A photovoltaic anomaly detection method, device, equipment and medium

Abstract

This application discloses a method, apparatus, device, and medium for detecting photovoltaic anomalies. The method includes: acquiring irradiance correlation data and power generation data of a target user during a testing period; determining a target period category based on the irradiance correlation data of the target user during the testing period and at least two pre-determined period categories; and determining whether the target user's photovoltaic equipment is abnormal based on the power generation data of the target user during the testing period and power generation data matching the target period category. This technical solution solves the problem that staff can only discover photovoltaic equipment anomalies after a significant decrease in power generation, enabling timely detection of abnormal photovoltaic equipment and ensuring the power generation efficiency of users.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic anomaly detection technology, and in particular to a method, apparatus, equipment and medium for detecting photovoltaic anomalies. Background Technology

[0002] Distributed photovoltaic (PV) power stations refer to power generation systems that utilize decentralized photovoltaic resources and are located near users. Distributed PV offers advantages such as convenient installation, low investment threshold, high flexibility, and the ability to effectively increase PV utilization. However, how to monitor the operational status of PV equipment is a problem that urgently needs to be solved.

[0003] In the existing system, when staff discover a significant drop in the power generation of photovoltaic equipment, they will inspect and repair the equipment. However, by this time, the photovoltaic equipment has already shown a major malfunction, and the above-mentioned methods will affect the power generation efficiency of the photovoltaic equipment. Furthermore, after a major malfunction occurs, the lifespan of the photovoltaic equipment may be affected. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for detecting photovoltaic anomalies, so as to realize timely detection of photovoltaic equipment malfunctions and ensure the power generation efficiency of users.

[0005] According to one aspect of the present invention, a method for detecting photovoltaic anomalies is provided, the method comprising:

[0006] Obtain radiation irradiance correlation data and power generation data of the target user during the period to be detected;

[0007] Based on the radiation irradiance correlation data of the target user in the period to be detected, and at least two pre-determined period categories, determine the target period category to which the period to be detected belongs;

[0008] Based on the power generation data of the target user during the detection period, and the power generation data matching the target period category, it is determined whether the photovoltaic equipment of the target user is abnormal.

[0009] According to another aspect of the present invention, a photovoltaic anomaly detection device is provided, comprising:

[0010] The data acquisition module is used to acquire radiation irradiance correlation data and power generation data of the target user during the detection period;

[0011] The target cycle category determination module is used to determine the target cycle category to which the test cycle belongs based on the radiation irradiance correlation data of the target user in the test cycle and at least two pre-determined cycle categories.

[0012] The anomaly detection module is used to determine whether there is an anomaly in the photovoltaic equipment of the target user based on the power generation data of the target user in the period to be detected and the power generation data that matches the target period category.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the photovoltaic anomaly detection method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the photovoltaic anomaly detection method according to any embodiment of the present invention.

[0018] The technical solution of this application includes: acquiring irradiance correlation data and power generation data of a target user during a testing period; determining the target period category to which the testing period belongs based on the irradiance correlation data of the target user during the testing period and at least two predetermined period categories; and determining whether the photovoltaic equipment of the target user is abnormal based on the power generation data of the target user during the testing period and power generation data matching the target period category. This technical solution determines the target period category to which the testing period belongs by using the irradiance correlation data of the target user during the testing period, and then determines whether the photovoltaic equipment of the target user is abnormal based on the power generation data of the target user during the testing period and the power generation data matching the target period category. This solves the problem that staff can only discover abnormalities in photovoltaic equipment after a significant decrease in power generation. This solution can promptly detect abnormal photovoltaic equipment, ensuring the power generation efficiency of users.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a photovoltaic anomaly detection method provided according to Embodiment 1 of this application;

[0022] Figure 2 This is a flowchart of a photovoltaic anomaly detection method according to Embodiment 2 of this application;

[0023] Figure 3 This is a schematic diagram of a photovoltaic anomaly detection device according to Embodiment 3 of this application;

[0024] Figure 4 This is a schematic diagram of the structure of an electronic device that implements a photovoltaic anomaly detection method according to an embodiment of this application. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] Example 1

[0028] Figure 1This application provides a flowchart of a photovoltaic anomaly detection method according to Embodiment 1. This embodiment is applicable to situations involving anomaly detection of photovoltaic equipment. The method can be executed by a photovoltaic anomaly detection device, which can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0029] S110: Obtain radiation irradiance correlation data and power generation data of the target user during the detection period.

