A method, device, equipment and medium for identifying inefficient patterns of photovoltaic power plants

Abstract

The present application discloses a photovoltaic power station inefficiency mode recognition method, device, equipment and medium, which relates to the photovoltaic power station detection technology field, including: preliminarily judging whether the photovoltaic power station is a preliminary inefficient power station according to a first inefficiency judgment value obtained based on the daily equivalent power generation hours and the daily equivalent power generation hours standard value and a second inefficiency judgment value obtained based on the current daily power generation rate and the standard power generation rate; if it is a preliminary inefficient power station, judging whether the consecutive days for which the photovoltaic power station is determined as a preliminary inefficient power station exceeds a preset number of days, if it exceeds, the preliminary inefficient power station is an inefficient power station; evaluating the inefficient mode loss rate of the inefficient power station through an inefficient mode evaluation model so as to determine the reason why the inefficient power station is in the inefficient mode based on the inefficient mode loss rate; the inefficient mode loss rate includes the component tilt angle loss rate, the component spacing loss rate, the component pollution loss rate, the equipment failure loss rate and the power restriction loss rate. It can accurately determine the inefficient power station and determine the inefficiency cause and inefficiency degree of the inefficient power station.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power station detection, and in particular to a method, device, equipment and medium for identifying inefficient patterns of photovoltaic power stations. Background Art

[0002] The scale of photovoltaic power station construction is increasing day by day, and the application of photovoltaic power station centralized control platform is crucial for the operation and management of power systems. It is extremely important to timely identify the problems of photovoltaic power stations, explore the reasons for the low power generation efficiency of photovoltaic power stations, and guide the targeted technical transformation and efficiency improvement measures of photovoltaic power stations.

[0003] Currently, after photovoltaic power stations are centrally connected to the monitoring platform, fault alarms are mostly pushed through equipment remote signaling alarms or simple alarm logic, or only irradiation data is used to calculate power generation efficiency, or equipment abnormalities are checked through manual inspections. This is inefficient and often leads to false alarms and missed alarms of power station inefficiency. It is also impossible to intuitively feedback the number of inefficient power stations, the causes of inefficiency, and the extent of inefficiency losses.

[0004] In summary, how to accurately identify inefficient power plants and determine the causes and degrees of inefficiency of inefficient power plants is a problem that needs to be solved urgently. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a method, device, equipment and medium for identifying an inefficient pattern of a photovoltaic power station, which can accurately determine an inefficient power station and determine the inefficiency cause and degree of inefficiency of the inefficient power station. The specific scheme is as follows:

[0006] In a first aspect, the present application discloses a method for identifying an inefficient pattern of a photovoltaic power station, comprising:

[0007] The ratio of the current day's equivalent power generation hours of each photovoltaic power station to the standard value of the current day's equivalent power generation hours is calculated to obtain a first inefficiency judgment value, and the ratio of the current day's power generation rate of each photovoltaic power station to the standard power generation rate is calculated to obtain a second inefficiency judgment value;

[0008] Preliminarily determining whether each of the photovoltaic power stations is a preliminary inefficient power station based on the first inefficiency determination value and the second inefficiency determination value;

[0009] If the preliminary determination result is that the photovoltaic power station is a preliminary inefficient power station, determining whether the consecutive days for which the photovoltaic power station is determined as a preliminary inefficient power station exceeds a preset number of days, and if it exceeds the preset number of days, determining the preliminary inefficient power station as an inefficient power station;

[0010] The inefficiency mode loss rate of the inefficient power plant is evaluated by an inefficiency mode evaluation model so as to determine the reason why the inefficient power plant is in an inefficiency mode based on the inefficiency mode loss rate; the inefficiency mode loss rate includes component inclination loss rate, component spacing loss rate, component contamination loss rate, equipment failure loss rate and power shortage loss rate.

[0011] The step of calculating the ratio of the current day's daily equivalent power generation hours of each photovoltaic power station to the daily equivalent power generation hours standard value to obtain the first inefficiency determination value includes:

[0012] Based on a preset ground distance threshold, determine a cluster of power stations with similar ground distances corresponding to each photovoltaic power station on the current day;

[0013] Based on the daily equivalent generating hours in each of the power station clusters with similar ground distances, calculate the daily equivalent generating hours standard value corresponding to each of the power station clusters with similar ground distances;

[0014] The ratio of the daily equivalent generating hours corresponding to each photovoltaic power station to the standard value of the daily equivalent generating hours of the power station cluster with a close ground distance corresponding to the photovoltaic power station is calculated to obtain a first inefficiency judgment value.

[0015] The calculating of the ratio of the current day power generation rate of each photovoltaic power station to the standard power generation rate to obtain the second inefficiency determination value includes:

[0016] Determine the set of meteorologically similar historical days corresponding to each photovoltaic power station on the current day;

[0017] Based on the historical day power generation efficiency in each of the meteorologically similar historical day sets, calculate the standard power generation efficiency corresponding to each of the meteorologically similar historical day sets;

[0018] The ratio of the current daily power generation rate corresponding to each photovoltaic power station to the standard power generation efficiency of the meteorologically similar historical day set corresponding to the photovoltaic power station is calculated to obtain a second inefficiency determination value.

