A photovoltaic power station power generation monitoring system based on edge computing

Abstract

The present invention relates to the technical field of photovoltaic power generation efficiency adaptive regulation, and relates to a photovoltaic power station power generation monitoring system based on edge computing. The method executed by the system includes: acquiring temperature data of photovoltaic panels; clustering the data; for a class of photovoltaic panels, finding a number of first photovoltaic panels with the lowest power generation efficiency, in response to the number of first photovoltaic panels being greater than a set number threshold, then for a first photovoltaic panel, determining an initial step length and a second step length, the value of the initial step length is positively correlated with the difference between its power generation efficiency and the maximum power generation efficiency, , is the th step length, is a natural constant, is an attenuation factor, is the th power increase, and in response to the output power no longer increasing, stopping the adjustment; if there is a difference between the power generation efficiency of the adjusted first photovoltaic panel and the maximum power generation efficiency of its class that is greater than or equal to the set alarm threshold, an alarm is given, thereby improving the accuracy of the power generation efficiency after the adjustment is completed.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation efficiency adaptive regulation. The present invention relates to a photovoltaic power station power generation monitoring system based on edge computing. Background Art

[0002] With the development of new energy sources such as photovoltaics, intelligent monitoring of photovoltaic power stations has attracted more and more attention. Monitoring photovoltaic power stations based on disturbance observation methods can improve the efficiency of photovoltaic power generation.

[0003] Photovoltaic power plants are highly complex: Modern photovoltaic power plants are usually composed of a large number of photovoltaic modules, inverters and monitoring equipment. Large-scale photovoltaic power plants make real-time monitoring and management of power generation data more complicated. There may be data processing delay issues: Traditional monitoring systems usually transmit data to a central server for processing, which may lead to data transmission delays and poor real-time monitoring effects.

[0004] The significance of the photovoltaic power station power generation monitoring system based on edge computing lies in: compared with the central server, using edge computing node devices close to the data source to process data can reduce data transmission delays; by processing data on edge computing node devices, the dependence on the central server can be reduced and the stability of the monitoring system can be improved; real-time analysis of data can detect and locate system faults more quickly and improve the maintenance efficiency of the monitoring system.

[0005] Related prior art, such as the patent document with authorization announcement number CN101635540B, discloses a tracking method for a photovoltaic power generation maximum power point tracking device, which uses a perturbation observation method to improve photovoltaic power generation efficiency. However, since the perturbation step size of the traditional perturbation observation method is fixed, it may lead to a large difference between the output voltage after adjustment calculated using the traditional perturbation observation method and the output voltage corresponding to the maximum power point, that is, the accuracy of the output voltage after adjustment is poor. Summary of the invention

[0006] In order to solve the technical problem that there is a large difference between the output voltage after adjustment calculated using the traditional disturbance observation method and the output voltage corresponding to the maximum power point, the present invention proposes a photovoltaic power station power generation monitoring system based on edge computing.

[0007] The present invention provides a photovoltaic power station power generation monitoring system based on edge computing, including an edge computing node, the edge computing node including: a processor and a memory, the memory storing computer program instructions, when the computer program instructions are executed by the processor, the following method steps are implemented:

[0008] Get the temperature data of photovoltaic panels;

[0009] Clustering the temperature data of each photovoltaic panel to classify all photovoltaic panels; for a type of photovoltaic panels, calculating the power generation efficiency of each photovoltaic panel, finding a number of first photovoltaic panels with the lowest power generation efficiency, and adjusting the power generation efficiency of the first photovoltaic panels; wherein, in response to the number of the first photovoltaic panels being greater than a set number threshold, then: for a first photovoltaic panel, determining an initial step size and a second step size using an improved perturbation observation method;

[0010]

[0011] The subsequent step length is determined according to the above formula, where , , Respectively , Second step length, is a natural constant, is the attenuation factor, , Respectively , The power increase amount is determined for each iteration, and in response to the output power no longer increasing, the adjustment is stopped, and the power generation efficiency corresponding to the iteration is determined;

[0012] If the difference between the power generation efficiency of at least one adjusted first photovoltaic panel and the maximum power generation efficiency of the photovoltaic panels of the same type is greater than or equal to the set alarm threshold, a maintenance alarm is issued.

