Method, device, equipment and medium for determining annual power generation of a wind farm

Abstract

The present application discloses a method, device, equipment and medium for determining the annual power generation of a wind farm. The method uses a trained wind speed prediction model to analyze a historical wind speed time series of a set duration to obtain an estimated annual average wind speed; based on the estimated annual average wind speed and the actual annual average wind speed, the interannual variation rate of the wind speed is obtained. The wind speed at the hub height of the wind turbine is a key factor in determining the power generation of a wind farm. Therefore, the interannual variation rate of the hub height wind speed can be determined based on the linear relationship between the hub height wind speed and the historical wind speed and the interannual variation rate of the wind speed. The interannual variation rate of the power generation can be determined based on the wind speed sensitivity factor, power, wind speed, wind frequency and the interannual variation rate of the hub height wind speed in each wind speed segment; the interannual variation rate of power generation is used to evaluate the change in power generation in the next year. Based on the interannual variation rate of power generation and the actual power generation in the current year, the estimated power generation in the next year can be determined, thereby realizing the prediction of the long-term power generation of the wind farm.

Description

Technical Field

[0001] The present application relates to the technical field of wind power generation, and in particular to a method, apparatus, device, and computer-readable storage medium for determining the annual power generation of a wind farm. Background Art

[0002] my country's wind resources are unevenly distributed, concentrated primarily in the "Three Northern" regions, while power load centers are primarily in East China. With the large-scale development and grid integration of wind power in my country, the challenge of maximizing wind power consumption has become increasingly prominent. Cross-regional power dispatch and market-based power trading are effective means of addressing this issue.

[0003] Transmission from wind power bases is primarily based on long-term transactions, and cross-regional power trading often relies on annual contracts supplemented by monthly temporary transactions. Therefore, long-term power generation forecasts for wind farms are necessary to provide a basis for the effective implementation of cross-regional, long-term power transmission and market transactions, maximizing the generation capacity of wind farms and the transmission capacity of transmission channels.

[0004] Currently, methods used to predict wind farm power generation fall into three main categories. The first is physical methods: These use Numerical Weather Prediction (NWP) as input data and, combined with information about the surrounding terrain and roughness, simulate wind speed at hub height, thereby deriving power generation from the wind farm. This method is computationally intensive and time-consuming, and is generally used for power generation assessment during wind farm site selection. The second is time series methods: Based on past wind speed or power generation data from a wind farm, a prediction model is established through pattern recognition, parameter estimation, and model verification. This method requires a large amount of historical data over a long period of time. However, wind farms currently operate for relatively short periods of time, and this data is insufficient to meet the algorithm's requirements. The third is machine learning methods: These utilize artificial intelligence learning methods such as neural networks and support vector machines, learning and training on large amounts of historical data to establish a nonlinear mapping relationship between input variables and output power. This method is primarily suitable for short-term wind farm power generation forecasting and is not suitable for long-term power generation forecasting.

[0005] It can be seen that how to predict the long-term power generation of a wind farm is a problem that those skilled in the art need to solve. Summary of the Invention

[0006] The purpose of the embodiments of the present application is to provide a method, device, equipment and medium for determining the annual power generation of a wind farm, which can realize the prediction of the long-term power generation of the wind farm.

[0007] To solve the above technical problems, an embodiment of the present application provides a method for determining the annual power generation of a wind farm, comprising:

[0008] Use the trained wind speed prediction model to analyze the historical wind speed time series of a set period to obtain the estimated annual average wind speed;

[0009] The interannual variation rate of wind speed is obtained based on the annual estimated average wind speed and the annual actual average wind speed;

[0010] Determining the interannual variation rate of the hub height wind speed based on the linear relationship between the hub height wind speed and the historical wind speed and the interannual variation rate of the wind speed;

[0011] Determine the interannual variation rate of generated electricity based on the wind speed sensitivity factor, power, wind speed, wind frequency of each wind speed segment and the interannual variation rate of the wind speed at the hub height;

[0012] Based on the inter-annual change rate of power generation and the actual power generation in the current year, the estimated power generation for the next year is determined.

[0013] Optionally, obtaining the interannual change rate of wind speed based on the annual estimated average wind speed and the annual actual average wind speed includes:

[0014] Calculating the difference between the estimated annual average wind speed and the actual annual average wind speed;

[0015] The ratio of the difference to the actual annual average wind speed is taken as the interannual change rate of wind speed.

[0016] Optionally, determining the interannual variation rate of the hub height wind speed based on the linear relationship between the hub height wind speed and the historical wind speed and the interannual variation rate of the wind speed includes:

[0017] Perform correlation analysis on the wind speed time series at the hub height of the wind tower and the preset historical wind speed time series to determine the linear relationship between the wind speed at the hub height and the historical wind speed;

[0018] The interannual variation rate of wind speed is corrected based on the linear relationship to obtain the interannual variation rate of wind speed at hub height.