[0019] The step of determining a set of meteorologically similar historical days corresponding to each photovoltaic power station on the current day includes:

[0020] Normalizing the characteristic quantities of the historical meteorological data of each photovoltaic power station to obtain a normalized matrix of each photovoltaic power station;

[0021] The entropy weight method is used to calculate the weight corresponding to the characteristic quantity of the historical meteorological data of each photovoltaic power station to obtain a weight matrix of each photovoltaic power station;

[0022] Calculating the absolute distance between the characteristic quantities of the meteorological data of the current day and the historical day based on the normalized matrix and the weight matrix and based on the Mahalanobis distance calculation method;

[0023] A set of meteorologically similar historical days corresponding to each photovoltaic power station on the current day is constructed based on the target number of historical days with the smallest absolute distance.

[0024] Wherein, the preliminarily judging whether each of the photovoltaic power stations is a preliminary inefficient power station based on the first inefficiency judgment value and the second inefficiency judgment value includes:

[0025] Determine a first weight corresponding to the first inefficiency determination value and a second weight corresponding to the second inefficiency determination value;

[0026] Determine a comprehensive determination value corresponding to each of the photovoltaic power stations based on the first inefficiency determination value and the first weight and the second inefficiency determination value and the second weight;

[0027] If the comprehensive determination value of the photovoltaic power station is greater than a preset threshold, it is preliminarily determined that the photovoltaic power station is a preliminarily inefficient power station.

[0028] Wherein, the evaluating the inefficiency mode loss rate of the inefficient power station by using the inefficiency mode evaluation model includes:

[0029] Based on a calculation formula for component tilt angle loss rate, and according to actual component tilt angle and optimal component tilt angle, the component tilt angle loss rate of the inefficient power station is evaluated;

[0030] Based on the calculation formula of the component spacing loss rate, and according to the actual theoretical power generation at the actual component spacing and the optimal theoretical power generation at the optimal component spacing, the component spacing loss rate of the inefficient power station is evaluated;

[0031] Based on the component contamination loss rate calculation formula, and according to the first power generation efficiency fitting value within a preset time period after the latest power plant cleaning date and the second power generation efficiency fitting value within a preset time period before the latest power plant cleaning date corresponding to the power generation efficiency fitting curve, the component contamination loss rate of the inefficient power plant is evaluated;

[0032] If there is no faulty equipment on the current day, the equipment failure loss rate is 0. If there is a faulty equipment on the current day, the equipment failure loss rate of the inefficient power plant is evaluated based on the equipment failure loss rate calculation formula and the average equivalent generating hours of several faulty equipment on the first day and the average equivalent generating hours of the fault-free equipment on the second day;

[0033] Based on the power curtailment loss rate calculation formula and according to the average power generation efficiency of non-power curtailment days within a preset number of consecutive days and the daily power generation efficiency of the current day, the power curtailment loss rate of the inefficient power station is evaluated.

[0034] The calculation formula of the component tilt angle loss rate is:

[0035] ;

[0036] represents the tilt angle loss rate of the component; represents the optimal component inclination angle; represents the actual component inclination angle;

[0037] The calculation formula of the component spacing loss rate is:

[0038] ;

[0039] represents the component spacing loss rate; represents the actual theoretical power generation; represents the optimal theoretical power generation; Indicates the actual component spacing; represents the optimal component spacing;

[0040] The calculation formula of the component pollution loss rate is:

[0041] ;

[0042] represents the contamination loss rate of the component; represents the first power generation efficiency fitting value; represents the second power generation efficiency fitting value;

[0043] The equipment failure loss rate calculation formula is:

[0044] ;

[0045] Indicates the failure loss rate of the equipment; represents the average value of equivalent generating hours on the first day; represents the average value of equivalent generating hours on the second day;

[0046] The power-limiting loss rate calculation formula is:

[0047] ;

[0048] represents the power-limiting loss rate; represents the average value of the power generation efficiency; It represents the daily power generation efficiency.

[0049] In a second aspect, the present application discloses a photovoltaic power station inefficiency pattern recognition device, comprising:

[0050] A judgment value calculation module, used to calculate the ratio of the current day's equivalent generating hours of each photovoltaic power station to the standard value of the current day's equivalent generating hours to obtain a first inefficiency judgment value, and calculate the ratio of the current day's power generation rate of each photovoltaic power station to the standard power generation rate to obtain a second inefficiency judgment value;

[0051] A first judgment module, configured to judge whether each of the photovoltaic power stations is a preliminary inefficient power station based on the first inefficiency judgment value and the second inefficiency judgment value;

[0052] The second judgment module is used to judge whether the consecutive days for which the photovoltaic power station is determined as a preliminary inefficient power station exceeds a preset number of days if the photovoltaic power station is a preliminary inefficient power station, and if it exceeds the preset number of days, determine the preliminary inefficient power station as an inefficient power station;

[0053] An evaluation module is used to evaluate the inefficiency mode loss rate of the inefficient power plant through an inefficiency mode evaluation model, so as to determine the reason why the inefficient power plant is in an inefficiency mode based on the inefficiency mode loss rate; the inefficiency mode loss rate includes component inclination loss rate, component spacing loss rate, component contamination loss rate, equipment failure loss rate and power limitation loss rate.

[0054] In a third aspect, the present application discloses an electronic device, comprising:

[0055] Memory, used to store computer programs;

[0056] The processor is used to execute the computer program to implement the photovoltaic power station inefficiency pattern recognition method disclosed above.

[0057] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the above-disclosed photovoltaic power station inefficiency pattern recognition method is implemented.

