Wind power plant generating capacity optimization method based on multivariable association

Abstract

The invention relates to the technical field of wind power, in particular to a wind power plant generating capacity optimization method based on multivariable association. Firstly, research objects are selected by comprehensively considering wind power plant scale, geographic position and operation time; selecting a target environment parameter data stream and a target environment influence data stream, selecting a sample data stream, and analyzing the characteristics of the sample data stream; then, calculating relevance indexes of the target environment parameters and the influence data flow large value and small value and an overall relevance index of the target environment parameters and the influence data flow large value and small value; and finally, judging the influence on the generating capacity according to the relevance index, and formulating an optimization strategy. Environmental factors are comprehensively analyzed to provide a basis for optimization, a strategy is scientifically formulated to improve the power generation efficiency, and an effective method is provided for power generation capacity optimization of the wind power plant.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power, and in particular to a method for optimizing power generation of a wind farm based on multi-variable correlation. Background Art

[0002] With the continuous growth of global demand for energy and the increasing awareness of environmental protection, the development and utilization of renewable energy has become a key development direction in the energy field. As a clean and renewable energy source, wind energy accounts for an increasing proportion of the global energy structure. As the main form of wind energy utilization, the optimization of wind farm power generation is of vital importance to improving wind energy utilization efficiency, reducing energy costs and promoting sustainable development.

[0003] However, the power generation of wind farms is affected by a variety of complex environmental factors. Wind speed and direction are key factors that directly affect power generation, and their changes are random and uncertain. At the same time, other environmental factors such as temperature, humidity, and air pressure will also affect power generation. For example, changes in temperature will affect air density, thereby changing the power output of wind turbines; changes in humidity and air pressure may affect the physical properties of the air, indirectly affecting power generation.

[0004] At present, the existing wind farm power generation optimization methods have certain limitations. On the one hand, many methods tend to only focus on the impact of a single environmental factor on power generation, while ignoring the role of other factors and the interrelationships between the factors. This single factor consideration method cannot fully and accurately reflect the actual situation of wind farm power generation, and it is difficult to achieve effective optimization. On the other hand, although some methods consider multiple factors, they lack systematic analysis methods and scientific decision-making basis, and cannot accurately evaluate the impact of different environmental factors on power generation and the complex relationship between them, resulting in the lack of pertinence and effectiveness in the formulation of optimization strategies. Therefore, a wind farm power generation optimization method that can comprehensively consider multiple environmental factors and their interrelationships is needed to improve the power generation efficiency and economic benefits of wind farms. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention proposes a wind farm power generation optimization method based on multi-variable correlation, which provides a basis for optimization by comprehensively analyzing various environmental factors and their correlations, and scientifically formulates strategies to achieve the purpose of improving power generation efficiency.

[0006] The technical solution of the present invention is as follows:

[0007] A wind farm power generation optimization method based on multi-variable association, comprising:

[0008] A wind farm is selected as the research object, and the environmental parameters that directly affect the power generation are collected by wind farm monitoring equipment and recorded as the target environmental parameter data flow, and other environmental factors that may affect the power generation are recorded as the target environmental impact data flow;

[0009] Select a data stream from the target environmental parameter data stream and the target environmental impact data stream as a sample data stream, determine the maximum value point and the minimum value point in the sample data stream, determine the large value range and the small value range through the maximum value point and the minimum value point, and then calculate the data diversity index of the sample data stream and the characteristic parameters of the large value and the small value in the sample data stream;

[0010] The correlation index between the large values ​​and the correlation index between the small values ​​of the target environmental parameter data stream and the target environmental impact data stream in the sample data stream is calculated by using the characteristic parameters of the large values ​​and the small values ​​of the sample data stream, and the correlation index between the large values ​​and the small values ​​and the data diversity index of the sample data stream is used to calculate the correlation index between the overall target environmental impact data stream and the environmental parameter data set;

[0011] According to the correlation indicators between the overall target environmental impact data flow and the environmental parameter data set, the impact of the correlation indicators on power generation is analyzed, including judging the positive and negative correlation and the strength of the correlation, evaluating the impact of different environmental factors on power generation, and then formulating power generation optimization strategies.

[0012] Furthermore, the wind farm selection method is to select a wind farm with the highest comprehensive evaluation value from multiple wind farms as a research object based on the scale, geographical location, and operation time of the wind farm;

[0013] Among them, the comprehensive evaluation value S of the wind farm is calculated as follows:

[0014]

[0015] Among them, ω1 is the wind farm scale weight, ω2 is the geographical location weight, ω3 is the operating time weight, and ω1+ω2+ω3=1, C is the installed capacity, Cmax is the maximum installed capacity among all candidate wind farms; D is the distance between the wind farm and the main electricity consumption area, V is the local annual average wind speed, T is the operating time, and Tmax is the maximum operating time among all candidate wind farms.