[0013] The larger it is, the more likely it is that the output voltage corresponding to the current step size of the first photovoltaic panel is closer to the output voltage corresponding to the maximum power point. The step size of the next iteration should be smaller so that the difference between the output voltage after adjustment and the output voltage corresponding to the maximum power point is smaller, that is, the adjustment accuracy is improved.

[0014] Optionally, a difference between the power generation efficiency of the first photovoltaic panel and a maximum power generation efficiency of the first type of photovoltaic panel is greater than a set difference threshold.

[0015] The first photovoltaic panel is limited so that the photovoltaic panel with a smaller difference from the maximum power generation efficiency may not adjust the power generation efficiency to reduce the amount of calculation.

[0016] Optionally, the calculation formula of the initial step length is:

[0017]

[0018] In the formula, is the initial step size, is the maximum power generation efficiency of the photovoltaic panel of the type mentioned above, is the power generation efficiency of the first photovoltaic panel, U is the current output voltage of the first photovoltaic panel, is the current output voltage of the photovoltaic panel with the highest power generation efficiency among the photovoltaic panels of the type, is the current output voltage of the photovoltaic panel with the lowest power generation efficiency among the photovoltaic panels of the type, and y is the set division threshold.

[0019] The larger it is, the larger the initial step size should be to increase the speed of adjusting the power generation efficiency.

[0020] The role of is to adaptively adjust the baseline value of the initial step length. The function of is to control the sign of the step size, that is, to control the direction of voltage adjustment.

[0021] Optionally, the second step length is the same as the initial step length.

[0022] The purpose is to speed up the adjustment as much as possible. The second step length can also be set by yourself.

[0023] Optionally, the calculation formula for the power generation efficiency of each photovoltaic panel is:

[0024]

[0025] In the formula, is the power generation efficiency of the t-th photovoltaic panel in the s-th class, is the area of ​​the t-th photovoltaic panel, , and are respectively the current output voltage, current output current and current solar radiation intensity of the t-th photovoltaic panel.

[0026] The power generation efficiency is calculated through the current data of each photovoltaic panel to improve the accuracy of subsequent power generation efficiency adjustments, which is conducive to improving economic benefits.

[0027] Optionally, cluster the temperature data of each photovoltaic panel, including:

[0028] Determine the temperature sequence of each photovoltaic panel and cluster the temperature sequences of each photovoltaic panel;

[0029] The calculation formula for the distance between temperature series in the clustering algorithm is:

[0030]

[0031] In the formula, is the distance between the temperature sequence of the i-th photovoltaic panel among all photovoltaic panels and the temperature sequence of the j-th photovoltaic panel among all photovoltaic panels, is a function that uses the DTW algorithm to calculate the DTW distance between temperature series. is the temperature sequence of the i-th photovoltaic panel, is the temperature sequence of the j-th photovoltaic panel.

[0032] Even if the lengths of the two temperature sequences are different, the DTW algorithm can be used to calculate the DTW distance between the two temperature sequences.

[0033] Optionally, cluster the temperature data of each photovoltaic panel, including:

[0034] Cluster the current temperature data of each photovoltaic panel.

[0035] Optionally, the clustering algorithm is a k-means clustering algorithm.

[0036] Optionally, in response to the number of the first photovoltaic panels being not greater than a set number threshold, the power generation efficiency of the first photovoltaic panels is adjusted using an incremental conductance method.

[0037] Beneficial effects of the present invention:

[0038] The present invention adjusts the output voltage of the photovoltaic panel with the lowest power generation efficiency in the same category by comparing the power generation efficiency of photovoltaic panels of the same category to improve the power generation efficiency. Specifically, the step size is adaptively adjusted according to the difference between the power generation efficiency of the photovoltaic panel whose power generation efficiency is to be adjusted and the maximum power generation efficiency of the photovoltaic panels of the same category, and the difference in the adjacent power increase. The effect is to speed up the adjustment speed and improve the adjustment accuracy (that is, to improve the accuracy of adjusting the output voltage or power generation efficiency of the photovoltaic panel with lower power generation efficiency, so that the adjusted output voltage is closer to the output voltage corresponding to the maximum power point).

