A method and system for adaptive recognition of photovoltaic string tilt orientation

Abstract

The present application relates to the technical field of photovoltaic power station intelligent operation and maintenance, and discloses a photovoltaic string inclination direction adaptive identification method and system, which comprises the following steps: obtaining historical data of all photovoltaic strings connected to each type of inverter of the photovoltaic power station and metadata of the photovoltaic power station design; the metadata comprises longitude and latitude information of the photovoltaic power station and all inclination direction combinations registered by the photovoltaic power station; the historical data comprises historical current and voltage data; based on the historical data, the photovoltaic strings in normal operation are screened out, and the power generation capacity of each photovoltaic string is calculated; the theoretical irradiation potential of all inclination direction combinations is calculated; and the power generation capacity of each photovoltaic string is matched with the theoretical irradiation potential to obtain the photovoltaic string inclination direction identification result. The present application realizes accurate identification of the photovoltaic string inclination direction by automatic matching with the existing historical data and power station metadata, and provides important basic data support for subsequent implementation of fine operation and maintenance and analysis at the string level.

Description

Technical Field

[0001] This invention relates to the field of intelligent operation and maintenance technology for photovoltaic power plants, specifically to an adaptive identification method and system for the tilt angle orientation of photovoltaic strings. Background Technology

[0002] Currently, there are two main methods for determining the tilt angle and orientation in distributed photovoltaic (PV) systems: The first method involves maintenance personnel manually measuring the tilt angle and orientation of the PV strings at specific sites using measuring equipment. However, for widely distributed and numerous PV power plants, this method is not only costly but also inefficient, making it unsuitable for online management platforms integrating a large number of PV power plants. The second method involves using scanning equipment to acquire point cloud models and orthophotos of the site, then using image detection models to determine the image's location and thus the tilt angle and orientation of each PV string in the image. This method fully utilizes intelligent measurement methods; however, the equipment is expensive and has a certain false detection rate. Both of these methods require personnel to go to the site and collect data using equipment, neglecting the data generated during inverter operation. For a large number of distributed power plants, analyzing the data generated during equipment operation offers greater economic efficiency and convenience.

[0003] Typically, photovoltaic (PV) power plants record their existing tilt angle combinations during construction, and this information is registered as part of the plant's metadata when it is connected to the management system. However, a distributed power plant may have multiple inverters, each connected to multiple strings. A current technical challenge is how to use intelligent algorithms to accurately assign tilt angles based on the recorded historical current and voltage data of the strings, ensuring that all strings are assigned a clear and accurate tilt angle. Summary of the Invention

[0004] In view of this, the present invention provides an adaptive identification method and system for the tilt angle orientation of photovoltaic strings, which solves the problem of how to determine the tilt angle orientation of photovoltaic strings without actual on-site measurement.

[0005] In a first aspect, the present invention provides an adaptive identification method for the tilt angle orientation of photovoltaic strings, the method comprising:

[0006] Acquire historical data of all photovoltaic strings connected to various types of inverters in a photovoltaic power station, as well as metadata of the photovoltaic power station design; wherein, the metadata includes: inverter model, latitude and longitude information of the photovoltaic power station, and all registered tilt angle and orientation combinations of the photovoltaic power station; the historical data includes: historical current data and historical voltage data.

[0007] Based on historical data, photovoltaic strings that are in normal operating condition are selected, and the power generation capacity of each photovoltaic string is calculated.

[0008] Calculate the theoretical irradiance potential of all tilt-orientation combinations in the metadata;

[0009] By matching the power generation capacity of each photovoltaic string with its theoretical irradiance potential, the tilt angle of the photovoltaic string is identified.

[0010] The adaptive identification method for the tilt angle orientation of photovoltaic strings provided in this invention acquires historical data of all photovoltaic strings connected to various types of inverters in a photovoltaic power station, as well as metadata of the photovoltaic power station design. It analyzes multiple key information sources to ensure the final identification result is based on comprehensive data, thus improving the accuracy of tilt angle orientation identification. Accurately identifying the tilt angle orientation of photovoltaic strings helps operation and maintenance personnel better understand whether the actual layout of each part of the power station matches the optimal light reception conditions. This allows for targeted adjustments and optimizations to unreasonable tilt angle orientations, improving the overall power generation efficiency of the photovoltaic power station and providing a strong basis for decisions regarding the long-term stable and efficient operation of the power station.

[0011] In one optional implementation, the process of calculating the power generation capacity of each photovoltaic string includes:

[0012] Based on historical data of photovoltaic strings connected to the same type of inverter operating normally, the average power of each photovoltaic string connected to the same type of inverter is calculated, and the power generation capacity of each photovoltaic string is calculated based on the average power of each photovoltaic string.

[0013] The power generation capacity data of all photovoltaic strings connected to different types of inverters are divided into multiple power generation capacity intervals according to the power generation capacity. The number of intervals is the same as the number of tilt angle combinations.

[0014] This invention calculates the average power based on historical data of photovoltaic strings operating normally with inverters of the same type, thereby determining the power generation capacity. This grouping calculation according to inverter type eliminates interference factors caused by different inverters, making the calculated average power and power generation capacity of each photovoltaic string more accurately reflect the string's own power generation characteristics, improving data reliability. The reasonably divided power generation capacity range corresponds to the number of tilt angle combinations. When matching the power generation capacity with the theoretical irradiance potential, it can more precisely and accurately find the power generation capacity range corresponding to each tilt angle combination, improving the overall matching accuracy, thus more reliably obtaining the identification result of the photovoltaic string tilt angle and optimizing the accuracy of the entire identification process.

