Photovoltaic power generation system, evaluation method thereof, and computer storage medium

Abstract

The invention provides a photovoltaic power generation system, an evaluation method thereof and a computer storage medium, the photovoltaic power generation system is electrically connected with a power grid, the photovoltaic power generation system comprises a photovoltaic management unit and an inverter, the photovoltaic management unit comprises a photovoltaic module, the photovoltaic management unit is electrically connected with the inverter, the inverter is electrically connected with the power grid, and the photovoltaic module is electrically connected with the inverter. The evaluation method of the photovoltaic power generation system comprises the following steps: acquiring daily power generation data of the photovoltaic power generation system in a historical time period, wherein the daily power generation data of the photovoltaic power generation system comprises the daily power generation amount of the photovoltaic power generation system and the daily rated power of the photovoltaic power generation system; according to the daily power generation data of the photovoltaic power generation system, calculating to obtain the daily full power generation hours of the photovoltaic power generation system; and evaluating the performance of the photovoltaic power generation system by analyzing the change trend of the daily full generation hours of the photovoltaic power generation system in the historical time period. The daily full generation hours of the photovoltaic power generation system can be used for constructing a unified evaluation framework, so that the performance of different systems can be evaluated conveniently.

Description

Technical Field

[0001] The present application relates to the field of power supply systems, and in particular to a photovoltaic power generation system, an evaluation method thereof, and a computer storage medium. Background Art

[0002] With the global emphasis on environmental protection and sustainable development, traditional energy sources are facing numerous challenges, including limited resources and environmental pollution. To achieve clean and low-carbon energy, renewable energy sources such as solar and wind power have experienced rapid development. In particular, the widespread application of renewable energy sources such as photovoltaics and wind power has led to the development of photovoltaic power generation systems, in which photovoltaic modules and inverters are crucial components.

[0003] As a photovoltaic power generation system ages, its performance may be affected by various factors. For example, the intensity of solar radiation, the temperature of the environment in which the photovoltaic power generation system operates, the duration of sunlight exposure to the photovoltaic modules, and the performance and efficiency of the inverter all influence the overall performance of the photovoltaic power generation system. Furthermore, with increasing age, the performance of the inverter may decline, leading to a decline in the performance of the photovoltaic power generation system. Alternatively, with increasing age, due to variations in solar radiation intensity and duration, the performance of the photovoltaic modules may also decline, leading to a decline in the performance of the photovoltaic power generation system. Therefore, evaluating the performance of the photovoltaic power generation system is crucial for the management of individual devices in the system, such as maintenance decisions and equipment lifespan assessment.

[0004] In existing technologies, the performance of photovoltaic power generation systems can be evaluated based on indicators such as the system's power generation and power generation. However, these indicators are closely related to the system's overall design and application scenarios. The indicators used to evaluate performance vary depending on the overall design and application scenarios of the photovoltaic power generation system. Furthermore, the standards for performance evaluation parameters can also vary depending on the overall system design and application scenarios. This makes it difficult to standardize the performance evaluation of traditional photovoltaic power generation systems. Summary of the Invention

[0005] In view of this, embodiments of the present application are directed to providing a photovoltaic power generation system, an evaluation method thereof, and a computer storage medium.

[0006] In a first aspect, a method for evaluating a photovoltaic power generation system is provided, wherein the photovoltaic power generation system is electrically connected to a power grid, the photovoltaic power generation system includes a photovoltaic management unit and an inverter, the photovoltaic management unit includes photovoltaic modules, the photovoltaic management unit is electrically connected to the inverter, and the inverter is electrically connected to the power grid. The method for evaluating the photovoltaic power generation system includes: obtaining daily power generation data of the photovoltaic power generation system within a historical period, the daily power generation data of the photovoltaic power generation system including: daily power generation of the photovoltaic power generation system and daily rated power of the photovoltaic power generation system; calculating the daily full power generation hours of the photovoltaic power generation system based on the daily power generation data of the photovoltaic power generation system; and evaluating the performance of the photovoltaic power generation system by analyzing the changing trend of the daily full power generation hours of the photovoltaic power generation system within the historical period.

[0007] According to the first aspect, the performance of the photovoltaic power generation system is evaluated by analyzing the changing trend of the daily full power hours of the photovoltaic power generation system during the historical period, including: obtaining time series data of the daily full power hours of the photovoltaic power generation system based on the daily full power hours of the photovoltaic power generation system; analyzing the time series data by a data analysis method to obtain analysis results of the time series data, and the data analysis method is used to seasonally adjust the time series data to filter out data with seasonal components; and evaluating the performance of the photovoltaic power generation system by analyzing the analysis results of the time series data.

[0008] According to the first aspect, or any implementation of the first aspect above, the data analysis method is a seasonal trend decomposition STL analysis method based on local weighted regression. The STL analysis method is used to decompose time series data into seasonal component data, trend component data and residual component data. The residual component data is the data remaining after removing the seasonal component data and trend component data from the time series data.

[0009] According to the first aspect, or any implementation method of the first aspect above, the performance of the photovoltaic power generation system is evaluated by analyzing the changing trend of the daily full-power hours of the photovoltaic power generation system during the historical period, including: obtaining the peak value of the daily full-power hours of the photovoltaic power generation system each year; and evaluating the performance of the photovoltaic power generation system by analyzing the peak value of the daily full-power hours of the photovoltaic power generation system each year.

[0010] According to the first aspect, or any implementation method of the first aspect above, the peak value of the daily full-power hours of the photovoltaic power generation system each year is obtained, including: aggregating data on the daily full-power hours of the photovoltaic power generation system on a monthly basis to obtain the monthly average of the daily full-power hours of the photovoltaic power generation system each month; and obtaining the peak value of the daily full-power hours of the photovoltaic power generation system each year through the monthly average of the daily full-power hours of the photovoltaic power generation system each month.

[0011] According to the first aspect, or any implementation of the first aspect above, the evaluation method further includes: obtaining the peak value of the daily full power generation hours of the photovoltaic power generation system each year through a peak detection algorithm.

[0012] According to the first aspect, or any implementation method of the first aspect above, the performance of the photovoltaic power generation system is evaluated by analyzing the peak value of the daily full-power hours of the photovoltaic power generation system each year, including: performing linear regression fitting on the obtained peak value of the daily full-power hours of the photovoltaic power generation system each year, and calculating the attenuation rate of the daily full-power hours in the historical period; and evaluating the performance of the photovoltaic power generation system based on the attenuation rate.