[0039] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0041] Figure 1 is a flowchart schematically illustrating a method step performed by a photovoltaic power station power generation monitoring system based on edge computing according to an embodiment of the present invention;

[0042] Figure 2 is a schematic diagram schematically showing a power-voltage characteristic curve of a photovoltaic panel in an embodiment of the present invention;

[0043] Figure 3 The figure schematically shows a structural block diagram of a photovoltaic power station power generation monitoring system based on edge computing according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations appearing in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as S1, S2, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that if descriptions such as "first", "second", "A1", "B1" and the like appear in this article, then their role is to distinguish different messages, devices, modules, etc., and does not represent the order of precedence, nor does it limit "A1", "B1", "first" and "second" to be different types; in other words, their role is only to distinguish the described objects, and does not have any order or technical meaning. For example: the first feature of an image is the feature of the image, wherein the first has no technical meaning and is only used to distinguish objects. The role of adding "first" includes: facilitating narration, understanding and explanation, and facilitating citing different objects, which can make the article more concise and clear. For example: the first feature and the second feature are different features.

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0046] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0047] The perturbation step size of the traditional perturbation observation method is fixed. If the step size is too large, the system may not be able to accurately track the maximum power point, while if the step size is too small, the response speed of the system may be reduced. Based on this, the present invention proposes a photovoltaic power station power generation monitoring system based on edge computing to solve the above problems. When adjusting the power generation efficiency of the photovoltaic panel, the present invention adaptively adjusts the step size (i.e., the voltage perturbation step size) according to the change in the output power of the photovoltaic panel to improve the accuracy of tracking the maximum power point.

[0048] The present invention controls the photovoltaic power generation efficiency through edge computing nodes.

[0049] Figure 1FIG. 1 is a flowchart schematically showing a method step performed by a photovoltaic power station power generation monitoring system based on edge computing according to an embodiment of the present invention. Figure 1 The specific instructions are as follows:

[0050] S1: Obtain photovoltaic panel related data, including photovoltaic panel temperature data.

[0051] In one embodiment, a data set of each photovoltaic panel is obtained, the data set includes data points, the data points include temperature data, output voltage, output current and solar radiation intensity, and the temperature sequence of each photovoltaic panel includes temperature data of the corresponding photovoltaic panel.

[0052] In one embodiment, a voltage sensor is used to collect the output voltage of the photovoltaic panel, a current sensor is used to collect the output current of the photovoltaic panel, a temperature sensor is used to collect the temperature of the photovoltaic panel, and a solar radiometer is used to obtain the solar radiation intensity.

[0053] The implementer can set the data collection time interval by himself. The collection time interval can be 10 seconds as an empirical value. The implementer can set the number of data points in each data set by himself, which can be 50 as an empirical value.

[0054] In one embodiment, the data in each data set has the same collection start time and the same collection end time, and the data included in the same data point has the same collection time.

[0055] In one embodiment, for example, for a photovoltaic panel, its data set is: ((A1, B1, C1, D1), (A2, B2, C2, D2)......(AN, BN, CN, DN)), where (A1, B1, C1, D1) is the first data point in the data set, A1 is temperature data, B1 is output voltage, C1 is output current, D1 is solar radiation intensity, A1, B1, C1 and D1 are collected at the same time, and the collection time intervals of adjacent data points are the same. (AN, BN, CN, DN) is the data point corresponding to the current time, such as AN, BN, CN and DN are the current temperature data, current output voltage, current output current and current solar radiation intensity of the photovoltaic panel respectively. (A1, A2......AN) is the temperature sequence corresponding to the photovoltaic panel. Wherein, "......" is an ellipsis. For another photovoltaic panel, its data set is ((AL1, BL1, CL1, DL1), (AL2, BL2, CL2, DL2) ... (ALN, BLN, CLN, DLN)), where AL1 is temperature data, BL1 is output voltage, CL1 is output current, DL1 is solar radiation intensity, and the collection time of (AL1, BL1, CL1, DL1) is the same as the collection time of (A1, B1, C1, D1). The total number of data points in the data set of the one photovoltaic panel and the other photovoltaic panel is the same.

[0056] At this point, data collection is completed.

[0057] The edge computing node is used to process the above collected data.

[0058] In one embodiment, the edge computing node pre-processes the collected data. For example, since some individual data may be missing, the missing data can be filled in according to the data around the missing data. For example, ((A1, B1, C1, D1), (B2, C2, D2), (A3, B3, C3, D3)), if A2 is missing, then A2 can be filled in with the average of A1 and A3.

[0059] S2: Cluster the temperature data of each photovoltaic panel to classify all photovoltaic panels.

