Power limiting state identification method and device, computer equipment and readable storage medium

Abstract

The invention provides a power limiting state identification method and device, computer equipment and a readable storage medium, and the method comprises the steps: obtaining the operation data of a photovoltaic power station and the meteorological data of the environment where the photovoltaic power station is located, and carrying out the recognition of the power limiting state according to the operation data of the photovoltaic power station or the meteorological data of the photovoltaic power station in combination with a plurality of types of power limiting power curves; and identifying the power limiting state of the photovoltaic power station. Wherein the power limiting state comprises a switching-out power limiting state, a peak clipping power limiting state and a current adjusting power limiting state. According to the invention, the accuracy of power limiting state detection of the photovoltaic power station can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, computer equipment and readable storage medium for identifying a power-limiting state. Background Art

[0002] In the scenario of distributed photovoltaics cooperating with peak load regulation, the power generation of photovoltaic power stations needs to be limited. The identification of power limit status of photovoltaic power stations usually adopts the following two methods: one is to establish a mapping model through meteorological data or sample inverter data, calculate the theoretical power generation of the power station, and compare it with the deviation degree of actual power, set a threshold to judge the power limit status; the other is to calculate the correlation between the actual power curve and the typical power limit power curve to identify the power limit status.

[0003] However, the first method relies on the accuracy of theoretical power calculation and is not suitable for power stations that cannot obtain meteorological data or sample inverter data. The second method is only applicable to a single type of power curtailment curve and is difficult to cover multiple power curtailment modes, limiting the accuracy and applicability of identification. Summary of the invention

[0004] The present application provides a power-limiting state identification method, device, computer equipment and readable storage medium, which can improve the accuracy of power-limiting state identification of a photovoltaic power station.

[0005] In a first aspect, the present application provides a method for identifying a power-limiting state, the method comprising:

[0006] Acquiring operation data of the photovoltaic power station and meteorological data of the environment in which the photovoltaic power station is located;

[0007] According to the operation data of the photovoltaic power station, or according to the meteorological data of the photovoltaic power station, combined with various types of power curtailment curves, the power curtailment state of the photovoltaic power station is identified; wherein the power curtailment state includes power cut state, peak shaving state and current regulation state.

[0008] Optionally, the operation data of the photovoltaic power station includes power data; and the identifying the power limit state of the photovoltaic power station according to the operation data of the photovoltaic power station and in combination with multiple types of power limit power curves includes:

[0009] Acquire a first number of data points in which the power of the photovoltaic power station is greater than zero in a first preset time period;

[0010] Acquire a second number of data points in which the power of the photovoltaic power station is equal to zero in a second preset time period;

[0011] Acquire a third number of data points in which the power of the photovoltaic power station is greater than zero in a third preset time period;

[0012] When the first number, the second number and the third number simultaneously meet a first preset condition, determining that the power-limiting state of the photovoltaic power station is in a power-limiting state;

[0013] The first preset period is earlier than the second preset period, and the second preset period is earlier than the third preset period.

[0014] Optionally, the first preset condition includes:

[0015] The first number is greater than or equal to a first threshold, the second number is greater than or equal to a second threshold, and the third number is greater than or equal to a third threshold.

[0016] Optionally, the identifying the power limit state of the photovoltaic power station according to the operation data of the photovoltaic power station in combination with multiple types of power limit power curves includes:

[0017] Acquiring power data of the photovoltaic power station in a fourth preset time period corresponding to a set peak power consumption period;

[0018] Performing a data cleaning operation on the power data of the fourth preset time period to obtain cleaned power data;

[0019] Performing linear regression on the power data after cleaning to obtain a corresponding fitting curve, and calculating the slope corresponding to the fitting curve;

[0020] When the slope meets a second preset condition, it is determined that the power limiting state of the photovoltaic power station is a peak-shaving power limiting state; the second preset condition includes that the absolute value of the slope is less than a fourth threshold.

[0021] Optionally, performing a data cleaning operation to obtain cleaned power data includes:

[0022] Deleting data points with zero power in the power data of the fourth preset time period to obtain first power data;

[0023] Data points below the first quantile and above the second quantile in the first power data are deleted to obtain the cleaned power data.

[0024] Optionally, the meteorological data includes rainfall in the area where the photovoltaic power station is located within a target time range; and identifying the power limit state of the photovoltaic power station based on the meteorological data of the photovoltaic power station and combining multiple types of power limit power curves includes:

[0025] Acquiring the rainfall of the photovoltaic power station on that day, and when the rainfall of the photovoltaic power station on that day is greater than or equal to a fifth threshold, not performing a power-limiting state identification operation on the photovoltaic power station;

[0026] On days when the daily rainfall of the photovoltaic power station is less than the fifth threshold, constructing a string current data set of the photovoltaic power station according to the string current data of the photovoltaic power station in a fifth preset time period before the day;

[0027] According to the string current data set of the photovoltaic power station, determine the average value of the string current data in the sixth preset time period before the current day as the historical current value, and the average value of the string current on the current day as the current current value;

[0028] The current change rate of the string current of the photovoltaic power station is determined according to the historical current value and the current current value; when the current change rate of the string current of the photovoltaic power station is greater than or equal to a sixth threshold value, the power limiting state of the photovoltaic power station is determined to be a current regulation power limiting state.