[0058] It can be seen that the present application calculates the ratio of the daily equivalent generating hours of each photovoltaic power station on the current day to the standard value of the daily equivalent generating hours to obtain a first inefficiency judgment value, and calculates the ratio of the current daily generating rate of each photovoltaic power station on the current day to the standard generating rate to obtain a second inefficiency judgment value; based on the first inefficiency judgment value and the second inefficiency judgment value, it is preliminarily judged whether each photovoltaic power station is a preliminary inefficient power station; if the preliminary judgment result is that the photovoltaic power station is a preliminary inefficient power station, it is judged whether the consecutive days for which the photovoltaic power station is determined to be a preliminary inefficient power station exceeds the preset number of days, and if it exceeds the preset number of days, the preliminary inefficient power station is determined to be an inefficient power station; the inefficient mode loss rate of the inefficient power station is evaluated by an inefficient mode evaluation model, so as to determine the reason why the inefficient power station is in an inefficient mode based on the inefficient mode loss rate; the inefficient mode loss rate includes component inclination loss rate, component spacing loss rate, component contamination loss rate, equipment failure loss rate and power limitation loss rate. It can be seen that the present application determines inefficient power stations by making two consecutive judgments using the inefficiency judgment value judgment and the number of days judgment. Compared with directly using the power generation efficiency judgment or manual investigation judgment, the number of judgments is increased and more rigorous, so it can improve the accuracy of the judgment of inefficient power stations and reduce false alarms and omissions; the present application further determines the inefficiency causes and degree of inefficiency of inefficient power stations by evaluating the inefficiency mode loss rate; in summary, the present application can accurately determine inefficient power stations and determine the inefficiency causes and degree of inefficiency of inefficient power stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0060] Figure 1 A flow chart of a photovoltaic power station inefficiency pattern recognition method disclosed in this application;

[0061] Figure 2 A flowchart of a specific photovoltaic power station inefficiency pattern recognition method disclosed in this application;

[0062] Figure 3 This is a schematic diagram of the structure of a photovoltaic power station inefficiency pattern recognition device disclosed in this application;

[0063] Figure 4 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] After photovoltaic power stations are centrally connected to the monitoring platform, fault alarms are mostly pushed through equipment remote signaling alarms or simple alarm logic, or only irradiation data is used to calculate power generation efficiency, or equipment abnormalities are checked through manual inspections. This is inefficient and often leads to false alarms and missed alarms of power station inefficiency. It is also impossible to intuitively feedback the number of inefficient power stations, the causes of inefficiency, and the extent of inefficiency losses.

[0066] To this end, the embodiment of the present application proposes a photovoltaic power station inefficiency pattern recognition solution, which can accurately identify inefficient power stations and determine the inefficiency causes and inefficiency levels of the inefficient power stations.

[0067] The present application discloses a method for identifying inefficiency patterns of photovoltaic power plants. Figure 1 As shown, the method includes:

[0068] Step S11: Calculate the ratio of the current day's equivalent generating hours of each photovoltaic power station to the standard value of the current day's equivalent generating hours to obtain a first inefficiency judgment value, and calculate the ratio of the current day's power generation rate of each photovoltaic power station to the standard power generation rate to obtain a second inefficiency judgment value.

[0069] In this embodiment, when determining the inefficiency of a power station, not only the daily equivalent power generation hours but also the current daily power generation rate should be considered.

[0070] In this embodiment, the daily equivalent power generation hours standard value is calculated according to the daily equivalent power generation hours corresponding to several photovoltaic power stations that are close to each photovoltaic power station, and a first inefficiency judgment value is obtained based on the daily equivalent power generation hours of each photovoltaic power station and the daily equivalent power generation hours standard value; specifically, the first inefficiency judgment value is obtained by calculating the ratio of the daily equivalent power generation hours of each photovoltaic power station on the current day to the daily equivalent power generation hours standard value, including: determining the power station cluster with a close ground distance corresponding to each photovoltaic power station on the current day based on a preset ground distance threshold; calculating the daily equivalent power generation hours standard value corresponding to each power station cluster with a close ground distance based on the daily equivalent power generation hours in each of the power station clusters with a close ground distance; calculating the ratio of the daily equivalent power generation hours corresponding to each of the photovoltaic power stations to the daily equivalent power generation hours standard value of the power station cluster with a close ground distance corresponding to the photovoltaic power station, to obtain the first inefficiency judgment value.

[0071] It should be pointed out that the ground distance between photovoltaic power stations is mainly calculated based on the longitude and latitude of the photovoltaic power stations. First, the longitude and latitude of each photovoltaic power station are obtained. The ground distance calculation formula between two photovoltaic power stations is as follows:

[0072]

[0073] r is the radius of the Earth, a constant;

[0074] , are the dimensions between the two power stations, , They are the longitudes between the two power stations. Both longitude and latitude are in radians.

[0075] It should be pointed out that the preset ground distance threshold is generally 50km~100km, and in actual application it is appropriately adjusted according to the number of photovoltaic power station clusters.

[0076] It should be pointed out that the daily equivalent generating hours = actual power generation of the power station / rated capacity of the power station.

[0077] It should be pointed out that the standard value of daily equivalent generating hours corresponding to the cluster is calculated based on the quantile. Specifically, the standard value of daily equivalent generating hours corresponding to each cluster of power stations with similar ground distances is calculated based on the number of daily equivalent generating hours in each cluster of power stations with similar ground distances, including: taking the first target quantile from the number of daily equivalent generating hours in each cluster of power stations with similar ground distances, to obtain the standard value of daily equivalent generating hours corresponding to each cluster of power stations with similar ground distances; the first target quantile may be the 85th quantile, and may also be set specifically according to actual conditions.

