Photovoltaic power station data acquisition and processing method and device and storage medium

Abstract

According to the photovoltaic power station data acquisition and processing method and device and the storage medium, real-time operation data and real-time meteorological data of a photovoltaic power station are acquired, the real-time operation data comprise box transformer substation data, combiner box data, inverter data and booster station data, and the real-time meteorological data comprise temperature and irradiation; constructing real-time three-dimensional data corresponding to the real-time operation data, the real-time temperature and the real-time irradiation; comparing the real-time three-dimensional data with a preset data prediction model, and judging whether the real-time three-dimensional data is abnormal or not; wherein the data prediction model is constructed based on historical operation data of the photovoltaic power station; if the data of the real-time three-dimensional data is judged to be abnormal, removing the real-time three-dimensional data; and if the real-time three-dimensional data is judged to be normal, storing the real-time three-dimensional data. According to the embodiment of the invention, the collected real-time data is screened and rejected, and the accuracy of the stored real-time data is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of photovoltaic power stations, and particularly relates to a method, device and storage medium for data collection and processing of a photovoltaic power station. Background Art

[0002] With the continuous growth of the installed capacity of photovoltaic power generation, the installed capacity of photovoltaic modules has gradually developed from the MW level to the GW level. At present, the designed operation life of photovoltaic power stations is more than 25 years, and the digital monitoring and operation and maintenance platform has become a "standard configuration" for projects. With the popularization of unmanned photovoltaic power stations, intelligent online monitoring has become an industry trend.

[0003] For the existing collection of operation data of photovoltaic power stations, the collected data is not screened and eliminated, resulting in a low accuracy rate of the application model of advanced algorithms and unable to carry out corresponding benchmarking work. Therefore, how to efficiently, accurately and comprehensively collect the operation data of the power station and process and store the data has become the key to the digital operation and development of photovoltaic power stations. Summary of the Invention

[0004] In view of the above problems, the present invention proposes a method, device and storage medium for data collection and processing of a photovoltaic power station.

[0005] In a first aspect of the present invention, there is provided a method for data collection and processing of a photovoltaic power station, including:

[0006] Collecting real-time operation data and real-time meteorological data of the photovoltaic power station, wherein the real-time operation data includes box transformer data, bus duct combiner box data, inverter data and step-up substation data, and the real-time meteorological data includes real-time temperature and real-time irradiance;

[0007] Constructing real-time three-dimensional data corresponding to the real-time operation data, the real-time temperature and the real-time irradiance;

[0008] Comparing the real-time three-dimensional data with a preset data prediction model to determine whether the data of the real-time three-dimensional data is abnormal; wherein, the data prediction model is constructed based on the historical operation data of the photovoltaic power station;

[0009] If it is determined that the data of the real-time three-dimensional data is abnormal, then eliminate it;

[0010] If it is determined that the data of the real-time three-dimensional data is normal, then store it.

[0011] Further, the data prediction model is constructed based on the historical operation data of the photovoltaic power station, specifically including:

[0012] Collecting historical operation data of the photovoltaic power station and instantaneous meteorological data corresponding to the historical operation data, wherein the instantaneous meteorological data includes instantaneous temperature and instantaneous irradiance;

[0013] Eliminate null values, dead values, and mutant values from the historical operation data;

[0014] Construct a three-dimensional database corresponding to the historical operation data, the instantaneous temperature, and the instantaneous irradiance, establish a mapping relationship between temperature, irradiance, and operation data, and obtain the data prediction model.

[0015] Further, comparing the real-time three-dimensional data with a preset data prediction model to determine whether the data of the real-time three-dimensional data is abnormal specifically includes:

[0016] Input the real-time temperature and the real-time irradiance into the data prediction model to obtain predicted operation data;

[0017] Compare the real-time operation data with the predicted operation data. If the difference percentage between the real-time operation data and the predicted operation data is less than a preset threshold, determine that the real-time operation data is normal; if the difference percentage between the real-time operation data and the predicted operation data is greater than the preset threshold, determine that the real-time operation data is abnormal.