[0015] In one optional implementation, the historical data further includes: historical irradiance data;

[0016] The process involves calculating the average power output of each photovoltaic string connected to a similar inverter based on historical data of normally operating photovoltaic strings connected to the same type of inverter, and then calculating the power generation capacity of each photovoltaic string based on its average power output. This includes:

[0017] Calculate the power value of each photovoltaic string connected to each type of inverter;

[0018] For photovoltaic strings with historical irradiance data or numerical weather forecast irradiance, the average power for all days can be obtained using the calculated power value;

[0019] For photovoltaic strings lacking historical irradiance data and numerical weather forecast irradiance, the irradiance value under theoretical sunny conditions is calculated based on the timestamp information corresponding to historical current data and historical voltage data. The number of sunny days is determined by judging the peak power and power fluctuation of a day in historical data, and the average power of the number of sunny days is calculated.

[0020] The average power of each photovoltaic string is calculated and arranged according to its value. The photovoltaic string with the highest average power connected to the same type of inverter is taken as the benchmark string.

[0021] The power generation capacity is represented by the ratio of the average power of other photovoltaic strings connected to the same type of inverter to the corresponding benchmark string.

[0022] For photovoltaic (PV) strings lacking historical irradiance data and numerical weather forecast irradiance, this invention can calculate the irradiance value under theoretical sunny conditions based on the timestamp information corresponding to historical current and voltage data. Furthermore, it determines the number of sunny days by judging peak power and power fluctuations, and finally calculates the average power of sunny days. This method demonstrates strong flexibility, enabling a relatively scientific calculation of the power generation capacity of the corresponding PV string even under the unfavorable condition of missing irradiance data. It ensures that the entire calculation process covers all PV strings without omissions due to data gaps. The PV string with the highest average power connected to the same type of inverter is used as the benchmark string. Then, the ratio of the average power of other PV strings connected to the same type of inverter to the corresponding benchmark string is used to characterize the power generation capacity. By establishing a benchmark and calculating the ratio, a relatively standardized measurement scale is provided for the power generation capacity of different PV strings, facilitating a direct comparison of the relative power generation capacity of each string under the same inverter type.

[0023] In one optional implementation, determining the number of sunny days by judging the peak power and power fluctuation of a day in historical data includes:

[0024] Obtain the peak power on day d And judge Is the power value greater than the maximum power value within a preset historical time period by a preset multiple? If so, the power peak value on day d meets the requirements.

[0025] Obtain the mean of the absolute values ​​of the first-order differences of power on day d. And judge Is it less than the mean of the absolute values ​​of the first-order differences of the minimum power within a preset historical time period, which is less than a preset multiple? If so, then the power fluctuation on day d is determined to meet the requirements.

[0026] The number of days that simultaneously meet the requirements for peak power and power fluctuation is taken as the number of sunny days.

[0027] This invention comprehensively considers two important dimensions: peak power and power fluctuation throughout the day. Under sunny conditions, solar radiation is usually relatively stable and sufficient, which causes the photovoltaic string power to exhibit a high peak value and relatively stable variation characteristics. Judging from these two aspects is more logical and rigorous than judging the actual power generation performance of the photovoltaic string under sunny conditions, and can more accurately select the number of days that meet the characteristics of sunny days.

[0028] In one alternative implementation, the theoretical irradiance potential of all tilt-orientation combinations in the computed metadata includes:

[0029] The extraterrestrial irradiance is calculated based on the latitude and longitude information of the photovoltaic power station, and the position of the sun is calculated based on the latitude and longitude information of the photovoltaic power station.

[0030] For photovoltaic strings with historical irradiance data or numerical weather forecast irradiance, the total irradiance of the tilted surface is calculated based on the historical irradiance data and time of the photovoltaic strings.

[0031] For photovoltaic strings lacking historical irradiance data and numerical weather forecast irradiance, calculate the theoretical clear-sky irradiance for the time period corresponding to historical clear days.

[0032] The total irradiance of the tilted surface for each tilt angle combination is obtained based on irradiance data, extraterrestrial irradiance, solar position, time, and tilt angle orientation.

[0033] The irradiance potential corresponding to all tilt angle combinations is sorted by numerical value, in the same way as the average power of the photovoltaic string.

[0034] This invention comprehensively considers various factors, including the latitude and longitude of the photovoltaic power station, the sun's position, irradiance data, tilt angle, and time. These factors are interrelated and all have a crucial impact on the irradiance received by the photovoltaic strings. By comprehensively incorporating and calculating these factors, the total irradiance of the tilt surface for each tilt angle combination can more scientifically and accurately reflect the actual theoretical irradiance potential, laying a solid foundation for subsequent accurate matching and tilt angle identification. The irradiance potential corresponding to all tilt angle combinations is sorted according to their numerical values, and the sorting method is the same as that used to sort the average power of the photovoltaic strings. When matching the power generation capacity of the photovoltaic strings with the theoretical irradiance potential, the same sorting method makes it easier and more intuitive to correlate the two, facilitating the quick and accurate identification of the tilt angle combination that best matches the power generation capacity of each photovoltaic string, thus improving the efficiency and accuracy of the entire tilt angle identification process.