[0029] Optionally, determining the current change rate of the string current of the photovoltaic power station according to the historical current value and the current current value includes:

[0030] Determining a difference between the historical current value and the current current value;

[0031] The quotient between the difference and the historical current value is used as the current change rate of the string current of the photovoltaic power station.

[0032] Optionally, when the string current change rate of any string of the photovoltaic power station is greater than or equal to the sixth threshold, it is determined that the power limiting state of the photovoltaic power station is the current regulation power limiting state.

[0033] In a second aspect, the present application further provides a power-limiting state identification device, comprising:

[0034] An information acquisition module, used for acquiring characteristic variables of the inverter and embedding the characteristic variables into the circuit breaker;

[0035] An object identification module, used for obtaining an identification result of the circuit breaker for the inverter to be connected according to the characteristic variable after the circuit breaker is powered on;

[0036] The power-limiting state identification module is used to connect the circuit breaker with the inverter that has passed the identification according to the identification result, so as to establish the power-limiting state identification between the circuit breaker and the inverter.

[0037] In a third aspect, the present application also provides a computer device, comprising a processor and a memory; the memory is used to store a computer program; the processor is used to execute the computer program stored in the memory to implement the steps of the power-limiting state identification method as described above.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium storing a computer program, wherein the computer program is loaded by a processor to perform the steps of the power-limiting state identification method as described above.

[0039] The embodiments of the present application can perform feature extraction and analysis on a variety of typical power curtailment curves, can effectively distinguish different types of power curtailment, improve the accuracy of power curtailment status identification, and avoid dependence on meteorological data or model inverter data, so that the method of the present application can also be stably applied in photovoltaic power stations that lack such external data, and is applicable to a variety of power curtailment modes. Through feature identification of different power curtailment curves, it can improve the applicability and identification effect in various types of distributed photovoltaic power stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 It is a flowchart of a power-limiting state identification method provided in an embodiment of the present application;

[0042] Figure 2 It is a power curve diagram of a photovoltaic power station in a power-cutting state provided in an embodiment of the present application;

[0043] Figure 3 It is a power curve diagram of a photovoltaic power station in a peak-shaving and power-limiting state provided in an embodiment of the present application;

[0044] Figure 4 It is a power curve diagram of a photovoltaic power station in a current regulation and power limiting state provided in an embodiment of the present application;

[0045] Figure 5 is a schematic diagram of an exemplary process for performing multiple power-limiting state identifications provided in an embodiment of the present application;

[0046] Figure 6 It is a functional module diagram of a power-limiting state identification device provided in an embodiment of the present application;

[0047] Figure 7 It is a schematic diagram of the structure of the computer device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0049] In the description of the present application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the feature. In the description of the present application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0050] In this application, the word "exemplary" is used to mean "used as an example, illustration or description". Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. At the same time, it is to be understood that in the specific implementation of this application, when user information, user data and other related data are involved, when the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data shall comply with relevant laws, regulations and standards of relevant countries and regions.

[0051] In order to enable any person skilled in the art to implement and use the present application, the following description is provided. In the following description, details are listed for the purpose of explanation. It should be understood that those of ordinary skill in the art will recognize that the present application can be implemented without using these specific details. In other examples, known structures and processes will not be elaborated in detail to avoid unnecessary details that make the description of the present application obscure. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest range of principles and features disclosed in the present application.

[0052] In the prior art, the identification of power-limited status of photovoltaic power stations usually adopts the following two methods: one is to establish a mapping model through meteorological data or model inverter data, calculate the theoretical power generation of the power station, and compare it with the actual power generation, and determine the power-limited status by setting a deviation threshold. This method relies on external meteorological information and model inverter data to ensure the accuracy of theoretical power generation. The second is to calculate the correlation between the actual power curve of the power station and the typical power-limited power curve to determine whether there is a power-limited status. This method only needs to use the power data of the power station, avoiding dependence on meteorological data and inverter model data.

[0053] However, the existing practices have obvious shortcomings. On the one hand, the theoretical power calculation method based on meteorological data or sample machine data is applicable to power stations with complete data, but it is difficult to implement in the absence of meteorological data or sample machine inverter data, which limits the scope of application of this method; on the other hand, the method of identifying the power-limiting state by correlation with the typical power-limiting power curve is only applicable to a certain type of power-limiting curve, and it is difficult to cover various types of power-limiting such as power-limiting, peak-shaving and current-regulating power-limiting, resulting in low accuracy and universality of the identification results.

[0054] Therefore, the power limit identification method of the present application can accurately identify different types of power limit states of a photovoltaic power station without relying on meteorological data.

[0055] The present application provides a power-limiting state identification method, apparatus, computer equipment, and readable storage medium, which are described in detail below.

[0056] Figure 1 FIG. 1 is a flow chart of a method for identifying a power-limiting state in an embodiment of the present application. Figure 1 As shown, the power-limiting state identification method may include the following steps 101-102.