[0019] Optionally, determining the inter-annual variation rate of electric power generation according to the wind speed sensitivity factor, power, wind speed, wind frequency of each wind speed segment and the inter-annual variation rate of the wind speed at the hub height includes:

[0020] According to the obtained dynamic power curve of the wind turbine, the power and wind speed corresponding to each wind speed segment are determined;

[0021] Determining a wind speed sensitivity factor corresponding to the current wind speed segment based on the power and wind speed corresponding to the current wind speed segment and the power and wind speed corresponding to the wind speed segment forwardly adjacent to the current wind speed segment;

[0022] Determine a wind speed sensitivity coefficient based on the wind speed sensitivity factor, power, wind speed, and wind frequency corresponding to all the wind speed segments;

[0023] The product of the wind speed sensitivity coefficient and the inter-annual variation rate of the hub height wind speed is used as the inter-annual variation rate of power generation.

[0024] Optionally, determining the wind speed sensitivity coefficient according to the wind speed sensitivity factors, power, wind speed, and wind frequency corresponding to all the wind speed segments includes:

[0025] When the wind speed sensitivity factor, power, wind speed and wind frequency corresponding to all the wind speed segments are obtained, the wind speed sensitivity coefficient formula is called to calculate the wind speed sensitivity coefficient;

[0026] The wind speed sensitivity coefficient formula is:

[0027]

[0028] Among them, ξ E,v represents the wind speed sensitivity coefficient, f k represents the wind frequency corresponding to the k-th wind speed segment, c v,k represents the wind speed sensitivity factor corresponding to the k-th wind speed segment, v k represents the wind speed corresponding to the k-th wind speed segment, p k represents the power corresponding to the kth wind speed segment, and N represents the total number of wind speed segments.

[0029] Optionally, the training process of the wind speed prediction model includes:

[0030] Obtain the initial wind speed time series of the preset sample size;

[0031] Converting the initial wind speed time series into a wind speed time series to be trained with a monthly resolution;

[0032] The initial wind speed prediction model is trained using the wind speed time series to be trained to obtain a trained wind speed prediction model.

[0033] Optionally, analyzing a historical wind speed time series of a set duration using a trained wind speed prediction model to obtain an estimated annual average wind speed includes:

[0034] Inputting the acquired historical wind speed time series into the trained wind speed prediction model to obtain the monthly estimated average wind speed corresponding to each of the twelve months;

[0035] The average of all the monthly estimated average wind speeds is taken as the annual estimated average wind speed.

[0036] The embodiment of the present application further provides a device for determining the annual power generation of a wind farm, comprising an analyzing unit, an obtaining unit, a first determining unit, a second determining unit, and a third determining unit;

[0037] The analysis unit is used to analyze the historical wind speed time series of a set time period using the trained wind speed prediction model to obtain the annual estimated average wind speed;

[0038] The obtaining unit is used to obtain the interannual change rate of wind speed based on the annual estimated average wind speed and the annual actual average wind speed;

[0039] The first determining unit is configured to determine the interannual variation rate of the hub height wind speed based on the linear relationship between the hub height wind speed and the historical wind speed and the interannual variation rate of the wind speed;

[0040] The second determining unit is configured to determine the interannual variation rate of the generated electricity based on the wind speed sensitivity factor, power, wind speed, wind frequency of each wind speed segment and the interannual variation rate of the wind speed at the hub height;

[0041] The third determining unit is configured to determine the estimated power generation for the next year based on the inter-annual change rate of power generation and the actual power generation for the current year.

[0042] Optionally, the obtaining unit includes a calculating subunit and an acting subunit;

[0043] The calculation subunit is used to calculate the difference between the annual estimated average wind speed and the annual actual average wind speed;

[0044] The subunit is used to take the ratio of the difference to the actual annual average wind speed as the interannual change rate of wind speed.

[0045] Optionally, the first determination unit is used to perform a correlation analysis on the wind speed time series at the hub height of the wind measurement tower and a preset historical wind speed time series to determine a linear relationship between the hub height wind speed and the historical wind speed; and based on the linear relationship, correct the interannual variation rate of the wind speed to obtain the interannual variation rate of the hub height wind speed.

[0046] Optionally, the second determining unit includes a parameter determining subunit, a factor determining subunit, a coefficient determining subunit and an as subunit;

[0047] The parameter determination subunit is used to determine the power and wind speed corresponding to each wind speed segment based on the acquired dynamic power curve of the wind turbine generator set;

[0048] The factor determination subunit is configured to determine a wind speed sensitivity factor corresponding to the current wind speed segment based on the power and wind speed corresponding to the current wind speed segment and the power and wind speed corresponding to the wind speed segment forwardly adjacent to the current wind speed segment;

[0049] The coefficient determination subunit is used to determine the wind speed sensitivity coefficient according to the wind speed sensitivity factor, power, wind speed and wind frequency corresponding to all the wind speed segments;

[0050] The subunit is configured to take the product of the wind speed sensitivity coefficient and the inter-annual variation rate of the hub height wind speed as the inter-annual variation rate of power generation.

