Photovoltaic power generation system and historical data preprocessing method and device thereof, and electronic device

Abstract

The application discloses a photovoltaic power generation system and a historical data preprocessing method and device thereof and electronic equipment; the historical data preprocessing method comprises the following steps: extracting a photovoltaic power generation historical time period and corresponding original photovoltaic power generation data; acquiring meteorological data corresponding to the photovoltaic power generation historical time period; calculating corrected photovoltaic power generation data in the photovoltaic power generation historical time period according to the acquired meteorological data; obtaining a random value by subtracting the absolute value of the corrected photovoltaic power generation data from the original photovoltaic power generation data; identifying an abnormal random value based on a normal distribution, if the abnormal random value exists, deleting original power generation historical data corresponding to the abnormal random value, otherwise, retaining the original power generation historical data; the accuracy and reliability of the residual original photovoltaic power generation data are ensured by the above method, and the space and time complexity are reduced.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power generation data processing technology, and in particular to a photovoltaic power generation system and its historical data preprocessing method and apparatus, as well as electronic equipment. Background Technology

[0002] Photovoltaics (PV) is a crucial source of green energy, and the analysis of corrected PV power generation data is a vital evaluation tool for green buildings. As the global energy structure transitions towards cleaner energy, PV power generation, as one of the most promising renewable energy sources, is experiencing rapid growth in installed capacity. Monitoring the operational status of PV power generation systems, predicting power generation, and grid dispatching rely on massive amounts of historical raw PV power generation data. However, due to limitations in sensor accuracy, environmental interference, and data acquisition equipment malfunctions, the actual raw PV power generation data often suffers from the following challenges:

[0003] Due to communication interruptions, equipment failures, and other reasons, historical data often shows missing data for continuous or discrete time periods, which directly affects long-term trend analysis and model training.

[0004] When extreme weather occurs, such as sudden cloud cover, strong winds, or momentary equipment failures, such as inverter malfunctions, the original photovoltaic power generation data may deviate from the normal fluctuation range. Traditional threshold methods are difficult to accurately identify outliers in complex scenarios.

[0005] Actual power generation is dynamically affected by multiple factors such as light intensity, ambient temperature, and wind speed. The original data is superimposed with irreproducible random noise, such as irradiance fluctuations caused by rapid cloud movement, resulting in high data dispersion and making it difficult to extract stable feature patterns. Summary of the Invention

[0006] To address the issue of outliers in historical power generation data in photovoltaic power generation systems, this invention provides a photovoltaic power generation system and its historical data preprocessing method, apparatus, and electronic equipment.

[0007] The present invention adopts the following technical solution:

[0008] The first aspect of this invention discloses a method for preprocessing historical data of a photovoltaic power generation system, comprising:

[0009] Extract historical time periods of photovoltaic power generation and the corresponding raw photovoltaic power generation data;

[0010] Obtain meteorological data corresponding to the historical time period of photovoltaic power generation;

[0011] The instantaneous power of the photovoltaic modules in the photovoltaic power generation system is calculated based on the acquired meteorological data.

[0012] The corrected photovoltaic power generation data for the historical time period is calculated based on the sum of the products of the instantaneous power of the photovoltaic modules in the photovoltaic power generation system and the time interval of acquiring meteorological data.

[0013] A random value is obtained by subtracting the absolute value of the corrected photovoltaic power generation data from the original photovoltaic power generation data;

[0014] Based on the normal distribution, abnormal random values ​​are identified. If an abnormal random value exists, the original historical power generation data corresponding to that abnormal random value is deleted; otherwise, the original historical power generation data is retained.

[0015] According to the historical data preprocessing method, the historical data preprocessing method further includes:

[0016] Cluster the non-abnormal random values ​​to obtain the time period range, and then take the weighted average of the non-abnormal random values ​​within the time period range to obtain the weighted average random value corresponding to the time period range.