[0057] Step 101: Acquire the operation data of the photovoltaic power station and the meteorological data of the environment where the photovoltaic power station is located.

[0058] In some embodiments, the operation data of the photovoltaic power station may include power data, string current and voltage data, and inverter information of the photovoltaic power station.

[0059] Specifically, the output power of the photovoltaic power station at different time periods can be recorded, and the resolution can be set to 15 minutes, that is, the time interval for data collection, and power data is collected every 15 minutes to more accurately reflect the power generation status of the power station. The current and voltage information of each string can also be recorded, which can help identify the current or power change characteristics under different power-limiting conditions. Inverter information can include the operating parameters of the inverter, which is convenient for analyzing the operating status of the power generation equipment and the response to power-limiting events.

[0060] In some embodiments, the meteorological data may include rainfall data of the environment where the photovoltaic power station is located. For example, the rainfall information of the area where the photovoltaic power station is located may be recorded to distinguish the impact of weather changes on the power generation, especially on rainy days, so as to improve the accuracy of identifying the power limit state of the photovoltaic power station by eliminating the impact of weather reasons.

[0061] Step 102: Identify the power curtailment state of the photovoltaic power station based on the operation data of the photovoltaic power station or the meteorological data of the photovoltaic power station in combination with various types of power curtailment power curves.

[0062] Among them, the power-limiting state may include the power-limiting state, the peak-cutting power-limiting state and the current-regulating power-limiting state. Various types of power-limiting power curves may include: Figure 2 , Figure 3 and Figure 4 The power curve diagram of power cutting, the power curve diagram of peak cutting and the power curve diagram of current regulating power cutting are shown. The above concepts will be specifically explained below.

[0063] Power outage refers to the situation where the grid supply and demand are unbalanced and the power generation exceeds the power demand. The grid takes measures to completely shut down the photovoltaic power station. This usually occurs during peak hours with sufficient sunlight. Figure 2 As shown, the power curve of power outage shows that the power of the power station suddenly drops to zero during the high power generation period (such as 8:00 to 16:00), the power continues to be zero during the shutdown period, and the power returns to normal during the non-power-cutoff period.

[0064] Peak load reduction refers to controlling the power output of power plants near a relatively constant threshold during periods of high power generation, to avoid excessive power and maintain the stability of the power grid. Figure 3 As shown, the power curve of the peak shaving and power limiting state is usually presented as a "trapezoidal" shape, that is, during the peak period of photovoltaic power generation, the power is maintained near the set upper limit, showing a small range of fluctuations.

[0065] The current regulation power-limiting state refers to controlling the power output of the power station by adjusting the current output of the photovoltaic strings so that it floats around the limited target power. Figure 4 As shown, the power curve of the current regulation power-limiting state shows that the actual power is lower than the theoretical power, and the power curve fluctuates up and down with the current regulation, which is significantly lower than the expected power generation level.

[0066] It can be understood that the present application compares the real-time collected data of the photovoltaic power station with the power curves of several typical power-limiting states, and determines the power-limiting state of the photovoltaic power station one by one according to the power curve characteristics of different power-limiting modes. Subsequently, the recognition accuracy is improved based on data cleaning and feature matching, thereby realizing intelligent judgment of the power-limiting state of the photovoltaic power station.

[0067] In some embodiments, step 102 may include the following steps:

[0068] First, obtaining a first number of data points in which the power of the photovoltaic power station is greater than zero in a first preset time period;

[0069] Next, obtaining a second number of data points in which the power of the photovoltaic power station is equal to zero in a second preset time period;

[0070] Then, obtaining a third number of data points in which the power of the photovoltaic power station is greater than zero in a third preset time period;

[0071] Finally, when the first number, the second number, and the third number all meet the first preset condition, it is determined that the power-limiting state of the photovoltaic power station is in a power-limiting state;

[0072] The first preset period is earlier than the second preset period, and the second preset period is earlier than the third preset period.

[0073] In some embodiments, the first preset condition may include: the first number is greater than or equal to a first threshold, the second number is greater than or equal to a second threshold, and the third number is greater than or equal to a third threshold.

[0074] In some embodiments, before identifying the power-limiting state, the power data of the photovoltaic power station can be collected first. For example, a data point p of power data is collected every 15 minutes, so there are 96 data points in 24 hours, p = [p1, p2, ..., p 96 ]. According to the characteristics of power outage and Figure 2 From the power curve, it can be seen that the downtime of a photovoltaic power station in a power-cut state is generally between 8:00 and 16:00, and the duration of power cuts may vary. The power curve in a power-cut state shows that the power is normal in the morning and evening, and the power is 0 for a long time in the middle period from 8:00 to 16:00. According to the collected power data of the photovoltaic power station throughout the day, if there is two hours or more of effective power accumulated from 5:00 to 8:00 in the morning, one hour or more of effective power accumulated from 17:00 to 19:00 in the evening, and four hours or more of power is 0 accumulated from 8:00 to 16:00, it can be considered that the power station has a power-cut behavior.