[0051] Optionally, the coefficient determination subunit is configured to, upon obtaining the wind speed sensitivity factors, power, wind speed, and wind frequency corresponding to all the wind speed segments, call a wind speed sensitivity coefficient formula to calculate the wind speed sensitivity coefficient;

[0052] The wind speed sensitivity coefficient formula is:

[0053]

[0054] Among them, ξ E,v represents the wind speed sensitivity coefficient, f k represents the wind frequency corresponding to the k-th wind speed segment, c v,k represents the wind speed sensitivity factor corresponding to the k-th wind speed segment, v k represents the wind speed corresponding to the k-th wind speed segment, p k represents the power corresponding to the kth wind speed segment, and N represents the total number of wind speed segments.

[0055] Optionally, with respect to the training process of the wind speed prediction model, the device further includes an acquisition unit, a conversion unit, and a training unit;

[0056] The acquisition unit is used to acquire an initial wind speed time series of a preset sample size;

[0057] The conversion unit is used to convert the initial wind speed time series into a wind speed time series to be trained with a monthly resolution;

[0058] The training unit is used to train the initial wind speed prediction model using the wind speed time series to be trained to obtain a trained wind speed prediction model.

[0059] Optionally, the analysis unit is used to input the acquired historical wind speed time series into the trained wind speed prediction model to obtain the monthly estimated average wind speed corresponding to each of the twelve months; and take the average of all the monthly estimated average wind speeds as the annual estimated average wind speed.

[0060] An embodiment of the present application further provides an electronic device, including:

[0061] memory for storing computer programs;

[0062] A processor is configured to execute the computer program to implement the steps of the above-mentioned method for determining the annual power generation of a wind farm.

[0063] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for determining the annual power generation of a wind farm as described above are implemented.

[0064] As can be seen from the above technical solution, the trained wind speed prediction model is used to analyze the historical wind speed time series of a set time length to obtain the annual estimated average wind speed; based on the annual estimated average wind speed and the annual actual average wind speed, the interannual variation rate of wind speed is obtained. The interannual variation rate of wind speed is used to reflect the wind speed changes in long-term meteorological data. Its spatial resolution is usually tens of kilometers, which cannot accurately characterize the wind speed changes in the selected wind farm. Therefore, in practical applications, when predicting the power generation of a selected wind farm, it is necessary to adjust the interannual variation rate of wind speed to obtain a wind speed variation rate that is more in line with the actual situation of the wind farm. The wind speed at the hub height of the wind turbine is a key factor in determining the power generation of the wind farm. Therefore, in this application, the interannual variation rate of the hub height wind speed can be determined based on the linear relationship between the hub height wind speed and the historical wind speed and the interannual variation rate of wind speed. The interannual variation rate of the hub height wind speed can reflect the interannual variation of the wind speed of the currently selected wind farm. Wind speed sensitivity factor, power, wind speed, and wind frequency are important parameters that reflect changes in power generation. The interannual variability of power generation can be determined based on the wind speed sensitivity factor, power, wind speed, wind frequency, and the interannual variability of hub-height wind speed for each wind speed range. The interannual variability of power generation is used to assess changes in power generation for the following year. Based on the interannual variability and the actual power generation for the current year, the estimated power generation for the following year can be determined, enabling long-term power generation forecasting for the wind farm. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0066] Figure 1 A flow chart of a method for determining the annual power generation of a wind farm provided in an embodiment of the present application;

[0067] Figure 2 A schematic diagram of the structure of a device for determining the annual power generation of a wind farm provided in an embodiment of the present application;

[0068] Figure 3 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] The following will be combined with the accompanying 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 only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0070] The terms "including" and "having," as well as any variations thereof, in the specification and claims of this application and the accompanying drawings, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements and may include steps or elements that are not listed.

[0071] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0072] Next, a method for determining the annual power generation of a wind farm provided by an embodiment of the present application is described in detail. Figure 1 A flow chart of a method for determining the annual power generation of a wind farm provided in an embodiment of the present application, the method comprising:

[0073] S101: Analyze the historical wind speed time series of a set time period using the trained wind speed prediction model to obtain an estimated annual average wind speed.

[0074] In the embodiment of the present application, a seasonal autoregressive integrated moving average model (SARIMA) is used as a wind speed prediction model.

[0075] The wind speed prediction model is trained by a large amount of wind speed time series data so that the wind speed prediction model can estimate the monthly average wind speed. In the embodiment of the present application, the output result of the wind speed prediction model can be referred to as the monthly estimated average wind speed.

[0076] In order to meet the long-term power generation forecast, the number of output results of the wind speed prediction model can be controlled. For example, when the annual power generation needs to be predicted, when training the wind speed prediction model, the wind speed prediction model can be set to output the estimated monthly average wind speed for 12 months.