[0017] Obtain the historical photovoltaic power generation time period corresponding to the abnormal random value, and use the sum of the corrected photovoltaic power generation data and the weighted average random value corresponding to the historical photovoltaic power generation time period as the corresponding original photovoltaic power generation data.

[0018] According to the aforementioned historical data preprocessing method, the identification of anomalous random values ​​specifically includes:

[0019] Abnormal random values ​​can be identified using the 3σ principle of the Laida criterion or the interquartile range method.

[0020] Based on the historical data preprocessing method described above, the corrected photovoltaic power generation data is calculated using the following formula:

[0021]

[0022] Where E represents the corrected photovoltaic power generation data, t1 is the start time of the historical photovoltaic power generation period, and t2 is the end time of the historical photovoltaic power generation period. Δt represents the instantaneous power of the photovoltaic modules in the photovoltaic power generation system, and Δt represents the time interval for acquiring meteorological data.

[0023] Based on the aforementioned historical data preprocessing method, the instantaneous power of the photovoltaic modules in the photovoltaic power generation system is calculated using the following formula:

[0024]

[0025] Where η_ref is the photovoltaic module conversion efficiency, G is the current irradiance, G_ref is the reference irradiance, T is the current ambient temperature, T_ref is the reference temperature, α is the temperature decay coefficient, and A is the area of ​​the photovoltaic module in the photovoltaic power generation system.

[0026] According to the historical data preprocessing method, the historical data preprocessing method further includes:

[0027] When extracting historical time periods of photovoltaic power generation and the corresponding original photovoltaic power generation data, a historical photovoltaic power generation data record table is generated. Based on the historical photovoltaic power generation data record table, a corrected photovoltaic power generation data column and a random value column are added, and a corrected historical photovoltaic power generation data record table is generated.

[0028] A second aspect of this invention discloses a historical data preprocessing apparatus for a photovoltaic power generation system, used to perform a historical data preprocessing method, comprising:

[0029] The historical data extraction module is used to extract historical time periods of photovoltaic power generation and the corresponding raw photovoltaic power generation data;

[0030] The meteorological data acquisition module is used to acquire meteorological data corresponding to historical time periods of photovoltaic power generation;

[0031] The data calculation module is used to calculate the instantaneous power of the photovoltaic modules of the photovoltaic power generation system based on the acquired meteorological data; calculate the corrected photovoltaic power generation data within the historical time period based on the sum of the products of the instantaneous power of the photovoltaic modules of the photovoltaic power generation system and the time interval of acquiring the meteorological data; and obtain a random value by subtracting the corrected photovoltaic power generation data from the original photovoltaic power generation data.

[0032] The abnormal random value identification module is used to identify abnormal random values ​​based on the normal distribution. If an abnormal random value exists, the original historical power generation data corresponding to the abnormal random value is deleted; otherwise, the original historical power generation data is retained.

[0033] A third aspect of the present invention discloses a photovoltaic power generation system, including the historical data preprocessing device as described in claim 7.

[0034] A fourth aspect of the present invention discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when loaded onto the processor, implements the aforementioned historical data preprocessing method.

[0035] A fifth aspect of the present invention discloses a storage medium comprising a stored program, wherein the program, when running, controls the device where the storage medium is located to execute the aforementioned historical data preprocessing method.

[0036] Compared with the prior art, the beneficial effects of the present invention include at least the following:

[0037] 1. This invention calculates corrected photovoltaic power generation data by constructing a corrected photovoltaic power generation data calculation model, and uses the absolute value of the original photovoltaic power generation data minus the corrected photovoltaic power generation data as a random value. The random value theoretically conforms to a normal distribution. By identifying and deleting the original historical power generation data corresponding to abnormal random values, the identification and deletion of abnormal original photovoltaic power generation data is realized, ensuring the accuracy and reliability of the remaining original photovoltaic power generation data, while reducing space and time complexity.