[0078] In this embodiment, the standard power generation efficiency is calculated based on the power generation efficiencies of several historical days, and the second inefficiency judgment value is obtained based on the standard power generation efficiency and the current day power generation rate; specifically, the second inefficiency judgment value is obtained by calculating the ratio of the current day power generation rate of each photovoltaic power station to the standard power generation rate, including: determining the set of meteorologically similar historical days corresponding to each photovoltaic power station on the current day; calculating the standard power generation efficiency corresponding to each set of meteorologically similar historical days based on the historical day power generation efficiencies in each set of meteorologically similar historical days; calculating the ratio of the current day power generation rate corresponding to each photovoltaic power station to the standard power generation efficiency of the set of meteorologically similar historical days corresponding to the photovoltaic power station, to obtain the second inefficiency judgment value.

[0079] It should be pointed out that since the locations of different photovoltaic power stations may vary greatly, the weather may also vary greatly. Therefore, it is necessary to first obtain the historical meteorological data and historical power generation data of each photovoltaic power station; the historical meteorological data includes instantaneous radiation intensity, temperature, humidity, weather, and rainfall, and the historical power generation data is the power generation power.

[0080] It should be noted that the standard power generation efficiency is calculated based on the quantile. Specifically, the standard power generation efficiency corresponding to each set of meteorologically similar historical days is calculated based on the power generation efficiency of each historical day in the set of meteorologically similar historical days, including: taking the second target quantile from the power generation efficiency of each historical day in the set of meteorologically similar historical days to obtain the standard power generation efficiency corresponding to each set of meteorologically similar historical days. The second target quantile can be the 85th quantile, and can also be specifically set according to actual conditions.

[0081] In this embodiment, the standard power generation efficiency is obtained through the similar day theory. Specifically, the determination of the set of meteorologically similar historical days corresponding to each photovoltaic power station on the current day includes: normalizing the characteristic quantities of the historical meteorological data of each photovoltaic power station to obtain a normalized matrix of each photovoltaic power station; using the entropy weight method to calculate the weights corresponding to the characteristic quantities of the historical meteorological data of each photovoltaic power station to obtain a weight matrix of each photovoltaic power station; calculating the absolute distance between the characteristic quantities of the meteorological data of the current day and the historical day based on the normalized matrix and the weight matrix and based on the Mahalanobis distance calculation method; and constructing the set of meteorologically similar historical days corresponding to each photovoltaic power station on the current day based on the target number of historical days with the minimum absolute distance.

[0082] It should be pointed out that the normalization processing is to standardize the characteristic quantity of the historical meteorological data of each photovoltaic power station through maximum and minimum normalization to obtain the normalized matrix of each photovoltaic power station; the target number of historical days with the smallest absolute distance also needs to be the historical days with the absolute difference of irradiation not exceeding the preset value, and the preset value can be 0.5kWh / m2, which can be changed according to actual conditions and is not specifically limited here; the target number can be determined according to the number of historical samples, generally about 5% of the number of historical samples.

[0083] Step S12: Preliminarily judging whether each of the photovoltaic power stations is a preliminary inefficiency power station based on the first inefficiency judgment value and the second inefficiency judgment value.

[0084] In this embodiment, a sum judgment value is obtained based on the first inefficiency judgment value and the second inefficiency judgment value for subsequent judgment, and a comprehensive judgment value can be obtained based on weight or other methods; specifically, the preliminary judgment of whether each of the photovoltaic power stations is a preliminary inefficiency power station based on the first inefficiency judgment value and the second inefficiency judgment value includes: determining a first weight corresponding to the first inefficiency judgment value and a second weight corresponding to the second inefficiency judgment value; determining a comprehensive judgment value corresponding to each of the photovoltaic power stations based on the first inefficiency judgment value and the first weight and the second inefficiency judgment value and the second weight; if the comprehensive judgment value of the photovoltaic power station is greater than a preset threshold, it is preliminarily judged that the photovoltaic power station is a preliminary inefficiency power station.

[0085] It should be pointed out that the weights of the first inefficiency determination value and the second inefficiency determination value can be calculated respectively by a subjective evaluation method or an expert opinion method, and the comprehensive inefficiency determination value of the power station can be obtained by weighting.

[0086] It should be pointed out that the preset threshold can generally be set to 5%-20%, and can be set specifically according to the number of power stations and the number of operation and maintenance personnel.

[0087] Step S13: If the preliminary judgment result is that the photovoltaic power station is a preliminary inefficient power station, it is determined whether the consecutive days for which the photovoltaic power station is determined as a preliminary inefficient power station exceeds a preset number of days; if it exceeds the preset number of days, the preliminary inefficient power station is determined as an inefficient power station.

[0088] In this embodiment, if the number of consecutive days that the photovoltaic power station is determined to be a preliminary inefficient power station does not exceed the preset number of days, the preliminary inefficient power station is not considered to be an inefficient power station.

[0089] It should be pointed out that after the preliminary judgment on whether it is an inefficient power station, a secondary judgment is required to improve the judgment accuracy. If the number of consecutive days that a photovoltaic power station is determined as a preliminary inefficient power station exceeds the preset number of days, the preliminary inefficient power station is considered to be an inefficient power station. After the power station is determined as a preliminary inefficient power station due to temporary inefficiency caused by other reasons, the preliminary inefficient power station can be excluded from the ranks of inefficient power stations.