[0077] To improve the accuracy of the wind speed prediction model, a large amount of sample data can be selected for training. In practical applications, wind speed time series from datasets such as EAR5 and MERRA-2 can be downloaded from the internet and a preset number of wind speed time series can be selected as samples. The preset number of samples can be set based on actual needs. For example, the preset number of samples can be 60 consecutive months of wind speed time series.

[0078] For ease of distinction, the wind speed time series used for model training can be referred to as the initial wind speed time series, and the wind speed time series after resolution conversion can be referred to as the wind speed time series to be trained.

[0079] Considering that the wind speed time series is usually at hourly resolution, in order to achieve monthly wind speed prediction, after obtaining the initial wind speed time series with a preset sample size, the initial wind speed time series can be converted into a training wind speed time series with monthly resolution.

[0080] In a specific implementation, the wind speed data contained in the initial wind speed time series with hourly resolution can be converted into the wind speed time series to be trained with monthly resolution by performing an averaging operation.

[0081] The initial wind speed prediction model is trained using the wind speed time series to obtain a trained wind speed prediction model.

[0082] When the wind speed prediction model needs to be called to predict the annual power generation in the future, the trained wind speed prediction model can be used to analyze the historical wind speed time series of the set time length to obtain the annual estimated average wind speed.

[0083] Taking the annual power generation forecast as an example, the set duration value needs to be greater than or equal to 5 years, for example, the set duration can be 60 months.

[0084] In practice, a 60-month historical wind speed time series covering nearly five years can be input into a trained wind speed prediction model. The model will then output the estimated monthly average wind speed for each of the next 12 months. The average of these 12 monthly estimated average wind speeds is then used as the estimated annual average wind speed.

[0085] S102: Obtain an interannual change rate of wind speed based on the annual estimated average wind speed and the annual actual average wind speed.

[0086] The estimated annual average wind speed is used to indicate the predicted annual average wind speed for the next year, and the actual annual average wind speed is used to indicate the annual average wind speed for the current year.

[0087] In an embodiment of the present application, the difference between the annual estimated average wind speed and the annual actual average wind speed can be calculated; and the ratio of the difference to the annual actual average wind speed is used as the interannual change rate of wind speed.

[0088] In specific implementation, the interannual change rate of wind speed can be calculated according to the following formula:

[0089]

[0090] Among them, η v,LT represents the interannual variability of wind speed, v 1,LT represents the estimated annual average wind speed, v 0,LT Indicates the actual annual average wind speed.

[0091] For example, the wind speed prediction model can be used to predict the estimated annual average wind speed for 2022, assuming it is 5 m / s. Based on the actual wind speed time series data for 2021, the actual annual average wind speed for 2021 can be determined. This annual average wind speed can be called the annual actual average wind speed. Assuming it is 4 m / s, the interannual variability of wind speed is (5-4) / 4*100%=25%.

[0092] S103: Determine the interannual variation rate of the hub height wind speed based on the linear relationship between the hub height wind speed and the historical wind speed and the interannual variation rate of the wind speed.

[0093] The interannual wind speed variability (IVS) reflects long-term wind speed variations in meteorological data. Its spatial resolution is typically tens of kilometers, which cannot accurately represent wind speed variations at a selected wind farm. In practical applications, when predicting power generation at a selected wind farm, it is necessary to adjust the IVS to obtain a wind speed variability that better reflects the actual wind farm situation.

[0094] The wind speed at the turbine hub height is a key factor in determining the power generation of a wind farm. For ease of description, the wind speed at the turbine hub height may be referred to as the hub-height wind speed. In this application, the interannual rate of change of the hub-height wind speed can be determined based on the linear relationship between the hub-height wind speed and the historical wind speed, as well as the interannual rate of change of wind speed. The interannual rate of change of the hub-height wind speed can reflect the interannual variability of the wind speed at the currently selected wind farm.

[0095] In the embodiment of the present application, a correlation analysis may be performed between the wind speed time series at the hub height of the wind measurement tower and a preset historical wind speed time series to determine a linear relationship between the wind speed at the hub height and the historical wind speed.

[0096] Through correlation analysis, the linear relationship expression between the hub height wind speed and the historical wind speed can be obtained, such as y = kx + b, where x represents the historical wind speed time series, y represents the hub height wind speed time series, b represents the intercept, and k represents the slope.

[0097] Based on the linear relationship between the wind speed at hub height and the historical wind speed, the interannual variation rate of wind speed can be corrected to the interannual variation rate of the wind speed at hub height.

[0098] In specific implementation, the interannual variation rate of wind speed can be corrected to the interannual variation rate of hub height wind speed according to the following formula:

[0099]

[0100] Among them, η v,hub represents the interannual variation rate of wind speed at hub height, v 0,LT represents the actual annual average wind speed, η v,LT represents the interannual variability of wind speed.

[0101] S104: Determine the inter-annual variation rate of the generated electricity based on the wind speed sensitivity factor, power, wind speed, wind frequency, and the inter-annual variation rate of the wind speed at the hub height in each wind speed segment.