[0016] Furthermore, the target environmental parameter data stream includes wind speed and wind direction, and the corresponding data is collected by an anemometer and a wind vane;

[0017] The target environment impact data stream includes temperature, humidity and air pressure, and the corresponding data are collected by a thermometer, a hygrometer and a barometer respectively.

[0018] Furthermore, the sample data stream selection complies with the following principles: the sample data stream can reflect the fluctuation of environmental factors; and there should be a potential correlation between the sample data stream and the power generation.

[0019] Furthermore, the maximum value range in the sample data stream is [0.9ymax, ymax], and the minimum value range is [ymin, 1.1ymin];

[0020] Among them, y max and min are the maximum and minimum values ​​in the sample data stream respectively.

[0021] Furthermore, the data diversity index of the sample data stream is calculated using standard deviation, and the calculation steps are as follows: the sample data stream is Y = {y1, y2, y3, ..., yi, ..., yn}, and the average value of the sample data stream is calculated Calculate standard deviation Where yi is the i-th sample data stream and n is the total number of data points.

[0022] Furthermore, the characteristic parameters of the large value and the small value in the sample data stream include:

[0023] The frequency of large values ​​f G max,

[0024] Maximum value and average value The degree of deviation d G max, the formula is: Where n G max is the maximum value of y Gmax The number of times it appears in the sample data stream;

[0025] The frequency of small values ​​f G min,

[0026] Small value y G min and average The degree of deviation d G min, Where n G min is the minimum value of y G The number of times min appears in the sample data stream.

[0027] Furthermore, the calculation formula for the correlation index between the maximum values ​​of the target environment parameter data stream and the target environment impact data stream in the sample data stream is:

[0028]

[0029] Among them, R Gmax is the correlation index between large values, fst is the frequency of large values ​​appearing simultaneously, and f G max1 and d G max1 and max2 are the target environment parameter data streams in the sample data stream, and the large value y appears after the large value range is screened Gmax1 Frequency of occurrence and maximum value y Gmax1 The degree of deviation from the mean, f G max2 and d G max2 are the target environment in the sample data stream, which affects the data stream and the large value y that appears after filtering through the large value range Gmax2 Frequency and maximum value y Gmax2 The degree of deviation from the mean.

[0030] The calculation formula of the correlation index between the minimum values ​​of the target environmental parameter data stream and the target environmental impact data stream is:

[0031]

[0032] Among them, R G min is the correlation index between small values, fs′t is the frequency of small values ​​appearing simultaneously, and f G min1 and d G min1 is the target environmental parameter data stream in the sample data stream, and the small value y appears after filtering through the large value range G min1 frequency and minimum value y G min1 is the degree of deviation from the mean value, f G min2 and d G min2 are the small values ​​y that appear in the target environment impact data stream in the sample data stream after filtering through the small value range G min2 frequency and minimum value y G How much min2 deviates from the mean.

[0033] Furthermore, the calculation formula for the correlation index between the overall target environmental impact data stream and the environmental parameter data set is:

[0034]

[0035] Among them, R G max is the correlation index between large values, R G min is the correlation index between small values, and σ is the standard deviation of the sample data stream, which represents the data diversity index of the sample data stream.

[0036] Furthermore, the impact of the correlation index on power generation includes:

[0037] If R>0, it means that the target environmental impact data stream is positively correlated with the environmental parameter data set, that is, the environmental impact factors are consistent with the environmental parameters that directly affect power generation, and have a promoting effect on power generation;

[0038] If R < 0, it indicates a negative correlation, that is, the environmental influencing factors have opposite trends to the environmental parameters that directly affect power generation, and have an inhibitory effect on power generation;

[0039] If R = 0, it means there is no obvious linear correlation between the two;

[0040] When |R| is close to 1, it means that the correlation is strong and the environmental factors have a greater impact on power generation;

[0041] When |R| is close to 0, it means that the correlation is weak and the environmental factors have little impact on power generation.

[0042] The beneficial effects of the present invention are: comprehensive collection of data on environmental parameters that directly affect power generation and other environmental factors that may affect power generation. Through comprehensive analysis of environmental factors, including determining sample data streams, calculating their characteristic parameters and correlation indicators, etc., the mutual relationship between environmental factors and their influence on power generation can be accurately grasped, providing a solid theoretical basis and data support for power generation optimization.

[0043] According to the correlation index between environmental factors and environmental parameter data sets, it is possible to accurately determine whether their impact on power generation is positively correlated or negatively correlated, as well as the strength of the correlation. Based on these judgments, a scientific power generation optimization strategy can be formulated.