[0038] 2. After deleting abnormal photovoltaic power generation data, this invention clusters non-abnormal random values ​​to obtain time ranges, performs weighted averaging on the non-abnormal random values ​​within the time range to obtain the weighted average random value corresponding to the time range, and then calculates new photovoltaic power generation data by correcting the photovoltaic power generation data and the weighted average random value, which is then used as the corresponding original photovoltaic power generation data. This method is less likely to introduce secondary errors and does not require training with a large amount of unlabeled data. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a flowchart of the historical data preprocessing method of Embodiment 1 of the present invention;

[0041] Figure 2 This is a flowchart of the historical data preprocessing method in Embodiment 2 of the present invention;

[0042] Figure 3 This is a flowchart of the historical data preprocessing method in Embodiment 3 of the present invention;

[0043] Figure 4 This is a block diagram of the historical data preprocessing device of the present invention;

[0044] In the picture:

[0045] 401. Historical data extraction module; 402. Meteorological data acquisition module; 403. Data calculation module; 404. Abnormal random value identification module. Detailed Implementation

[0046] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0047] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0048] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0049] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0050] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0051] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0052] To address the issue of outliers in historical power generation data within photovoltaic (PV) power generation systems, this problem includes two scenarios: missing original PV power generation data and abnormal values ​​in the original PV power generation data. Figure 1 As shown, Embodiment 1 of the present invention provides a method for preprocessing historical data of a photovoltaic power generation system, including the following steps:

[0053] Step S110: Extract the historical time period of photovoltaic power generation and the corresponding raw photovoltaic power generation data.

[0054] The photovoltaic power generation historical time period shall include at least the start and end times of the photovoltaic power generation historical time period.

[0055] The original photovoltaic power generation data refers to the photovoltaic power generation data in the historical data of the photovoltaic power generation system.

[0056] Step S120: Obtain meteorological data corresponding to the historical time period of photovoltaic power generation.

[0057] The meteorological data can be obtained from the official meteorological website.

[0058] The meteorological data shall include at least: ambient temperature and light intensity.

[0059] Meteorological data may also include wind speed.

[0060] Preferred, but not limited, is the acquisition of meteorological data at equal intervals.

[0061] In one embodiment, the interval for the historical time period of photovoltaic power generation is 1 hour, and the interval for acquiring meteorological data can be 1 second, 2 seconds, etc.

[0062] Step S130: Calculate the instantaneous power of the photovoltaic modules of the photovoltaic power generation system based on the acquired meteorological data.

[0063] Step S140: Calculate the corrected photovoltaic power generation data for the historical time period based on the sum of the products of the instantaneous power of the photovoltaic modules in the photovoltaic power generation system and the time interval for acquiring meteorological data.

[0064] Specifically, the corrected photovoltaic power generation data E for a certain historical photovoltaic power generation period is calculated using the following formula:

[0065]

[0066] Where E represents the corrected photovoltaic power generation data, t1 is the start time of the historical photovoltaic power generation period, and t2 is the end time of the historical photovoltaic power generation period. Δt represents the instantaneous power of the photovoltaic modules in the photovoltaic power generation system, and Δt represents the time interval for acquiring meteorological data, with the unit being W.

[0067] Specifically, the instantaneous power of the photovoltaic modules in a photovoltaic power generation system is calculated using the following formula. :

[0068]

[0069] Where η_ref is the photovoltaic module conversion efficiency, G is the current irradiance in W / m², G_ref is the reference irradiance, T is the current ambient temperature in °C, T_ref is the reference temperature, α is the temperature decay coefficient, and A is the area of ​​the photovoltaic module in the photovoltaic power generation system.

[0070] Specifically, the photovoltaic module conversion efficiency η_ref is the conversion efficiency of the photovoltaic module under the reference irradiance G_ref and the reference temperature T_ref.

[0071] Preferably, but not limitingly, the reference irradiance G_ref is typically taken as 1000 W / m².