[0060] Each photovoltaic panel corresponds to a temperature sequence. In one embodiment, all temperature sequences are clustered to obtain one or more clusters, thereby completing the classification of all photovoltaic panels.

[0061] In one embodiment, clustering the temperature data of each photovoltaic panel includes: clustering the temperature sequences of each photovoltaic panel, and the calculation formula of the distance between the temperature sequences in the clustering algorithm is:

[0062]

[0063] In the formula, is the distance between the temperature sequence of the i-th photovoltaic panel among all photovoltaic panels and the temperature sequence of the j-th photovoltaic panel among all photovoltaic panels, is a function that uses the DTW algorithm to calculate the DTW distance between temperature series. is the temperature sequence of the i-th photovoltaic panel, is the temperature sequence of the j-th photovoltaic panel.

[0064] The DTW algorithm is an existing technology and will not be described in detail. The reason for using the DTW algorithm to calculate the distance between temperature sequences is that when the transmission signal is weak or the acquisition fails, the length of the collected temperature sequence may be inconsistent. In this case, the DTW algorithm can be used to calculate the distance between temperature sequences.

[0065] In one embodiment, the clustering algorithm may be a k-means clustering algorithm, and the number of initial centers may be set by the implementer. The implementer may randomly select K1 temperature sequences as initial centers, and K1 may be an empirical value of 3. The k-means clustering algorithm is a prior art.

[0066] In one embodiment, the clustering algorithm may be DBSCAN density clustering, and the implementer may set the preset neighborhood radius and the minimum number of samples according to the specific scenario. DBSCAN density clustering is a prior art.

[0067] The explanation is as follows: the power generation efficiency of photovoltaic panels is related to the intensity of solar radiation, the temperature of photovoltaic panels, etc. For multiple photovoltaic panels, when the conditions such as the intensity of solar radiation and the temperature of photovoltaic panels are the same or have a small difference, the power voltage characteristic curves of each photovoltaic panel are the same or have a small difference. Therefore, it is necessary to compare the power generation efficiency of photovoltaic panels under the same environment and with small temperature differences in order to determine the power generation efficiency of each photovoltaic panel, and then adjust the output voltage of photovoltaic panels with low power generation efficiency to improve the power generation efficiency of photovoltaic panels. Conversely, if the power generation efficiency of photovoltaic panels under different environments and / or different temperatures is compared, the power generation efficiency of photovoltaic panels with low power generation efficiency may not be improved when the output voltage of photovoltaic panels with low power generation efficiency is adjusted. In other words, the photovoltaic panel with low power generation efficiency may be at or near the maximum power point because the power voltage characteristic curves of different photovoltaic panels are different.

[0068] The solar radiation intensity is the same at the same time, but the temperature of multiple photovoltaic panels at the same time may be different. Therefore, it is necessary to cluster the temperature series of photovoltaic panels so that the temperature series of photovoltaic panels with small temperature differences are clustered into one category. Among them, the temperature series can reflect the change of photovoltaic panel temperature. The temperature difference between the two photovoltaic panels corresponding to two temperature series with small DTW distance difference is small.

[0069] After clustering is completed, multiple clusters are obtained, and the temperature, solar radiation intensity, etc. of each photovoltaic panel corresponding to the same cluster are slightly different or the same.

[0070] It should be noted that the shape of the power-voltage characteristic curve of the photovoltaic panel is similar to a quadratic function image with the opening facing downward.

[0071] In another embodiment, clustering the temperature data of each photovoltaic panel includes: clustering the current temperature data of all photovoltaic panels. This method can reduce the amount of calculation.

[0072] S3: Calculate the power generation efficiency of each photovoltaic panel.

[0073] In one embodiment, the calculation formula for the power generation efficiency of each photovoltaic panel is:

[0074]

[0075] In the formula, is the power generation efficiency of the t-th photovoltaic panel in the s-th class, is the area of ​​the t-th photovoltaic panel, , and are the current output voltage, current output current and current solar radiation intensity of the t-th photovoltaic panel, respectively. In other words, , and are the output voltage, output current and solar radiation intensity of the last data point in the data set of the t-th photovoltaic panel. It should be noted that the calculated power generation efficiency is the power generation efficiency at the current moment, that is, the power generation efficiency corresponding to the current output voltage.