[0102] The inter-annual variation rate of hub-height wind speed can reflect the inter-annual variation of wind speed at the currently selected wind farm. Wind speed sensitivity factor, power, wind speed, and wind frequency are important parameters reflecting changes in power generation. Therefore, in this embodiment of the present application, the inter-annual variation rate of power generation can be determined based on the wind speed sensitivity factor, power, wind speed, wind frequency, and the inter-annual variation rate of hub-height wind speed for each wind speed range.

[0103] In the specific implementation, the power and wind speed corresponding to each wind speed segment are determined based on the obtained dynamic power curve of the wind turbine; the wind speed sensitivity factor corresponding to the current wind speed segment is determined based on the power and wind speed corresponding to the current wind speed segment and the power and wind speed corresponding to the wind speed segment adjacent to the current wind speed segment in the forward direction.

[0104] In practical applications, the wind speed sensitivity factor corresponding to the k-th wind speed segment can be calculated according to the following formula:

[0105]

[0106] Among them, c v,k Represents the wind speed sensitivity factor of the kth wind speed segment, in kW / m·s -1 ;p k represents the power corresponding to the k-th wind speed segment; p k-1 represents the power corresponding to the k-1th wind speed segment; v k represents the wind speed corresponding to the k-th wind speed segment; v k-1 Indicates the wind speed corresponding to the k-1th wind speed segment. It is agreed that p0=0 and v0=0.

[0107] After determining the sensitivity factors corresponding to each wind speed segment, the wind speed sensitivity coefficient can be determined based on the wind speed sensitivity factors, power, wind speed, and wind frequency corresponding to all wind speed segments.

[0108] In practical applications, when the wind speed sensitivity factor, power, wind speed and wind frequency corresponding to all wind speed segments are obtained, the wind speed sensitivity coefficient formula can be used to calculate the wind speed sensitivity coefficient;

[0109] The formula for wind speed sensitivity coefficient is:

[0110]

[0111] Among them, ξ E,v represents the wind speed sensitivity coefficient, f k represents the wind frequency corresponding to the k-th wind speed segment, c v,k represents the wind speed sensitivity factor corresponding to the k-th wind speed segment, v k represents the wind speed corresponding to the k-th wind speed segment, p k represents the power corresponding to the kth wind speed segment, and N represents the total number of wind speed segments.

[0112] The wind speed sensitivity coefficient is used to characterize the proportion of power generation change caused by wind speed, fully considering the influence of wind frequency distribution and power curve.

[0113] After the wind speed sensitivity coefficient is determined, the product of the wind speed sensitivity coefficient and the inter-annual variation rate of the hub height wind speed can be used as the inter-annual variation rate of power generation.

[0114] In practical applications, we can use the formula η E =ξ E,v η v,hub The interannual variation rate of power generation η is calculated E .

[0115] S105: Determine the estimated power generation for the next year based on the inter-annual change rate of power generation and the actual power generation for the current year.

[0116] The inter-annual change rate of power generation is used to evaluate the change in power generation in the next year. Based on the inter-annual change rate of power generation and the actual power generation in the current year, the estimated power generation in the next year can be determined.

[0117] In practical applications, the formula E1=E0(1+η E ) to calculate the estimated power generation E1 for the next year. Where E0 represents the actual power generation in that year, η E Indicates the inter-annual variation rate of power generation.

[0118] The method for determining the annual power generation of a wind farm provided in the embodiment of the present application is theoretically practical and highly operational, and can provide a basis for the formulation of long-term power transmission and market-based trading plans for wind farms, which is of great significance for improving the level of wind power consumption.

[0119] As can be seen from the above technical solution, a trained wind speed prediction model is used to analyze a historical wind speed time series of a set duration to obtain an estimated annual average wind speed; based on the estimated annual average wind speed and the actual annual average wind speed, the interannual wind speed variation rate is obtained. The interannual wind speed variation rate is used to reflect the wind speed variation of long-term meteorological data. Its spatial resolution is usually tens of kilometers, which cannot accurately represent the wind speed variation of the selected wind farm. In practical applications, when predicting the power generation of a selected wind farm, it is necessary to adjust the interannual wind speed variation rate to obtain a wind speed variation rate that better fits the actual situation of the wind farm. The wind speed at the hub height of the wind turbine is a key factor in determining the power generation of a wind farm. Therefore, in this application, the interannual wind speed variation rate at the hub height can be determined based on the linear relationship between the hub height wind speed and the historical wind speed and the interannual wind speed variation rate. The interannual wind speed variation rate at the hub height can reflect the interannual wind speed variation of the currently selected wind farm. Wind speed sensitivity factor, power, wind speed, and wind frequency are important parameters reflecting changes in power generation. The interannual variation rate of power generation can be determined based on the wind speed sensitivity factor, power, wind speed, wind frequency and the interannual variation rate of wind speed at hub height in each wind speed segment. The interannual variation rate of power generation is used to evaluate the changes in power generation in the next year. Based on the interannual variation rate of power generation and the actual power generation in the current year, the estimated power generation for the next year can be determined, thus realizing the prediction of the long-term power generation of the wind farm.