[0075] As an example only, assuming that the first preset time period, the second preset time period and the third preset time period can be morning, midday and evening time periods respectively, the number of data points greater than zero in the morning power data is counted in the first preset time period from 5:00 to 8:00 as the first number, which is used to determine the normal power generation of the power station before the power restriction period begins.

[0076] Assuming that the acquisition resolution of power data is 15 minutes, the first preset period contains 13 data points, and the corresponding index range is p 21 to p 33 The calculation formula for the first quantity is: Assuming that the first threshold is 8, when the number of data points of effective power in the first preset period reaches 8 (corresponding to effective power generation of 2 hours or more), the threshold condition is met, indicating that the power station has normal power generation in the morning, which can be specifically expressed as:

[0077] The number of data points with zero power in the second preset time period from 8:00 to 16:00 can be counted as the second number to determine whether the power station is in a power-limited state of long-term shutdown. This period contains 33 data points, and the corresponding index range is p 33 to p 65 The second quantity is calculated as: Assuming that the second threshold is 16, when the number of data points with zero power reaches 16 (corresponding to shutdown for 4 hours or more), the second threshold is met, indicating that the power station is in shutdown state most of the time during the power-limited period, which can be specifically expressed as:

[0078] The number of data points with power greater than zero in the third preset time period from 17:00 to 19:00 can be counted as the third number to confirm the normal power generation of the photovoltaic power station after the power restriction ends. This period contains 9 data points, and the corresponding index range is p 69 to p 77 The calculation formula of the third quantity can be expressed as: Assuming that the third threshold is 4, when the number of effective power data points reaches 4 (corresponding to effective power generation of 1 hour or more), meeting the third threshold indicates that the photovoltaic power station resumes power generation after the power restriction period ends, which can be specifically expressed as:

[0079] In this scenario, the second quantity threshold is the largest, followed by the first quantity, and the smallest is the third quantity, which meets the requirements of the first preset condition, that is, when the first quantity, the second quantity, and the third quantity simultaneously meet their respective threshold requirements (that is, the first quantity ≥ 8, the second quantity ≥ 16, and the third quantity ≥ 4), it is determined that the power station is currently in a power outage state. Therefore, the situation where the first quantity, the second quantity, and the third quantity simultaneously meet the first preset condition can be expressed as:

[0080]

[0081] In some embodiments, the power cut status of the photovoltaic power station can also be identified by:

[0082] First, power data of the photovoltaic power station in a fourth preset time period corresponding to a set peak power consumption period is obtained;

[0083] Next, performing a data cleaning operation on the power data of the fourth preset time period to obtain cleaned power data;

[0084] Then, linear regression is performed on the power data after cleaning to obtain the corresponding fitting curve, and the slope corresponding to the fitting curve is calculated;

[0085] Finally, when the slope satisfies the second preset condition, determine that the power curtailment state of the PV power station is the peak shaving and power curtailment state; the second preset condition includes that the absolute value of the slope is less than the fourth threshold.

[0086] It can be understood that as Figure 3 shown, the power curve of the PV power station in the peak shaving and power curtailment state usually presents a "trapezoidal" shape. During the period with large photovoltaic power generation, the power of the PV power station often fluctuates around a relatively constant level. The degree of power fluctuation during this period is used to judge whether there is peak shaving and power curtailment behavior in the power station, that is, if the power shows small fluctuations for a long time, it is considered that the power station has peak shaving and power curtailment behavior.

[0087] Only as an example, assuming that the fourth preset period is the period of common electricity consumption peaks, the power data of the PV power station during the high power generation period, such as the power data from 10:00 to 14:00, can be selected as the analysis object, and this period can be defined as the fourth preset period. During this period, if the power station is in the peak shaving and power curtailment state, the power output usually fluctuates slightly around a constant value.

[0088] After obtaining the cleaned power data, a linear regression model can be used to fit the cleaned data to obtain a fitting curve for calculating the degree of power fluctuation during this period. The formula for the fitting curve of the linear regression model is expressed as:

[0089] p′ = b + kt + ε;

[0090] where, b is the intercept of the fitting curve, k is the slope of the fitting curve, and ε is the random error.

[0091] In some embodiments, the slope k can be calculated by the least squares method, which can be specifically expressed as:

[0092]

[0093] where, and are the mean values of the independent variable and the dependent variable respectively, representing the overall trend of the cleaned data.

[0094] In some embodiments, assuming that the fourth threshold is T = 0.1, by analyzing the slope k of the fitting curve, when |k| < T, it can be considered that the degree of power fluctuation of the power data is small, the power data of the PV power station remains almost the same for a long time, and the power station has peak shaving and power curtailment behavior. The closer the value of |k| is to 0, the smaller the degree of fluctuation.

[0095] In some embodiments, the cleaned power data is obtained through the following method:

[0096] First, data points with zero power in the power data of the fourth preset time period are deleted to obtain first power data;

[0097] Next, data points in the first power data that are lower than the first quantile and higher than the second quantile are deleted to obtain cleaned power data.