[0035] In one optional implementation, the step of matching the power generation capacity of each photovoltaic string with its theoretical irradiance potential to obtain the photovoltaic string tilt angle identification result includes:

[0036] The power generation capacity of each photovoltaic string is sorted, and each photovoltaic string is matched with a tilt angle combination with the same irradiance potential ranking according to the sorting order;

[0037] After matching is completed, all photovoltaic strings connected to all types of inverters in the photovoltaic power station correspond to a tilt angle orientation value, and the photovoltaic string tilt angle orientation identification result is obtained.

[0038] The matching method employed in this embodiment of the invention leverages the prior prior sorting of power generation capacity and irradiance potential, enabling the two to be correlated in an ordered and corresponding manner. Since the sorting process itself is based on the scientific analysis and organization of relevant data, this sorting and matching method can accurately link photovoltaic strings with the tilt angle combination that best matches their power generation performance, greatly improving matching accuracy, reducing mismatches, and thus providing a strong guarantee for obtaining reliable tilt angle identification results.

[0039] Secondly, the present invention provides an adaptive identification system for the tilt angle orientation of photovoltaic strings, comprising:

[0040] The data acquisition module is used to acquire historical data of all photovoltaic strings of various types of inverters connected to the photovoltaic power station, as well as metadata of the photovoltaic power station design; wherein, the metadata includes: inverter model, latitude and longitude information of the photovoltaic power station, and all tilt angle and orientation combinations registered by the photovoltaic power station; the historical data includes: historical current data and historical voltage data.

[0041] The power generation capacity calculation module is used to filter out photovoltaic strings that are in normal operation based on historical data and calculate the power generation capacity of each photovoltaic string.

[0042] The irradiation data acquisition module is used to calculate the theoretical irradiation potential of all tilt-orientation combinations in the metadata;

[0043] The tilt angle orientation identification module is used to match the power generation capacity of each photovoltaic string with its theoretical irradiance potential to obtain the tilt angle orientation identification result of the photovoltaic string.

[0044] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the adaptive identification method for the tilt angle orientation of photovoltaic strings as described in the first aspect or any corresponding embodiment.

[0045] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the adaptive identification method for the tilt angle orientation of photovoltaic strings according to the first aspect or any corresponding embodiment thereof.

[0046] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the adaptive identification method for the tilt angle orientation of photovoltaic strings in the first aspect or any corresponding embodiment described above. Attached Figure Description

[0047] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0048] Figure 1 A flowchart illustrating the adaptive identification method for the tilt angle orientation of photovoltaic strings according to an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of the average total irradiance of a tilted surface over a day for different combinations of tilt angles according to an embodiment of the present invention;

[0050] Figure 3 A flowchart illustrating an adaptive identification method for the tilt angle orientation of a photovoltaic string according to a specific example of an embodiment of the present invention;

[0051] Figure 4A structural block diagram of an adaptive identification system for the tilt angle orientation of photovoltaic strings according to an embodiment of the present invention;

[0052] Figure 5 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention 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, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] Typically, photovoltaic (PV) power plants record their existing tilt angle combinations during construction, and this information is registered as part of the plant's metadata when it is connected to the management system. However, a distributed power plant may have multiple inverters, each connected to multiple strings. A current technical challenge is how to use intelligent algorithms to accurately assign tilt angles based on the recorded historical current and voltage data of the strings, ensuring that all strings are assigned a clear and accurate tilt angle.

[0055] Considering that after a large number of photovoltaic power plants are connected to the operation and management platform, it is necessary to determine the tilt angle orientation of each photovoltaic string of each inverter. This embodiment provides an adaptive identification method for the tilt angle orientation of photovoltaic strings. By processing and analyzing the historical data collected from the photovoltaic strings and matching it with existing tilt angle orientation combinations, the problem of determining the tilt angle orientation of distributed photovoltaic strings is solved. Figure 1 This is a flowchart of an adaptive identification method for the tilt angle orientation of photovoltaic strings according to an embodiment of the present invention, as shown below. Figure 1 As shown, the process includes the following steps:

[0056] S101, acquire historical data of all photovoltaic strings of various types of inverters connected to the photovoltaic power station, as well as metadata of the photovoltaic power station design; among which, metadata includes: inverter model, latitude and longitude information of the photovoltaic power station, all tilt angle and orientation combinations registered by the photovoltaic power station, and historical data, including: historical current data and historical voltage data.

[0057] Specifically, distributed photovoltaic (PV) power stations typically employ multiple inverters, each connected to multiple PV strings. A PV string is a circuit unit formed by connecting PV modules (solar panels) in series. In this embodiment of the invention, the PV power station includes M types of inverters, with N types of inverters of the i-th type. i The number of strings for each inverter of the i-th type is S. iLet the sequence length collected for each photovoltaic string be the same and denoted as T. Then, the sequence of current and voltage of the k-th string of the j-th inverter of the i-th type, with a step size of T, can be expressed as:

[0058] I i,j,k ={I i,j,k (1),…,I i,j,k (T)};

[0059] V i,j,k ={V i,j,k (1),…,V i,j,k (T)};

[0060] Where i represents the inverter type, i = {1, 2, ..., M}, and there are M types in total; j represents the j-th inverter, j = {1, 2, ..., N}. i}, where N represents the number of inverters; k represents the k-th photovoltaic string, k = {1, 2, ..., S} i}, where S represents the number of photovoltaic strings; T represents the length of the sequence.