[0120] Figure 2 A schematic diagram of the structure of a device for determining the annual power generation of a wind farm provided in an embodiment of the present application, comprising an analyzing unit 21, an obtaining unit 22, a first determining unit 23, a second determining unit 24, and a third determining unit 25;

[0121] An analysis unit 21 is configured to analyze a historical wind speed time series of a set duration using a trained wind speed prediction model to obtain an estimated annual average wind speed;

[0122] Obtaining unit 22, for obtaining an interannual variation rate of wind speed based on the annual estimated average wind speed and the annual actual average wind speed;

[0123] A first determining unit 23 is configured to determine an interannual variation rate of the hub height wind speed based on a linear relationship between the hub height wind speed and the historical wind speed and the interannual variation rate of the wind speed;

[0124] The second determining unit 24 is configured to determine the inter-annual variation rate of the generated electricity based on the wind speed sensitivity factor, power, wind speed, wind frequency, and the inter-annual variation rate of the wind speed at the hub height in each wind speed segment;

[0125] The third determining unit 25 is configured to determine the estimated power generation for the next year based on the inter-annual change rate of power generation and the actual power generation for the current year.

[0126] Optionally, the obtaining unit includes a calculating subunit and an acting subunit;

[0127] A calculation subunit, used to calculate the difference between the annual estimated average wind speed and the annual actual average wind speed;

[0128] As a subunit, the ratio of the difference to the actual annual average wind speed is used as the interannual change rate of wind speed.

[0129] Optionally, the first determination unit is used to perform a correlation analysis on the wind speed time series at the hub height of the wind measurement tower and a preset historical wind speed time series to determine a linear relationship between the hub height wind speed and the historical wind speed; and based on the linear relationship, the interannual variation rate of the wind speed is corrected to obtain the interannual variation rate of the hub height wind speed.

[0130] Optionally, the second determining unit includes a parameter determining subunit, a factor determining subunit, a coefficient determining subunit and an as subunit;

[0131] The parameter determination subunit is used to determine the power and wind speed corresponding to each wind speed segment based on the acquired dynamic power curve of the wind turbine;

[0132] a factor determination subunit, configured to determine a wind speed sensitivity factor corresponding to the current wind speed segment based on the power and wind speed corresponding to the current wind speed segment and the power and wind speed corresponding to the wind speed segment forwardly adjacent to the current wind speed segment;

[0133] The coefficient determination subunit is used to determine the wind speed sensitivity coefficient according to the wind speed sensitivity factor, power, wind speed and wind frequency corresponding to all wind speed segments;

[0134] As a subunit, it is used to take the product of the wind speed sensitivity coefficient and the inter-annual variation rate of the hub height wind speed as the inter-annual variation rate of power generation.

[0135] Optionally, the coefficient determination subunit is used to calculate the wind speed sensitivity coefficient by calling the wind speed sensitivity coefficient formula when the wind speed sensitivity factor, power, wind speed and wind frequency corresponding to all wind speed segments are obtained;

[0136] The formula for wind speed sensitivity coefficient is:

[0137]

[0138] Among them, ξ E,v represents the wind speed sensitivity coefficient, f k represents the wind frequency corresponding to the k-th wind speed segment, c v,k represents the wind speed sensitivity factor corresponding to the k-th wind speed segment, v k represents the wind speed corresponding to the k-th wind speed segment, p k represents the power corresponding to the kth wind speed segment, and N represents the total number of wind speed segments.

[0139] Optionally, for the training process of the wind speed prediction model, the device further includes an acquisition unit, a conversion unit and a training unit;

[0140] An acquisition unit, used for acquiring an initial wind speed time series of a preset sample size;

[0141] A conversion unit, used to convert the initial wind speed time series into a monthly resolution wind speed time series to be trained;

[0142] The training unit is used to train the initial wind speed prediction model using the wind speed time series to be trained to obtain a trained wind speed prediction model.

[0143] Optionally, the analysis unit is used to input the acquired historical wind speed time series into a trained wind speed prediction model to obtain the estimated monthly average wind speed corresponding to each of the twelve months; and the average of all the estimated monthly average wind speeds is used as the estimated annual average wind speed.

[0144] Figure 2 The description of the features in the corresponding embodiment can be found in Figure 1 The relevant descriptions of the corresponding embodiments will not be repeated here one by one.