[0098] In some embodiments, the power data of the fourth preset period can be cleaned, firstly removing data points with zero power to ensure that only valid power generation data is retained. Then, the percentile method is used to remove outliers. For example, power data below the 5% percentile and above the 95% percentile can be defined as outliers and removed to ensure the stability of the remaining data, so as to improve the accuracy of peak load shaving and power restriction identification.

[0099] The meteorological data may include the rainfall in the area where the photovoltaic power station is located within the target time range. In some embodiments, the power limit state of the photovoltaic power station can also be identified by the following methods:

[0100] First, the rainfall of the photovoltaic power station on that day is obtained. When the rainfall of the photovoltaic power station on that day is greater than or equal to the fifth threshold, the power-limiting state identification operation is not performed on the photovoltaic power station.

[0101] Next, on days when the daily rainfall of the photovoltaic power station is less than the fifth threshold, a string current data set of the photovoltaic power station is constructed according to the string current data of the photovoltaic power station in the fifth preset time period before the day;

[0102] Then, according to the string current data set of the photovoltaic power station, determine the average value of the string current data in the sixth preset time period before the day as the historical current value, and the average value of the string current on the day as the current current value;

[0103] Finally, the current change rate of the string current of the photovoltaic power station is determined according to the historical current value and the current current value; when the current change rate of the string current of the photovoltaic power station is greater than or equal to the sixth threshold, the power limiting state of the photovoltaic power station is determined to be the current regulation power limiting state.

[0104] In some embodiments, the daily rainfall of the photovoltaic power station on the target date can be obtained. If the daily rainfall is greater than or equal to the fifth threshold, it is considered that the climate conditions may cause the current to drop, and the power-limiting state identification operation is not performed on the photovoltaic power station. The fifth threshold may be a set rainfall threshold, for example, the fifth threshold may be set to 1 mm. If the daily rainfall is less than the fifth threshold, it is determined that the weather is clear and the power-limiting state identification can be performed.

[0105] On sunny days, the string current data of the photovoltaic power station is collected, and the string current data set is constructed from the sunny data in the fifth preset period before the day, which is recorded as I = {I1, I2, ..., I N}, where N is the number of sunny days. For example, if the fifth preset period is three months, then N is the number of sunny days in the three months.

[0106] In the string current data set, assuming that the sixth preset period is 7 days, the average of the daily average currents of the first 7 sunny days can be taken as the historical current value of the string, recorded as I 历史 Then the string current data of the target date are averaged to obtain the current value of that day, which is recorded as I 当前 The current change rate of the string current of the photovoltaic power station is then determined based on the historical current value and the current current value. When the current change rate is greater than or equal to the sixth threshold, it is considered that the current drop reaches the power limit state, and the photovoltaic power station is determined to be in the current regulation power limit state.

[0107] In some embodiments, the current change rate of the string current of the photovoltaic power station can be determined by:

[0108] determining the difference between the historical current value and the current current value;

[0109] The quotient between the difference and the historical current value is taken as the current change rate of the string current of the photovoltaic power station.

[0110] In specific implementation, the current change rate of the string current can be calculated based on the historical current value and the current current value. The specific formula can be expressed as:

[0111]

[0112] Assume that the sixth threshold is set to 0.5, then when ratio≥0.5, the power station is in a current regulation power limiting state.

[0113] In the above manner, the embodiment of the present application screens the rainfall on the target date to eliminate the fluctuation interference of rainfall on the current. Under clear weather conditions, by calculating the change rate of historical current and current current, it is possible to effectively identify whether the power station is in a current regulation power limit state, effectively improving the accuracy of power limit identification.

[0114] In some embodiments, when the string current change rate of any string of the photovoltaic power station is greater than or equal to the sixth threshold, the power limiting state of the photovoltaic power station is determined to be a current regulation power limiting state. It can be understood that an abnormal change in the current of a single string can indicate the power limiting state of the entire power station. Since power limiting controls the current output of each string to reduce the total power output, even if the current change rate of one string exceeds the threshold, it is sufficient to determine that the entire photovoltaic power station is in a current regulation power limiting state.

[0115] In some embodiments, when it is determined that the photovoltaic power station is in a power-limited state and the type of the power-limited state is determined, power-limited information can be sent to a set terminal device to prompt operation and maintenance and data analysis and processing of the photovoltaic power station.

[0116] In some embodiments, different types of power curtailment states indicate that the operation of the PV power station is affected by external or internal factors. Therefore, by identifying the type of power curtailment (such as power curtailment due to power outage, peak curtailment, or current regulation), the operation and maintenance team can conduct targeted inspections of the power station equipment to troubleshoot potential problems, such as inverter failure, string abnormalities, or line problems. Maintenance measures may include checking string currents, inverter connection status, whether cables are properly connected, etc., to ensure that the equipment operates as expected and reduce the impact of unexpected power curtailment on the power station output power.