[0061] In the metadata of this invention embodiment, the latitude and longitude information of the photovoltaic power station is represented as (lon, lat), and all registered tilt angle orientation combinations of the photovoltaic power station are represented as {(A i B i Let A be a subset of the subsets ... i and B i Let represent the tilt angle and orientation of the i-th combination, respectively. The total number of combinations of tilt angle and orientation is G.

[0062] S102, based on historical data, select photovoltaic strings that are in normal operating condition and calculate the power generation capacity of each photovoltaic string.

[0063] In order to achieve accurate tilt angle matching in this embodiment of the invention, a fault detection algorithm based on historical data must be used to ensure that the used photovoltaic strings are fault-free. Faulty inverters are not included in the calculation. The fault detection algorithm is a relatively mature existing algorithm, and no specific limitations are imposed here. The process of calculating the power generation capacity of each photovoltaic string includes:

[0064] S1021, Based on historical data of photovoltaic strings that are normally operating in the same type of inverter, calculate the average power of each photovoltaic string connected to the same type of inverter, and calculate the power generation capacity of each photovoltaic string based on the average power of each photovoltaic string.

[0065] Specifically, first, calculate the power value of each photovoltaic string connected to each type of inverter. There are N inverters of model i. i There are N photovoltaic strings in total. i ×S iWe select a series of photovoltaic strings with actual current and calculate the point-by-point power value of each string. For the k-th string of the j-th inverter, the corresponding power is: P i,j,k =I i,j,k V i,j,k The calculation of the average power of a photovoltaic string is divided into two cases:

[0066] ① When the power station has historical measured irradiance or numerical weather forecast irradiance (including direct irradiance, diffuse irradiance, and total horizontal irradiance), the corresponding historical current and voltage data can be used directly. In this case, the average power of the string data over all days can be calculated directly:

[0067] ② In the absence of historical measured irradiance and numerical weather forecast irradiance at the power station, the theoretical irradiance value under clear sky conditions can be calculated based on the timestamp information corresponding to historical current and voltage data. To achieve a higher degree of matching, only data under clear sky conditions are used as a reference in the calculation process, rather than data under all meteorological conditions.

[0068] For photovoltaic (PV) strings lacking historical irradiance data and numerical weather forecast irradiance, this invention can calculate the irradiance value under theoretical sunny conditions based on the timestamp information corresponding to historical current and voltage data. Furthermore, it determines the number of sunny days by judging peak power and power fluctuations, and finally calculates the average power of sunny days. This method demonstrates strong flexibility, enabling the relatively scientific calculation of the power generation capacity of the corresponding PV strings even under the unfavorable condition of missing irradiance data. It ensures that the entire calculation process covers all PV strings and avoids omissions due to data gaps.

[0069] In this embodiment of the invention, sunny day data is filtered by judging two indicators: peak power and power fluctuation in historical data for a single day. The process is as follows:

[0070] 1. Obtain the peak power on day d. And judge Is the power value greater than the maximum power value within a preset historical time period by a preset multiple? If so, the power peak value on day d meets the requirements.

[0071] 2. Obtain the mean of the absolute values ​​of the first-order differences in power on day d. And judge Is it less than the mean of the absolute values ​​of the first-order differences of the minimum power within a preset historical time period, which is less than a preset multiple? If so, then the power fluctuation on day d is determined to meet the requirements.

[0072] 3. The number of days that simultaneously meet the requirements for peak power and power fluctuation is taken as the number of sunny days.

[0073] This invention comprehensively considers two important dimensions: peak power and power fluctuation throughout the day. Under sunny conditions, solar radiation is typically relatively stable and abundant, resulting in photovoltaic (PV) strings exhibiting high peak power and relatively stable fluctuations. Judging from these two aspects aligns more closely with the actual power generation performance of PV strings on sunny days, making the logic more reasonable and rigorous, and enabling more accurate selection of days that meet the characteristics of sunny weather. In a specific embodiment, the process is as follows:

[0074] 1) Determine the peak power of a day

[0075] For example, determining the peak power on day d. Is it greater than 0.8P? max , where P max Let's assume the maximum power value is within a preset historical time period; if so, then the power peak value on day d meets the requirement. Assuming there are C data points per day, for T time steps of the dataset, we can calculate that the dataset contains T / C days. The maximum power value on day d ∈ [1, T / C] is then calculated as follows: The maximum power across the entire dataset is Pmax = maxPi,j,k1,…,Pi,j,kT. Determine the peak power on day d. If the condition is met, then the power peak value for that day meets the requirements. Continue to assess the volatility of the power sequence for that day.

[0076] 2) Determine the daily volatility

[0077] For example, using the mean of the absolute values ​​of the first-order differences of the power on day d. This value is used to measure the magnitude of fluctuations in meteorological factors on a given day; the greater the fluctuation in power due to meteorological factors, the larger the value. The calculation is as follows: By judgment Whether it holds true determines the volatility of power on that day.

