconstruction scheme adopts a method combining historical data of PV power generation equipment with neural networks for data reconstruction. First, a data reconstruction model for PV power generation equipment is constructed using neural network technology. Then, the data reconstruction model is trained using historical data of PV power generation equipment, and data reconstruction is achieved based on the trained neural network model.

[0005] In the process of implementing the embodiments of this application, at least the following technical problems were found in the related art:

[0006] Training models based on historical data involves a large amount of data processing and has a low processing rate. Furthermore, reconstructing data based on historical data cannot accurately reflect the operating conditions of the current day. The curves displayed using such reconstructed data tend to have more demonstrative value than real value in guiding the operation of power generation equipment. Summary of the Invention

[0007] This application provides a method for filling power data of photovoltaic power generation equipment and a data monitoring system to solve the problems of large data processing volume, low data processing rate and inability to reflect the current real operation of photovoltaic power generation equipment in the process of model training based on historical data.

[0008] In a first aspect, embodiments of this application provide a method for filling power data of a photovoltaic power generation device, applied to a data monitoring system for the photovoltaic power generation device, wherein the data monitoring system acquires the power and electricity data of the photovoltaic power generation device at set intervals; the method includes:

[0009] The raw power data acquired within a set time period is first fitted and filled to obtain the first power data;

[0010] After analyzing the raw power data obtained within a set time period and determining the target points where missing power values ​​need to be filled, the second power data related to the corresponding target point is extracted from the first power data according to each target point. After performing a second fitting on the second power data to obtain the power fitting result, the first filled power value of each target point is obtained according to the power fitting result.

[0011] The missing power value at the target point is filled according to the first filling power value.

[0012] In one possible implementation, the step of performing a first fitting and filling process on the raw power data acquired within a set time period to obtain the first power data includes:

[0013] The charge fitting and filling operation is performed cyclically; wherein the charge fitting and filling operation includes:

[0014] Obtain combinations of missing power values ​​in the original power data where the time interval between two adjacent power values ​​is greater than the first time interval. , );

[0015] Pick Preset quantity of power value and Then, a number of power values ​​are set, the corresponding time series T and power series M are determined, and a first fitting is performed based on the time series T and power series M to obtain the power fitting formula corresponding to each combination of power missing points.

[0016] In missing point combination ( , Within the corresponding time interval, a filling power point is determined every second time interval, and the filling power value corresponding to each filling power point is determined based on the corresponding power fitting formula. The original power data is then filled as the original power data for the next cycle.

[0017] When there is no missing battery data combination, the corresponding battery data is used as the first battery data; wherein, the second time interval is shorter than the first time interval.

[0018] In one possible implementation, prior to the cyclic execution of the charge fitting and filling operation, the following is also included:

[0019] Before the first power value in the original power data, a set number of first power values ​​are continuously compensated according to the second time interval; and after the last power value in the original power data, a set number of second power values ​​are continuously compensated according to the second time interval.

[0020] Wherein, the first power value is zero; the second power value is determined based on the last power value in the original power data.

[0021] In one possible implementation, after determining the filling charge value corresponding to each filling charge point based on the corresponding charge fitting formula, the method further includes:

[0022] Calculate the difference between each filled power value and the corresponding power values ​​in the two adjacent original power data.

[0023] When the power difference is either negative or positive, discard the corresponding fill power value.

[0024] In one possible implementation, before performing a first fitting and filling process on the raw power data acquired within a set time period to obtain the first power data, the method further includes:

[0025] The raw power and energy data acquired within a set time period are converted in seconds according to the sampling time, and the raw power and energy data are initialized as time axis coordinates.

[0026] The step of sequentially extracting the second power data related to the corresponding target point from the first power data according to each target point includes:

[0027] Based on the time axis coordinates corresponding to each target point, a set number of power values ​​are extracted from the first power data before and after the target point as the second power data.

[0028] In one possible implementation, obtaining the first filling power value for each target point based on the power fitting result includes:

[0029] The electrical energy fitting results for each target point are differentiated, and the first filling power value for each target point is determined based on the time axis coordinates of each target point and the corresponding differentiation results; wherein, the electrical energy fitting results are fitting formulas.

[0030] In one possible implementation, after obtaining the first filling power value for each target point based on the power fitting result, the method further includes:

[0031] A third fitting is performed on the original power data to obtain the power fitting result;

[0032] Based on the power fitting results and combined with the original power data and the acquisition accuracy of the original power data, the first filling power value is corrected to obtain the second filling power value for each target point.

[0033] The step of filling the power missing value of the target point according to the first filling power value includes:

[0034] The power missing value at the target point is filled with the second filling power value.

[0035] In one possible implementation, the third fitting of the original power data to obtain the power fitting result includes:

[0036] The original power data is segmented to obtain multiple segmented power data.

[0037] The power fitting results are obtained by performing a third fitting on the power data of each segment, and the segment fitting formula of the multi-segment curve is obtained.

[0038] In one possible implementation, the step of correcting the first filling power value based on the power fitting result and in conjunction with the original energy data and the acquisition accuracy of the original power data to obtain the second filling power value for each target point includes:

[0039] Iterate through each target point and perform the following operations:

[0040] The fitted power value corresponding to the target point is determined according to the piecewise fitting formula corresponding to the target point, and multiple target power values ​​adjacent to the target point in the full power data are determined; wherein, the full power data is the power data set of each of the first filled power values ​​and the original power data;

[0041] When the first filling power value corresponding to the target point is greater than multiple adjacent target power values, and the ratio of the first filling power value corresponding to the target point to the corresponding fitted power value is greater than a set threshold, the ratio of the first filling power value corresponding to the target point to the set threshold is used as the second filling power value.