[0117] In some embodiments, after the power-limiting state of a photovoltaic power station is identified, the data collected during the power-limiting period may contain abnormal points, such as zero power or a sharp drop in current, which may interfere with the long-term power generation efficiency analysis and power forecasting of the power station. To this end, these abnormal data can be cleared through data analysis and processing to ensure the accuracy and completeness of historical data. Data cleaning and annotation processing help optimize future power forecasting and operation analysis models and improve the overall intelligent management capabilities of power stations. In addition, historical power-limiting state records and data analysis results can provide a basis for long-term planning and strategy adjustments of power stations, and help optimize power-limiting strategies and load management.

[0118] It should also be noted that if Figure 5 As shown, the photovoltaic power station can perform power-off identification, peak-cutting identification and current regulation identification in sequence. If one type of power-cutting identification is passed, there is no need to perform the next type of identification operation. If it is detected that the photovoltaic power station does not belong to any of the above three types of power-cutting states, it is determined that the photovoltaic power station is currently in a non-power-cutting state.

[0119] But it should be noted that Figure 5 The process is only an exemplary method for identifying power restrictions in photovoltaic power stations. In specific applications, the execution order of each type of power restriction identification operation is not limited. For example, in addition to the above-mentioned method of sequentially executing power cut identification, peak power restriction identification and current regulation power restriction identification, peak power restriction identification or current regulation power restriction identification can also be executed first. Therefore, the above three types of power restriction identification operations can be arranged and combined according to needs to obtain the required power restriction identification process, and the embodiments of the present application do not limit this.

[0120] In order to better understand the execution process of the power limit identification method of the present application, a specific example is given below for illustration.

[0121] Taking a distributed photovoltaic power station connected to the grid in a certain region as an example, the operation data and meteorological data of the photovoltaic power station in the region from January to August 2024 can be collected, and the daily power data is recorded as p = [p1, p2, ..., p 96 ], the current data of each string is recorded as I i =[I i1 ,I i2 ,…,I i96 ], where i is the i-th string, the power and current data resolution is 15 minutes, and the meteorological data can include the daily rainfall at the longitude and latitude of the power station, denoted by R.

[0122] Next, different power restriction states can be identified in turn based on the daily operation data and meteorological data of the photovoltaic power station, including power outage, peak-cutting and current regulation.

[0123] In the power outage identification stage, the power data of the whole day can be used as p = [p1, p2, ..., p 96 ], calculate the number of data points with power greater than 0 or equal to 0 in a specific time period, for example, the morning period (5:00 to 8:00): count the number of data points with power greater than 0 between 5:00 and 8:00 as L1, and the calculation formula is:

[0124]

[0125] The case where the power is equal to 0 from 8:00 to 16:00 on the power restriction judgment day is recorded as L2, and the calculation formula is:

[0126]

[0127] The case where the power is greater than 0 from 17:00 to 19:00 on the power restriction judgment day is recorded as L3, and the calculation formula is:

[0128]

[0129] When the following conditions are met, the photovoltaic power station is judged to be in a power outage state and the power station is considered to be in a power outage state:

[0130] (L1≥8)and(L2≥16)and(L3≥4).

[0131] In the peak load shaving and power rationing identification stage, if the photovoltaic power station is not in the power shaving and power rationing state, the peak load shaving and power rationing state is further identified. The specific steps are as follows:

[0132] The power data from 10:00 to 14:00 can be selected as the analysis object, and the data points with a power of 0 can be removed. At the same time, the percentile method is used to remove outliers (data below the 5% quantile or above the 95% quantile). The cleaned power data is recorded as p′=[p′1,p′2,…,p′n , where \(x = [1, 2, \ldots, n]\) represents the time series of the cleaned data.

[0133] Next, linear regression can be performed on the cleaned data, and the fitting formula is:

[0134] \(p'=b + kt+\varepsilon\);

[0135] where \(b\) is the intercept, \(k\) is the slope, and \(\varepsilon\) is the random error.

[0136] Then, the least squares method can be used to solve for the slope \(k\), and the formula is:

[0137]

[0138] where, are the mean of the independent variable and the mean of the dependent variable respectively. When \(|k|\lt T\), it is considered that the fluctuation degree of the power data is small, and the data remains almost consistent over a long period of time, indicating that the power station has the behavior of peak shaving and load shedding.

[0139] In the current regulation and load shedding identification stage, if the power station is not in the peak shaving and load shedding state, it is necessary to continue to judge whether it is in the current regulation and load shedding state. The basis for this state judgment is the change in the series current, and the specific steps are as follows:

[0140] First, the daily rainfall on the day of load shedding judgment can be checked. If the daily rainfall on that day is greater than or equal to 1 mm, it is a rainy day, and the load shedding state of the PV power station is not identified. If the daily rainfall is less than 1 mm, it is a sunny day.

[0141] Next, based on the series current data of sunny days in the past three months, a current data set \(I'=[I'_1, I'_2, \ldots, I' N \) can be constructed, where \(N\) is the number of sunny days, and \(I' j =[I i1 , I i2 , \ldots, I i96 represents the current data of the \(i\)-th series on the \(j\)-th day.