[0018] Further, the preset threshold is 5%.

[0019] Further, the null value is no data; the dead value is more than 10 consecutive identical data; the mutant value is data with a difference of more than 20% between the front and back data.

[0020] Further, after collecting the real-time operation data and real-time meteorological data of the photovoltaic power station, before constructing the real-time three-dimensional data corresponding to the real-time operation data, the real-time temperature, and the real-time irradiance, it further includes:

[0021] Eliminate null values, dead values, and mutant values from the real-time operation data.

[0022] Further, the collection period of the real-time operation data and the real-time meteorological data is less than the first preset time interval; the storage period of the real-time operation data and the real-time meteorological data is less than the second preset time interval.

[0023] The second aspect of the present invention provides a device for collecting and processing photovoltaic power station data, including:

[0024] A first collection unit for collecting the real-time operation data and real-time meteorological data of the photovoltaic power station, where the operation data includes box transformer data, busbar trunking data, inverter data, and step-up substation data, and the real-time meteorological data includes real-time temperature and real-time irradiance;

[0025] A first construction unit for constructing real-time three-dimensional data corresponding to the real-time operation data, the real-time temperature, and the real-time irradiance;

[0026] A judgment unit, configured to compare the real-time three-dimensional data with a preset data prediction model to determine whether the data of the real-time three-dimensional data is abnormal; wherein, the data prediction model is constructed based on the historical operation data of the photovoltaic power station.

[0027] A first elimination unit, configured to eliminate if it is determined that the data of the real-time three-dimensional data is abnormal.

[0028] A storage unit, configured to store if it is determined that the data of the real-time three-dimensional data is normal.

[0029] Further, the device further includes:

[0030] A second acquisition unit, configured to acquire the historical operation data of the photovoltaic power station and the instantaneous meteorological data corresponding to the historical operation data, where the instantaneous meteorological data includes instantaneous temperature and instantaneous irradiance.

[0031] A second elimination unit, configured to eliminate null values, dead values, and mutation values in the historical operation data.

[0032] A second construction unit, configured to construct a three-dimensional database corresponding to the historical operation data, the instantaneous temperature, and the instantaneous irradiance, establish a mapping relationship between temperature, irradiance, and operation data, and obtain the data prediction model.

[0033] In a third aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored program, wherein the program executes the method described above when running.

[0034] A method, device, and storage medium for data acquisition and processing of a photovoltaic power station provided by an embodiment of the present invention screen and eliminate the acquired real-time data, improve the accuracy of the stored real-time data, and improve the accuracy of the advanced algorithm application model.

[0035] Other features and advantages of the present invention will be described in the following specification, and part of them will become obvious from the specification, or be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained through the structures pointed out in the specification, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0037] Figure 1 shows the flowchart of the method for collecting and processing photovoltaic power station data in an embodiment of the present invention;

[0038] Figure 2 shows the flowchart of constructing a data prediction model in an embodiment of the present invention;

[0039] Figure 3 shows the block diagram of the device for collecting and processing photovoltaic power station data in an embodiment of the present invention. Detailed implementation manners

[0040] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0041] A method, device and storage medium for collecting and processing photovoltaic power station data provided by an embodiment of the present invention are applied to the collection and processing of the operation data of a photovoltaic power station.