[0072] Preferably, but not limitingly, the reference temperature T_ref is typically taken as 25°C.

[0073] This invention designs and modifies a calculation model for photovoltaic power generation data to calculate the theoretical photovoltaic power generation over a historical period. This corrects the original data, improves the accuracy of power generation calculation, indirectly reflects the actual power generation capacity, provides reliable input for subsequent data processing, and enhances the system's analytical precision.

[0074] Step S150: Obtain a random value by subtracting the absolute value of the corrected photovoltaic power generation data from the original photovoltaic power generation data.

[0075] Step S160: Identify abnormal random values ​​based on normal distribution. If abnormal random values ​​exist, delete the original historical power generation data corresponding to the abnormal random values; otherwise, retain the original historical power generation data.

[0076] In one embodiment, anomalous random values ​​are identified according to the 3σ principle of the Raida criterion. If an anomalous random value exists, the original historical power generation data corresponding to that anomalous random value is deleted; otherwise, the original historical power generation data is retained.

[0077] The Laida criterion's 3σ principle for identifying outliers is as follows:

[0078]

[0079] Where x is the data to be identified, μ is the mean of the data, and σ is the standard deviation of the data.

[0080] In another embodiment, anomalous random values ​​can be identified using the interquartile range method.

[0081] This invention utilizes the principle that random values ​​theoretically conform to a normal distribution, and uses an identification algorithm to find random values ​​that do not conform to a normal distribution, i.e., outliers, which can quickly locate abnormal original photovoltaic power generation data.

[0082] When the original photovoltaic power generation data is missing, the random value calculated by step S150 does not conform to a normal distribution. When the value of the original photovoltaic power generation data is abnormal, the random value calculated by step S150 also does not conform to a normal distribution.

[0083] By following the steps above, outliers in the original photovoltaic power generation data can be quickly identified.

[0084] This invention calculates corrected photovoltaic power generation data by constructing a corrected photovoltaic power generation data calculation model. The absolute value of the original photovoltaic power generation data minus the corrected photovoltaic power generation data is used as a random value. The random value theoretically conforms to a normal distribution. By identifying and deleting the original historical power generation data corresponding to abnormal random values, the invention achieves the identification and deletion of abnormal original photovoltaic power generation data, ensuring the accuracy and reliability of the remaining original photovoltaic power generation data, while reducing space and time complexity.

[0085] Preferably, but not restrictively, when extracting historical photovoltaic power generation time periods and corresponding original photovoltaic power generation data, a historical photovoltaic power generation data record table is generated; on the basis of the historical photovoltaic power generation data record table, a corrected photovoltaic power generation data column and a random value column are added, and a corrected historical photovoltaic power generation data record table is generated.

[0086] This invention introduces a historical data correction record table for photovoltaic power generation, which explicitly displays the correction logic and data association, avoiding the drawback of only storing the final correction result without recording the intermediate process, which would lead to the correction logic being untraceable.

[0087] In existing technologies, preprocessing methods for photovoltaic power generation data are mainly divided into two categories:

[0088] Missing values ​​can be filled using historical mean, linear interpolation, or spline interpolation, but this method is sensitive to outliers and can easily introduce quadratic errors.

[0089] Models such as LSTM and random forests can be used to predict missing values, but they rely on a large amount of unlabeled data for training and do not separate random perturbations from real fluctuations, thus limiting the model's generalization ability.

[0090] To address the issues of introducing quadratic errors and limited model generalization ability in supplementing historical data in photovoltaic power generation systems, such as... Figure 2 As shown, Embodiment 2 of the present invention provides a method for preprocessing historical data of a photovoltaic power generation system, including the following steps:

[0091] Step S210: Extract the historical time period of photovoltaic power generation and the corresponding raw photovoltaic power generation data.

[0092] Step S220: Obtain meteorological data corresponding to the historical time period of photovoltaic power generation.