[0013] According to the first aspect, or any implementation of the first aspect above, before evaluating the performance of the photovoltaic power generation system by analyzing the changing trend of the daily full-power hours of the photovoltaic power generation system in a historical period, the evaluation method also includes: using a triple standard deviation criterion algorithm to detect the daily full-power hours of the photovoltaic power generation system and eliminate abnormal values in the daily full-power hours of the photovoltaic power generation system.

[0014] On the second aspect, the present application provides a photovoltaic power generation system, which is electrically connected to the power grid, and the photovoltaic power generation system includes: a photovoltaic management unit, which includes photovoltaic modules; an inverter, one end of the inverter is electrically connected to the photovoltaic management unit, and the other end of the inverter is electrically connected to the power grid; an evaluation unit, which is used to evaluate the performance of the photovoltaic power generation system by analyzing the changing trend of the daily full-time power generation hours of the photovoltaic power generation system within a historical period, wherein the daily full-time power generation hours of the photovoltaic power generation system are calculated based on the daily power generation data of the photovoltaic power generation system, and the daily power generation data of the photovoltaic power generation system include: the daily power generation of the photovoltaic power generation system, and the daily rated power of the photovoltaic power generation system.

[0015] In a third aspect, the present application provides a computer-readable storage medium, which is used for a program code executed by a computer, wherein the program code includes a method for executing an evaluation method of a photovoltaic power generation system on a first side.

[0016] In a fourth aspect, an embodiment of the present application provides a computer program, which includes commands for executing the photovoltaic power generation system evaluation method of the first aspect.

[0017] In the embodiment of the present application, the daily full power hours of the photovoltaic power generation system can be used to construct a unified evaluation framework, which facilitates the evaluation of the performance of different photovoltaic power generation systems or the same system at different time periods. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of a photovoltaic power generation system evaluation method provided in an embodiment of the present application.

[0019] Figure 2 This is a flow chart of another photovoltaic power generation system evaluation method provided in an embodiment of the present application.

[0020] Figure 3 This is a flow chart of another photovoltaic power generation system evaluation method provided in an embodiment of the present application.

[0021] Figure 4 This is a schematic diagram of the normal distribution of the daily full-power hours of a photovoltaic power generation system provided in an embodiment of the present application.

[0022] Figure 5 A schematic flow chart of a photovoltaic power generation system evaluation method provided in an embodiment of the present application.

[0023] Figure 6 This is a timing analysis diagram of the daily full-power hours of a photovoltaic power generation system analyzed by STL in an embodiment of the present application.

[0024] Figure 7 A peak diagram of the daily full-power hours of a photovoltaic power generation system provided in an embodiment of the present application.

[0025] Figure 8 A schematic diagram of the attenuation trend of the daily full-power hours of a photovoltaic power generation system provided in an embodiment of the present application.

[0026] Figure 9 A schematic structural diagram of a photovoltaic power generation system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field based on this application are within the scope of protection of this application.

[0028] The term "and / or" in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0029] In the description and claims of the embodiments of this application, the terms "first" and "second" are used to distinguish different objects, rather than to describe a specific order of objects. For example, the terms "first target object" and "second target object" are used to distinguish different objects, rather than to describe a specific order of objects.

[0030] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0031] It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0032] With the global emphasis on environmental protection and sustainable development, traditional energy sources face numerous challenges, including limited resources and environmental pollution. To achieve clean and low-carbon energy, renewable energy sources such as solar and wind power have experienced rapid development. In particular, renewable energy sources such as photovoltaics and wind power are being widely used, such as photovoltaic power generation systems. These systems utilize photovoltaic modules to directly convert sunlight into electricity. In photovoltaic power generation systems, the electricity generated by these modules is direct current (DC), while most common loads in daily life require AC power. Therefore, when a photovoltaic power generation system is connected to the grid, an inverter is required to convert the DC power generated by the modules into AC to meet the electricity needs of homes, businesses, and industries. Therefore, both photovoltaic modules and inverters are crucial components of a photovoltaic power generation system.

[0033] As a photovoltaic power generation system ages, its performance may be affected by various factors. For example, factors such as solar radiation intensity, the ambient temperature of the system, the duration of sunlight exposure to the photovoltaic modules, and the performance and efficiency of the inverter all influence the overall performance of the photovoltaic power generation system. With age, inverter performance may degrade, leading to degradation in the performance of the photovoltaic power generation system. Alternatively, with age, due to variations in solar radiation intensity and duration, photovoltaic module performance may also degrade, leading to degradation in the performance of the photovoltaic power generation system. Therefore, evaluating the performance of a photovoltaic power generation system is crucial for managing individual devices within the system, including maintenance decisions and equipment lifespan assessment.

[0034] In existing technology, the performance of a photovoltaic power generation system can be evaluated based on metrics such as power generation and power yield. These metrics are closely related to the overall design and application scenario of the photovoltaic power generation system. For example, when a photovoltaic power generation system is used in a small system (e.g., less than 5kW), the inverter can be a single-phase inverter; when a photovoltaic power generation system is used in a larger system (e.g., greater than 5kW), the inverter can be a three-phase inverter. Therefore, the power generation and power yield of the photovoltaic power generation system vary depending on the inverter selected. Connecting photovoltaic modules in series increases the overall system voltage, thereby increasing the inverter input voltage. Connecting photovoltaic modules in parallel maintains a consistent voltage and cumulative current, making it suitable for scenarios requiring increased current output. Therefore, the series and parallel configuration of photovoltaic modules can result in different power outputs for the photovoltaic power generation system.

[0035] Therefore, the performance indicators used to evaluate photovoltaic power generation systems vary depending on their overall design and application scenarios. Furthermore, the standards for performance evaluation parameters vary depending on the overall system design and application scenarios, making it difficult to achieve a unified standard for the performance evaluation of traditional photovoltaic power generation systems. Furthermore, evaluation parameters are also affected by system design (such as photovoltaic module connection method, inverter configuration, etc.) and light intensity, further hindering the standardization of photovoltaic power generation system performance standards.

[0036] To address the above issues, this application proposes a photovoltaic power generation system evaluation method. By using the full-power hours of a photovoltaic power generation system, this method places photovoltaic power generation systems of different overall designs and application scenarios within a unified evaluation framework, providing a new, standardized indicator for their performance evaluation. Furthermore, because the full-power hours provide a unified performance evaluation indicator and are simple to calculate and can be regularly calculated and analyzed, the causes of photovoltaic power generation system performance degradation can be promptly identified, allowing for better long-term maintenance and management of each device in the photovoltaic power generation system.

[0037] Full-power hours refers to the number of hours within a given period during which a power generation device reaches its rated capacity. Full-power hours is a key indicator of power generation device performance. The formula for calculating full-power hours is: Full-power hours = Power generation device's power generation / Power generation device's rated power. By comparing a power generation device's power generation with its rated power, full-power hours can reflect the actual utilization efficiency of the power generation device. It is understood that using full-power hours to evaluate power generation device performance is independent of the type of power generation device or external factors, and can be used to compare the performance of different power generation devices.