[0042] The set threshold is the ratio of the acquisition accuracy of the original electricity data to the acquisition accuracy of the original power data.

[0043] Secondly, embodiments of this application provide a data monitoring system for photovoltaic power generation equipment, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the computer program, it implements the steps of the method described in the first aspect or any possible implementation of the first aspect.

[0044] Thirdly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method as described in the first aspect or any possible implementation of the first aspect.

[0045] This application provides a method and data monitoring system for filling power data of a photovoltaic power generation device. By performing a first fitting and filling process on the raw power data acquired within a set time period, missing power data caused by various reasons is compensated for, thus obtaining complete power data and obtaining first power data. The raw power data acquired within the set time period is analyzed to determine target points with missing power values. Then, second power data related to each target point is sequentially extracted from the first power data. After performing a second fitting process on the second power data to obtain power fitting results, the first filling power value for each target point is calculated based on the power fitting results. The missing power values ​​at the target points are then filled based on the first filling power values. This application abandons the method of reconstructing data using historical data; the filling process uses real-time data within a small time range acquired according to a set time period. Specifically, this application uses a method of fitting power data within a small range to ensure the accuracy of the filled power value within a minimal range. In this application embodiment, power data and energy data of the photovoltaic power generation device are acquired in real time at set time intervals, and the relatively stable power data acquired in real time is used for fitting and filling to obtain complete first power data. Then, based on the first power data, the power filling value is determined in segments within a small range to fill in the missing power values. Compared with the method of relying on historical power data for analysis and power filling, this method improves the power filling efficiency and filling accuracy, and can effectively reflect the current operating status of photovoltaic power generation equipment. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0047] Figure 1 This is a schematic diagram of abnormal power data;

[0048] Figure 2 This is a schematic diagram of normal power data;

[0049] Figure 3 This is a flowchart illustrating the implementation of a power data filling method for a photovoltaic power generation device according to an embodiment of this application;

[0050] Figure 4a This is a schematic diagram of the process for acquiring first power data according to an embodiment of this application;

[0051] Figure 4b This is a schematic diagram of the first power data provided in an embodiment of this application;

[0052] Figure 5a This is a schematic flowchart illustrating the calculation of power missing value according to an embodiment of this application;

[0053] Figure 5b This is a schematic diagram of the power curve filling result provided in an embodiment of this application;

[0054] Figure 6a This is a schematic diagram illustrating an anomaly in the first fill power value provided in an embodiment of this application;

[0055] Figure 6b This is a schematic diagram of the first filling power value correction process provided in an embodiment of this application;

[0056] Figure 6c This is a schematic diagram of power value correction filling provided in an embodiment of this application;

[0057] Figure 7 This is a flowchart illustrating the implementation of a power data filling method for a photovoltaic power generation device according to another embodiment of this application;

[0058] Figure 8 This is a flowchart illustrating the segmentation of raw power data according to another embodiment of this application;

[0059] Figures 9a-9d This is the experimental data curve;

[0060] Figure 10 This is a schematic diagram of the structure of a data monitoring system for photovoltaic power generation equipment provided in an embodiment of this application. Detailed Implementation

[0061] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0062] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0063] Unless otherwise stated, the term "multiple" means two or more. The character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B. The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0064] The terms used in this application are for describing embodiments only and are not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. Similarly, the term “and / or” as used herein means including one or more of the associated listed elements and all possible combinations thereof. Additionally, when used in this application, the terms “comprise” and its variations “comprises” and / or “comprising” refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitation, an element defined by the phrase “comprising an…” does not exclude the presence of additional identical elements in the process, method, or apparatus that includes said element.

[0065] In this application, each embodiment focuses on describing the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, then the relevant parts can be referred to the description of the method section.

[0066] The method provided in this application is applicable to the field of photovoltaic power generation and is specifically applied to the data monitoring system of photovoltaic power generation equipment. The data monitoring system acquires the electricity and power data of photovoltaic power generation equipment at set intervals to ensure the real-time performance and accuracy of the data, and to achieve accurate statistics on power generation and monitoring of equipment operating status.

[0067] Optionally, the power and electricity data of the photovoltaic power generation equipment can be acquired once a day to facilitate detailed statistics and analysis of daily power generation. The photovoltaic power generation equipment samples power and electricity approximately every 5 minutes.

[0068] In the theoretical system, based on the characteristics of photovoltaic power generation, the power consumption curve should show a continuous upward trend, while the power curve should exhibit a normal distribution. However, due to missing data points, a large number of points with zero values ​​appear. Combined with the influence of external factors affecting the inverter, this causes the power generation process to exhibit nonlinear characteristics. Therefore, although the power consumption curve shows an upward trend with occasional plateaus, the power curve fluctuates frequently and appears to have no discernible pattern. In this situation, we cannot directly fill in the missing power data by fitting the power curve. Instead, we should first fit the overall upward-trending power consumption curve and then indirectly calculate the missing power.