[0078] Furthermore, inverter model i corresponds to N strings. i ×S i Based on the average power of each photovoltaic string calculated in the previous step, these strings can be sorted in ascending order (or descending order; this embodiment uses ascending order of average power for each photovoltaic string as an example). The benchmark string for this inverter model is then the photovoltaic string with the highest average power, calculated as follows:

[0079] The benchmark string has the strongest power generation capacity. The power generation capacity of other strings can be measured by dividing by the average power of the benchmark string. For the k-th string of the j-th inverter, its power generation capacity is calculated as follows:

[0080]

[0081] In this embodiment of the invention, the photovoltaic string with the highest average power connected to each inverter model is used as the benchmark string. Then, the power generation capacity is characterized by the ratio of the average power of other photovoltaic strings connected to the same inverter model to the corresponding benchmark string. By setting a benchmark and calculating the ratio, a relatively standardized measurement scale is provided for the power generation capacity of different photovoltaic strings, making it convenient to intuitively compare the relative power generation capacity of each string under the same inverter type.

[0082] S1022 divides the power generation capacity data of all photovoltaic strings connected to different types of inverters into multiple power generation capacity intervals according to the power generation capacity, and the number of intervals is the same as the number of tilt angle combinations.

[0083] This invention calculates the power generation capacity of each photovoltaic string in inverters of the same type. For inverter of model i, the power generation capacity of all its strings is expressed as follows: The power generation capacity of all strings of different types of inverters in a power plant is expressed as follows:

[0084]

[0085] The photovoltaic strings connected to all inverters in the power station are arranged in ascending order of power generation capacity. The total number of photovoltaic strings in the power station is... All the permuted strings can be represented as:

[0086] Q o =sort(Q)={q1,…,q H};

[0087] Here, sort() represents the ascending order sorting operation, q1 and q H These are the strings with the smallest and largest power generation capacity of the power plant, respectively.

[0088] The number of intervals is the same as the number of tilt angle combinations, which is G. The length of each interval for power generation capacity is: The data range of the g-th interval [1, G] can be represented as [q1+(g-1)L,q1+gL]. The power generation capacity of all the strings after arrangement is divided into different intervals according to the size: {[q1+(g-1L,q1+gL|1≤g≤G}.

[0089] S103, calculate the theoretical irradiance potential of all tilt-orientation combinations in the metadata.

[0090] Specifically, different tilt angles correspond to different photovoltaic panel placement methods, and this difference directly affects the amount of irradiance received by the photovoltaic panels. Figure 2 The diagram illustrates the variation in theoretical total irradiance under different tilt angle combinations under the same meteorological conditions on a given day. Meteorological irradiance is typically calculated for horizontal surfaces, requiring a conversion model to transform the horizontal surface irradiance to the total irradiance for tilted surfaces. Therefore, this embodiment of the invention calculates the theoretical irradiance potential for all tilt angle combinations using the location of the photovoltaic power station and meteorological data. Specifically:

[0091] 1) Calculate extraterrestrial irradiance: Extraterrestrial irradiance reflects the energy of the sun reaching the Earth's surface without the influence of an atmosphere. The Spencer model from the pvlib library is used to calculate the extraterrestrial irradiance at a specified location over a period of time.

[0092] 2) Calculate the sun's position: Using the Solar Position Algorithm (SPA), input the latitude and longitude loc(Lon,lat) and the corresponding time t to calculate the sun's zenith angle Z and azimuth angle A at time t: [Z,A]=SPA(loc(Lon,lat),t).

[0093] 3) Calculate the total irradiance of the inclined surface, divided into two scenarios:

[0094] ① For existing power plant measured irradiance or numerical weather prediction (NWP) irradiance, the existing irradiance can be directly input into the conversion model to calculate the total irradiance of the inclined surface.

[0095] ② In cases where historical irradiance data and numerical weather prediction (NWP) irradiance are lacking, the Ineichen clear-sky irradiance model from the pvlib library (the pvlib library is a Python library for photovoltaic system analysis, and the Ineichen clear-sky irradiance model is a model for calculating solar irradiance under clear-sky conditions) is used to calculate the theoretical clear-sky irradiance for the time period corresponding to the historical clear days (the number of clear days obtained in step a1).

[0096] Further inputting irradiance data, external irradiance, solar position, time, tilt angle, and orientation into the Perez model in the pvlib library (pvlib is a Python library for photovoltaic system analysis; the Perez model is primarily used to calculate the anisotropic diffuse component of solar radiation, enabling more accurate estimation of the amount of solar radiation received on the tilted plane) calculates the total irradiance of the tilted plane for each combination of tilt angle and orientation. Taking existing irradiance data as an example, the total irradiance of the tilted plane is calculated as follows:

[0097]

[0098] This invention comprehensively considers various factors, including the latitude and longitude of the photovoltaic power station, the sun's position, irradiance data, tilt angle, and time. These factors are interrelated and all have a crucial impact on the irradiance received by the photovoltaic strings. By comprehensively incorporating and calculating these factors, the total irradiance of the tilt surface for each tilt angle combination can more scientifically and accurately reflect the actual theoretical irradiance potential, laying a solid foundation for subsequent precise matching and tilt angle identification.