[0030] The target users can be those who have already installed photovoltaic equipment, including but not limited to individual users, household users, and enterprise users. The testing period can be determined based on actual conditions. This application embodiment does not limit the duration of the testing period; for example, the testing period can be one day, or it can be a portion of a day. The irradiance correlation data for the testing period can reflect the illumination conditions during that period. The acquisition time and quantity of power generation data for the testing period can be preset. Taking a 24-hour testing period as an example: the number of power generation data points for the testing period can be 96, acquired every 15 minutes.

[0031] Specifically, the power generation data of the target user is related to the irradiance. The higher the irradiance, the higher the power generation, and the lower the irradiance, the lower the power generation. Therefore, if the power generation data of the period to be tested differs too much from the power generation data of a period with similar irradiance correlation data, it indicates that there may be an anomaly in the photovoltaic equipment.

[0032] In this embodiment of the application, optionally, the radiation irradiance correlation data includes at least one of the following: average value, standard deviation, maximum value, and number of peaks of radiation irradiance.

[0033] In this embodiment, irradiance correlation data can reflect illumination conditions. For example, the average irradiance can reflect the average light intensity, and the average irradiance for the detection period can be obtained by averaging the irradiance values ​​for each period. The standard deviation of irradiance can reflect the magnitude of light intensity fluctuations. The number of irradiance peaks can reflect weather conditions. For example, if there are many peaks, the weather may be cloudy. The number of irradiance peaks can be determined based on the number of irradiance values ​​in each irradiance data set that are greater than the values ​​on both sides.

[0034] S120, based on the radiation irradiance correlation data of the target user in the period to be detected, and at least two pre-determined period categories, determine the target period category to which the period to be detected belongs.

[0035] Among them, at least two pre-determined periodic categories can be determined based on the historical radiation illuminance correlation data of each period. For example, the radiation illuminance correlation data of sunny, cloudy and rainy days within a certain period of time are different. At least two periodic categories can be divided based on the radiation illuminance correlation data of each weather. The radiation illuminance correlation data corresponding to each periodic category has a certain similarity, and the radiation illuminance correlation data between each periodic category has a certain difference.

[0036] Specifically, in one feasible embodiment, the similarity between the radiation irradiance correlation data of the target user in the period to be detected and the radiation irradiance correlation data of each period category is different. The period category with the highest similarity and / or the period category that meets the preset similarity threshold can be determined as the target period category to which the period to be detected belongs.

[0037] S130, based on the power generation data of the target user in the period to be detected, and the power generation data that matches the target period category, determine whether there is any abnormality in the photovoltaic equipment of the target user.

[0038] For example, the power generation data matching the target cycle category refers to the historical power generation data of the target cycle category. For instance, if the target cycle category corresponds to sunny days, then the historical power generation data on sunny days is the power generation data matching the target cycle category.

[0039] In this embodiment, if the power generation data of the target user in the detection period is highly similar in distribution to the power generation data matching the target period category, it can be determined that the target user's photovoltaic equipment is operating normally. If the power generation data of the target user in the detection period is not highly similar in distribution to the power generation data matching the target period category, it can be determined that the target user's photovoltaic equipment is abnormal. Furthermore, an anomaly detection algorithm can be used to determine whether there are any anomalies in the target user's power generation data in the detection period that differ significantly from the power generation data matching the target period category, thereby determining whether the target user's photovoltaic equipment is abnormal.