[0069] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0070] Figure 3 This is a flowchart illustrating the implementation of a power data filling method for a photovoltaic power generation device according to an embodiment of this application. Figure 3 As shown, the method includes the following steps:

[0071] S301, perform a first fitting and filling process on the raw power data obtained within a set time to obtain the first power data.

[0072] The method provided in this application is implemented by a data monitoring system for photovoltaic power generation equipment. In practice, the data monitoring system acquires the electricity and power data of the photovoltaic power generation equipment at preset time intervals to obtain raw electricity and power data. During actual data acquisition, due to time delays or data transmission errors, missing electricity and power values ​​may occur. To ensure the accuracy of the missing power data indirectly calculated based on electricity levels and to guarantee complete data filling, it is necessary to supplement the raw electricity and power data.

[0073] When acquiring the electricity and power data of the photovoltaic power generation equipment once a day, the raw electricity and power data are the electricity and power data from the previous day. Furthermore, throughout the day, the photovoltaic power generation equipment records the electricity and power values ​​approximately every 5 minutes.

[0074] Therefore, after performing the first fitting and filling on the original power data obtained within a set time in S301, a more complete first power data can be obtained compared to the original power data, that is, there is a power value corresponding to a 5-minute interval.

[0075] In addition, when filling in the power data, the data is fitted based on the original power data to ensure that the power data is smooth.

[0076] S302, after analyzing the raw power data obtained within a set time period and determining the target points where missing power values ​​need to be filled, the second power data related to the corresponding target point is extracted from the first power data according to each target point. After performing a second fitting on the second power data to obtain the power fitting result, the first filled power value of each target point is obtained according to the power fitting result.

[0077] Specifically, second power data related to the corresponding target point is extracted from the first power data for each target point to ensure the accuracy of the power value filling within a minimal range. The filling power value is then obtained by fitting power data within a small range.

[0078] The power fitting result is either a power fitting formula or a power fitting curve that facilitates data monitoring and analysis by relevant technical personnel. When obtaining the first filling power value for each target point based on the power fitting result, the coordinates of the target point are substituted into the power fitting formula to calculate the corresponding filling power value, or the corresponding filling power value is read from the power fitting curve based on the coordinates of the target point.

[0079] S303, fill the missing power value of the target point according to the first filling power value.

[0080] In this embodiment, by performing a first fitting and filling process on the raw power data acquired within a set time period, the missing power data caused by various reasons is compensated for, thereby obtaining complete power data and obtaining the first power data. The raw power data acquired within the set time period is analyzed to determine target points with missing power values. Then, based on each target point, the relevant second power data is sequentially extracted from the first power data. After performing a second fitting process on the second power data to obtain power fitting results, the first filling power value for each target point is calculated based on the power fitting results. Then, the missing power values ​​at the target points are filled based on the first filling power values. This application abandons the method of reconstructing data using historical data; the filling process uses real-time data within a small time range acquired according to a set time period. Specifically, this application uses a method of fitting power data within a small range to ensure the accuracy of the filled power values ​​within the smallest possible range. In this embodiment, by setting a time interval, the power data and energy data of the photovoltaic power generation equipment are acquired in real time, and the relatively stable power data acquired in real time is used for fitting and filling to obtain complete first power data. Then, based on the first power data, the power filling value is determined in segments within a small range to fill in the missing power values. Compared with the method of relying on historical power data for analysis and power filling, this method improves the power filling efficiency and filling accuracy, and can effectively reflect the current operating status of photovoltaic power generation equipment.

[0081] Optionally, the first fit and the second fit are different, with the second fit having a higher polynomial degree than the first fit.

[0082] In polynomial fitting, a higher-order polynomial (i.e., a higher degree) will result in a fit closer to the actual value. However, when errors exist in the actual data, the fitting result may approximate those errors. Therefore, during fitting, the polynomial order should be avoided as it may affect the accuracy of the fitting result, while the polynomial order should also be avoided as it may prevent overfitting.

[0083] In the embodiments of this application, the original power consumption data is first fitted to obtain first power consumption data. Then, a portion of the first power consumption data is extracted based on the target location for a second fitting to obtain the power consumption fitting result. Since the power consumption data obtained from the first fitting is used in the second fitting process, the power consumption values ​​are relatively smooth, and the power consumption error is smaller than that of the original power consumption data. Therefore, the second fitting has a higher polynomial order than the first fitting to ensure a more accurate fitting of the power consumption data. The first fitting, on the other hand, chooses a relatively lower polynomial order to avoid overfitting.

[0084] In one possible implementation, the first fit is a 5-term fit, and the second fit is a 10-term fit.

[0085] The overall characteristics of the power curve are not obvious due to the influence of various factors. If the power curve is directly fitted to complete the power, it may lead to a decrease in power or excessive deviation between the fitted value and the actual value in some places. To solve this problem, embodiment S301 of this application divides the power into multiple stages and avoids the above situations by fitting the power curve in segments.

[0086] In one possible implementation, the raw power data acquired within a set time period is first fitted and filled to obtain first power data, including:

[0087] The battery level fitting and filling operation is performed repeatedly; the battery level fitting and filling operation includes:

[0088] Identify combinations of missing battery values ​​in the original battery data where the time interval between two adjacent battery values ​​is greater than the first time interval. , );

[0089] Pick Preset quantity of power value and Then, a number of power values ​​are set, the corresponding time series T and power series M are determined, and the first fitting is performed based on the time series T and power series M to obtain the power fitting formula corresponding to each combination of power missing points.