[0093] Step S230: Calculate the instantaneous power of the photovoltaic modules of the photovoltaic power generation system based on the acquired meteorological data.

[0094] Step S240: Calculate the corrected photovoltaic power generation data for the historical time period based on the sum of the products of the instantaneous power of the photovoltaic modules in the photovoltaic power generation system and the time interval for acquiring meteorological data.

[0095] Step S250: Obtain a random value by subtracting the absolute value of the corrected photovoltaic power generation data from the original photovoltaic power generation data.

[0096] Step S260: Identify abnormal random values ​​based on normal distribution. If abnormal random values ​​exist, delete the original historical power generation data corresponding to the abnormal random values; otherwise, retain the original historical power generation data.

[0097] Step S270: Cluster the non-abnormal random values ​​to obtain the time period range, and perform a weighted average of the non-abnormal random values ​​within the time period range to obtain the weighted average random value corresponding to the time period range.

[0098] Preferably, but not limitingly, the time period range includes one or more historical photovoltaic power generation time periods, that is, one historical photovoltaic power generation time period corresponds to one time period range.

[0099] Step S280: Obtain the historical time period of photovoltaic power generation corresponding to the abnormal random value, and use the sum of the corrected photovoltaic power generation data and the weighted average random value corresponding to the historical time period of photovoltaic power generation as the corresponding original photovoltaic power generation data.

[0100] This invention, after deleting abnormal photovoltaic power generation data, clusters non-abnormal random values ​​to obtain time ranges, then performs a weighted average of the non-abnormal random values ​​within the time range to obtain a weighted average random value corresponding to the time range. Finally, it calculates new photovoltaic power generation data by correcting the photovoltaic power generation data and the weighted average random value, and uses this as the corresponding original photovoltaic power generation data. This method is less prone to introducing secondary errors and does not require training with a large amount of unlabeled data.

[0101] Preferably, but not restrictively, the corrected photovoltaic power generation data column and the random value column in the historical photovoltaic power generation data correction record table are deleted to complete the historical data preprocessing of the photovoltaic power generation system.

[0102] This invention eliminates redundancy, reduces storage and transmission costs, and outputs well-structured preprocessed data by deleting the corrected photovoltaic power generation data column and the random value column from the historical photovoltaic power generation data correction record table.

[0103] like Figure 3 As shown, Embodiment 3 of the present invention provides a preferred embodiment of a method for preprocessing historical data of a photovoltaic power generation system, which specifically includes the following steps:

[0104] Step S310, as shown in Table 1, extract the historical time period of photovoltaic power generation and the corresponding original photovoltaic power generation data, and generate a historical data record table of photovoltaic power generation. The historical time period of photovoltaic power generation includes the start time and end time of the historical time period of photovoltaic power generation.

[0105] Table 1 Historical Data Record of Photovoltaic Power Generation

[0106]

[0107] It should be noted that the time periods listed in Table 1 above are for illustrative purposes only, and other time periods may be used in other embodiments to characterize the historical time periods of photovoltaic power generation.

[0108] Step S311, as shown in Table 2, adds a corrected photovoltaic power generation data column and a random value column to the historical photovoltaic power generation data record table, and generates a corrected historical photovoltaic power generation data record table.

[0109] Table 2 Historical Data Correction Record of Photovoltaic Power Generation

[0110]

[0111] Step S320: Obtain meteorological data corresponding to the historical time period of photovoltaic power generation from the meteorological website. The meteorological data includes at least: ambient temperature and light intensity.

[0112] Step S330: Calculate the instantaneous power of the photovoltaic modules of the photovoltaic power generation system based on the acquired meteorological data.

[0113] Step S340: Calculate the corrected photovoltaic power generation data for the historical period based on the sum of the products of the instantaneous power of the photovoltaic modules in the photovoltaic power generation system and the time interval for acquiring meteorological data, and fill it into the corresponding corrected photovoltaic power generation data column in the historical photovoltaic power generation data correction record table.