[0145] As can be seen from the above technical solution, a trained wind speed prediction model is used to analyze a historical wind speed time series of a set duration to obtain an estimated annual average wind speed; based on the estimated annual average wind speed and the actual annual average wind speed, the interannual wind speed variation rate is obtained. The interannual wind speed variation rate is used to reflect the wind speed variation of long-term meteorological data. Its spatial resolution is usually tens of kilometers, which cannot accurately represent the wind speed variation of the selected wind farm. In practical applications, when predicting the power generation of a selected wind farm, it is necessary to adjust the interannual wind speed variation rate to obtain a wind speed variation rate that better fits the actual situation of the wind farm. The wind speed at the hub height of the wind turbine is a key factor in determining the power generation of a wind farm. Therefore, in this application, the interannual wind speed variation rate at the hub height can be determined based on the linear relationship between the hub height wind speed and the historical wind speed and the interannual wind speed variation rate. The interannual wind speed variation rate at the hub height can reflect the interannual wind speed variation of the currently selected wind farm. Wind speed sensitivity factor, power, wind speed, and wind frequency are important parameters reflecting changes in power generation. The interannual variation rate of power generation can be determined based on the wind speed sensitivity factor, power, wind speed, wind frequency and the interannual variation rate of wind speed at hub height in each wind speed segment. The interannual variation rate of power generation is used to evaluate the changes in power generation in the next year. Based on the interannual variation rate of power generation and the actual power generation in the current year, the estimated power generation for the next year can be determined, thus realizing the prediction of the long-term power generation of the wind farm.

[0146] Figure 3 A structural diagram of an electronic device provided in an embodiment of the present application, such as Figure 3As shown, the electronic device includes: a memory 20 for storing computer programs;

[0147] The processor 21 is configured to implement the steps of the method for determining the annual power generation of a wind farm in the above embodiment when executing a computer program.

[0148] The electronic device provided in this embodiment may include but is not limited to a smart phone, a tablet computer, a laptop computer, or a desktop computer.

[0149] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0150] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include high-speed random access memory, and non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 20 is at least used to store the following computer program 201, wherein, after the computer program is loaded and executed by the processor 21, it can implement the relevant steps of the method for determining the annual power generation of a wind farm disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include but is not limited to the linear relationship between the wind speed at the hub height and the historical wind speed, the actual power generation of the year, etc.

[0151] In some embodiments, the electronic device may further include a display screen 22 , an input / output interface 23 , a communication interface 24 , a power supply 25 , and a communication bus 26 .

[0152] Those skilled in the art will understand that Figure 3 The structures shown in the figure do not constitute a limitation of the device you carry with you, and may include more or fewer components than shown.

[0153] It is understandable that if the method for determining the annual power generation of a wind farm in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium and executes all or part of the steps of the methods of each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), electrically erasable programmable ROM, register, hard disk, removable disk, CD-ROM, magnetic disk or optical disk, etc. Various media that can store program code.

[0154] Based on this, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for determining the annual power generation of a wind farm as described above are implemented.

[0155] The above describes in detail the method, apparatus, device, and computer-readable storage medium for determining the annual power generation of a wind farm provided by the embodiments of the present application. The various embodiments are described in a progressive manner throughout this specification, with each embodiment focusing on the differences from the other embodiments. Similar or identical parts between the various embodiments can be referenced to each other. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; for relevant details, refer to the method description.

[0156] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0157] The above is a detailed introduction to the method, device, equipment and computer-readable storage medium for determining the annual power generation of a wind farm provided by the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present invention, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.

Claims

1. A method for determining the annual power generation of a wind farm, characterized in that: include: Use the trained wind speed prediction model to analyze the historical wind speed time series of a set period to obtain the estimated annual average wind speed; The interannual variation rate of wind speed is obtained based on the annual estimated average wind speed and the annual actual average wind speed; Determining the interannual variation rate of the hub height wind speed based on the linear relationship between the hub height wind speed and the historical wind speed and the interannual variation rate of the wind speed; Determine the interannual variation rate of generated electricity based on the wind speed sensitivity factor, power, wind speed, wind frequency of each wind speed segment and the interannual variation rate of the wind speed at the hub height; Determine the estimated power generation for the next year based on the inter-annual change rate of power generation and the actual power generation in the current year; Determining the inter-annual variation rate of generated electricity based on the wind speed sensitivity factor, power, wind speed, wind frequency of each wind speed segment and the inter-annual variation rate of the hub height wind speed includes: According to the obtained dynamic power curve of the wind turbine, the power and wind speed corresponding to each wind speed segment are determined; Determining a wind speed sensitivity factor corresponding to the current wind speed segment based on the power and wind speed corresponding to the current wind speed segment and the power and wind speed corresponding to the wind speed segment forwardly adjacent to the current wind speed segment; Determine a wind speed sensitivity coefficient based on the wind speed sensitivity factor, power, wind speed, and wind frequency corresponding to all the wind speed segments; The product of the wind speed sensitivity coefficient and the inter-annual variation rate of the hub height wind speed is used as the inter-annual variation rate of power generation; Determining the wind speed sensitivity coefficient according to the wind speed sensitivity factors, power, wind speed, and wind frequency corresponding to all the wind speed segments includes: When the wind speed sensitivity factor, power, wind speed and wind frequency corresponding to all the wind speed segments are obtained, the wind speed sensitivity coefficient formula is called to calculate the wind speed sensitivity coefficient; The wind speed sensitivity coefficient formula is: ； in, represents the wind speed sensitivity coefficient, represents the wind frequency corresponding to the k-th wind speed segment, represents the wind speed sensitivity factor corresponding to the k-th wind speed segment, represents the wind speed corresponding to the k-th wind speed segment, represents the power corresponding to the kth wind speed segment, and N represents the total number of wind speed segments.