[0042] Figure 1 shows the flowchart of the method for collecting and processing photovoltaic power station data in an embodiment of the present invention, as Figure 1 shown, the method includes:

[0043] S101: Collect the real-time operation data and real-time meteorological data of the photovoltaic power station, where the real-time operation data includes transformer substation data, busbar trunking unit data, inverter data and booster station data, and the real-time meteorological data includes real-time temperature and real-time irradiance;

[0044] In an embodiment of the present invention, the operation data of the photovoltaic power station at least includes transformer substation data, busbar trunking unit data, inverter data and booster station data. Specifically, the transformer substation data includes data such as voltage, current, active power, reactive power, power factor, etc.; the busbar trunking unit data includes DC busbar trunking unit data and AC busbar trunking unit data. The DC busbar trunking unit data includes data such as branch current, voltage, power, internal machine temperature, alarm operation status, etc., and the AC busbar trunking unit data includes data such as active power, reactive power, apparent power, frequency, power factor, input current, etc.; the inverter data includes data such as active power, branch current, input power, conversion efficiency, reactive power, power factor, MPPT current, MPPT voltage, line current, line voltage, grid frequency, etc.; the booster station data includes data such as active power, reactive power, phase current, phase voltage, power factor, switch status, etc. The meteorological data at least includes temperature and irradiance.

[0045] It should be noted that the operation data, temperature, and irradiation all have corresponding timestamps. For example, at a certain moment T, the collected data is specifically the operation data X at moment T, the temperature Y at moment T, and the irradiation Z at moment T. Collecting the real-time operation data and real-time meteorological data of the photovoltaic power station means that the real-time operation data and real-time meteorological data are collected at the same moment, and the two types of data at the same moment correspond in time.

[0046] In the embodiment of the present invention, the collection period of the real-time operation data and the real-time meteorological data is less than the first preset time interval. In a specific implementation manner, the first preset time interval is 1 minute. Of course, those skilled in the art should understand that the first preset time interval can also be set to other time intervals, such as 30 seconds or 90 seconds, as long as the collected data can accurately reflect the operation state of the photovoltaic power station, and no more limitations are made here.

[0047] In the embodiment of the present invention, after collecting the real-time operation data and the real-time meteorological data of the photovoltaic power station, before constructing the real-time three-dimensional data corresponding to the real-time operation data, the real-time temperature, and the real-time irradiation, it further includes: removing null values, dead values, and mutation values in the real-time operation data. Specifically, the null value is no data; the dead value is more than 10 groups of consecutive identical data; the mutation value is data with a difference of more than 20% between the previous and subsequent data.

[0048] In the embodiment of the present invention, during the process of collecting photovoltaic power station data, due to communication anomalies, individual data may be missing. For short-term individual data missing, it can be supplemented by filling the missing data with the average value of adjacent data before and after. For long-term data missing, it is recommended not to supplement.

[0049] S102: Construct real-time three-dimensional data corresponding to the real-time operation data, the real-time temperature, and the real-time irradiation;

[0050] In the embodiment of the present invention, for example, at moment T1, real-time operation data X1, real-time temperature Y1, and real-time irradiation Z1 are collected, then a three-dimensional data coordinate (X1, Y1, Z1) at moment T1 is formed; at moment T2, real-time operation data X2, real-time temperature Y2, and real-time irradiation Z2 are collected, then a three-dimensional data coordinate (X2, Y2, Z2) at moment T2 is formed; and so on in this way. At moment Tn, real-time operation data Xn, real-time temperature Yn, and real-time irradiation Zn are collected, then a three-dimensional data coordinate (Xn, Yn, Zn) at moment Tn is formed. It should be noted that preferably, a 24-hour time period in a day is used as the time cycle. For example, moment T1 is 9:00, and moment T2 is 9:01. No more examples are given here.

[0051] S103: Compare the real-time 3D data with a preset data prediction model to determine whether the data in the real-time 3D data is abnormal; wherein, the data prediction model is constructed based on the historical operation data of the photovoltaic power station;

[0052] If the data is abnormal, proceed to step S104; if the data is normal, proceed to step S105.