[0090] In missing point combination ( , Within the corresponding time interval, a filling power point is determined every second time interval, and the filling power value corresponding to each filling power point is determined based on the corresponding power fitting formula. The original power data is then filled as the original power data for the next cycle.

[0091] When there is no missing battery data combination, the corresponding battery data is used as the first battery data; wherein, the second time interval is shorter than the first time interval.

[0092] Optionally, the first time interval is 300s; the second time interval is 600s. The first time interval corresponds to a 5-minute interval for measuring the electrical quantity and power in the system.

[0093] In actual implementation, when multiple power data points are missing, even after a single power data filling process, some power data may still remain missing. Therefore, it is necessary to repeatedly fill in the missing power values ​​to ensure that complete power data is obtained. When there is no combination of missing power points where the time interval between two adjacent power values ​​is greater than the first time interval, the power data is determined to be the complete first power data, and subsequent power value calculations are performed.

[0094] In one possible implementation, before performing the charge fitting and filling operation in a loop, the following is also included:

[0095] Before the first power value in the original power data, a set number of first power values ​​are continuously compensated according to the second time interval, and after the last power value in the original power data, a set number of second power values ​​are continuously compensated according to the second time interval.

[0096] The first power value is zero; the second power value is determined based on the last power value in the original power data.

[0097] Theoretically, the battery level curve should be S-shaped, but due to data gaps, there may be gaps in the middle or at the beginning and end. Therefore, when the battery level gaps combine ( , When the battery level is located at a relatively early or late position in the original battery data, the combination of missing battery points ( , )Pick Preset quantity of power value and After setting a number of power values, there are cases where no power value can be obtained for power fitting, resulting in the inability to effectively fill in the missing power values.

[0098] Based on the power generation principle of photovoltaic (PV) power generation equipment, the power generation is zero per unit time before sunrise and after sunset. Therefore, the power curve increases from 0 to a certain level and then remains constant. Thus, data with a value of 0 can be filled before the original power data at 5-minute intervals, and data with the last power value can be filled after the original power data. Alternatively, power values ​​can be filled after the original power data based on the last power value and the power change trend. Furthermore, the number of filled values ​​should be consistent with the number of power values ​​obtained on one side when constructing the power sequence M during the power fitting curve acquisition process. This ensures that when supplementing power values ​​that are relatively early or late in the original power data, the power values ​​can be successfully obtained for fitting.

[0099] In this implementation, multiple power values ​​are continuously compensated before and after the power data to make the power data more complete, thereby providing an accurate basis for subsequent data analysis and processing.

[0100] In one specific embodiment, based on the steps of fitting and filling the original power data in the above embodiments, the process of performing a first fitting and filling on the original power data obtained within a set time to obtain the first power data is as follows: Figure 4a As shown. The result of filling the power curve is as follows. Figure 4b As shown in the figure.

[0101] In one possible implementation, after determining the filling charge value corresponding to each filling charge point based on the corresponding charge fitting formula, the method further includes:

[0102] Calculate the difference between each filled power value and the corresponding power values ​​in the two adjacent original power data.

[0103] When the power difference is either negative or positive, discard the corresponding fill power value.

[0104] According to the working characteristics of photovoltaic power generation equipment, the power generation should increase continuously as the power generation time extends. Therefore, when selecting a power value from the power data, the power value should be greater than or equal to the power value before it and less than or equal to the power value after it.

[0105] When the difference between the filled power value and the power values ​​of the two adjacent original power values ​​are both negative, the filled power value is less than the previous power value. When the difference between the filled power value and the power values ​​of the two adjacent original power values ​​are both positive, the filled power value is greater than the subsequent power value. In both of these cases, the filled power value does not match the actual situation and therefore needs to be discarded.

[0106] In this embodiment, by calculating the difference between the power values ​​of each fill power value and the corresponding power values ​​of the two adjacent original power data, reasonable fill power values ​​can be effectively selected, providing an accurate basis for power filling and improving the accuracy of power filling.

[0107] In one possible implementation, before performing a first fitting and padding on the raw power data acquired within a set time period to obtain the first power data, the method further includes:

[0108] The raw power and energy data acquired within a set time period are converted in seconds according to the sampling time, and the raw power and energy data are initialized as time axis coordinates.

[0109] Sequentially extract the second power data related to the corresponding target point from the first power data for each target point, including:

[0110] Based on the time axis coordinates corresponding to each target point, a set number of power values ​​are extracted from the first power data before and after the target point as the second power data.

[0111] In practice, the electricity and power values ​​of the photovoltaic power generation equipment are measured approximately every 5 minutes, and the measurement times are not always the same. Therefore, it is not possible to directly determine the power supplement value using the raw data. For this reason, the data needs to be processed into a two-dimensional curve with time as the horizontal axis and electricity or power as the vertical axis, with the time unit being seconds.

[0112] In one specific embodiment, after acquiring the daily electricity or power data, the time at each point is converted to the second of the day to construct the horizontal axis. For example, the time "09:49:06" needs to be converted to 9 × 3600 + 49 × 60 + 6 = 35346.