[0038] The following combination Figure 1, the evaluation method of the photovoltaic power generation system proposed in the embodiment of the present application is described.

[0039] Figure 1 A schematic diagram of a flow chart of a photovoltaic power generation system evaluation method provided in an embodiment of the present application. Figure 1 The photovoltaic power generation system in the plant can be electrically connected to the grid.

[0040] In some embodiments, Figure 1 The photovoltaic power generation system may include a photovoltaic management unit and an inverter. The photovoltaic management unit may include photovoltaic components. The photovoltaic management unit may be electrically connected to the inverter, and the inverter may be electrically connected to the power grid.

[0041] In some embodiments, the photovoltaic management unit may include a plurality of photovoltaic modules connected in series, a plurality of photovoltaic modules connected in parallel, or a plurality of photovoltaic modules connected in series and parallel.

[0042] In some embodiments, the inverter may be a single-phase inverter, or the inverter may be a three-phase inverter.

[0043] Step S110 , obtaining daily power generation data of the photovoltaic power generation system in a historical period.

[0044] In some embodiments, the daily power generation data of the photovoltaic power generation system may include: the daily power generation of the photovoltaic power generation system and the daily rated power of the photovoltaic power generation system.

[0045] In some embodiments, the power generation of a photovoltaic power generation system refers to the total amount of electrical energy generated within a specific time period. For example, the total amount of electrical energy actually generated by the photovoltaic power generation system within 24 hours a day can be called the daily power generation of the photovoltaic power generation system.

[0046] In some embodiments, the rated power of a photovoltaic power generation system refers to the maximum power value that the photovoltaic power generation system can stably output under standard test conditions. For example, the maximum power value that the photovoltaic power generation system can stably output within 24 hours a day is the daily rated power of the photovoltaic power generation system. In some embodiments, the rated power of a photovoltaic power generation system is generally related to the equipment parameters, overall design, and application scenarios included in the photovoltaic power generation system. For example, the rated power of a photovoltaic power generation system can be determined by the total power of the photovoltaic modules and needs to match the rated capacity of the inverter.

[0047] In some embodiments, the photovoltaic modules or inverters in the photovoltaic power generation system may affect the power generation and rated power of the photovoltaic power generation system.

[0048] For example, the series and parallel connection of PV modules can affect the voltage and current output characteristics of a PV power generation system, and thus the system's power generation and rated power. For example, connecting PV modules in series increases the system's total voltage. Connecting PV modules in parallel increases the system's total current. The choice of series and parallel connection of PV modules must be tailored to the inverter's input requirements, system losses, and other factors to determine the system's rated power and power generation.

[0049] For example, the inverter type can affect the power generation and rated power of a photovoltaic power generation system. For example, when a photovoltaic power generation system is used in a small system, such as one with a power of less than 5kW, the inverter can be a single-phase inverter. However, when a photovoltaic power generation system is used in a higher-power system, such as one with a power of more than 5kW, the inverter can be a three-phase inverter. It is understood that when a photovoltaic power generation system is used in a higher-power system, it needs to provide a higher rated power output and higher efficiency, thereby indirectly increasing the power generation of the photovoltaic power generation system.

[0050] Step S120: The daily full power generation hours of the photovoltaic power generation system can be calculated based on the daily power generation data of the photovoltaic power generation system.

[0051] In some embodiments, the daily full-power hours of a photovoltaic power generation system can be calculated using the following formula: Daily full-power hours of a photovoltaic power generation system = Daily power generation of the photovoltaic power generation system / Daily rated power of the photovoltaic power generation system. The daily full-power hours can quantify the actual utilization rate of the photovoltaic power generation system in a single day by combining the daily power generation and the daily rated power. Because the daily full-power hours reflect the utilization rate of the photovoltaic power generation system under actual operating conditions, they are not affected by the overall design of the photovoltaic power generation system or the application scenario, such as the connection relationship between photovoltaic modules or the inverter type.

[0052] In some embodiments, by acquiring daily power generation data of the photovoltaic power generation system during a historical period, the daily full power generation hours of the photovoltaic power generation system during the historical period can be obtained.

[0053] Step S130 , evaluating the performance of the photovoltaic power generation system by analyzing the changing trend of the daily full power generation hours of the photovoltaic power generation system in a historical period.

[0054] In some embodiments, the changing trend of the photovoltaic power generation system's daily full-power hours over a historical period can reflect the utilization rate of the photovoltaic power generation system under actual operating conditions and can demonstrate the photovoltaic power generation system's actual power generation capacity. For example, when the overall design of a photovoltaic power generation system is completed and the application scenario has been determined, the photovoltaic power generation system's daily rated power is determined. Therefore, as the performance of the photovoltaic power generation system declines over time, it will affect the daily power generation of the photovoltaic power generation system. Therefore, by analyzing the changing trend of the photovoltaic power generation system's daily full-power hours over a historical period, the performance of the photovoltaic power generation system can be evaluated.

[0055] The daily full-power hours of the photovoltaic power generation system proposed in the embodiments of the present application can be used to construct a unified evaluation framework to facilitate the evaluation of the performance of different photovoltaic power generation systems or the same system at different time periods.

[0056] In some embodiments, since the calculation of the daily full-power hours is simple and can intuitively reflect the actual utilization efficiency of the system, the changing trend of the daily full-power hours of the photovoltaic power generation system can be tracked over a long period of time, so as to promptly discover whether its performance shows a downward trend, and provide strong support for the long-term maintenance and management of the system equipment through analysis.

[0057] The power generation of a photovoltaic system is affected by factors such as solar radiation intensity, duration of sunshine, the ambient temperature of each device in the photovoltaic system, and seasonality. This can lead to significant fluctuations in the trend of the system's daily full-power hours over historical periods. For example, in the summer, when solar radiation intensity is high and sunshine duration is long and sufficient, the power generation of a photovoltaic system will be significantly greater than in the winter, when solar radiation intensity is low and sunshine duration is short and insufficient.

[0058] In some embodiments, when analyzing the changing trend of the daily full power hours of a photovoltaic power generation system within a historical period, the data on seasonal components in the data on the daily full power hours within the historical period can be first filtered out, and then the data on the daily full power hours after filtering can be analyzed to improve the accuracy of the performance evaluation of the photovoltaic power generation system.