[0090] Step S14: Evaluate the inefficiency mode loss rate of the inefficient power plant through an inefficiency mode evaluation model, so as to determine the reason why the inefficient power plant is in an inefficiency mode based on the inefficiency mode loss rate; the inefficiency mode loss rate includes component tilt loss rate, component spacing loss rate, component contamination loss rate, equipment failure loss rate and power limitation loss rate.

[0091] In this embodiment, the inefficiency mode evaluation model may include a design factor inefficiency evaluation sub-model, a pollution factor inefficiency evaluation sub-model, a fault factor inefficiency evaluation sub-model, and a power limitation factor inefficiency evaluation sub-model; the design factor inefficiency evaluation model is used to evaluate the component inclination loss rate and the component spacing loss rate of the inefficient power station, the pollution factor inefficiency evaluation sub-model is used to evaluate the component pollution loss rate of the inefficient power station, the fault factor inefficiency evaluation sub-model is used to evaluate the equipment failure loss rate of the inefficient power station, and the power limitation factor inefficiency evaluation sub-model is used to evaluate the power limitation loss rate of the inefficient power station.

[0092] It can be seen that the present application calculates the ratio of the daily equivalent generating hours of each photovoltaic power station on the current day to the standard value of the daily equivalent generating hours to obtain a first inefficiency judgment value, and calculates the ratio of the current daily generating rate of each photovoltaic power station on the current day to the standard generating rate to obtain a second inefficiency judgment value; based on the first inefficiency judgment value and the second inefficiency judgment value, it is preliminarily judged whether each photovoltaic power station is a preliminary inefficient power station; if the preliminary judgment result is that the photovoltaic power station is a preliminary inefficient power station, it is judged whether the consecutive days for which the photovoltaic power station is determined to be a preliminary inefficient power station exceeds the preset number of days, and if it exceeds the preset number of days, the preliminary inefficient power station is determined to be an inefficient power station; the inefficient mode loss rate of the inefficient power station is evaluated by an inefficient mode evaluation model, so as to determine the reason why the inefficient power station is in an inefficient mode based on the inefficient mode loss rate; the inefficient mode loss rate includes component inclination loss rate, component spacing loss rate, component contamination loss rate, equipment failure loss rate and power limitation loss rate. It can be seen that the present application determines inefficient power stations by making two consecutive judgments using the inefficiency judgment value judgment and the number of days judgment. Compared with directly using the power generation efficiency judgment or manual investigation judgment, the number of judgments is increased and more rigorous, so it can improve the accuracy of the judgment of inefficient power stations and reduce false alarms and omissions; the present application further determines the inefficiency causes and degree of inefficiency of inefficient power stations by evaluating the inefficiency mode loss rate; in summary, the present application can accurately determine inefficient power stations and determine the inefficiency causes and degree of inefficiency of inefficient power stations.

[0093] The embodiment of the present application discloses a specific method for identifying inefficient patterns of photovoltaic power plants. Compared with the previous embodiment, this embodiment further illustrates and optimizes the technical solution. Figure 2 As shown, specifically including:

[0094] Step S21: Based on the component tilt loss rate calculation formula, the component tilt loss rate of the inefficient power station is evaluated according to the actual component tilt and the optimal component tilt.

[0095] In this embodiment, the actual component inclination of the power station is obtained, and the optimal component inclination of the power station is calculated with the goal of maximizing the amount of radiation received by the component inclination throughout the year. Then, the component inclination loss rate calculation formula is used to obtain the component inclination loss rate; the component inclination loss rate calculation formula is:

[0096] ;

[0097] represents the tilt angle loss rate of the component; represents the optimal component inclination angle; Represents the actual component inclination angle.

[0098] It should be pointed out that the optimal component inclination angle of the power station can be obtained through conventional calculation formulas or photovoltaic design simulation software.

[0099] Step S22: Based on the component spacing loss rate calculation formula, and according to the actual theoretical power generation at the actual component spacing and the optimal theoretical power generation at the optimal component spacing, the component spacing loss rate of the inefficient power station is evaluated.

[0100] In this embodiment, firstly, according to the actual component spacing of the historical power station, the inclined length of the historical component array, and the actual component inclination angle of the historical power station, the optimal component spacing of the power station is calculated with the goal of minimizing the radiation loss caused by shadowing throughout the year, and the current actual component spacing is obtained. The component spacing loss rate of the inefficient power station is obtained by using the current actual component spacing, the optimal component spacing, and the component spacing loss rate calculation formula; the component spacing loss rate calculation formula is:

[0101] ;

[0102] represents the component spacing loss rate; represents the actual theoretical power generation; represents the optimal theoretical power generation; Indicates the actual component spacing; represents the optimal component spacing.

[0103] It should be pointed out that the actual theoretical power generation and the optimal theoretical power generation can be obtained through conventional calculation formulas or photovoltaic design simulation software.

[0104] Step S23: Based on the component contamination loss rate calculation formula, and according to the first power generation efficiency fitting value within a preset time period after the most recent power plant cleaning date and the second power generation efficiency fitting value within a preset time period before the most recent power plant cleaning date corresponding to the power generation efficiency fitting curve, the component contamination loss rate of the inefficient power plant is evaluated.