[0113] In this embodiment, the sampling time is converted to seconds, and the original power data and energy data are initialized as time axis coordinates. This helps to unify the power data and energy data to the same standard time scale, making it easier to obtain the corresponding power data according to the time axis coordinates of the target point, thereby providing valuable information for calculating the power value of the target point.

[0114] In one possible implementation, the first filling power value for each target point is obtained based on the energy fitting results, including:

[0115] The electrical energy fitting results for each target point are differentiated, and the first filling power value for each target point is determined based on the time axis coordinates of each target point and the corresponding differentiation results; wherein, the electrical energy fitting results are fitting formulas.

[0116] Among them, the power fitting result is a fitting formula or fitting curve. According to the relationship between power and energy: "Power comes from the integral of energy". The filling power value is obtained by differentiating the power fitting result. This process is equivalent to the mapping from power to energy.

[0117] In one specific embodiment, based on the steps related to power missing value calculation in the above embodiments, the power missing value calculation process is as follows: Figure 5a As shown. The power curve filling result is as follows. Figure 5b As shown in the figure.

[0118] In the system, the precision of the electricity data is 0.1 in some parts and 1 in others, while the precision of the power data is 0.01. Therefore, directly obtaining the power value from the electricity data (or obtaining the power curve by differentiating the electricity curve) will result in a large error. For example, if there is 0 kWh of electricity at time point A and 1 kWh of electricity at time point B, assuming the power remains constant during this time interval, after 5 minutes, the power during this period would be: (1000-0)×12=12000 kW. However, in reality, there may have been continuous power generation before time point A (and after time point B), with the power generation at point A being 0.4 and at point B being 0.5. The actual power would then be: (500-400)×12=1200 kW. As you can see, the calculated result differs by a factor of 10. Therefore, to ensure the accuracy of the power filling, the filled power value needs to be verified and corrected.

[0119] In one possible implementation, after obtaining the first filling power value for each target point based on the power fitting results, the method further includes:

[0120] A third fitting is performed on the original power data to obtain the power fitting result;

[0121] The first filling power value is corrected based on the power fitting results and the original power data and the accuracy of the original power data acquisition, so as to obtain the second filling power value of each target point.

[0122] The power missing values ​​at the target points are filled based on the first filled power value, including:

[0123] The missing power value at the target point is filled with the second filling power value.

[0124] Optionally, the first fit, the second fit, and the third fit are different, with the second fit having a higher polynomial degree than the first fit, and the first fit having a higher polynomial degree than the third fit.

[0125] In the embodiments of this application, the original power consumption data is first fitted to obtain first power consumption data. Then, a portion of the first power consumption data is extracted based on the target location for a second fitting to obtain the power consumption fitting result. Since the power consumption data obtained from the first fitting is used in the second fitting process, the power consumption values ​​are relatively smooth, and the power consumption error is smaller than that of the original power consumption data. Therefore, the second fitting has a higher polynomial order than the first fitting to ensure a more accurate fitting of the power consumption data. The first fitting, on the other hand, chooses a relatively lower polynomial order to avoid overfitting.

[0126] In the subsequent correction of the first filled power value, the original power data was segmented, and a third fitting was performed to obtain the power fitting result. In this case, since the segmented data has fewer data points and the errors before and after are relatively small, a polynomial order lower than that of the first fitting was selected for fitting to meet the correction requirements.

[0127] In one possible implementation, the first fit is a 5-term fit, the second fit is a 10-term fit, and the third fit is a 2-term fit.

[0128] In this embodiment, the first, second, and third fittings are least squares polynomial fittings. Based on the principle of minimizing the sum of squared errors in least squares polynomial fitting, by constructing a polynomial model that adapts to data changes, the actual fluctuations in electricity and power can be accurately captured and reflected. In this embodiment, for power curves with frequent fluctuations and electricity curves with occasional stable periods, least squares polynomial fitting can effectively smooth the fluctuations in power and electricity data, extract the main trends of power and electricity changes, and provide a reliable basis for electricity and power filling.

[0129] In one possible implementation, a third fitting is performed on the original power data to obtain the power fitting result, including:

[0130] The raw power data is segmented to obtain multiple segmented power data.

[0131] The power fitting results are obtained by performing a third fitting on the power data of each segment, and the segment fitting formula of the multi-segment curve is obtained.

[0132] In the actual operation of photovoltaic power generation equipment, there are situations where the power generation is zero for a period of time due to weather conditions or temporary cloud cover blocking sunlight. Therefore, fitting power data with continuously zero power for a period of time to obtain the power value will increase the data volume and may also affect the accuracy of the power filling result. In a specific embodiment, the original power data can be segmented by setting the number of consecutive zero points, or by setting the number of zero points within a time period.

[0133] For example, when segmenting the original power data by setting the number of consecutive zero points, if the number of consecutive zero points is set to 5, the power values ​​at power points 6-10 and 30-40 will be consecutively 0. In this case, power point 30-40 will not participate in the third fitting. When segmenting the original power data by setting the number of zero points within a time period, if the number of zero points is greater than 4 within a consecutive 30 minutes (taking a sampling interval of 5 minutes as an example), the power data for the corresponding 30 minutes will not participate in the third fitting.

[0134] In this embodiment, the original power data is segmented, and a third fitting is performed on the effective power segment data to obtain the segmented fitting formula of the multi-segment curve, thereby improving the accuracy of power value filling.