[0053] The data prediction model is constructed based on the historical operation data of the photovoltaic power station, Figure 2 The flowchart of constructing the data prediction model in the embodiment of the present invention is shown. The method specifically includes:

[0054] S201: Collect the historical operation data of the photovoltaic power station and the instantaneous meteorological data corresponding to the historical operation data. The instantaneous meteorological data includes instantaneous temperature and instantaneous irradiance;

[0055] In the embodiment of the present invention, the historical operation data of the photovoltaic power station at least includes historical transformer data, historical busbar trunking unit data, historical inverter data, and historical step-up substation data. The instantaneous meteorological data at least includes instantaneous temperature and instantaneous irradiance.

[0056] The historical operation data and the instantaneous meteorological data corresponding to the historical operation data are both data persistently stored in a dedicated data storage platform or database set for the photovoltaic power station. The dedicated data storage platform or database stores at least the data of the recent 3 years.

[0057] It should be noted that the historical operation data and the instantaneous meteorological data corresponding to the historical operation data, that is, the historical operation data and the instantaneous meteorological data, are collected at the same moment in the past. The two types of data at the same moment are corresponding in time.

[0058] S202: Remove the null values, dead values, and mutation values in the historical operation data;

[0059] In the embodiment of the present invention, the null value in the historical operation data is no data; the dead value is more than 10 groups of consecutive identical data; the mutation value is data with a difference of more than 20% between the previous and subsequent data.

[0060] S203: Construct a three-dimensional database corresponding to the historical operation data, the instantaneous temperature, and the instantaneous irradiance, establish a mapping relationship between temperature, irradiance, and operation data, and obtain the data prediction model.

[0061] The historical operation data of the photovoltaic power station includes data in various time periods, various weather conditions, and different temperatures.

[0062] In an embodiment of the present invention, for example, at time T1 on day A in history, the historical operation data is x1, the instantaneous temperature is y1, and the instantaneous irradiation is z1, then a three-dimensional data coordinate (x1, y1, z1) is formed at time T1; at time T1 on day B in history, the historical operation data is x2, the instantaneous temperature is y2, and the instantaneous irradiation is z2, then a three-dimensional data coordinate (x2, y2, z2) is formed at time T1; at time T1 on day C in history, the historical operation data is x3, the instantaneous temperature is y3, and the instantaneous irradiation is z3, then a three-dimensional data coordinate (x3, y3, z3) is formed at time T1; and so on in this way, thereby obtaining a three-dimensional database corresponding to the historical operation data, the instantaneous temperature, and the instantaneous irradiation at time T1, and establishing a mapping relationship between the temperature, irradiation, and operation data at time T1. The mapping relationships between the temperature, irradiation, and operation data at times T2, T3, T4, and up to Tn are established in sequence to obtain the data prediction model.

[0063] Input the real-time temperature and the real-time irradiation into the data prediction model to obtain predicted operation data; compare the real-time operation data with the predicted operation data. If the difference percentage between the real-time operation data and the predicted operation data is less than a preset threshold, it is determined that the real-time three-dimensional data is normal; if the difference percentage between the real-time operation data and the predicted operation data is greater than the preset threshold, it is determined that the real-time three-dimensional data is abnormal.

[0064] In an embodiment of the present invention, for example, at time T1, the real-time operation data X1, the real-time temperature Y1, and the real-time irradiation Z1 are collected. Input the real-time temperature Y1 and the real-time irradiation Z1 into the data prediction model to obtain the predicted operation data x1. If the difference percentage between the real-time operation data X1 and the predicted operation data x1 is less than 5%, it is determined that the real-time three-dimensional data is normal; if the difference percentage between the real-time operation data X1 and the predicted operation data x1 is greater than 5%, it is determined that the real-time three-dimensional data is abnormal. It should be noted that in this embodiment, the preset threshold is set to 5%, and of course, it can also be other values, which are not limited here too much.

[0065] S104: If it is determined that the data of the real-time three-dimensional data is abnormal, then eliminate it;

[0066] Eliminate the real-time three-dimensional data determined to be abnormal.

[0067] S105: If it is determined that the data of the real-time three-dimensional data is normal, then store it.