[0105] In this embodiment, the historical cleaning records of the power station are obtained, the daily power generation efficiency from the last cleaning date of the power station to the present is obtained, and the third-order fitting is performed on the daily power generation efficiency time series to obtain the power generation efficiency fitting value (first power generation efficiency fitting value) one week after the cleaning date and the actual power generation efficiency fitting value (second power generation efficiency fitting value) one week before the evaluation date corresponding to the fitting curve. Then, the component pollution loss rate calculation formula is used to evaluate the component pollution loss rate of the inefficient power station; the component pollution loss rate calculation formula is:

[0106] ;

[0107] represents the contamination loss rate of the component; represents the first power generation efficiency fitting value; represents the second power generation efficiency fitting value.

[0108] Step S24: If there is no faulty equipment on the current day, the equipment failure loss rate is 0. If there is a faulty equipment on the current day, the equipment failure loss rate of the inefficient power station is evaluated based on the equipment failure loss rate calculation formula and the average equivalent generating hours of several faulty equipment on the first day and the average equivalent generating hours of the fault-free equipment on the second day.

[0109] In this embodiment, if there is a power station fault alarm information, the power station fault alarm information is obtained, and it is determined whether there is an equipment fault on the evaluated date (the current day). If it is not a fault date, the power station equipment failure loss rate is output as 0; if it is a fault date, the average daily equivalent generating hours of the power station model equipment or other fault-free equipment (the average equivalent generating hours on the second day) and the average daily equivalent generating hours of the faulty equipment on that day (the average equivalent generating hours on the first day) are obtained, and then the equipment failure loss rate calculation formula is used to evaluate the equipment failure loss rate of the inefficient power station; the equipment failure loss rate calculation formula is:

[0110] ;

[0111] Indicates the failure loss rate of the equipment; represents the average value of equivalent generating hours on the first day; Represents the average value of equivalent generating hours on the second day.

[0112] Step S25: Based on the power curtailment loss rate calculation formula and according to the average power generation efficiency of non-power curtailment days within a preset number of consecutive days and the daily power generation efficiency of the current day, the power curtailment loss rate of the inefficient power station is evaluated.

[0113] In this embodiment, the power restriction record of the power station is obtained to determine whether the evaluated date (the current day) is a power restriction date. If it is not a power restriction date, the power restriction loss rate of the power station is output as 0; if it is a power restriction date, the average daily power generation efficiency (average power generation efficiency) of the set of non-power restriction days in the past 30 days and the daily power generation efficiency (daily power generation efficiency) of the evaluated date are obtained.

[0114] The power-limiting loss rate calculation formula is:

[0115] ;

[0116] represents the power-limiting loss rate; represents the daily power generation efficiency; It represents the average value of the power generation efficiency.

[0117] It should be pointed out that the specific evaluation date may not be the current date and can be set according to the specific evaluation situation.

[0118] It can be seen that the present application is based on the component tilt loss rate calculation formula, and evaluates the component tilt loss rate of the inefficient power station according to the actual component tilt and the optimal component tilt; based on the component spacing loss rate calculation formula, and based on the actual theoretical power generation at the actual component spacing and the optimal theoretical power generation at the optimal component spacing, evaluate the component spacing loss rate of the inefficient power station; based on the component contamination loss rate calculation formula, and according to the first power generation efficiency fitting value within the preset time period after the latest power station cleaning date corresponding to the power generation efficiency fitting curve and the second power generation efficiency fitting value within the preset time period before the latest power station cleaning date, evaluate the component contamination loss rate of the inefficient power station; if there is no faulty equipment on the current day, the equipment failure loss rate is 0, if there is a faulty equipment on the current day, based on the equipment failure loss rate calculation formula, and according to the average value of the first day equivalent power generation hours of several faulty equipment and the average value of the second day equivalent power generation hours of the fault-free equipment, evaluate the equipment failure loss rate of the inefficient power station; based on the power restriction loss rate calculation formula, and according to the average power generation efficiency of non-power restriction dates within a preset number of consecutive days and the daily power generation efficiency of the current day, evaluate the power restriction loss rate of the inefficient power station. It can be seen that the present application specifically discloses specific evaluation methods for component tilt loss rate, component spacing loss rate, component contamination loss rate, equipment failure loss rate and power limitation loss rate, so as to intuitively reflect the source of power station inefficiency problems.

[0119] Correspondingly, the present application also discloses a photovoltaic power station inefficiency pattern recognition device, see Figure 3 As shown, the device comprises:

[0120] The judgment value calculation module 11 is used to calculate the ratio of the daily equivalent power generation hours of each photovoltaic power station on the current day to the standard value of the daily equivalent power generation hours to obtain a first inefficiency judgment value, and calculate the ratio of the current daily power generation rate of each photovoltaic power station on the current day to the standard power generation rate to obtain a second inefficiency judgment value;

[0121] A first judgment module 12, configured to judge whether each of the photovoltaic power stations is a preliminary inefficient power station based on the first inefficiency judgment value and the second inefficiency judgment value;

[0122] The second judgment module 13 is used to judge whether the consecutive days for which the photovoltaic power station is determined as a preliminary inefficient power station exceeds a preset number of days if the photovoltaic power station is a preliminary inefficient power station, and if it exceeds the preset number of days, determine the preliminary inefficient power station as an inefficient power station;

[0123] The evaluation module 14 is used to evaluate the inefficiency mode loss rate of the inefficient power plant through an inefficiency mode evaluation model, so as to determine the reason why the inefficient power plant is in an inefficient mode based on the inefficiency mode loss rate; the inefficiency mode loss rate includes component inclination loss rate, component spacing loss rate, component contamination loss rate, equipment failure loss rate and power limitation loss rate.