[0099] Furthermore, the irradiation potential corresponding to all tilt angle combinations. Sort the data in ascending order (using the same sorting method as the average power of the photovoltaic strings). The sorted sequence is: F o ={f1,…,f G}, where f1, f G Representing the minimum and maximum irradiance potentials respectively, the corresponding tilt angle θ and orientation τ combination can be expressed as: {(θ1,τ1),…,(θ G ,τ G )}.

[0100] In this embodiment of the invention, the irradiance potential corresponding to all tilt angle combinations is sorted according to numerical value, and the sorting method is the same as the sorting method for the average power of photovoltaic strings. When matching the power generation capacity of photovoltaic strings with theoretical irradiance potential in the future, the same sorting method makes it easier and more intuitive to match the two, which facilitates the quick and accurate identification of the tilt angle combination that best matches the power generation capacity of each photovoltaic string, and helps to improve the efficiency and accuracy of the entire tilt angle identification process.

[0101] S104, the power generation capacity of each photovoltaic string is matched with the theoretical irradiance potential to obtain the tilt angle identification result of the photovoltaic string.

[0102] Specifically, under identical hardware conditions, strings with higher power generation capacity correspond to greater irradiance. The magnitude of irradiance depends on the tilt angle and orientation of the installed string; the optimal tilt angle and orientation correspond to the maximum irradiance. In this embodiment of the invention, the power generation capacity of each photovoltaic string is ranked, and each photovoltaic string is matched with a tilt angle and orientation combination of the same irradiance potential ranking according to the ranking order. After matching, all photovoltaic strings connected to all types of inverters in the photovoltaic power station correspond to a tilt angle and orientation value, resulting in the photovoltaic string tilt angle and orientation identification result.

[0103] Specifically, it will be in the g-range of power generation capacity ranking [q] G +(g-1)L,q G The string of +gL] and the tilt-orientation combination ranked g by irradiance potential (θ) g ,τg Matching is performed on each interval, where g∈[1,G]. All intervals are matched sequentially with their corresponding tilt angles. After matching, all strings of all inverter types in the power station correspond to a tilt angle value (θ). g ,τ g ), g∈[1,G], realizes the automatic allocation of tilt angle orientation for all strings.

[0104] The matching method employed in this embodiment of the invention leverages the prior prior sorting of power generation capacity and irradiance potential, enabling the two to be correlated in an ordered and corresponding manner. Since the sorting process itself is based on the scientific analysis and organization of relevant data, this sorting and matching method can accurately link photovoltaic strings with the tilt angle combination that best matches their power generation performance, greatly improving matching accuracy, reducing mismatches, and thus providing a strong guarantee for obtaining reliable tilt angle identification results.

[0105] In one specific embodiment, the adaptive identification method for the tilt angle orientation of photovoltaic strings provided by this invention, such as... Figure 3 As shown, by acquiring historical data of all photovoltaic strings connected to various types of inverters in a photovoltaic power station, as well as metadata of the photovoltaic power station design, and comprehensively analyzing multiple key information, the final identification results can be based on a more comprehensive data foundation. This helps improve the accuracy of tilt angle identification. Accurately identifying the tilt angle of photovoltaic strings helps operation and maintenance personnel better understand whether the actual layout of each part of the power station matches the optimal light reception conditions. Consequently, they can make targeted adjustments and optimizations to unreasonable tilt angles, improve the overall power generation efficiency of the photovoltaic power station, and provide a strong basis for decision-making on the long-term stable and efficient operation of the power station.

[0106] This embodiment also provides an adaptive identification system for the tilt angle of photovoltaic strings. This system is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the systems described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0107] This embodiment provides an adaptive identification system for the tilt angle orientation of photovoltaic strings, such as... Figure 4 As shown, it includes:

[0108] The data acquisition module 401 is used to acquire historical data of all photovoltaic strings of various types of inverters connected to the photovoltaic power station, as well as metadata of the photovoltaic power station design. The metadata includes: latitude and longitude information of the photovoltaic power station, all tilt angle and orientation combinations registered by the photovoltaic power station, and historical data, including: historical current data and historical voltage data.

[0109] The power generation capacity calculation module 402 is used to filter out photovoltaic strings that are in normal operation based on historical data and calculate the power generation capacity of each photovoltaic string.

[0110] Irradiation data acquisition module 403 is used to calculate the theoretical irradiation potential of all tilt angle combinations in the metadata;

[0111] The tilt angle orientation identification module 404 is used to match the power generation capacity of each photovoltaic string with the theoretical irradiance potential to obtain the tilt angle orientation identification result of the photovoltaic string.

[0112] In some alternative implementations, the power generation capacity calculation module 402 includes:

[0113] The power generation capacity calculation unit is used to calculate the average power of each photovoltaic string connected to the same type of inverter based on historical data of photovoltaic strings operating normally, and to calculate the power generation capacity of each photovoltaic string based on the average power of each photovoltaic string.

[0114] The power generation capacity interval division unit is used to divide the power generation capacity data of all photovoltaic strings connected to different types of inverters into multiple power generation capacity intervals according to the size of the power generation capacity. The number of intervals is the same as the number of tilt angle combinations.

[0115] In some optional implementations, the historical data further includes: historical irradiance data; and power generation capacity interval division units, including:

[0116] The power calculation subunit is used to calculate the power value of each photovoltaic string connected to various types of inverters;

[0117] The first average power calculation subunit is used to obtain the average power of all days for photovoltaic strings with historical irradiance data or numerical weather forecast irradiance using the calculated power value.