[0040] The technical solution of this application includes: acquiring irradiance correlation data and power generation data of a target user during a testing period; determining the target period category to which the testing period belongs based on the irradiance correlation data of the target user during the testing period and at least two predetermined period categories; and determining whether the photovoltaic equipment of the target user is abnormal based on the power generation data of the target user during the testing period and power generation data matching the target period category. This technical solution determines the target period category to which the testing period belongs by using the irradiance correlation data of the target user during the testing period, and then determines whether the photovoltaic equipment of the target user is abnormal based on the power generation data of the target user during the testing period and the power generation data matching the target period category. This solves the problem that staff can only discover abnormalities in photovoltaic equipment after a significant decrease in power generation. This solution can promptly detect abnormal photovoltaic equipment, ensuring the power generation efficiency of users.

[0041] Example 2

[0042] Figure 2 This is a flowchart of a photovoltaic anomaly detection method provided in Embodiment 2 of this application. This embodiment of the application specifies the determination process of each cycle category based on the above embodiment.

[0043] like Figure 2 As shown, the method in this embodiment of the application specifically includes the following steps:

[0044] S210: Obtain radiation irradiance correlation data and power generation data of the target user during the detection period.

[0045] S220, based on the radiation irradiance correlation data of the target user in the period to be detected, and at least two predetermined period categories, determine the target period category to which the period to be detected belongs.

[0046] In this embodiment of the application, optionally, the process of determining the at least two periodic categories includes steps A1-A2:

[0047] Step A1: Determine the initial values ​​of the parameters of the expectation maximization algorithm model based on the historical irradiance correlation data of the target user over at least two historical periods.

[0048] Step A2: Based on the historical irradiance correlation data for each historical period and the initial parameter values ​​of the expectation-maximization algorithm model, Gaussian mixture clustering is performed to obtain at least two period categories.

[0049] In this scheme, Gaussian mixture clustering is used to obtain at least two periodic categories for the target user's historical irradiance data over at least two historical periods. During the Gaussian mixture clustering process, it can be assumed that there are k Gaussian distributions (usually referred to as k clusters). The specific value of k can be determined based on the actual situation. For example, if weather conditions are distinguished as sunny, cloudy, overcast, and rainy, then the number of Gaussian distributions k equals 4.

[0050] Furthermore, the Gaussian mixture model can be expressed as:

[0051]

[0052] Where k is the number of Gaussian distributions, α k μ is the weighting coefficient. k For the mean, ∑ k Let θ be the covariance matrix, and θ be the parameters of the Gaussian mixture model, where θ = (α1, ..., α2). k μ1,…,μ k ,∑1,…,∑ k x represents the historical irradiance correlation data of the target user over at least two historical periods, and xj represents the irradiance correlation data of the target user over the period to be detected.

[0053] Specifically, based on the historical irradiance correlation data of the target user over at least two historical periods, the initial values ​​of the parameters of the expectation-maximization algorithm model are determined. Then, the weighting coefficients, mean, and covariance matrix in the Gaussian mixture model are obtained through the expectation-maximization algorithm, thereby completing Gaussian mixture clustering and obtaining at least two period categories.

[0054] In this embodiment of the application, optionally, the parameters of the expectation maximization algorithm model include weighting coefficients, mean, and covariance matrix.

[0055] The weighting coefficients, mean, and covariance matrix of the expected value maximization algorithm model correspond to the Gaussian mixture model, so that the values ​​of the weighting coefficients, mean, and covariance matrix of the Gaussian mixture model can be obtained through the expected value maximization algorithm.

[0056] In this embodiment of the application, optionally, the initial values ​​of the parameters of the expected maximization algorithm model are determined based on the historical irradiance correlation data of the target user over at least two historical periods, including steps B1-B3:

[0057] Step B1: The initial value of the weighting coefficient is determined as the ratio of the number of cycles in the target cycle category to the total number of cycles in all cycle categories.

[0058] It should be noted that steps B1-B3 can be executed in any order or simultaneously, and the execution order is not limited in this embodiment.

[0059] For example, if the total number of cycles for each cycle category is 4, with sunny days accounting for 668 cycles, rainy days for 1457 cycles, cloudy days for 557 cycles, and partly cloudy days for 1396 cycles, then the initial value of the weighting coefficient α1-k is:

[0060] α1-k=(0.16, 0.35, 0.14, 0.35).