[0076] S4: Adjusting the power generation efficiency of the photovoltaic panels. Specifically, comparing the power generation efficiency of photovoltaic panels in the same category, when the power generation efficiency of some photovoltaic panels is low, improving the power generation efficiency of the some photovoltaic panels according to the difference between the power generation efficiency of the some photovoltaic panels and the power generation efficiency of other photovoltaic panels in the same category.

[0077] Next, we analyze the photovoltaic panels in any class. For a class of photovoltaic panels (all photovoltaic panels corresponding to a cluster), we find several first photovoltaic panels with the lowest power generation efficiency (the first photovoltaic panels are several photovoltaic panels with the lowest power generation efficiency) and adjust the power generation efficiency of the first photovoltaic panels.

[0078] The explanation is as follows: because the power generation environment and temperature of photovoltaic panels of the same type are basically the same, the power generation efficiency of all photovoltaic panels in the same type is basically the same under normal circumstances. If the power generation efficiency of a photovoltaic panel in a type is significantly different from the maximum power generation efficiency of photovoltaic panels in the type (i.e., the maximum power generation efficiency), the maximum output power of the photovoltaic panel should be adjusted, i.e., its output voltage should be adjusted to increase its power generation efficiency.

[0079] Explanation of the relationship between temperature and power generation efficiency: At lower temperatures, the electron mobility and photoelectric conversion efficiency of photovoltaic panels will be improved. However, as the temperature rises, the internal resistance of the photovoltaic material increases, and the flow of electrons in the material becomes difficult, thereby reducing the photoelectric conversion efficiency.

[0080] The implementer can set the quantity threshold according to the specific implementation scenario. For example, the quantity threshold can be an empirical value of 9.

[0081] In response to the number of the first photovoltaic panels being greater than a set number threshold, then: for a first photovoltaic panel, the improved perturbation observation method (the present solution improves the perturbation observation method) is used to determine the initial step size and the second step size, according to , determine the subsequent step length, where , , Respectively , Second step length, is a natural constant, is the attenuation factor, , Respectively , The power increase amount is times, and the output power of the photovoltaic panel is determined in each iteration. In response to the output power of the photovoltaic panel no longer increasing, the adjustment is stopped, and the power generation efficiency corresponding to the iteration and the corresponding adjusted output voltage are determined. At this point, the power generation efficiency adjustment of the first photovoltaic panel is completed.

[0082] For example, after adding the 10th disturbance step, the output power is G1 watts, where the output powers for the first 10 times are all in an increasing state. For example, G1 watt is greater than the output power corresponding to the 9th disturbance step. After adding the 11th disturbance step, the output power is G2 watts, where G2 is less than G1. Then the output voltage corresponding to the maximum power generation efficiency of this photovoltaic panel is the output voltage corresponding to G1 watt (the output voltage after adding the 10th disturbance step).

[0083] In one embodiment, in response to the number of the first photovoltaic panels being not greater than a set number threshold, the power generation efficiency of the first photovoltaic panels is adjusted using an incremental conductance method, which is a prior art.

[0084] It should be noted that the amount of computation corresponding to the incremental conductance method is large, while the amount of computation corresponding to the perturbation observation method is small.

[0085] Further explanation is as follows: and Negative correlation. The larger the value is, the more likely it is that the difference between the output voltage corresponding to this iteration and the output voltage corresponding to the maximum power point is smaller. At this time, the step size should be reduced to avoid the step size being too large, which will lead to a large difference between the final adjusted output voltage and the output voltage corresponding to the maximum power point, so as to improve the accuracy of the desired adjusted output voltage.

[0086] Further explanation is as follows: For ease of understanding, now combined with Figure 2 To explain, Figure 2 Schematic diagram schematically showing a power-voltage characteristic curve of a photovoltaic panel in an embodiment of the present invention, such as Figure 2 As shown, 201 is the maximum power point, 202 is the initial step length, 203 is the second step length, 204 is the third step length, 205 is the first power increase, 206 is the second power increase, and 207 is the third power increase. If 202=203=204, then combined with the slope of each point on the power-voltage characteristic curve, it can be seen that In fact, combined with this solution, we know that 203 is less than 204, so in this solution .

[0087] From another perspective, if If the value is larger, the step size may be larger at this time, and the step size of the next iteration should be reduced to avoid the step size being too large, which may cause the final adjusted output voltage to differ too much from the output voltage corresponding to the maximum power point.