[0142] In the data set, the series current data from 10:00 to 14:00 can be selected, and the outliers below the 5% quantile or above the 95% quantile can be removed, and the current change rate of each series can be calculated. The specific steps are as follows:

[0143] First, calculate the average of the daily average currents of the first 7 sunny days as the historical current value \(I 历史 \), then calculate the average of the series currents on the date of load shedding judgment as the current current value \(I 当前 \), and finally calculate the current change rate:

[0144]

[0145] When the current change rate ratio of any group of strings is ≥ 0.5, it can be determined that the photovoltaic power station is in a current regulation and power limiting state.

[0146] The embodiments of the present application can perform feature extraction and analysis on a variety of typical power curtailment curves, can effectively distinguish different types of power curtailment, improve the accuracy of power curtailment status identification, and avoid dependence on meteorological data or model inverter data, so that the method of the present application can also be stably applied in photovoltaic power stations that lack such external data, and is applicable to a variety of power curtailment modes. Through feature identification of different power curtailment curves, it can improve the applicability and identification effect in various types of distributed photovoltaic power stations.

[0147] In a possible example, in order to better implement the power-limiting state identification method in the embodiment of the present application, on top of the power-limiting state identification method, the embodiment of the present application further provides a power-limiting state identification device 200, such as Figure 6 As shown, the power-limiting state identification device 200 includes:

[0148] The data acquisition module 201 is used to acquire the operation data of the photovoltaic power station and the meteorological data of the environment where the photovoltaic power station is located;

[0149] The power-limiting identification module 202 is used to identify the power-limiting state of the photovoltaic power station based on the operating data of the photovoltaic power station or the meteorological data of the photovoltaic power station, combined with various types of power-limiting power curves; wherein the power-limiting state includes power-off state, peak-cutting state and current-regulating power-limiting state.

[0150] In the embodiment of the present application, the data acquisition module 201 and the power limit identification module 202 can be used to execute steps 101-102 of the aforementioned method embodiment respectively. For more detailed contents or specific implementations of each functional module, please refer to the description of the corresponding method steps, which will not be repeated here.

[0151] The power-limiting state identification device 200 provided in the present application first obtains the operation data of the photovoltaic power station and the meteorological data of the environment where the photovoltaic power station is located through the data acquisition module 201. Then, the power-limiting identification module 202 identifies the power-limiting state of the photovoltaic power station according to the operation data of the photovoltaic power station or the meteorological data of the photovoltaic power station in combination with various types of power-limiting power curves; wherein the power-limiting state includes the power-limiting state of the power-limiting state, the power-limiting state of the power-limiting state of the power-limiting state and the power-limiting state of the current regulation.

[0152] The present application also provides a computer device. Figure 7 , Figure 7 This is a basic structural block diagram of the computer device in this embodiment.

[0153] The computer device includes a memory 310 and a processor 320 that are connected to each other through a system bus. It should be noted that the figure only shows a computer device with components 310-320, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0154] Computer devices can be computing devices such as desktop computers, notebooks, PDAs, and cloud servers. Computer devices can interact with users through keyboards, mice, remote controls, touch pads, or voice control devices.

[0155] The memory 310 includes at least one type of readable storage medium, and the readable storage medium includes a non-volatile memory or a volatile memory, for example, a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc., and the RAM may include a static RAM or a dynamic RAM. In some embodiments, the memory 310 may be an internal storage unit of a computer device, for example, a hard disk or a memory of the computer device. In other embodiments, the memory 310 may also be an external storage device of a computer device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card or a flash card (Fla sh Card) equipped on the computer device. Of course, the memory 310 may also include both an internal storage unit of the computer device and its external storage device. In this embodiment, the memory 310 is generally used to store an operating system and various application software installed on the computer device, such as the program code of the above method. In addition, the memory 310 may also be used to temporarily store various types of data that have been output or are to be output. In some embodiments, the memory 310 may also be a register.

[0156] The processor 320 is generally used to perform the overall operation of the computer device. In this embodiment, the memory 310 is used to store program codes or instructions, the program code includes computer operation instructions, and the processor 320 is used to execute the program codes or instructions stored in the memory 310 or process data, such as running the program code of the above method.

[0157] In this article, the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus system can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0158] Another embodiment of the present application also provides a computer-readable medium, which may be a computer-readable signal medium or a computer-readable medium. A processor in a computer reads a computer-readable program code stored in the computer-readable medium, so that the processor can execute the functional actions specified in each step or a combination of steps in the above method; and generate a device for implementing the functional actions specified in each block or a combination of blocks in the block diagram.

[0159] Computer-readable media include but are not limited to electronic, magnetic, optical, electromagnetic, infrared memory or semiconductor systems, devices or apparatuses, or any appropriate combination of the foregoing, the memory is used to store program codes or instructions, the program codes include computer operating instructions, and the processor is used to execute the program codes or instructions of the above methods stored in the memory.

[0160] For the definitions of memory and processor, please refer to the description of the aforementioned computer device embodiment and will not be repeated here.

[0161] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0162] Each functional unit or module in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0163] If the integrated unit is implemented in the form of 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, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program code.