[0059] For example, the number of daily full-power hours of a photovoltaic power generation system can be tracked over a period of time, such as on a yearly basis. The annual daily full-power hours are seasonally adjusted using data analysis methods to filter out seasonal components from the data and capture trends. This allows for more accurate analysis of the long-term operating trends of the photovoltaic power generation system and performance evaluation.

[0060] by Figure 2 The embodiment of the present application is described as follows. Figure 2In the embodiment, step S130 may include steps S210 to S230.

[0061] Step S210 , obtaining time series data of the daily full power generation hours of the photovoltaic power generation system according to the daily full power generation hours of the photovoltaic power generation system.

[0062] In some embodiments, the daily power generation and daily rated power of a photovoltaic power generation system can be obtained, and the daily full power generation hours of the photovoltaic power generation system can be calculated. For example, time series data of the daily full power generation hours of the photovoltaic power generation system over a period of time can be obtained. For example, time series data of the daily full power generation hours of the photovoltaic power generation system over a year can be obtained.

[0063] In some embodiments, a triple standard deviation (3sigma) algorithm may be used to detect the daily full power hours of a photovoltaic power generation system and remove outliers, thereby improving the data quality of the daily full power hours used for data analysis.

[0064] For example, when obtaining the daily power generation of a photovoltaic power generation system, some interference factors may cause the obtained daily power generation to be abnormal, which in turn leads to an abnormal number of daily full-power hours. For example, if the power generation data reported by the photovoltaic power generation system is delayed, or if the accumulated power generation data of the photovoltaic power generation system is reset to zero due to software failure, hardware failure, or other reasons during the operation of the equipment in the photovoltaic power generation system, it will be impossible to obtain the true information of the daily power generation.

[0065] In an embodiment of the present application, a triple standard deviation criterion algorithm can be used to detect the number of daily full-time hours and eliminate outliers in the number of daily full-time hours. For example, the triple standard deviation criterion algorithm is a statistical rule used to describe data distribution. This algorithm is based on normal distribution theory. In a normal distribution, approximately 99.73% of the data will fall within the range of ±3 times the mean, and data exceeding this range is considered an outlier. This method is widely used in scenarios such as quality management, process control, and anomaly detection.

[0066] by Figure 4 For example, Figure 4 It is a normal distribution graph, also known as a Gaussian distribution graph. Figure 4 The horizontal axis in represents the value range of the data, that is, the value range of the daily full-time hours. μ can represent the mean value of the daily full-time hours data set, and σ can represent the standard deviation of the daily full-time hours data set. Figure 4 The μ-3σ, μ-2σ, μ-σ, μ, μ+σ, μ+2σ, and μ+3σ in the equation can represent the value of the mean plus or minus several times the standard deviation. These values are used to divide the distribution range of the daily full-load hours. Figure 4The vertical axis in represents the probability density, which is the probability of a value within a unit interval around a specific value on the normal distribution curve. It can be understood that when the probability density is larger, the height of the curve at that point is higher, indicating that the data is more likely to take a value near that point.

[0067] Calculate the mean μ and standard deviation σ of the daily full-hours dataset collected within a month, and determine the lower threshold μ-3σ and upper threshold μ+3σ. Data in the daily full-hours dataset that exceeds the upper threshold μ+3σ or falls below the lower threshold μ-3σ are considered outliers and are removed from the daily full-hours dataset collected that month.

[0068] Step S220 , analyzing the time series data using a data analysis method to obtain analysis results of the time series data. The data analysis method is used to perform seasonal adjustments on the time series data to filter out data with seasonal components.

[0069] In some embodiments, a data analysis method can be used to seasonally adjust the time series data, and the data with seasonal components can be filtered out from the time series data of the daily full-power hours of the photovoltaic power generation system, so that the long-term trend of the performance of the photovoltaic power generation system can be more clearly identified, such as system aging, equipment attenuation, etc.

[0070] In some embodiments, the data analysis method is a time series analysis method. For example, the data analysis method can be a seasonal trend decomposition of timeseries (STL) analysis method based on local weighted regression. STL is a time series decomposition method using robust local weighted regression as a smoothing method, wherein local weighted regression (locally weighted scatterplot smoothing, LOWESS or LOESS) is a local polynomial regression fitting, which is a common method for smoothing two-dimensional scatter plots. The STL analysis method combines the simplicity of traditional linear regression and the flexibility of nonlinear regression. The STL analysis method can decompose time series data into seasonal component data, trend component data, and residual component data. Wherein, the residual component data is the data remaining after removing the seasonal component data and the trend component data from the time series data. The STL analysis method can extract the seasonal component data and the trend component data based on LOESS, and the remaining part is the residual component data.

[0071] For example, the STL analysis method is used to process time series data. The specific steps are as follows:

[0072] Extract trend components: Use LOESS to smooth the time series data to remove seasonal and residual effects, thereby obtaining the trend component.

[0073] Extracting seasonal components: Extracting seasonal fluctuations by subtracting the trend component from the original time series. This process also uses the LOESS method to smooth and extract periodic fluctuation patterns.

[0074] Residual component: The remaining component after removing the trend and seasonality is called the residual, which represents the unpredictable part of the time series data.

[0075] The STL analysis method can handle complex seasonal patterns. For example, traditional seasonal analysis methods require that the seasonal component must be fixed, while the STL analysis method can handle seasonal patterns that change over time through LOESS, making it more flexible. The STL analysis method has strong adaptability. For example, the STL analysis method can handle time series data with relatively smooth trend changes and is suitable for time series data with nonlinear trends, cyclical fluctuations, or different seasonal patterns. At the same time, the STL analysis method has good decomposition effects. For example, the STL analysis method can effectively separate the trend, seasonality, and residual components in time series data, which helps to understand the inherent structure of time series data and provide useful information for subsequent analysis. Therefore, compared with traditional seasonal decomposition methods, such as the classic additive / multiplicative decomposition, the STL analysis method is more flexible and robust, and is particularly suitable for time series with complex seasonal fluctuations.

[0076] Step S230 , evaluating the performance of the photovoltaic power generation system by analyzing the analysis results of the time series data.

[0077] After step S220, if the time series data is analyzed using the STL analysis method, trend data after LOESS smoothing can be obtained, and the trend data has filtered out seasonal components and residual component data. Based on the trend data, the performance of the photovoltaic power generation system can be evaluated.

[0078] In an embodiment of the present application, by adopting a data analysis method that can filter out seasonal component data to analyze the daily full-power hours of the photovoltaic power generation system, the trend analysis of the daily full-power hours of the photovoltaic power generation system can be clearly captured, and the long-term operating trend of the photovoltaic power generation system can be more accurately analyzed, and its performance can be evaluated.