[0118] The second average power calculation subunit, for photovoltaic strings lacking historical irradiance data and numerical weather forecast irradiance, calculates the irradiance value under theoretical sunny conditions based on the timestamp information corresponding to historical current data and historical voltage data, and determines the number of sunny days by judging the peak power and power fluctuation of a day in historical data, and calculates the average power of the number of sunny days.

[0119] The benchmark string acquisition sub-unit is used to arrange the average power of each photovoltaic string according to its numerical value, and to select the photovoltaic string with the highest average power connected to the same type of inverter as the benchmark string.

[0120] The power generation capacity calculation unit is used to characterize the power generation capacity by comparing the average power of other photovoltaic strings connected to the same type of inverter with the corresponding benchmark string.

[0121] In some alternative implementations, the number of sunny days is determined by analyzing the peak power and power fluctuations of a day in historical data, including:

[0122] Obtain the peak power on day d And judge Is the power value greater than the maximum power value within a preset historical time period by a preset multiple? If so, the power peak value on day d meets the requirements.

[0123] Obtain the mean of the absolute values ​​of the first-order differences of power on day d. And judge Is it less than the mean of the absolute values ​​of the first-order differences of the minimum power within a preset historical time period, which is less than a preset multiple? If so, then the power fluctuation on day d is determined to meet the requirements.

[0124] The number of days that simultaneously meet the requirements for peak power and power fluctuation is taken as the number of sunny days.

[0125] In some alternative implementations, the irradiation data acquisition module 403 includes:

[0126] The first calculation unit is used to calculate the extraterrestrial irradiance based on the latitude and longitude information of the photovoltaic power station, and to calculate the position of the sun based on the latitude and longitude information of the photovoltaic power station.

[0127] The second calculation unit is used to calculate the total irradiance of the tilted surface based on the historical irradiance data and time of the photovoltaic string with historical irradiance data or numerical weather forecast irradiance.

[0128] The third calculation unit is used to calculate the theoretical clear sky irradiance for the time period corresponding to the historical clear days for photovoltaic strings that lack historical irradiance data and numerical weather forecast irradiance.

[0129] The fourth calculation unit is used to obtain the total irradiance of the tilted surface for each tilt angle combination based on irradiance data, extraterrestrial irradiance, solar position, time, and tilt angle orientation.

[0130] The irradiance potential sorting unit is used to sort the irradiance potential corresponding to all tilt angle combinations according to their numerical values. The sorting method is the same as the sorting method for the average power of photovoltaic strings.

[0131] In some alternative implementations, the tilt orientation recognition module includes:

[0132] The matching unit is used to sort the power generation capacity of each photovoltaic string and match each photovoltaic string with the tilt angle combination with the same irradiance potential ranking according to the sorting order.

[0133] The identification unit is used to identify the tilt angle orientation of all photovoltaic strings connected to all types of inverters in the photovoltaic power station after matching, so as to obtain the tilt angle orientation identification result of the photovoltaic string.

[0134] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0135] In this embodiment, the adaptive identification system for the tilt angle of the photovoltaic string is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit), a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0136] This invention also provides a computer device having the above-described features. Figure 4 The diagram shows an adaptive identification system for the tilt angle orientation of photovoltaic strings.

[0137] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 5 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 5 Take a processor 10 as an example.

[0138] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0139] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0140] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0141] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0142] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0143] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor central control systems, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the above embodiments are implemented.

[0144] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0145] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. An adaptive identification method for the tilt angle orientation of photovoltaic strings, characterized in that, include: Acquire historical data of all photovoltaic strings connected to various types of inverters in a photovoltaic power station, as well as metadata of the photovoltaic power station design; wherein, the metadata includes: inverter model, latitude and longitude information of the photovoltaic power station, and all registered tilt angle and orientation combinations of the photovoltaic power station; the historical data includes: historical current data, historical voltage data, and historical irradiance data. Based on historical data, photovoltaic (PV) strings in normal operating condition are selected, and the power generation capacity of each PV string is calculated. This includes: calculating the average power of each PV string connected to the same type of inverter based on historical data of PV strings in normal operating condition, and calculating the power generation capacity of each PV string based on the average power of each PV string; dividing the power generation capacity data of all PV strings connected to different types of inverters into multiple power generation capacity intervals according to the power generation capacity, with the number of intervals being the same as the number of tilt angle / orientation combinations. The theoretical irradiance potential of all tilt angle / orientation combinations in the metadata is calculated, including: calculating the external irradiance based on the latitude and longitude information of the photovoltaic power station, and calculating the solar position based on the latitude and longitude information of the photovoltaic power station; for photovoltaic strings with historical irradiance data or numerical weather prediction irradiance, calculating the total tilt surface irradiance based on the historical irradiance data and time of the photovoltaic string; for photovoltaic strings lacking historical irradiance data and numerical weather prediction irradiance, calculating the theoretical clear sky irradiance for the time period corresponding to the historical clear days; obtaining the total tilt surface irradiance for each tilt angle / orientation combination based on irradiance data, external irradiance, solar position, time, and tilt angle / orientation; and sorting the irradiance potential corresponding to all tilt angle / orientation combinations according to their numerical values, in the same way as sorting the average power of the photovoltaic strings. The power generation capacity of each photovoltaic string is matched with its theoretical irradiance potential to obtain the photovoltaic string tilt angle orientation identification result. This includes: sorting the power generation capacity of each photovoltaic string, and matching each photovoltaic string with a tilt angle orientation combination with the same irradiance potential ranking according to the sorting order; after the matching is completed, all photovoltaic strings connected to all types of inverters in the photovoltaic power station correspond to a tilt angle orientation value, thus obtaining the photovoltaic string tilt angle orientation identification result.