[0124] Among them, the more specific working process of each of the above modules can refer to the corresponding content disclosed in the above embodiments, which will not be repeated here.

[0125] It can be seen that the present application calculates the ratio of the daily equivalent generating hours of each photovoltaic power station on the current day to the standard value of the daily equivalent generating hours to obtain a first inefficiency judgment value, and calculates the ratio of the current daily generating rate of each photovoltaic power station on the current day to the standard generating rate to obtain a second inefficiency judgment value; based on the first inefficiency judgment value and the second inefficiency judgment value, it is preliminarily judged whether each photovoltaic power station is a preliminary inefficient power station; if the preliminary judgment result is that the photovoltaic power station is a preliminary inefficient power station, it is judged whether the consecutive days for which the photovoltaic power station is determined to be a preliminary inefficient power station exceeds the preset number of days, and if it exceeds the preset number of days, the preliminary inefficient power station is determined to be an inefficient power station; the inefficient mode loss rate of the inefficient power station is evaluated by an inefficient mode evaluation model, so as to determine the reason why the inefficient power station is in an inefficient mode based on the inefficient mode loss rate; the inefficient mode loss rate includes component inclination loss rate, component spacing loss rate, component contamination loss rate, equipment failure loss rate and power limitation loss rate. It can be seen that the present application determines inefficient power stations by making two consecutive judgments using the inefficiency judgment value judgment and the number of days judgment. Compared with directly using the power generation efficiency judgment or manual investigation judgment, the number of judgments is increased and more rigorous, so it can improve the accuracy of the judgment of inefficient power stations and reduce false alarms and omissions; the present application further determines the inefficiency causes and degree of inefficiency of inefficient power stations by evaluating the inefficiency mode loss rate; in summary, the present application can accurately determine inefficient power stations and determine the inefficiency causes and degree of inefficiency of inefficient power stations.

[0126] Furthermore, an embodiment of the present application also provides an electronic device. Figure 4 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0127] Figure 4 A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the photovoltaic power station inefficiency pattern recognition method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0128] In this embodiment, the power supply 26 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 24 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0129] In addition, the memory 22, as a carrier for storing resources, may be a read-only memory, a random access memory, a disk or an optical disk, etc., and the resources stored thereon may include a computer program 221, and the storage method may be temporary storage or permanent storage. In addition to including a computer program that can be used to complete the photovoltaic power station inefficiency pattern recognition method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 221 may further include a computer program that can be used to complete other specific tasks.

[0130] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the above-disclosed photovoltaic power station inefficiency pattern recognition method is implemented.

[0131] The specific steps of the method can refer to the corresponding contents disclosed in the above embodiments, which will not be repeated here.

[0132] The various embodiments in this application are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0133] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0134] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0135] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0136] The above is a detailed introduction to a photovoltaic power station inefficiency pattern recognition method, device, equipment, and storage medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for identifying inefficiency patterns of photovoltaic power plants, characterized in that: include: The ratio of the current day's equivalent power generation hours of each photovoltaic power station to the standard value of the current day's equivalent power generation hours is calculated to obtain a first inefficiency judgment value, and the ratio of the current day's power generation rate of each photovoltaic power station to the standard power generation rate is calculated to obtain a second inefficiency judgment value; Preliminarily determining whether each of the photovoltaic power stations is a preliminary inefficient power station based on the first inefficiency determination value and the second inefficiency determination value; If the preliminary determination result is that the photovoltaic power station is a preliminary inefficient power station, determining whether the consecutive days for which the photovoltaic power station is determined as a preliminary inefficient power station exceeds a preset number of days, and if it exceeds the preset number of days, determining the preliminary inefficient power station as an inefficient power station; The inefficiency mode loss rate of the inefficient power plant is evaluated by an inefficiency mode evaluation model so as to determine the reason why the inefficient power plant is in an inefficiency mode based on the inefficiency mode loss rate; the inefficiency mode loss rate includes component inclination loss rate, component spacing loss rate, component contamination loss rate, equipment failure loss rate and power shortage loss rate.

2. The photovoltaic power station inefficiency pattern recognition method according to claim 1, characterized in that: The calculating of the ratio of the current day's daily equivalent power generation hours of each photovoltaic power station to the daily equivalent power generation hours standard value to obtain the first inefficiency determination value includes: Based on a preset ground distance threshold, determine a cluster of power stations with similar ground distances corresponding to each photovoltaic power station on the current day; Based on the daily equivalent generating hours in each of the power station clusters with similar ground distances, calculate the daily equivalent generating hours standard value corresponding to each of the power station clusters with similar ground distances; The ratio of the daily equivalent generating hours corresponding to each photovoltaic power station to the standard value of the daily equivalent generating hours of the power station cluster with a close ground distance corresponding to the photovoltaic power station is calculated to obtain a first inefficiency judgment value.

3. The photovoltaic power station inefficiency pattern recognition method according to claim 1, characterized in that: The calculating the ratio of the current day power generation rate of each photovoltaic power station to the standard power generation rate to obtain the second low efficiency determination value includes: Determine the set of meteorologically similar historical days corresponding to each photovoltaic power station on the current day; Based on the historical day power generation efficiency in each of the meteorologically similar historical day sets, calculate the standard power generation efficiency corresponding to each of the meteorologically similar historical day sets; The ratio of the current daily power generation rate corresponding to each photovoltaic power station to the standard power generation efficiency of the meteorologically similar historical day set corresponding to the photovoltaic power station is calculated to obtain a second inefficiency determination value.