[0088] Implementers can set the attenuation factor according to specific scenarios. For example, the attenuation factor can be ,in is the maximum value of the adjacent power increase in the historical data. The purpose is to eliminate In one embodiment, the attenuation factor may be ,in, is the adjustment factor, which can be set by the implementer as 0.15.

[0089] In one embodiment, .

[0090] In one embodiment, the photovoltaic panel with the maximum power generation efficiency among the one type of photovoltaic panels is determined, and the difference between the power generation efficiency of other photovoltaic panels in the one type of photovoltaic panels and the maximum power generation efficiency is calculated, and the difference between the power generation efficiency of the first photovoltaic panel and the maximum power generation efficiency of the one type of photovoltaic panels (the difference in this article may be the absolute value of the difference) is greater than a set difference threshold.

[0091] The implementer can set the difference threshold according to the specific implementation scenario. For example, the difference threshold can be set to an empirical value of 0.03.

[0092] In one embodiment, for the one first photovoltaic panel, in the improved perturbation observation method, the absolute value of the initial step size is positively correlated with the difference between the maximum power generation efficiency of the photovoltaic panels in this category and the power generation efficiency of the one first photovoltaic panel, and the second step size is determined based on the initial step size.

[0093] In one embodiment, the calculation formula of the initial step length is:

[0094]

[0095] In the formula, is the initial step size, is the maximum power generation efficiency of the photovoltaic panel of the type mentioned above, is the power generation efficiency of the first photovoltaic panel, U is the current output voltage of the first photovoltaic panel (the output voltage in the last data point in the corresponding data set), is the current output voltage of the photovoltaic panel with the highest power generation efficiency among the photovoltaic panels of the type, is the current output voltage of the photovoltaic panel with the lowest power generation efficiency among the photovoltaic panels of the type, and y is the set division threshold.

[0096] The following is explained: If The larger the value is, the greater the possibility is that the difference between the current output voltage of the first photovoltaic panel and the output voltage of the corresponding maximum power point is larger, and the initial step size should be larger to increase the speed at which the output voltage of the first photovoltaic panel reaches the maximum power point or the output voltage corresponding to the maximum power point.

[0097] The implementer can set the division threshold according to the specific scenario. The division threshold can be set to an empirical value of 20.

[0098] The role of is to determine the sign of the initial step size, that is, the direction of adjusting the voltage.

[0099] In another embodiment, .

[0100] In one embodiment, ,in, Adjust the value for the preset division, It can be set by the implementer according to the specific implementation scenario. Can be worth 25 experience points.

[0101] In one embodiment, Among them, if ,but The sign of is positive if ,but The sign is negative, and the implementer can set it according to the specific scenario The absolute value of .

[0102] In one embodiment, the implementer can set the initial step size according to the specific scenario.

[0103] In one embodiment, the second step size is the same as the initial step size.

[0104] In another embodiment, the second step size is 0.9 times the initial step size.

[0105] At this point, the power generation efficiency adjustment of the first photovoltaic panel is completed. Traverse the other first photovoltaic panels in the first type of photovoltaic panels to complete the power generation efficiency adjustment of the first photovoltaic panel. The power generation efficiency adjustment of photovoltaic panels in other types is the same as the principle of the above adjustment process and will not be repeated.

[0106] It should be noted that the process of processing the data to obtain the output voltage corresponding to the maximum power generation efficiency of each photovoltaic panel whose power generation efficiency is to be adjusted is performed in the edge computing node. The edge computing node is used to control the output voltage of each photovoltaic panel whose power generation efficiency is to be adjusted to be converted into the adjusted output voltage.

[0107] It should be noted that the step length is the disturbance amount (disturbance step length). In other words, the step length is a disturbance amount of the output voltage.

[0108] S5: If the difference between the power generation efficiency of at least one adjusted first photovoltaic panel and the maximum power generation efficiency of the photovoltaic panels of the same type is greater than or equal to the set alarm threshold, a maintenance alarm is issued.

[0109] Implementers can set alarm thresholds based on specific scenarios.

[0110] In one embodiment, if there is at least one photovoltaic panel that satisfies , a maintenance alarm is issued, where is the power generation efficiency of the a-th photovoltaic panel in the s-th class after power generation adjustment (i.e., the a-th first photovoltaic panel in the s-th class), is the maximum power generation efficiency of the photovoltaic panel in the sth cluster, is the comparison threshold. The implementer can set the comparison threshold according to the specific scenario. The empirical value can be 0.1.