[0061] Step B2, the initial value of the mean is determined to be at least one of the following: the average of the average irradiance of each historical period corresponding to the target period category, the average of the standard deviation of irradiance of each historical period corresponding to the target period category, the average of the maximum irradiance of each historical period corresponding to the target period category, and the average of the number of irradiance peaks of each historical period corresponding to the target period category.

[0062] For example, if the total number of periods for each period category is 4, corresponding to sunny, cloudy, overcast, and rainy days respectively, then the initial value of the mean corresponding to sunny days is μ1, the initial value of the mean corresponding to cloudy days is μ2, the initial value of the mean corresponding to overcast days is μ3, and the initial value of the mean corresponding to rainy days is μ4. Furthermore, the initial value of μ1 for the mean corresponding to sunny days can be expressed as:

[0063] μ1 = (average of the average irradiance values ​​for each historical period corresponding to a sunny day, average of the standard deviations of irradiance for each historical period corresponding to a sunny day, average of the maximum irradiance values ​​for each historical period corresponding to a sunny day, average of the number of irradiance peaks for each historical period corresponding to a sunny day). Furthermore, the expressions for the other period categories are similar to those for the sunny day, and will not be repeated in the embodiments of this application.

[0064] Step B3: The initial value of the covariance matrix is ​​determined to be at least one of the following: the variance of the average irradiance of each historical period corresponding to the target period category, the variance of the standard deviation of irradiance of each historical period corresponding to the target period category, the variance of the maximum irradiance of each historical period corresponding to the target period category, and the variance of the number of irradiance peaks of each historical period corresponding to the target period category.

[0065] For example, if the total number of periods for each period category is 4, corresponding to sunny, cloudy, overcast, and rainy days respectively, then the initial value of the covariance matrix corresponding to sunny days is Σ1, the initial value of the covariance matrix corresponding to cloudy days is Σ2, the initial value of the covariance matrix corresponding to overcast days is Σ3, and the initial value of the covariance matrix corresponding to rainy days is Σ4. Furthermore, the initial value of the mean corresponding to sunny days, Σ1, can be expressed as:

[0066] Σ1 = (variance of the average irradiance value for each historical period corresponding to a sunny day, variance of the standard deviation of irradiance for each historical period corresponding to a sunny day, variance of the maximum irradiance value for each historical period corresponding to a sunny day, variance of the number of irradiance peaks for each historical period corresponding to a sunny day). Furthermore, the expressions for the other period categories are similar to those for the sunny day, and will not be repeated in the embodiments of this application.

[0067] This scheme, through the above settings, obtains the initial parameter values ​​of the Expectation-Maximization (EM) algorithm model. It then iterates using the Expectation-Maximization algorithm to determine the values ​​of the weighting coefficients, mean, and covariance matrix. The further iterative process is as follows:

[0068] Let the initial value of θ be θ (0) for:

[0069] θ (0) =(α1) (0) ,…,α k (0) μ1 (0) ,…,μ k (0) ,∑1 (0) ,…,∑ k (0) );

[0070] At the t-th iteration:

[0071] θ (t) =(μ1) (t) ,…,μ k (t) ,∑1 (t) ,…,∑ k (t) );

[0072] At the (t+1)th iteration:

[0073]

[0074]

[0075]

[0076]

[0077] Where N is the total number of historical periods, N k N refers to the number of historical periods of the target period. k The following conditions must be met:

[0078]

[0079] Furthermore, the iteration stops when the Q function reaches its maximum value:

[0080]

[0081] Furthermore, ε can be set according to the actual situation, and iteration can stop when the following condition is met: |Q(θ) (t+1) ,θ (t) )-Q(θ (t) ,θ (t-1) )|<ε.

[0082] In this embodiment of the application, optionally, the target period category to which the period to be detected belongs is determined based on the radiation irradiance correlation data of the target user in the period to be detected and at least two predetermined period categories, including steps C1-C2:

[0083] Step C1: Based on Bayesian principles and the radiation correlation data of the target user in the period to be detected, determine the probability that the period to be detected belongs to each period category.