[0135] In one possible implementation, the first filling power value is corrected based on the power fitting result and in combination with the original energy data and the accuracy of the original power data acquisition, to obtain the second filling power value for each target point, including:

[0136] Iterate through each target point and perform the following operations:

[0137] The fitted power value corresponding to the target point is determined according to the piecewise fitting formula corresponding to the target point, and multiple target power values ​​adjacent to the target point in the full power data are determined; wherein, the full power data is the power data set of each first filled power value and the original power data;

[0138] When the first filling power value corresponding to the target point is greater than multiple adjacent target power values, and the ratio of the first filling power value corresponding to the target point to the corresponding fitted power value is greater than a set threshold, the ratio of the first filling power value corresponding to the target point to the set threshold is used as the second filling power value.

[0139] The threshold is set as the ratio of the accuracy of acquiring the original electricity data to the accuracy of acquiring the original power data.

[0140] The number of target power values ​​is less than a set number. Optionally, the number of target power values ​​is 1 to 5. Optionally, the number of target power values ​​is 3.

[0141] Taking a target power value of 3 as an example, the first filling power value corresponding to the target point is greater than the adjacent target power values, including: the first filling power value corresponding to the target point is greater than the previous 3 power values ​​and the next 3 power values.

[0142] During the actual operation of photovoltaic power generation equipment, there may be situations where dark clouds briefly block sunlight, causing the power generation to drop to zero for a period of time. Consequently, the fill power value may be much lower than its adjacent power values. However, if... Figure 6a As shown, when the ratio of the first filled power value to the corresponding fitted power value at the target point with an abscissa of 65000 exceeds a set threshold, it indicates that the fitted power value is abnormal and needs to be corrected. Next, the ratio of the first filled power value to the set threshold is used as the second filled power value. In this embodiment, by dividing the first filled power value by the set threshold, the problem of data deviation caused by rounding when converting low-precision electrical data to high-precision power data is solved in principle. The processing effect can be seen in the following section on... Figure 6c , Figures 9a-9d The content described.

[0143] In this embodiment, the abnormal filling points are located by segmenting and fitting the power curve, and then calculating its deviation value. The deviation value is scaled according to the accuracy of the power data, thereby correcting the filling power value and improving the accuracy of the power filling result.

[0144] In one specific embodiment, the power missing value correction process is as follows: Figure 6b As shown, the power missing value correction results are as follows: Figure 6c As shown.

[0145] Because of the difference in accuracy between electricity data and power data, there will be a significant error in obtaining the power value based on the electricity consumption. Figure 7 This document illustrates a flowchart of the implementation of a power data filling method for a photovoltaic power generation device according to another embodiment of this application. Figure 7 As shown, the method includes the following steps:

[0146] S701, perform a first fitting and filling process on the raw power data obtained within a set time to obtain the first power data;

[0147] S702, Analyze the raw power data obtained within a set time period, determine the target points where missing power values ​​need to be filled, and obtain the first filling power value for each target point based on the first power data;

[0148] S703, perform a third fitting on the original power data to obtain the power fitting result, and correct the first filling power value based on the power fitting result and the original power data and the acquisition accuracy of the original power data to obtain the second filling power value of each target point, and fill the missing power value of the target point with the second filling power value.

[0149] This embodiment abandons the method of reconstructing data using historical data. Instead, the filling process uses real-time data acquired within a small time range at set intervals. Specifically, this application acquires the electricity and power data of the photovoltaic power generation equipment in real time at set time intervals, and uses the relatively stable electricity data acquired in real time to fit and fill the data, thereby obtaining complete first electricity data. The power filling value is determined based on the first electricity data, and missing power values ​​are filled in. Compared with the method of relying on historical power data for analysis and power filling, the power filling efficiency is improved, and it can effectively reflect the current operating status of the photovoltaic power generation equipment. More importantly, this application also considers that the acquisition accuracy of electricity and power data in the data monitoring system usually has a difference of magnitude. If this difference in accuracy is not considered in the method of filling power data with electricity data, some missing data points may cause numerical deviations during data processing such as rounding due to the difference in accuracy, and the direction of the deviation is unpredictable, resulting in a large deviation between the filled power data and the true value. Therefore, this application corrects the first filled power value based on the power fitting result of the original power data. The correction process fully takes into account the acquisition accuracy of the power data and the power data to avoid excessive deviation of the power supplement value caused by the difference in acquisition accuracy of power data and power data, thereby improving the accuracy of power value filling.

[0150] In one possible implementation, a third fitting is performed on the original power data to obtain the power fitting result, including:

[0151] The raw power data is segmented to obtain multiple segmented power data.

[0152] The power fitting results are obtained by performing a third fitting on the power data of each segment, and the fitting formula for the multi-segment curve is obtained.

[0153] In one possible implementation, such as Figure 8 As shown, the raw power data is segmented, including:

[0154] Take the index sequence A of the points with a power value of 0 in the original power data;

[0155] Calculate the difference between the preceding and following indices in index sequence A, and construct the difference sequence B;

[0156] Take the index values ​​of the difference sequence B where the difference is greater than 1, and construct the index sequence C;

[0157] Based on the index values ​​in index sequence C, take sequence D from index sequence A, and then take sequence E with index C+1 from index sequence A;

[0158] Subtracting the second value of sequence E from the first value of sequence E yields sequence F;

[0159] Take the index G in sequence F that is less than the set value;

[0160] Delete sequence G+1 from sequence D / E;

[0161] The difference between sequence E and sequence D is used to obtain sequence H;

[0162] Delete sequence values ​​in sequence D / E that are less than a set value in sequence H, and use the retained sequence values ​​as segmentation points to segment the original power data according to the segmentation points.