2. The method for determining the annual power generation of a wind farm according to claim 1, characterized in that: The interannual wind speed variation rate obtained based on the annual estimated average wind speed and the annual actual average wind speed includes: Calculating the difference between the estimated annual average wind speed and the actual annual average wind speed; The ratio of the difference to the actual annual average wind speed is taken as the interannual change rate of wind speed.

3. The method for determining the annual power generation of a wind farm according to claim 1, characterized in that: Determining the interannual variation rate of the hub height wind speed based on the linear relationship between the hub height wind speed and the historical wind speed and the interannual variation rate of the wind speed includes: Perform correlation analysis on the wind speed time series at the hub height of the wind tower and the preset historical wind speed time series to determine the linear relationship between the wind speed at the hub height and the historical wind speed; The interannual variation rate of wind speed is corrected based on the linear relationship to obtain the interannual variation rate of wind speed at hub height.

4. The method for determining the annual power generation of a wind farm according to claim 1, characterized in that: The training process of the wind speed prediction model includes: Obtain the initial wind speed time series of the preset sample size; Converting the initial wind speed time series into a wind speed time series to be trained with a monthly resolution; The initial wind speed prediction model is trained using the wind speed time series to be trained to obtain a trained wind speed prediction model.

5. The method for determining the annual power generation of a wind farm according to any one of claims 1 to 4, characterized in that: The trained wind speed prediction model is used to analyze the historical wind speed time series of a set time period to obtain the annual estimated average wind speed, including: Inputting the acquired historical wind speed time series into the trained wind speed prediction model to obtain the monthly estimated average wind speed corresponding to each of the twelve months; The average of all the monthly estimated average wind speeds is taken as the annual estimated average wind speed.

6. A device for determining the annual power generation of a wind farm, characterized in that: comprising an analyzing unit, an obtaining unit, a first determining unit, a second determining unit, and a third determining unit; The analysis unit is used to analyze the historical wind speed time series of a set time period using the trained wind speed prediction model to obtain the annual estimated average wind speed; The obtaining unit is used to obtain the interannual change rate of wind speed based on the annual estimated average wind speed and the annual actual average wind speed; The first determining unit is configured to determine the interannual variation rate of the hub height wind speed based on the linear relationship between the hub height wind speed and the historical wind speed and the interannual variation rate of the wind speed; The second determining unit is configured to determine the interannual variation rate of the generated electricity based on the wind speed sensitivity factor, power, wind speed, wind frequency of each wind speed segment and the interannual variation rate of the wind speed at the hub height; The third determining unit is configured to determine an estimated power generation for the next year based on the inter-annual change rate of power generation and the actual power generation for the current year; The second determining unit includes a parameter determining subunit, a factor determining subunit, a coefficient determining subunit and an as subunit; The parameter determination subunit is used to determine the power and wind speed corresponding to each wind speed segment based on the acquired dynamic power curve of the wind turbine generator set; The factor determination subunit is configured to determine a wind speed sensitivity factor corresponding to the current wind speed segment based on the power and wind speed corresponding to the current wind speed segment and the power and wind speed corresponding to the wind speed segment forwardly adjacent to the current wind speed segment; The coefficient determination subunit is used to determine the wind speed sensitivity coefficient according to the wind speed sensitivity factor, power, wind speed and wind frequency corresponding to all the wind speed segments; The subunit is configured to take the product of the wind speed sensitivity coefficient and the inter-annual variation rate of the hub height wind speed as the inter-annual variation rate of power generation; The coefficient determination subunit is used to calculate the wind speed sensitivity coefficient by calling the wind speed sensitivity coefficient formula when the wind speed sensitivity factor, power, wind speed and wind frequency corresponding to all the wind speed segments are obtained; The wind speed sensitivity coefficient formula is: ； in, represents the wind speed sensitivity coefficient, represents the wind frequency corresponding to the k-th wind speed segment, represents the wind speed sensitivity factor corresponding to the k-th wind speed segment, represents the wind speed corresponding to the k-th wind speed segment, represents the power corresponding to the kth wind speed segment, and N represents the total number of wind speed segments.

7. An electronic device, characterized in that: include: memory for storing computer programs; A processor is configured to execute the computer program to implement the steps of the method for determining the annual power generation of a wind farm according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for determining the annual power generation of a wind farm according to any one of claims 1 to 5.

Images