[0084] Step C2: If the probability that the period to be detected belongs to the target period category meets the preset probability condition, then the target period category is determined as the target period category to which the period to be detected belongs.

[0085] For example, the probability that the period to be detected belongs to the i-th period category can be expressed as:

[0086]

[0087] Furthermore, in one feasible embodiment, the preset probability condition may be: determining the periodic category with the highest probability among the probabilities of the period to be detected belonging to each periodic category as the target periodic category to which the period to be detected belongs. In another feasible embodiment, the preset probability condition may be: determining the periodic category to which the period to be detected belongs that satisfies a preset probability threshold among the probabilities of the period to be detected belonging to each periodic category as the target periodic category to which the period to be detected belongs. In yet another feasible embodiment, the preset probability condition may be: determining the periodic category to which the period to be detected belongs that satisfies a preset probability threshold and has the highest probability among the probabilities of the period to be detected belonging to each periodic category as the target periodic category to which the period to be detected belongs.

[0088] S230, based on the anomaly factor algorithm and the power generation data matching the target period category, determine whether there are any abnormal time points in the power generation data of the period to be detected.

[0089] Specifically, this application employs an anomaly factor algorithm to determine whether there are abnormal time points in the power generation data of the period to be detected. This method offers the advantages of accurate judgment results and the ability to set judgment parameters according to actual conditions. For example, the power generation data matching the target period category is represented in a coordinate system, where the horizontal axis can be the acquisition time and the vertical axis can be the power generation. The power generation data of the period to be detected is then placed in the same coordinate system, and the anomaly factor algorithm is used to determine whether the power generation data of the period to be detected represents an abnormal time point in the power generation data matching the target period category.

[0090] For example, the reachable distance between two points (point P and point O) in the power generation data matching the target period category and the power generation data of the period to be detected is:

[0091] reach-dist MinPts(p,o) =max{k-distance(o),d(p,o)};

[0092] The local reachability density of point P in the power generation data of the period to be tested is:

[0093]

[0094] The local anomaly factor of p is:

[0095] Furthermore, the anomaly factor algorithm is an existing algorithm, and will not be described in detail in the embodiments of this application.

[0096] S240, if there are abnormal time points in the power generation data of the period to be detected, it is determined that the photovoltaic equipment of the target user is abnormal.

[0097] In this embodiment of the application, optionally, determining whether there are abnormal time points in the power generation data of the period to be detected based on the anomaly factor algorithm and the power generation data matching the target period category includes: calculating the local anomaly factor of the power generation data at each time point of the period to be detected and the power generation data at each time point of the target period category based on the anomaly factor algorithm; determining whether there are abnormal time points in the power generation data of the period to be detected based on the local anomaly factor of each time point; the existence of abnormal time points in the power generation data of the period to be detected includes: if the absolute value of the local anomaly factor of the target time point is determined to be greater than or equal to 1, then it is determined that there are abnormal time points in the power generation data of the period to be detected.

[0098] For example, the local anomaly factors of the power generation data at each time point of the period to be tested and the power generation data at each time point of the target period category are calculated respectively. If there are data in the power generation data at each time point of the period to be tested where the absolute value of the local anomaly factor is greater than or equal to 1, then it is determined that there are abnormal time points in the power generation data of the period to be tested, and it can be determined that the photovoltaic equipment of the target user is abnormal.

[0099] Example 3

[0100] Figure 3 This is a schematic diagram of a photovoltaic anomaly detection device provided in Embodiment 3 of this application. This device can execute the photovoltaic anomaly detection method provided in any embodiment of this invention, and possesses the corresponding functional modules and beneficial effects for executing the method. For example... Figure 3 As shown, the device includes:

[0101] Data acquisition module 310 is used to acquire radiation irradiance correlation data and power generation data of the target user during the detection period;

[0102] The target cycle category determination module 320 is used to determine the target cycle category to which the test cycle belongs based on the radiation irradiance correlation data of the target user in the test cycle and at least two predetermined cycle categories.