2. The method according to claim 1, characterized in that, The process involves calculating the average power output of each photovoltaic string connected to a similar inverter based on historical data of normally operating photovoltaic strings connected to the same type of inverter, and then calculating the power generation capacity of each photovoltaic string based on its average power output. This includes: Calculate the power value of each photovoltaic string connected to each type of inverter; For photovoltaic strings with historical irradiance data or numerical weather forecast irradiance, the average power for all days can be obtained using the calculated power value; For photovoltaic strings lacking historical irradiance data and numerical weather forecast irradiance, the irradiance value under theoretical sunny conditions is calculated based on the timestamp information corresponding to historical current data and historical voltage data. The number of sunny days is determined by judging the peak power and power fluctuation of a day in historical data, and the average power of the number of sunny days is calculated. The average power of each photovoltaic string is calculated and arranged according to its value. The photovoltaic string with the highest average power connected to the same type of inverter is taken as the benchmark string. The power generation capacity is represented by the ratio of the average power of other photovoltaic strings connected to the same type of inverter to the corresponding benchmark string.

3. The method according to claim 2, characterized in that, The method of determining the number of sunny days by judging the peak power and power fluctuation of a day in historical data includes: Obtain the peak power on day d The maximum power value within a preset historical time period is set; if so, the power peak value on day d meets the requirements. Obtain the mean of the absolute values ​​of the first-order differences of power on day d. and judge Is it less than the mean of the absolute values ​​of the first-order differences of the minimum power within a preset historical time period, which is less than a preset multiple? If so, then the power fluctuation on day d is determined to meet the requirements. The number of days that simultaneously meet the requirements for peak power and power fluctuation is taken as the number of sunny days.

4. An adaptive identification system for the tilt angle orientation of a photovoltaic string, characterized in that, include: The data acquisition module is used to acquire historical data of all photovoltaic strings of various types of inverters connected to the photovoltaic power station, as well as metadata of the photovoltaic power station design; wherein, the metadata includes: inverter model, latitude and longitude information of the photovoltaic power station, and all tilt angle and orientation combinations registered by the photovoltaic power station; the historical data includes: historical current data, historical voltage data, and historical irradiance data. The power generation capacity calculation module is used to filter out photovoltaic strings that are in normal operation based on historical data and calculate the power generation capacity of each photovoltaic string. This includes: calculating the average power of each photovoltaic string connected to the same type of inverter based on historical data of photovoltaic strings that are in normal operation; and calculating the power generation capacity of each photovoltaic string based on the average power of each photovoltaic string. The power generation capacity data of all photovoltaic strings connected to different types of inverters are divided into multiple power generation capacity intervals according to the power generation capacity, with the number of intervals being the same as the number of tilt angle / orientation combinations. The irradiance data acquisition module is used to calculate the theoretical irradiance potential of all tilt angle / orientation combinations in the metadata, including: calculating the external irradiance based on the latitude and longitude information of the photovoltaic power station, and calculating the solar position based on the latitude and longitude information of the photovoltaic power station; for photovoltaic strings with historical irradiance data or numerical weather prediction irradiance, calculating the total tilt surface irradiance based on the historical irradiance data and time of the photovoltaic string; for photovoltaic strings lacking historical irradiance data and numerical weather prediction irradiance, calculating the theoretical clear sky irradiance for the time period corresponding to the historical clear days; obtaining the total tilt surface irradiance for each tilt angle / orientation combination based on irradiance data, external irradiance, solar position, time, and tilt angle / orientation; and sorting the irradiance potential corresponding to all tilt angle / orientation combinations according to their numerical values, in the same way as sorting the average power of the photovoltaic strings. The tilt angle orientation identification module is used to match the power generation capacity of each photovoltaic string with its theoretical irradiance potential to obtain the tilt angle orientation identification result of the photovoltaic string. This includes: sorting the power generation capacity of each photovoltaic string, and matching each photovoltaic string with a tilt angle orientation combination with the same irradiance potential ranking according to the sorting order; after the matching is completed, all photovoltaic strings connected to all types of inverters in the photovoltaic power station correspond to a tilt angle orientation value, thus obtaining the photovoltaic string tilt angle orientation identification result.

5. A computer device, characterized in that, include: A memory and a processor are interconnected, the memory stores computer instructions, and the processor executes the computer instructions to perform the adaptive identification method for the tilt angle orientation of photovoltaic strings as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the adaptive identification method for the tilt angle orientation of the photovoltaic string as described in any one of claims 1-3.

7. A computer program product, characterized in that, Includes computer instructions for causing a computer to execute the adaptive identification method for the tilt angle orientation of photovoltaic strings as described in any one of claims 1-3.

Images