[0079] In some embodiments, the peak point of the daily full-time hours represents the moment when the photovoltaic power generation system can achieve maximum utilization efficiency under specific conditions. The peak point can reflect the performance of the photovoltaic power generation system under optimal conditions, such as optimal light, temperature and operating conditions. As the photovoltaic power generation system ages, the daily full-time hours will be affected by seasonal factors such as light intensity, or the daily full-time hours will be affected by factors such as weather changes, and the curve of the daily full-time hours will fluctuate. In an embodiment of the present application, the peak values of the daily full-time hours of the photovoltaic power generation system in different time periods can be obtained, and based on the analysis of these peak values, the performance of the photovoltaic power generation system can be evaluated, so that the long-term trend of the performance of the photovoltaic power generation system can be more clearly reflected. For example, by obtaining the peak points of the daily full-time hours every year and analyzing the performance of the photovoltaic power generation system based on these peak points, the optimal operating state of the photovoltaic power generation system can be more accurately reflected, and the influence of the above factors on the photovoltaic power generation system can be eliminated, so as to track the long-term performance trend of the photovoltaic power generation system.

[0080] by Figure 3 Take this application as an example to illustrate the example. Figure 3 In the embodiment, step S130 may include steps 310 to 320.

[0081] Step S310: Obtain the peak value of the daily full power generation hours of the photovoltaic power generation system each year.

[0082] Step S320 , evaluating the performance of the photovoltaic power generation system by analyzing the peak value of the daily full power generation hours of the photovoltaic power generation system each year.

[0083] In some embodiments, as the photovoltaic power generation system ages, the equipment in the photovoltaic power generation system will also produce certain losses, which will cause the daily full-time hours of the photovoltaic power generation system to decay. This type of decay is within the normal range of decay. Therefore, taking a year as an example, the peak value of the daily full-time hours of the photovoltaic power generation system can be obtained each year. By analyzing these peak values, the long-term trend of the photovoltaic power generation system performance can be tracked. When abnormal peak decay is found, it can be considered that the performance of the photovoltaic power generation system is abnormal. For example, when the peak decay rate in a certain year is significantly faster than the peak decay rate in previous years, it can be considered that the performance of the photovoltaic power generation system is abnormal.

[0084] In some embodiments, data on the daily full-power hours of a photovoltaic power generation system can be aggregated on a monthly basis to obtain a monthly average of the daily full-power hours of the photovoltaic power generation system. The monthly average of the daily full-power hours of the photovoltaic power generation system can then be used to determine the annual peak value of the daily full-power hours of the photovoltaic power generation system. Obtaining the monthly average of the daily full-power hours of the photovoltaic power generation system can effectively smooth out fluctuations in the daily full-power hours curve caused by factors such as weather, reducing the interference of short-term factors on the data analysis of the daily full-power hours.

[0085] In some embodiments, the peak value of the daily full-time hours of the photovoltaic power generation system each year can be obtained by the peak detection (find_peaks) algorithm. For example, since the daily full-time hours are greatly affected by the weather season, for example, the value of the daily full-time hours reaches a peak in spring and summer, and the value of the daily full-time hours is at a low point in autumn and winter. Therefore, it is unreasonable to compare the daily full-time hours in the winter of the previous year with the daily full-time hours in the summer of the current year. However, the months in which the peak value of the daily full-time hours occurs are generally more stable, for example, in the summer. The find_peaks algorithm can be used to capture the peak value of the daily full-time hours, and then the attenuation trend of the photovoltaic power generation system can be obtained by comparing the peak values of the daily full-time hours in different years, and the performance of the photovoltaic power generation system can be evaluated.

[0086] The find_peaks algorithm is a function in the SciPy library that is used to find local peaks in one-dimensional data. This function can help identify the peak locations in the data to be processed. The find_peaks algorithm identifies local peaks based on a set of rules and conditions. The find_peaks algorithm can include the following steps:

[0087] Step 1: Detection of local maxima. By default, the find_peaks algorithm considers a point to be a peak if and only if it is higher than both its left and right neighbors. Suppose we have a sequence y[i-1], y[i], y[i+1], and y[i]>y[i-1] and y[i]>y[i+1], then y[i] will be considered a peak.

[0088] Step 2, adjustable parameter conditions. In order to detect the peaks of the data to be processed more accurately and flexibly, the find_peaks algorithm allows the characteristics of the peaks to be defined by parameters, such as: height represents the lowest height of the peak. Distance represents the minimum horizontal distance between adjacent peaks. Prominence represents prominence, that is, the height difference between the peak and the valley around it. Width represents the width of the peak, which can also be understood as the distance required for both sides of the peak to drop to a certain height. Threshold represents the minimum difference between the peak and its adjacent values. Among them, height can only return peaks that exceed this height. Distance can avoid identifying multiple small peaks that are too close, and distance can also help screen significant peaks and ignore small fluctuations. Threshold can further filter out some small fluctuations.

[0089] Step 3: Condition-based iterative search. The find_peaks algorithm first finds all points that meet the local maximum conditions, then gradually applies the above parameter conditions to filter out peaks that do not meet the conditions. This is an iterative filtering process, where each parameter limit acts as a filter condition, gradually eliminating peaks that do not meet the conditions.

[0090] The daily peak hours of a photovoltaic power generation system are affected by factors such as solar radiation intensity, duration of sunshine, the ambient temperature of each device in the photovoltaic power generation system, and seasonality, resulting in a complex data environment. The find_peaks algorithm provides a rich set of parameter options, allowing for flexible adjustment of peak detection conditions based on data characteristics to adapt to various complex data environments. By adjusting parameters, accurate peak detection is achieved. Therefore, the find_peaks algorithm offers greater flexibility and accuracy when processing daily peak hours.

[0091] In some embodiments, step S320 may further include performing a linear regression fit on the obtained peak values of the daily full-power hours of the photovoltaic power generation system each year, thereby calculating the decay rate of the daily full-power hours over the historical period. Based on the decay rate, the performance of the photovoltaic power generation system can be evaluated.

[0092] In some embodiments, the decay rate may include an annual decay rate and an overall decay rate.

[0093] In some embodiments, after obtaining the peak value of the daily full power hours of the photovoltaic power generation system each year, the annual attenuation rate of the daily full power hours each year can be calculated based on the difference in the peak values of the daily full power hours from year to year.

[0094] For example, the annual decay rate can be calculated by subtracting the peak value of the daily full-load hours of this year from the peak value of the daily full-load hours of last year, and dividing the result by the peak value of the daily full-load hours of last year. The percentage obtained can be used as the annual decay rate. For example, the decay rate formula can be R s It can be considered as the peak value last year. e It can be considered as the peak value of this year. For example, if the peak value of daily full-load hours in 2020 is 3.056944 and the peak value of daily full-load hours in 2021 is 2.548304, then the annual decay rate of daily full-load hours from 2020 to 2021 is And so on.