[0103] The anomaly detection module 330 is used to determine whether there is an anomaly in the photovoltaic equipment of the target user based on the power generation data of the target user in the period to be detected and the power generation data that matches the target period category.

[0104] Optionally, the irradiance correlation data includes at least one of the following: average irradiance, standard deviation, maximum irradiance, and number of peaks.

[0105] Optionally, the device further includes:

[0106] The parameter initial value determination module is used to determine the initial values ​​of the parameters of the expectation maximization algorithm model based on the historical irradiance correlation data of the target user in at least two historical periods.

[0107] The Gaussian mixture clustering module is used to perform Gaussian mixture clustering based on historical irradiance correlation data for each historical period and the initial values ​​of the parameters of the expectation-maximization algorithm model, to obtain at least two period categories.

[0108] Optionally, the parameters of the expectation-maximization algorithm model include weighting coefficients, mean, and covariance matrix;

[0109] The Gaussian mixture clustering module includes:

[0110] The initial value determination unit for weighting coefficients is used to determine the initial value of the weighting coefficients as the ratio of the number of cycles in the target cycle category to the total number of cycles in all cycle categories.

[0111] The mean initial value determination unit is used to determine the initial value of the mean as at least one of the following: the average value of the average irradiance of each historical period corresponding to the target period category, the average value of the standard deviation of irradiance of each historical period corresponding to the target period category, the average value of the maximum irradiance of each historical period corresponding to the target period category, and the average value of the number of irradiance peaks of each historical period corresponding to the target period category.

[0112] The covariance matrix initial value determination unit is used to determine the initial value of the covariance matrix as at least one of the following: the variance of the average irradiance value of each historical period corresponding to the target period category, the variance of the standard deviation of irradiance of each historical period corresponding to the target period category, the variance of the maximum irradiance value of each historical period corresponding to the target period category, and the variance of the number of irradiance peaks of each historical period corresponding to the target period category.

[0113] Optionally, the target cycle category determination module 320 includes:

[0114] The probability determination unit is used to determine the probability that the period to be detected belongs to each period category based on Bayesian principles and the radiation illuminance correlation data of the target user in the period to be detected.

[0115] The target period category determination unit is used to determine the target period category to which the period to be detected belongs if the probability of determining that the period to be detected belongs to the target period category meets a preset probability condition.

[0116] Optionally, the anomaly detection module 330 includes:

[0117] An abnormal time point judgment unit is used to determine whether there are abnormal time points in the power generation data of the period to be detected based on the abnormal factor algorithm and the power generation data that matches the target period category.

[0118] An anomaly detection unit is used to determine that the photovoltaic equipment of the target user is abnormal if there are abnormal time points in the power generation data of the period to be detected.

[0119] Optional, the abnormal time point judgment unit includes:

[0120] The local anomaly factor calculation subunit is used to calculate the local anomaly factors of the power generation data at each time point of the period to be detected and the power generation data at each time point of the target period category, respectively, according to the anomaly factor algorithm.

[0121] The abnormal time point judgment subunit is used to determine whether there are abnormal time points in the power generation data of the period to be detected based on the local abnormal factors at each time point.

[0122] The anomaly detection unit includes:

[0123] The abnormal time point determination subunit is used to determine that there is an abnormal time point in the power generation data of the period to be detected if the absolute value of the local abnormal factor of the target time point is greater than or equal to 1.

[0124] The photovoltaic anomaly detection device provided in this application embodiment can execute the photovoltaic anomaly detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0125] Example 4

[0126] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0127] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0128] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0129] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as methods for detecting photovoltaic anomalies.

[0130] In some embodiments, the photovoltaic anomaly detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the photovoltaic anomaly detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the photovoltaic anomaly detection method by any other suitable means (e.g., by means of firmware).