[0163] Points with zero power often correspond to certain important physical phenomena in photovoltaic power generation equipment, such as the interruption of power generation due to passing clouds. Analyzing these zero-power points can provide a better understanding of the equipment's operating status, thus providing a reliable basis for power segmentation.

[0164] To facilitate understanding of the above process of "segmenting the raw power data", the following specific power data will be used for explanation:

[0165] The power data is as follows:

[0166]

[0167] Where I is the index, T is the time, and P is the power.

[0168] Then the index A where the power is 0 is:

[0169]

[0170] The index difference B is:

[0171]

[0172] The index C in index B that is greater than 1 is:

[0173]

[0174] Taking the value at index C / C+1 ​​in sequence A yields D / E:

[0175]

[0176] The sequence interval F is:

[0177]

[0178] Get G by taking the value with an index less than 6:

[0179]

[0180] Correcting D / E yields:

[0181]

[0182] Subtracting sequence D from sequence E yields H:

[0183]

[0184] By removing points less than 6 from sequence H from sequence D / E, we finally obtain sequence D / E:

[0185]

[0186] Therefore, in the above example, the continuous power point is between the 0th and 12th points.

[0187] In this embodiment, a power analysis sequence is constructed by extracting points with zero power values, and a series of analysis processes are performed based on the index differences of the power analysis sequence. In this way, relatively continuous and dispersed power values ​​can be determined according to the actual power variation patterns, thereby improving the accuracy of power segmentation.

[0188] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0189] To verify the effectiveness of the photovoltaic power generation equipment power data filling method provided in the embodiments of this application, the original normal power and electricity data are first obtained, and then... Figure 9a As exemplified, certain consecutive points in the power curve are randomly selected and the corresponding data is deleted, along with the power data within the interval containing the selected points. Subsequently, a power data filling test is performed using the power data filling method for photovoltaic power generation equipment proposed in this application embodiment.

[0190] In one specific embodiment, such as Figure 9b As shown, nine curves were selected for power data filling tests, and then, according to... Figure 9a The test data processing procedure shown yields... Figure 9c The test data curve is shown. Subsequently, a power data filling test was performed using the power data filling method for photovoltaic power generation equipment proposed in this application embodiment. For example... Figure 9d The image shows a comparison between the power data filling test results and the power curves in the original test data. According to... Figure 9d It can be seen that the trend of the power data filling result is basically consistent with that of the original test data. The data values ​​fluctuate within a certain range above and below the true values, and the area enclosed by the filling result is basically consistent with the area enclosed by the true data.

[0191] The photovoltaic power data filling method provided in this application, after unifying the time coordinates, fills the power curve by leveraging the continuity of the power curve, thereby creating conditions for filling the power curve. It utilizes the relationship between power and electricity to derive the derivative formula of the power curve, thereby obtaining the missing data of the power curve. Finally, it corrects the missing power values. Based on the above verification embodiments, it is confirmed that the solution of this application can obtain relatively perfect data that overcomes accuracy issues.

[0192] The following are device embodiments of this application. For details not described in detail, please refer to the corresponding method embodiments described above.

[0193] Figure 10 This is a schematic diagram of the structure of a data monitoring system for photovoltaic power generation equipment provided in one embodiment of this application. Figure 10 As shown, the data monitoring system 10 for photovoltaic power generation equipment in this embodiment includes: a processor 100, a memory 101, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, it implements the steps in the power data filling method embodiments of the various photovoltaic power generation equipment described above, for example... Figure 2 or Figure 7 The steps shown.

[0194] For example, the computer program 102 may be divided into one or more modules / units, which are stored in the memory 101 and executed by the processor 100 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 102 in the data monitoring system 10 of the photovoltaic power generation equipment.

[0195] The data monitoring system 10 for the photovoltaic power generation equipment can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The data monitoring system 10 for the photovoltaic power generation equipment may include, but is not limited to, a processor 100 and a memory 101. Those skilled in the art will understand that... Figure 10 This is merely an example of a data monitoring system 10 for photovoltaic power generation equipment and does not constitute a limitation on the data monitoring system 10 for photovoltaic power generation equipment. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the data monitoring system for photovoltaic power generation equipment may also include input / output devices, network access devices, buses, etc.

[0196] The processor 100 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0197] The memory 101 can be an internal storage unit of the photovoltaic power generation equipment's data monitoring system 10, such as a hard drive or memory of the photovoltaic power generation equipment's data monitoring system 10. The memory 101 can also be an external storage device of the photovoltaic power generation equipment's data monitoring system 10, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the photovoltaic power generation equipment's data monitoring system 10. Furthermore, the memory 101 can include both internal storage units and external storage devices of the photovoltaic power generation equipment's data monitoring system 10. The memory 101 is used to store the computer program and other programs and data required by the photovoltaic power generation equipment's data monitoring system. The memory 101 can also be used to temporarily store data that has been output or will be output.