[0095] In some embodiments, the performance of the photovoltaic power generation system can be evaluated based on the annual decay rate of the number of full-time hours per day.

[0096] For example, the performance of a photovoltaic power generation system can be evaluated based on the annual decay rate of the daily full-time hours over a historical period. For example, if the annual decay rate decays according to a certain rule, it can be considered that the performance of the photovoltaic power generation system is normal, and its performance decay may be due to attenuation caused by sunlight or equipment aging. If the annual decay rate suddenly drops sharply, it can be considered that the performance decay of the photovoltaic power generation system is abnormal. For example, if the annual decay rate of the daily full-time hours from 2020 to 2021 is 16.64%, and the annual decay rate of the daily full-time hours from 2023 to 2024 is 60.84%, the annual decay rate has dropped sharply, and it can be considered that the performance of the photovoltaic power generation system is abnormal at this time.

[0097] In some embodiments, a linear regression fit can be performed on the obtained peak values of the daily full-power hours of the photovoltaic power generation system each year, and the overall decay rate of the daily full-power hours can be calculated based on the fitted data. The performance of the photovoltaic power generation system can be evaluated based on the overall decay rate of the daily full-power hours over the historical period.

[0098] In some embodiments, linear regression fitting can be used to construct a curve reflecting the changing trend based on the peak points of daily full-power hours obtained over a historical period. This curve not only provides a visual representation of the temporal evolution of daily full-power hours, but also overcomes the shortcomings of analyzing only discrete peak points. Furthermore, since photovoltaic power generation systems are subject to significant fluctuations due to multiple factors, linear regression fitting can smooth these fluctuating data and extract a stable overall attenuation trend, making the analysis more reliable and avoiding misjudgments due to short-term data fluctuations.

[0099] The following mentioned Figure 8 For example, Figure 8The peak diagram of the daily full-time hours of the photovoltaic power generation system shown in the figure includes a linear attenuation trend curve and an actual data curve. Figure 8 The actual data curve in the figure is obtained based on the peak value of the daily full-time hours of the photovoltaic power generation system each year. Figure 8 The linear attenuation trend curve in the figure is obtained by linear regression fitting based on the peak value of the daily full-time hours of the photovoltaic power generation system each year. Figure 8 It can be seen from the data that the daily full-power hours of photovoltaic power generation systems will decline from 2020 to 2024.

[0100] Optionally, the overall decay rate of the daily full-load hours in the historical period can be calculated using the above Figure 8 In the linear attenuation trend curve, the ending value of the curve is subtracted from the starting value of the curve, and then divided by the starting value of the curve to get the percentage value. For example, first perform a linear regression fit on the peak value of the daily full-time hours in a historical period, such as Figure 8 As shown in Figure 2, a linear regression fitting can be performed on the peak values of daily full-load hours from 2020 to 2024, and a linear attenuation trend curve can be generated after fitting. In this curve, the peak value of daily full-load hours in 2020 after fitting is 3.156460, and the peak value of daily full-load hours in 2024 is 1.151738. Therefore, the overall attenuation rate of daily full-load hours from 2020 to 2024 is The overall attenuation rate can be compared with the industry average. If the overall attenuation rate of the daily full-power hours in the historical period is higher than the industry average, it can be considered that the performance of the photovoltaic power generation system is abnormal.

[0101] In some embodiments, the performance of the photovoltaic power generation system can be evaluated based on the annual decay rate of the peak daily full power hours of the photovoltaic power generation system year by year, combined with the overall decay rate of the daily full power hours in a historical period.

[0102] For example, the annual decay rates of the daily full-power hours over a historical period can be added together and compared with the overall decay rate of the daily full-power hours over the historical period. If the difference is within a certain range, the performance of the photovoltaic power generation system can be considered normal. If the difference is too large, the performance of the photovoltaic power generation system can be considered abnormal.

[0103] In some embodiments, the average annual decay rate can be calculated based on the overall decay rate and the number of years in the historical period. The performance of the photovoltaic power generation system can be evaluated by comparing the average annual decay rate with the annual decay rate mentioned above. In the above embodiment, the average annual decay rate from 2020 to 2024 is

[0104] For example, the annual average decay rate can be compared with the actual measured annual decay rate. If there is a large difference between the two, it can be considered that the performance of the photovoltaic power generation system is abnormal. For example, from 2020 to 2024, the annual average decay rate is The annual attenuation rate from 2023 to 2024 is 60.84%, which means that the performance of the photovoltaic power generation system is abnormal.

[0105] In some embodiments, the service life of the inverter in the photovoltaic power generation system may be no less than a first threshold. Optionally, the first threshold may be 3 years.

[0106] For example, long-term tracking of the performance of a photovoltaic power generation system requires a certain cost, such as human or material resources. Since the inverter is a key device in the photovoltaic power generation system, and generally speaking, the performance of the inverter is relatively stable within 3 years, when the inverter is used for more than 3 years, performance aging problems may occur, thereby affecting the performance of the photovoltaic power generation system. Therefore, in order to save system costs, system resources can be allocated more efficiently, and the performance of photovoltaic power generation systems with longer service time can be evaluated first. For example, photovoltaic power generation systems including long-cycle inverters can be screened out for long-term performance evaluation and tracking. For example, photovoltaic power generation systems with inverters that have been in use for more than 3 years.

[0107] Next, combine Figures 5 to 8 , the embodiments of this application are described in detail. Figure 5 Shown is a flow chart of a photovoltaic power generation system evaluation method provided in an embodiment of the present application.

[0108] Figure 5 The method shown in includes steps S510 to S560.

[0109] Step S510: collecting data on daily full-time hours.

[0110] The daily power generation of the photovoltaic power generation system can be obtained. For example, a power generation record can be reported at a frequency of 5 minutes. Generally, the daily power generation will reach its maximum value in the evening and remain unchanged until it is reset to zero the next day, thereby obtaining the maximum power generation of the day.

[0111] The daily rated power of the photovoltaic power generation system is obtained, and the number of hours of full power generation per day is calculated. Generally, the number of hours of full power generation per day is around 3-8 hours.

[0112] In some embodiments, the inverter can be a single-phase inverter or a three-phase inverter. The daily power generation of a photovoltaic power generation system may vary for different types of inverters, or for inverters of the same type with different capacities. Similarly, the daily rated power of a photovoltaic power generation system may also vary for different types of inverters, or for inverters of the same type with different capacities. Therefore, using the daily full power hours allows for comparison of different inverters on a comparable basis.