[0131] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0132] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0133] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0134] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0135] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0136] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0137] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0138] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting photovoltaic anomalies, characterized in that, include: Obtain radiation irradiance correlation data and power generation data of the target user during the period to be detected; Based on the radiation irradiance correlation data of the target user in the period to be detected, and at least two pre-determined period categories, determine the target period category to which the period to be detected belongs; Based on the power generation data of the target user during the detection period, and the power generation data matching the target period category, determine whether the photovoltaic equipment of the target user is abnormal; Based on the radiation irradiance correlation data of the target user in the period to be detected, and at least two pre-determined period categories, the target period category to which the period to be detected belongs is determined, including: Based on Bayesian principles and the radiation correlation data of the target user in the period to be detected, the probability of the period to be detected belonging to each period category is determined. If the probability that the period to be detected belongs to the target period category meets the preset probability condition, then the target period category is determined as the target period category to which the period to be detected belongs. The preset probability condition is at least one of the following: the periodic category with the highest probability, the periodic category with a probability reaching a preset probability threshold, or the periodic category that simultaneously satisfies both the highest probability and the preset probability threshold. The radiation irradiance correlation data includes at least one of the following: mean, standard deviation, maximum value, and number of peaks of radiation irradiance; The process for determining the at least two periodic categories includes: Based on the historical irradiance correlation data of the target user over at least two historical periods, determine the initial values ​​of the parameters of the expectation maximization algorithm model; Based on the historical irradiance correlation data for each historical period and the initial values ​​of the parameters of the expectation-maximization algorithm model, Gaussian mixture clustering is performed to obtain at least two period categories. The parameters of the expectation-maximization algorithm model include weighting coefficients, mean, and covariance matrix; Based on historical irradiance correlation data of the target user over at least two historical periods, determine the initial values ​​of the parameters for the expectation maximization algorithm model, including: The initial value of the weighting coefficient is determined as the ratio of the number of periods in the target periodic category to the total number of periods in all periodic categories; The initial value of the mean is determined to be at least one of the following: the average of the average irradiance of each historical period corresponding to the target period category, the average of the standard deviation of irradiance of each historical period corresponding to the target period category, the average of the maximum irradiance of each historical period corresponding to the target period category, and the average of the number of irradiance peaks of each historical period corresponding to the target period category. The initial value of the covariance matrix is ​​determined to be at least one of the following: the variance of the average irradiance of each historical period corresponding to the target period category, the variance of the standard deviation of irradiance of each historical period corresponding to the target period category, the variance of the maximum irradiance of each historical period corresponding to the target period category, and the variance of the number of irradiance peaks of each historical period corresponding to the target period category.

2. The method according to claim 1, characterized in that, Based on the power generation data of the target user during the detection period, and the power generation data matching the target period category, determine whether the target user's photovoltaic equipment is abnormal, including: Based on the anomaly factor algorithm and the power generation data matching the target period category, determine whether there are any abnormal time points in the power generation data of the period to be detected. If there are abnormal points in the power generation data of the period to be tested, it is determined that the photovoltaic equipment of the target user is abnormal.

3. The method according to claim 2, characterized in that, Based on the anomaly factor algorithm and the power generation data matching the target period category, determine whether there are any anomalous time points in the power generation data of the period to be detected, including: Based on the anomaly factor algorithm, the local anomaly factors of the power generation data at each time point of the period to be detected and the power generation data at each time point of the target period category are calculated respectively. Based on the local anomaly factors at each time point, determine whether there are any abnormal time points in the power generation data of the period to be detected; The power generation data for the period to be tested contains abnormal time points, including: If the absolute value of the local anomaly factor at the target time point is greater than or equal to 1, then it is determined that there is an anomaly time point in the power generation data of the period to be detected.

4. A photovoltaic anomaly detection device, used to perform the photovoltaic anomaly detection method as described in any one of claims 1-3, characterized in that, include: The data acquisition module is used to acquire radiation irradiance correlation data and power generation data of the target user during the detection period; The target cycle category determination module is used to determine the target cycle category to which the test cycle belongs based on the radiation irradiance correlation data of the target user in the test cycle and at least two pre-determined cycle categories. The anomaly detection module is used to determine whether there is an anomaly in the photovoltaic equipment of the target user based on the power generation data of the target user in the period to be detected and the power generation data that matches the target period category.

5. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the photovoltaic anomaly detection method according to any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the photovoltaic anomaly detection method according to any one of claims 1-3.

Images