[0198] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0199] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0200] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0201] In the embodiments provided in this application, it should be understood that the disclosed data monitoring system and method for the device / photovoltaic power generation equipment can be implemented in other ways. For example, the data monitoring system embodiments for the device / photovoltaic power generation equipment described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0202] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0203] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0204] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-described embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the power data filling method embodiments for each of the above-described photovoltaic power generation devices. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0205] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for filling power data of a photovoltaic power generation device, applied to a data monitoring system for a photovoltaic power generation device, wherein the data monitoring system acquires the power and electricity data of the photovoltaic power generation device at set time intervals; characterized in that, The method includes: The raw power data acquired within a set time period is first fitted and filled to obtain the first power data; After analyzing the raw power data obtained within a set time period and determining the target points where missing power values ​​need to be filled, the second power data related to the corresponding target point is extracted from the first power data according to each target point. After performing a second fitting on the second power data to obtain the power fitting result, the first filled power value of each target point is obtained according to the power fitting result. The missing power value at the target point is filled according to the first filling power value; The step of performing a first fitting and filling process on the raw power data acquired within a set time period to obtain the first power data includes: The charge fitting and filling operation is performed cyclically; wherein the charge fitting and filling operation includes: Obtain combinations of missing power values ​​in the original power data where the time interval between two adjacent power values ​​is greater than the first time interval. , ); Pick Preset quantity of power value and Then, a number of power values ​​are set, the corresponding time series T and power series M are determined, and a first fitting is performed based on the time series T and power series M to obtain the power fitting formula corresponding to each combination of power missing points. In missing point combination ( , Within the corresponding time interval, a filling power point is determined every second time interval, and the filling power value corresponding to each filling power point is determined based on the corresponding power fitting formula. The original power data is then filled as the original power data for the next cycle. When there is no missing battery data combination, the corresponding battery data is used as the first battery data; wherein, the second time interval is shorter than the first time interval.

2. The power data filling method for photovoltaic power generation equipment according to claim 1, characterized in that, Before the cyclic execution of the charge fitting and filling operation, the following is also included: Before the first power value in the original power data, a set number of first power values ​​are continuously compensated according to the second time interval; and after the last power value in the original power data, a set number of second power values ​​are continuously compensated according to the second time interval. Wherein, the first power value is zero; the second power value is determined based on the last power value in the original power data.

3. The method for filling power data into a photovoltaic power generation device according to claim 1, characterized in that, After determining the filling charge value corresponding to each filling charge point based on the corresponding charge fitting formula, the method further includes: Calculate the difference between each filled power value and the corresponding power values ​​in the two adjacent original power data. When the power difference is either negative or positive, discard the corresponding fill power value.

4. The method for filling power data of a photovoltaic power generation device according to any one of claims 1 to 3, characterized in that, Before performing a first fitting and filling process on the raw power data acquired within a set time period to obtain the first power data, the method further includes: The raw power and energy data acquired within a set time period are converted to seconds based on the sampling time, and the raw power and energy data are initialized as time axis coordinates. The step of sequentially extracting the second power data related to the corresponding target point from the first power data according to each target point includes: Based on the time axis coordinates corresponding to each target point, a set number of power values ​​are extracted from the first power data before and after the target point as the second power data.

5. The power data filling method for photovoltaic power generation equipment according to claim 4, characterized in that, The step of obtaining the first filling power value for each target point based on the power fitting result includes: The energy fitting results of each target point are differentiated, and the first filling power value of each target point is determined based on the time axis coordinates of each target point and the corresponding differentiation results; wherein, the energy fitting results are energy fitting formulas.

6. The method for filling power data into a photovoltaic power generation device according to claim 1, characterized in that, After obtaining the first filling power value for each target point based on the power fitting result, the method further includes: A third fitting is performed on the original power data to obtain the power fitting result; Based on the power fitting results and combined with the original power data and the acquisition accuracy of the original power data, the first filling power value is corrected to obtain the second filling power value for each target point. The step of filling the power missing value of the target point according to the first filling power value includes: The power missing value at the target point is filled with the second filling power value.

7. The method for filling power data in a photovoltaic power generation device according to claim 6, characterized in that, The third fitting of the original power data to obtain the power fitting result includes: The original power data is segmented to obtain multiple segmented power data. The power fitting results are obtained by performing a third fitting on the power data of each segment, and the segment fitting formula of the multi-segment curve is obtained.

8. The method for filling power data in a photovoltaic power generation device according to claim 7, characterized in that, The step of correcting the first filling power value based on the power fitting result and in combination with the original power data and the accuracy of the original power data acquisition to obtain the second filling power value for each target point includes: Iterate through each target point and perform the following operations: The fitted power value corresponding to the target point is determined according to the piecewise fitting formula corresponding to the target point, and multiple target power values ​​adjacent to the target point in the full power data are determined; wherein, the full power data is the power data set of each of the first filled power values ​​and the original power data; When the first filling power value corresponding to the target point is greater than multiple adjacent target power values, and the ratio of the first filling power value corresponding to the target point to the corresponding fitted power value is greater than a set threshold, the ratio of the first filling power value corresponding to the target point to the set threshold is used as the second filling power value. The set threshold is the ratio of the accuracy of acquiring the original electricity data to the accuracy of acquiring the original power data.

9. A data monitoring system for photovoltaic power generation equipment, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 8 above.

Images