[0113] Optionally, PV power generation systems with inverters connected for more than three years may be screened for data tracking and analysis of daily full power generation hours.

[0114] Step S520: processing the data of daily full-time delivery hours.

[0115] In some embodiments, a triple standard deviation algorithm may be used to process the daily full-load hours data to eliminate abnormal values.

[0116] In some embodiments, time series data of the daily full power hours of the photovoltaic power generation system can be obtained based on the daily full power hours of the photovoltaic power generation system. A time series diagram of the daily full power hours of the photovoltaic power generation system can be drawn based on this time series data to intuitively observe the long-term operating trend of the photovoltaic power generation system.

[0117] Step S530: analyzing the data of daily full-time delivery hours.

[0118] In some embodiments, since the daily full-power hours are significantly affected by weather and seasonal changes and have large fluctuations, the STL analysis method can be used to analyze the daily full-power hours of the photovoltaic power generation system, capture the trend component data therein, and filter out the seasonal component data and residual component data, so as to more accurately analyze the long-term operating trend of the photovoltaic power generation system.

[0119] like Figure 6 As shown, Figure 6 This is a data chart of the daily full-load hours that has been analyzed using the STL analysis method. Figure 6 The top graph is a time series data graph of the daily full-time hours. By analyzing the time series data of the daily full-time hours, the following three graphs are obtained: a trend component data graph, a seasonal component data graph, and a residual component data graph.

[0120] The STL analysis method is used to obtain trend component data that have been stripped of seasonal component data and residual component data. From the trend component data graph, it can be seen that there are relatively obvious peaks and valleys. However, due to the large fluctuation of the original data, the trend component data graph still has a certain degree of volatility.

[0121] Step S540: Aggregate data on the daily full-time hours.

[0122] The trend component data captured in step S530 still has a certain degree of volatility. The trend component data of the daily full dispatch hours can be aggregated by month to obtain the monthly average of the daily full dispatch hours, making the trend of the daily full dispatch hours more significant.

[0123] Step S550: Peak detection of daily full-time transmission hours data.

[0124] The peak detection algorithm can be used to perform peak detection on the monthly average of the aggregated daily full-time hours to obtain the peak point of the daily full-time hours each year to analyze the operating status and change trend of the photovoltaic power generation system year by year. Figure 7 As shown in Figure 2, the number of hours of full-time operation per day varies periodically and is closely related to the season. Figure 7 It can be seen that the number of daily full-time hours reaches a peak in spring and summer, and a trough in autumn and winter.

[0125] Step S560: Calculate the decay of the daily full-power hours.

[0126] The peak point of the daily full-power hours each year can be obtained according to step S550, and the yearly decay rate can be calculated.

[0127] Optionally, a linear regression machine learning model can be used to fit a regression curve to the peak points of the daily full-power hours obtained each year to calculate the overall attenuation rate.

[0128] like Figure 8 As shown, the straight line represents the actual data curve represented by the peak value of the daily full-time hours actually obtained. According to the actual data curve, the attenuation rate formula can be combined Calculate the annual decay rate of daily full-power hours year by year.

[0129] For example, the annual decay rate in 2021 relative to 2020 And so on.

[0130] At the same time Figure 8 In the figure, the dotted line can be used to represent the fitted data curve, which can also be called the linear decay trend. The overall decay rate can continue to be used Calculation, R s is the starting value, R e is the termination value, and the calculation of the average annual decay rate can be expressed as f=d / y, where y is the service life interval.

[0131] For example, the average annual decay rate = overall decay rate / number of data, the overall decay rate Figure 8 There are 4 intervals from 2020 to 2024, so the average annual decay rate is

[0132] Table 1 shows Figure 8 The attenuation result of the daily full-power hours curve is shown.

[0133] Table 1

[0134]

[0135] Step S570: performing attenuation analysis on the daily full-power hours.

[0136] The attenuation rate obtained in step S560 can be used to evaluate the operation of the photovoltaic power generation system. Photovoltaic power generation systems with severe overall attenuation or a steep drop in attenuation require special attention.

[0137] For example, as can be seen from Table 1 above, in 2024, the annual attenuation rate drops sharply, which requires special attention.

[0138] In the embodiment of the present application, the daily full-power hours of the photovoltaic power generation system can be used to construct a unified evaluation framework, which is convenient for evaluating the performance of different photovoltaic power generation systems or the same system at different time periods. Since its calculation is simple and can intuitively reflect the actual utilization efficiency of the system, the daily full-power hours of the photovoltaic power generation system can be tracked over a long period of time to promptly detect whether its performance shows a downward trend, and provide strong support for the long-term maintenance and management of the system equipment through analysis. At the same time, in the embodiment of the present application, by adopting a data analysis method that filters out seasonal components to analyze the daily full-power hours of the photovoltaic power generation system, its trend changes can be clearly captured, thereby more accurately evaluating the long-term operating trends and performance of the photovoltaic power generation system.

[0139] The above describes the method embodiment of the present application in detail. Based on the above content, the present application also proposes a photovoltaic power generation system. Figure 9 The system embodiment of the present application is described in detail. It should be understood that the description of the above method embodiment corresponds to the description of the system embodiment, so for parts not described in detail, reference can be made to the above method embodiment.

[0140] Figure 9 This is a schematic structural diagram of a photovoltaic power generation system provided in an embodiment of the present application. Figure 9 The photovoltaic power generation system 900 shown can be electrically connected to a power grid, and includes:

[0141] The photovoltaic management unit 910 includes a photovoltaic component.

[0142] The inverter 920 has one end electrically connected to the photovoltaic management unit, and the other end electrically connected to the grid.

[0143] Evaluation unit 930, the evaluation unit 930 is used to evaluate the performance of the photovoltaic power generation system by analyzing the changing trend of the daily full-power hours of the photovoltaic power generation system in a historical period, wherein the daily full-power hours of the photovoltaic power generation system are calculated based on the daily power generation data of the photovoltaic power generation system, and the daily power generation data of the photovoltaic power generation system includes: the daily power generation of the photovoltaic power generation system and the daily rated power of the photovoltaic power generation system.

[0144] Optionally, the evaluation unit 930 can also be used to obtain time series data of the daily full-time power generation hours of the photovoltaic power generation system based on the daily full-time power generation hours of the photovoltaic power generation system; and analyze the time series data through a data analysis method to obtain analysis results of the time series data, and the data analysis method is used to seasonally adjust the time series data to filter out data with seasonal components; and evaluate the performance of the photovoltaic power generation system by analyzing the analysis results of the time series data.

[0145] Optionally, the data analysis method can be a seasonal trend decomposition STL analysis method based on local weighted regression. The STL analysis method is used to decompose time series data into seasonal component data, trend component data and residual component data. The residual component data is the data remaining after removing the seasonal component data and trend component data from the time series data.