[0111] The explanation is as follows: When there are photovoltaic panels that meet If the PV panels, inverters, batteries and other components are faulty, someone should be sent to check.

[0112] Figure 3 FIG. 1 is a schematic diagram showing a structure block diagram of a photovoltaic power station power generation monitoring system based on edge computing according to an embodiment of the present invention. Figure 3 As shown, 01 is a communication bus. The present invention also provides a photovoltaic power generation monitoring system based on edge computing, the system includes an edge computing node, the edge computing node includes a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, any of the above method steps is implemented.

[0113] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0114] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0115] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0116] Additionally, the articles "a" and "an" as used in this application and the appended claims are generally construed to mean "one or more" unless specified otherwise or clear from context to be directed to a singular form.

[0117] Where the terms "includes," "having," "having," "having," or variations thereof are used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term "comprising."

[0118] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A photovoltaic power station power generation monitoring system based on edge computing, comprising an edge computing node, wherein the edge computing node comprises: A processor and a memory, wherein the memory stores computer program instructions, wherein when the computer program instructions are executed by the processor, the following method steps are implemented: Get the temperature data of photovoltaic panels; The temperature data of each photovoltaic panel is clustered to classify all photovoltaic panels; for a type of photovoltaic panel, the power generation efficiency of each photovoltaic panel is calculated, and several first photovoltaic panels with the lowest power generation efficiency are found, and the power generation efficiency of the first photovoltaic panels is adjusted. The calculation formula of the power generation efficiency is: ； In the formula, is the power generation efficiency of the t-th photovoltaic panel in the s-th class, is the area of ​​the t-th photovoltaic panel, , and are respectively the current output voltage, current output current and current solar radiation intensity of the t-th photovoltaic panel; In response to the number of the first photovoltaic panels being greater than a set number threshold, for one first photovoltaic panel, the initial step length and the second step length are determined using the improved perturbation observation method, and the calculation formula for the initial step length is: ； In the formula, is the initial step size, is the maximum power generation efficiency of the photovoltaic panel of the type mentioned above, is the power generation efficiency of the first photovoltaic panel, U is the current output voltage of the first photovoltaic panel, is the current output voltage of the photovoltaic panel with the highest power generation efficiency among the photovoltaic panels of the type, is the current output voltage of the photovoltaic panel with the lowest power generation efficiency among the photovoltaic panels of the type, and y is the set division threshold; The second step length is the same as the initial step length; according to , determine the subsequent step length, where , , Respectively , Second step length, is a natural constant, is the attenuation factor, , Respectively , The power increase amount is determined for each iteration, and in response to the output power no longer increasing, the adjustment is stopped, and the power generation efficiency corresponding to the iteration is determined; If the difference between the power generation efficiency of at least one adjusted first photovoltaic panel and the maximum power generation efficiency of the photovoltaic panels of the same type is greater than or equal to the set alarm threshold, a maintenance alarm is issued.

2. According to the photovoltaic power station power generation monitoring system based on edge computing according to claim 1, it is characterized in that: The difference between the power generation efficiency of the first photovoltaic panel and the maximum power generation efficiency of the photovoltaic panel of the first type is greater than a set difference threshold.

3. According to the photovoltaic power station power generation monitoring system based on edge computing according to claim 1, it is characterized in that: Clustering of temperature data of each photovoltaic panel, including: Determine the temperature sequence of each photovoltaic panel and cluster the temperature sequences of each photovoltaic panel; The calculation formula for the distance between temperature series in the clustering algorithm is: ； In the formula, is the distance between the temperature sequence of the i-th photovoltaic panel among all photovoltaic panels and the temperature sequence of the j-th photovoltaic panel among all photovoltaic panels, is a function that uses the DTW algorithm to calculate the DTW distance between temperature series. is the temperature sequence of the i-th photovoltaic panel, is the temperature sequence of the j-th photovoltaic panel.

4. According to the photovoltaic power station power generation monitoring system based on edge computing according to claim 1, it is characterized in that: Clustering of temperature data of each photovoltaic panel, including: Cluster the current temperature data of each photovoltaic panel.

5. The photovoltaic power station power generation monitoring system based on edge computing according to claim 1 is characterized in that: Also includes: In response to the number of the first photovoltaic panels being not greater than a set number threshold, the power generation efficiency of the first photovoltaic panels is adjusted using an incremental conductance method.

Images