[0114] Step S350: Subtract the absolute value of the corrected photovoltaic power generation data from the original photovoltaic power generation data to obtain a random value, and fill it into the corresponding random value column in the photovoltaic power generation historical data correction record table.

[0115] Step S360: Based on the normal distribution, identify abnormal random values ​​using the 3σ principle of the Laida criterion or the interquartile range method. If abnormal random values ​​exist, delete the original historical power generation data corresponding to the abnormal random values; otherwise, retain the original historical power generation data.

[0116] Step S370: Cluster the non-abnormal random values ​​using the k-means algorithm to obtain the time period range, and then perform a weighted average of the non-abnormal random values ​​within the time period range to obtain the weighted average random value corresponding to the time period range.

[0117] In one embodiment, three time periods are obtained through a clustering algorithm, which are named the morning time period, the noon time period, and the afternoon time period, respectively.

[0118] A time period may include one or more historical periods of photovoltaic power generation.

[0119] The non-abnormal random values ​​within the three time periods are weighted and averaged to obtain the weighted average random value corresponding to the three time periods.

[0120] Step S380: Obtain the historical time period of photovoltaic power generation corresponding to the abnormal random value, and use the sum of the corrected photovoltaic power generation data and the weighted average random value corresponding to the historical time period of photovoltaic power generation as the corresponding original photovoltaic power generation data.

[0121] Step S390: Delete the corrected photovoltaic power generation data column and the random value column from the historical photovoltaic power generation data correction record table to complete the preprocessing of historical data of the photovoltaic power generation system.

[0122] like Figure 4 As shown, Embodiment 4 of the present invention provides a historical data preprocessing device for a photovoltaic power generation system, comprising:

[0123] Historical data extraction module 401 is used to extract historical time periods of photovoltaic power generation and the corresponding raw photovoltaic power generation data;

[0124] Meteorological data acquisition module 402 is used to acquire meteorological data corresponding to historical time periods of photovoltaic power generation;

[0125] The data calculation module 403 is used to calculate the instantaneous power of the photovoltaic modules of the photovoltaic power generation system based on the acquired meteorological data; calculate the corrected photovoltaic power generation data within the historical time period based on the sum of the products of the instantaneous power of the photovoltaic modules of the photovoltaic power generation system and the time interval of acquiring the meteorological data; and obtain a random value by subtracting the corrected photovoltaic power generation data from the absolute value of the original photovoltaic power generation data.

[0126] The abnormal random value identification module 404 is used to identify abnormal random values ​​based on the normal distribution. If an abnormal random value exists, the original historical power generation data corresponding to the abnormal random value is deleted; otherwise, the original historical power generation data is retained.

[0127] Embodiment 5 of the present invention provides a photovoltaic power generation system, including the above-mentioned historical data preprocessing device.

[0128] Embodiment 6 of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is loaded onto the processor, it implements the above-described historical data preprocessing method.

[0129] Embodiment 7 of the present invention provides a storage medium storing a computer program that, when executed by a processor, implements the historical data preprocessing method disclosed in the present invention.

[0130] Storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Storage media can be, for example, but not limited to, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples of storage media (a non-exhaustive list) include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. Storage media as used herein is not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0131] The computer-readable program instructions described herein can be downloaded from storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper cables, fiber optic cables, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to storage media within the respective computing / processing device.