[0164] In the claims, any reference symbols placed between brackets shall not be construed as limiting the claims. The word "comprising" described in the present application does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application can be implemented with the aid of hardware comprising several different elements and with the aid of a suitably programmed computer. In a unit claim that lists a number of devices, several units of these devices may be embodied by the same hardware item. The use of first, second, and third, etc. does not indicate any order, and these words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

[0165] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for identifying a power-limiting state, characterized in that: The method comprises: Acquiring operation data of the photovoltaic power station and meteorological data of the environment in which the photovoltaic power station is located; According to the operation data of the photovoltaic power station, or according to the meteorological data of the photovoltaic power station, combined with various types of power curtailment curves, the power curtailment state of the photovoltaic power station is identified; wherein the power curtailment state includes power cut state, peak shaving state and current regulation state.

2. The method for identifying power-limiting status according to claim 1, characterized in that: The operation data of the photovoltaic power station includes power data; the identifying the power limit state of the photovoltaic power station according to the operation data of the photovoltaic power station and combining multiple types of power limit power curves includes: Acquire a first number of data points in which the power of the photovoltaic power station is greater than zero in a first preset time period; Acquire a second number of data points in which the power of the photovoltaic power station is equal to zero in a second preset time period; Acquire a third number of data points in which the power of the photovoltaic power station is greater than zero in a third preset time period; When the first number, the second number and the third number simultaneously meet a first preset condition, determining that the power-limiting state of the photovoltaic power station is in a power-limiting state; The first preset period is earlier than the second preset period, and the second preset period is earlier than the third preset period.

3. The method for identifying power-limiting status according to claim 2, characterized in that: The first preset condition includes: The first number is greater than or equal to a first threshold, the second number is greater than or equal to a second threshold, and the third number is greater than or equal to a third threshold.

4. The method for identifying power-limiting status according to claim 1, characterized in that: The step of identifying the power limiting state of the photovoltaic power station according to the operation data of the photovoltaic power station and combining multiple types of power limiting power curves includes: Acquiring power data of the photovoltaic power station in a fourth preset time period corresponding to a set peak power consumption period; Performing a data cleaning operation on the power data of the fourth preset time period to obtain cleaned power data; Performing linear regression on the power data after cleaning to obtain a corresponding fitting curve, and calculating the slope corresponding to the fitting curve; When the slope meets a second preset condition, it is determined that the power limiting state of the photovoltaic power station is a peak-shaving power limiting state; the second preset condition includes that the absolute value of the slope is less than a fourth threshold.

5. The method for identifying power-limiting status according to claim 4, characterized in that: Perform data cleaning operations to obtain cleaned power data, including: Deleting data points with zero power in the power data of the fourth preset time period to obtain first power data; Data points below the first quantile and above the second quantile in the first power data are deleted to obtain the cleaned power data.

6. The method for identifying power-limiting status according to claim 1, characterized in that: The meteorological data includes the rainfall in the area where the photovoltaic power station is located within the target time range; the identifying the power limit state of the photovoltaic power station based on the meteorological data of the photovoltaic power station and combining multiple types of power limit power curves includes: Acquiring the rainfall of the photovoltaic power station on that day, and when the rainfall of the photovoltaic power station on that day is greater than or equal to a fifth threshold, not performing a power-limiting state identification operation on the photovoltaic power station; On days when the daily rainfall of the photovoltaic power station is less than the fifth threshold, constructing a string current data set of the photovoltaic power station according to the string current data of the photovoltaic power station in a fifth preset time period before the day; According to the string current data set of the photovoltaic power station, determine the average value of the string current data in the sixth preset time period before the current day as the historical current value, and the average value of the string current on the current day as the current current value; The current change rate of the string current of the photovoltaic power station is determined according to the historical current value and the current current value; when the current change rate of the string current of the photovoltaic power station is greater than or equal to a sixth threshold value, the power limiting state of the photovoltaic power station is determined to be a current regulation power limiting state.

7. The method for identifying power-limiting status according to claim 6, characterized in that: The determining the current change rate of the string current of the photovoltaic power station according to the historical current value and the current current value includes: Determining a difference between the historical current value and the current current value; The quotient between the difference and the historical current value is used as the current change rate of the string current of the photovoltaic power station.

8. The method for identifying power-limiting status according to claim 7, characterized in that: When the string current change rate of any string of the photovoltaic power station is greater than or equal to the sixth threshold, it is determined that the power limiting state of the photovoltaic power station is a current regulation power limiting state.

9. A power-limiting state identification device, characterized in that: The device comprises: A data acquisition module, used to acquire the operation data of the photovoltaic power station and the meteorological data of the environment where the photovoltaic power station is located; A power-limiting identification module is used to identify the power-limiting state of the photovoltaic power station based on the operating data of the photovoltaic power station or the meteorological data of the photovoltaic power station in combination with multiple types of power-limiting power curves; wherein the power-limiting state includes a power-cutting state, a peak-shaving power-limiting state and a current-regulating power-limiting state.

10. A computer device, characterized in that: include: Processor and memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory to implement the steps of the power-limiting state identification method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: A computer program is stored, and the computer program is loaded by a processor to execute the steps of the power-limiting state identification method according to any one of claims 1 to 8.

Images