[0068] The real-time 3D data determined to be normal is stored. The implementation operation data and real-time meteorological data are persistently stored, and at least the data for the past 3 years should be saved. The data access system serves as a transit storage and saves data for at least 3 months. The PV power station should set up a dedicated data storage platform or database to persistently store real-time data. The storage capacity planning should configure the real-time data storage capacity according to the actual installed capacity, and at least 1T of storage capacity should be configured for every 10MW.

[0069] In the embodiment of the present invention, the storage period of the real-time operation data and the real-time meteorological data is less than the second preset time interval. In a specific implementation, the second preset time interval is 1 minute. Of course, those skilled in the art should understand that the second preset time interval can also be set to other time intervals, such as 30 seconds or 90 seconds, as long as the stored data can accurately reflect the operation status of the PV power station, and no further limitation is made here.

[0070] A method for data acquisition and processing of a PV power station provided by the embodiment of the present invention screens and eliminates the collected real-time data, improving the accuracy of the stored real-time data and the accuracy of the advanced algorithm application model.

[0071] The embodiment of the present invention also provides a device for data acquisition and processing of a PV power station, as Figure 3 shown. The device 30 includes:

[0072] A first acquisition unit 301 for acquiring the real-time operation data and real-time meteorological data of the PV power station. The operation data includes transformer data, busbar trunking data, inverter data, and booster station data. The real-time meteorological data includes real-time temperature and real-time irradiance;

[0073] A first construction unit 302 for constructing real-time 3D data corresponding to the real-time operation data, the real-time temperature, and the real-time irradiance;

[0074] A judgment unit 303 for comparing the real-time 3D data with a preset data prediction model to judge whether the data of the real-time 3D data is abnormal. Among them, the data prediction model is constructed based on the historical operation data of the PV power station;

[0075] A first elimination unit 304 for eliminating if it is determined that the data of the real-time 3D data is abnormal;

[0076] A storage unit 305 for storing if it is determined that the data of the real-time 3D data is normal.

[0077] In the embodiment of the present invention, the device 30 for data acquisition and processing of the PV power station further includes:

[0078] The second acquisition unit is configured to acquire historical operation data of the photovoltaic power station and instantaneous meteorological data corresponding to the historical operation data, where the instantaneous meteorological data includes instantaneous temperature and instantaneous irradiance;

[0079] The second rejection unit is configured to reject null values, dead values, and mutation values in the historical operation data;

[0080] The second construction unit is configured to construct a three-dimensional database corresponding to the historical operation data, the instantaneous temperature, and the instantaneous irradiance, establish a mapping relationship between temperature, irradiance, and operation data, and obtain the data prediction model.

[0081] It should be noted that the devices in the device embodiments for data acquisition and processing of the photovoltaic power station and the method embodiments are based on the same inventive concept.

[0082] In some embodiments, the functions or modules included in the device provided in the embodiments of the present invention can be used to execute the methods described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0083] The embodiments of the present invention also provide a computer-readable storage medium. At least one instruction or at least one segment of program is stored in the computer-readable storage medium, and the at least one instruction or at least one segment of program is loaded and executed by a processor to implement the above method. The computer-readable storage medium can be a non-volatile computer-readable storage medium.

[0084] The embodiments of the present invention also provide an electronic device. The electronic device includes at least one processor and a memory communicatively connected to the at least one processor. Wherein, at least one instruction or at least one segment of program is stored in the memory, and the at least one instruction or at least one segment of program is loaded and executed by the at least one processor to implement the above method.