[0146] Optionally, the evaluation unit 930 can also be used to obtain the peak value of the daily full-time hours of the photovoltaic power generation system each year; and evaluate the performance of the photovoltaic power generation system by analyzing the peak value of the daily full-time hours of the photovoltaic power generation system each year.

[0147] Optionally, the evaluation unit 930 can also be used to obtain the monthly average of the daily full-power hours of the photovoltaic power generation system by aggregating data on the daily full-power hours of the photovoltaic power generation system on a monthly basis; and obtain the peak value of the daily full-power hours of the photovoltaic power generation system each year through the monthly average of the daily full-power hours of the photovoltaic power generation system.

[0148] Optionally, the evaluation unit 930 may also be configured to obtain the peak value of the daily full power generation hours of the photovoltaic power generation system each year through a peak detection algorithm.

[0149] Optionally, the evaluation unit 930 may also be configured to eliminate abnormal values in the daily full power generation hours of the photovoltaic power generation system.

[0150] Optionally, the service life of the inverter is not less than a first threshold, where the first threshold may be 3 years.

[0151] In addition, an embodiment of the present application also proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a computer, the operations in the photovoltaic power generation system evaluation method provided in the above embodiment are implemented. The specific steps will not be described in detail here.

[0152] The embodiment of the present application further provides a computer program, which includes commands for executing the photovoltaic power generation system evaluation method provided by the above embodiment.

[0153] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity / operation / object from another entity / operation / object, and do not necessarily require or imply any actual relationship or order between these entities / operations / objects; the terms "include", "comprise", or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or system that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "includes a ..." does not exclude the presence of other identical elements in the process, method, article, or system that includes the element.

[0154] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For relevant details, please refer to the partial description of the method embodiment. The device embodiment described above is merely illustrative, and the units described as separate components may or may not be physically separated. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present application scheme. Those of ordinary skill in the art can understand and implement it without paying any creative work.

[0155] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0156] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, TV, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0157] The above are merely embodiments of the present application and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for evaluating a photovoltaic power generation system, characterized in that: The photovoltaic power generation system is electrically connected to a power grid, and includes a photovoltaic management unit and an inverter. The photovoltaic management unit includes photovoltaic modules, and the photovoltaic management unit is electrically connected to the inverter, and the inverter is electrically connected to the power grid. The evaluation method includes: Acquire daily power generation data of the photovoltaic power generation system within a historical period, wherein the daily power generation data of the photovoltaic power generation system includes: daily power generation of the photovoltaic power generation system and daily rated power of the photovoltaic power generation system; Calculating the daily full power generation hours of the photovoltaic power generation system based on the daily power generation data of the photovoltaic power generation system; The performance of the photovoltaic power generation system is evaluated by analyzing the changing trend of the daily full power generation hours of the photovoltaic power generation system within the historical period.

2. The evaluation method according to claim 1, wherein: The evaluating the performance of the photovoltaic power generation system by analyzing the changing trend of the daily full power generation hours of the photovoltaic power generation system in the historical period includes: According to the daily full power generation hours of the photovoltaic power generation system, obtaining time series data of the daily full power generation hours of the photovoltaic power generation system; Analyzing the time series data using a data analysis method to obtain analysis results of the time series data, wherein the data analysis method is used to seasonally adjust the time series data to filter out data with seasonal components; The performance of the photovoltaic power generation system is evaluated by analyzing the analysis results of the time series data.

3. The evaluation method according to claim 2, wherein: The data analysis method is a seasonal trend decomposition STL analysis method based on local weighted regression. The STL analysis method is used to decompose the time series data into seasonal component data, trend component data and residual component data. The residual component data is the data remaining after removing the seasonal component data and trend component data from the time series data.

4. The evaluation method according to claim 1, wherein: The evaluating the performance of the photovoltaic power generation system by analyzing the changing trend of the daily full power generation hours of the photovoltaic power generation system in the historical period includes: Obtaining the peak value of the daily full power generation hours of the photovoltaic power generation system each year; The performance of the photovoltaic power generation system is evaluated by analyzing the peak value of the daily full power generation hours of the photovoltaic power generation system each year.

5. The evaluation method according to claim 4, characterized in that The obtaining of the peak value of the daily full power generation hours of the photovoltaic power generation system each year includes: aggregating data on the daily full power hours of the photovoltaic power generation system on a monthly basis to obtain a monthly average of the daily full power hours of the photovoltaic power generation system; The peak value of the daily full power generation hours of the photovoltaic power generation system each year is obtained by using the monthly average value of the daily full power generation hours of the photovoltaic power generation system each month.

6. The evaluation method according to claim 4, characterized in that The obtaining of the peak value of the daily full power generation hours of the photovoltaic power generation system each year further comprises: obtaining the peak value of the daily full power generation hours of the photovoltaic power generation system each year by using a peak detection algorithm.

7. The evaluation method according to claim 4, characterized in that The performance of the photovoltaic power generation system is evaluated by analyzing the peak value of the daily full power generation hours of the photovoltaic power generation system each year, including: Performing linear regression fitting on the obtained peak values of the daily full-power hours of the photovoltaic power generation system each year, and calculating the decay rate of the daily full-power hours in the historical period; The performance of the photovoltaic power generation system is evaluated according to the attenuation rate.

8. The evaluation method according to claim 1, wherein: Before evaluating the performance of the photovoltaic power generation system by analyzing the changing trend of the daily full power generation hours of the photovoltaic power generation system within the historical period, the evaluation method further includes: A triple standard deviation criterion algorithm is used to detect the daily full power generation hours of the photovoltaic power generation system, and abnormal values in the daily full power generation hours of the photovoltaic power generation system are eliminated.

9. A photovoltaic power generation system, characterized in that: The photovoltaic power generation system is electrically connected to the power grid, and the photovoltaic power generation system includes: A photovoltaic management unit, wherein the photovoltaic management unit includes a photovoltaic module; an inverter, one end of the inverter being electrically connected to the PV management unit, and the other end of the inverter being electrically connected to the grid; An evaluation unit is configured to evaluate the performance of the photovoltaic power generation system by analyzing a changing trend of the daily full-power hours of the photovoltaic power generation system within a historical period, wherein the daily full-power hours of the photovoltaic power generation system are calculated based on the daily power generation data of the photovoltaic power generation system, and the daily power generation data of the photovoltaic power generation system includes: the daily power generation of the photovoltaic power generation system and the daily rated power of the photovoltaic power generation system.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the photovoltaic power generation system evaluation method according to any one of claims 1 to 8 is implemented.

Images