4. The photovoltaic power station inefficiency pattern recognition method according to claim 3, characterized in that: Determining the set of meteorologically similar historical days corresponding to each photovoltaic power station on the current day includes: Normalizing the characteristic quantities of the historical meteorological data of each photovoltaic power station to obtain a normalized matrix of each photovoltaic power station; The entropy weight method is used to calculate the weight corresponding to the characteristic quantity of the historical meteorological data of each photovoltaic power station to obtain a weight matrix of each photovoltaic power station; Calculating the absolute distance between the characteristic quantities of the meteorological data of the current day and the historical day based on the normalized matrix and the weight matrix and based on the Mahalanobis distance calculation method; A set of meteorologically similar historical days corresponding to each photovoltaic power station on the current day is constructed based on the target number of historical days with the smallest absolute distance.

5. The photovoltaic power station inefficiency pattern recognition method according to claim 1, characterized in that: The preliminarily judging whether each of the photovoltaic power stations is a preliminary inefficient power station based on the first inefficiency judgment value and the second inefficiency judgment value includes: Determine a first weight corresponding to the first inefficiency determination value and a second weight corresponding to the second inefficiency determination value; Determine a comprehensive determination value corresponding to each of the photovoltaic power stations based on the first inefficiency determination value and the first weight and the second inefficiency determination value and the second weight; If the comprehensive determination value of the photovoltaic power station is greater than a preset threshold, it is preliminarily determined that the photovoltaic power station is a preliminarily inefficient power station.

6. The photovoltaic power station inefficiency pattern recognition method according to any one of claims 1 to 5, characterized in that: The evaluating the inefficiency mode loss rate of the inefficient power station by using the inefficiency mode evaluation model includes: Based on a calculation formula for component tilt angle loss rate, and according to actual component tilt angle and optimal component tilt angle, the component tilt angle loss rate of the inefficient power station is evaluated; Based on the calculation formula of the component spacing loss rate, and according to the actual theoretical power generation at the actual component spacing and the optimal theoretical power generation at the optimal component spacing, the component spacing loss rate of the inefficient power station is evaluated; Based on the component contamination loss rate calculation formula, and according to the first power generation efficiency fitting value within a preset time period after the latest power plant cleaning date and the second power generation efficiency fitting value within a preset time period before the latest power plant cleaning date corresponding to the power generation efficiency fitting curve, the component contamination loss rate of the inefficient power plant is evaluated; If there is no faulty equipment on the current day, the equipment failure loss rate is 0. If there is a faulty equipment on the current day, the equipment failure loss rate of the inefficient power plant is evaluated based on the equipment failure loss rate calculation formula and the average equivalent generating hours of several faulty equipment on the first day and the average equivalent generating hours of the fault-free equipment on the second day; Based on the power curtailment loss rate calculation formula and according to the average power generation efficiency of non-power curtailment days within a preset number of consecutive days and the daily power generation efficiency of the current day, the power curtailment loss rate of the inefficient power station is evaluated.

7. The photovoltaic power station inefficiency pattern recognition method according to claim 6, characterized in that: The calculation formula of the component inclination loss rate is: ； represents the tilt angle loss rate of the component; represents the optimal component inclination angle; represents the actual component inclination angle; The calculation formula of the component spacing loss rate is: ； represents the component spacing loss rate; represents the actual theoretical power generation; represents the optimal theoretical power generation; Indicates the actual component spacing; represents the optimal component spacing; The calculation formula of the component pollution loss rate is: ； represents the contamination loss rate of the component; represents the first power generation efficiency fitting value; represents the second power generation efficiency fitting value; The equipment failure loss rate calculation formula is: ； Indicates the failure loss rate of the equipment; represents the average value of equivalent generating hours on the first day; represents the average value of equivalent generating hours on the second day; The power-limiting loss rate calculation formula is: ； represents the power-limiting loss rate; represents the average value of the power generation efficiency; It represents the daily power generation efficiency.

8. A photovoltaic power station inefficiency pattern recognition device, characterized in that: include: A judgment value calculation module, used to calculate the ratio of the current day's equivalent generating hours of each photovoltaic power station to the standard value of the current day's equivalent generating hours to obtain a first inefficiency judgment value, and calculate the ratio of the current day's power generation rate of each photovoltaic power station to the standard power generation rate to obtain a second inefficiency judgment value; A first judgment module, configured to judge whether each of the photovoltaic power stations is a preliminary inefficient power station based on the first inefficiency judgment value and the second inefficiency judgment value; The second judgment module is used to judge whether the consecutive days for which the photovoltaic power station is determined as a preliminary inefficient power station exceeds a preset number of days if the photovoltaic power station is a preliminary inefficient power station, and if it exceeds the preset number of days, determine the preliminary inefficient power station as an inefficient power station; An evaluation module is used to evaluate the inefficiency mode loss rate of the inefficient power plant through an inefficiency mode evaluation model, so as to determine the reason why the inefficient power plant is in an inefficiency mode based on the inefficiency mode loss rate; the inefficiency mode loss rate includes component inclination loss rate, component spacing loss rate, component contamination loss rate, equipment failure loss rate and power limitation loss rate.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the photovoltaic power station inefficiency pattern recognition method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program; wherein, when the computer program is executed by a processor, the photovoltaic power station inefficiency pattern recognition method according to any one of claims 1 to 7 is implemented.

Images