[0132] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for preprocessing historical data of a photovoltaic power generation system, characterized in that, include: Extract historical time periods of photovoltaic power generation and the corresponding raw photovoltaic power generation data; Obtain meteorological data corresponding to the historical time period of photovoltaic power generation; The instantaneous power of the photovoltaic modules in the photovoltaic power generation system is calculated based on the acquired meteorological data. The corrected photovoltaic power generation data for the historical time period is calculated based on the sum of the products of the instantaneous power of the photovoltaic modules in the photovoltaic power generation system and the time interval of acquiring meteorological data. A random value is obtained by subtracting the absolute value of the corrected photovoltaic power generation data from the original photovoltaic power generation data; Based on the normal distribution, abnormal random values ​​are identified. If an abnormal random value exists, the original historical power generation data corresponding to the abnormal random value is deleted; otherwise, the original historical power generation data is retained. Cluster the non-abnormal random values ​​to obtain a time period range, and then perform a weighted average of the non-abnormal random values ​​within the time period range to obtain the weighted average random value corresponding to the time period range. Obtain the historical photovoltaic power generation time period corresponding to the abnormal random value, calculate the new photovoltaic power generation data by summing the corrected photovoltaic power generation data and the weighted average random value corresponding to the historical photovoltaic power generation time period, and use it as the corresponding original photovoltaic power generation data.

2. The historical data preprocessing method according to claim 1, characterized in that: The method for identifying anomalous random values ​​based on normal distribution specifically includes: The anomalous random values ​​are identified using the 3σ principle of the Laida criterion or the interquartile range method.

3. The historical data preprocessing method according to claim 1, characterized in that: The corrected photovoltaic power generation data is calculated using the following formula: Where E represents the corrected photovoltaic power generation data, t1 is the start time of the historical photovoltaic power generation period, and t2 is the end time of the historical photovoltaic power generation period. ∆t represents the instantaneous power of the photovoltaic modules in the photovoltaic power generation system, and ∆t represents the time interval for acquiring meteorological data.

4. The historical data preprocessing method according to claim 3, characterized in that: The instantaneous power of photovoltaic modules in a photovoltaic power generation system can be calculated using the following formula: Where η_ref is the photovoltaic module conversion efficiency, G is the current irradiance, G_ref is the reference irradiance, T is the current ambient temperature, T_ref is the reference temperature, α is the temperature decay coefficient, and A is the area of ​​the photovoltaic module in the photovoltaic power generation system.

5. The historical data preprocessing method according to claim 1, characterized in that: The historical data preprocessing method also includes: When extracting historical time periods of photovoltaic power generation and the corresponding original photovoltaic power generation data, a historical photovoltaic power generation data record table is generated. Based on the historical photovoltaic power generation data record table, a corrected photovoltaic power generation data column and a random value column are added, and a corrected historical photovoltaic power generation data record table is generated.

6. A historical data preprocessing apparatus for a photovoltaic power generation system, used to execute the historical data preprocessing method according to any one of claims 1-5, characterized in that, include: The historical data extraction module is used to extract historical time periods of photovoltaic power generation and the corresponding raw photovoltaic power generation data; The meteorological data acquisition module is used to acquire meteorological data corresponding to the historical time period of the photovoltaic power generation. The data calculation module is used to calculate the instantaneous power of the photovoltaic modules of the photovoltaic power generation system based on the acquired meteorological data; calculate the corrected photovoltaic power generation data within the historical time period based on the sum of the products of the instantaneous power of the photovoltaic modules of the photovoltaic power generation system and the time interval of acquiring the meteorological data; and obtain a random value by subtracting the corrected photovoltaic power generation data from the original photovoltaic power generation data. The abnormal random value identification module is used to identify abnormal random values ​​based on the normal distribution. If an abnormal random value exists, the original historical power generation data corresponding to the abnormal random value is deleted; otherwise, the original historical power generation data is retained.

7. A photovoltaic power generation system, characterized in that: Includes the historical data preprocessing apparatus as described in claim 6.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the computer program is loaded into the processor, it implements the historical data preprocessing method according to any one of claims 1-5.

9. A storage medium, characterized in that: The storage medium includes a stored program, wherein, when the program is executed, it controls the device where the storage medium is located to perform the historical data preprocessing method according to any one of claims 1-5.

Images