[0085] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

[0086] Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for collecting and processing photovoltaic power station data, characterized in that, it includes: Collect the real-time operation data and real-time meteorological data of the photovoltaic power station. The real-time operation data includes transformer substation data, busbar trunking data, inverter data and step-up substation data. The real-time meteorological data includes real-time temperature and real-time irradiance; Construct real-time three-dimensional data corresponding to the real-time operation data, the real-time temperature, and the real-time irradiance; Compare the real-time three-dimensional data with a preset data prediction model to determine whether the data of the real-time three-dimensional data is abnormal; wherein, the data prediction model is constructed based on the historical operation data of the photovoltaic power station; If it is determined that the data of the real-time three-dimensional data is abnormal, then eliminate it; If it is determined that the data of the real-time three-dimensional data is normal, then store it.

2. The method according to claim 1, characterized in that, The data prediction model is constructed based on the historical operation data of the photovoltaic power station, and specifically includes: Collect the historical operation data of the photovoltaic power station and the instantaneous meteorological data corresponding to the historical operation data. The instantaneous meteorological data includes instantaneous temperature and instantaneous irradiance; Eliminate the null values, dead values and mutation values in the historical operation data; Construct a three-dimensional database corresponding to the historical operation data, the instantaneous temperature, and the instantaneous irradiance, establish a mapping relationship between temperature, irradiance and operation data, and obtain the data prediction model.

3. The method according to claim 2, characterized in that, The comparison of the real-time three-dimensional data with a preset data prediction model to determine whether the data of the real-time three-dimensional data is abnormal specifically includes: Input the real-time temperature and the real-time irradiance into the data prediction model to obtain predicted operation data; Compare the real-time operation data with the predicted operation data. If the difference percentage between the real-time operation data and the predicted operation data is less than a preset threshold, it is determined that the real-time operation data is normal; if the difference percentage between the real-time operation data and the predicted operation data is greater than the preset threshold, it is determined that the real-time operation data is abnormal.

4. The method according to claim 3, characterized in that, The preset threshold is 5%.

5. The method according to claim 2, characterized in that, The null value is no data; the dead value is more than 10 groups of consecutive identical data; the mutation value is data with a difference of more than 20% between the front and back data.

6. The method according to claim 1, characterized in that, After collecting the real-time operation data and real-time meteorological data of the photovoltaic power station, and before constructing the real-time three-dimensional data corresponding to the real-time operation data, the real-time temperature, and the real-time irradiance, it further includes: Eliminate the null values, dead values and mutation values in the real-time operation data.

7. The method according to claim 1, characterized in that, It further includes: The collection period of the real-time operation data and real-time meteorological data is less than the first preset time interval; The storage period of the real-time operation data and real-time meteorological data is less than the second preset time interval.

8. A device for collecting and processing photovoltaic power station data, characterized in that, it includes: A first acquisition unit for acquiring real-time operation data and real-time meteorological data of a photovoltaic power station, where the operation data includes transformer substation data, busbar trunking data, inverter data, and step-up substation data, and the real-time meteorological data includes real-time temperature and real-time irradiance; A first construction unit for constructing real-time three-dimensional data corresponding to the real-time operation data, the real-time temperature, and the real-time irradiance; A judgment unit for comparing the real-time three-dimensional data with a preset data prediction model to judge whether the data of the real-time three-dimensional data is abnormal; wherein, the data prediction model is constructed based on historical operation data of the photovoltaic power station; A first elimination unit for eliminating if it is determined that the data of the real-time three-dimensional data is abnormal; A storage unit for storing if it is determined that the data of the real-time three-dimensional data is normal.

9. The device according to claim 8, wherein, the device further includes: A second acquisition unit for acquiring historical operation data of the photovoltaic power station and instantaneous meteorological data corresponding to the historical operation data, where the instantaneous meteorological data includes instantaneous temperature and instantaneous irradiance; A second elimination unit for eliminating null values, dead values, and mutation values in the historical operation data; A second construction unit for constructing a three-dimensional database corresponding to the historical operation data, the instantaneous temperature, and the instantaneous irradiance, establishing a mapping relationship between temperature, irradiance, and operation data, and obtaining the data prediction model.

10. A computer-readable storage medium, wherein, the computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 7 above when running.

Images