[0044] This technology provides a general method framework for optimizing wind farm power generation through comprehensive analysis of various environmental factors of wind farms and scientific formulation of power generation optimization strategies. As long as the problem involves the impact of wind farm environmental factors on power generation, the method of this technology can be used for analysis and optimization, without being limited to specific wind farm types or environmental conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a schematic diagram of the overall process of promoting the digital transformation of new energy stations;

[0046] Figure 2 A detailed flow chart of the S100 step of the digital transformation promotion method for new energy stations;

[0047] Figure 3 A detailed flow chart of the S200 step of the method for promoting the digital transformation of new energy stations;

[0048] Figure 4 It is a detailed flow chart of the S300 step of the method for promoting the digital transformation of new energy stations;

[0049] Figure 5 This is a detailed flow chart of the S400 steps for the method to promote the digital transformation of new energy stations. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0051] See also Figure 1 , which shows a method for optimizing wind farm power generation based on multi-variable association provided by an embodiment of the present invention, comprising:

[0052] S100: Select a wind farm as a research object, and use wind farm monitoring equipment to collect environmental parameters that directly affect power generation and record them as target environmental parameter data flow, and other environmental factor data that may affect power generation and record them as target environmental impact data flow.

[0053] S200: Select a data stream from the target environment parameter data stream and the target environment impact data stream as a sample data stream, determine the maximum value point and the minimum value point in the sample data stream, determine the large value range and the small value range through the maximum value point and the minimum value point, and then calculate the data diversity index of the sample data stream and the characteristic parameters of the large value and the small value.

[0054] S300: Calculate the correlation index between the large values ​​and the correlation index between the small values ​​of the target environmental parameter data stream and the target environmental impact data stream in the sample data stream through the characteristic parameters of the large values ​​and the small values ​​of the sample data stream; and calculate the correlation index between the overall target environmental impact data stream and the environmental parameter data set by utilizing the correlation index between the large values ​​and the correlation index between the small values ​​and the data diversity index of the sample data stream.

[0055] S400: Analyze the impact of the overall target environmental impact data stream and the environmental parameter data set on power generation based on the correlation index, including judging the positive and negative correlation and the strength of the correlation, evaluating the impact of different environmental factors on power generation, and then formulating a power generation optimization strategy.

[0056] S100 selects one wind farm from multiple wind farms as a research object and collects relevant environmental data by comprehensively considering the scale, geographical location and operating time of the wind farm. At the same time, environmental parameters that directly affect power generation are collected as the target environmental parameter data flow, and other environmental factors that may affect power generation are collected as the target environmental impact data flow. The comprehensive multi-factor evaluation to select the research object can more comprehensively consider the actual situation of the wind farm, making the selection more scientific and reasonable. The collection of environmental data is relatively comprehensive, covering both direct and possible indirect factors, providing a rich data foundation for subsequent analysis and optimization.

[0057] Please refer to Figure 2 , which shows a flowchart of an exemplary wind farm power generation optimization method S100 based on multi-variable association of the present application, and its contents include:

[0058] S110: According to the scale, geographical location and operation time of the wind farm, a wind farm with the highest comprehensive evaluation value is selected from multiple wind farms as a research object.

[0059] For the scale of wind farms, the installed capacity C is used to measure it, the geographical location is comprehensively evaluated by the distance D from the main power consumption area and the local annual average wind speed V, and the operating time is represented by T;

[0060] Calculate the comprehensive evaluation value S of each wind farm using the following formula:

[0061]

[0062] Among them, ω1 is the wind farm scale weight, ω2 is the geographical location weight, ω3 is the operating time weight, and ω1+ω2+ω3=1, C is the installed capacity, Cmax is the maximum installed capacity among all candidate wind farms; D is the distance between the wind farm and the main power consumption area, V is the local annual average wind speed, T is the operating time, and Tmax is the maximum operating time among all candidate wind farms;

[0063] The wind farm with the highest comprehensive evaluation value S is selected as the research object.

[0064] S120: Target environment parameter data stream collection and target environment impact data stream collection.

[0065] The environmental parameters that directly affect the power generation are defined as the target environmental parameter data stream, which includes wind speed and wind direction. The corresponding data are collected through anemometers and wind vanes.

[0066] The anemometer collects wind speed data v(t) at a set time interval Δt, where t represents time. The collected data constitutes a wind speed data stream V = {v(t1), v(t2), v(t3), ...}.

[0067] The wind vane also collects wind direction data θ(t) at time interval Δt, and the collected data constitutes a wind direction data stream θ={θ(t1),θ(t2),θ(t3), ...}.

[0068] The data of other environmental factors that may affect the power generation are defined as the target environmental impact data stream. Including temperature, humidity, air pressure, the corresponding data is collected through thermometers, hygrometers and barometers. Changes in temperature affect the air density, which in turn affects the power output of the fan. Changes in humidity and air pressure may also affect the physical properties of the air, indirectly affecting the power generation.

[0069] The thermometer collects temperature data T(t) at time interval Δt, and the collected data constitutes a temperature data stream T={T(t1), T(t2), T(t3), ...}.

[0070] The hygrometer collects humidity data RH(t) at time intervals Δt, and the collected data constitutes a pressure data stream RH={RH(t1), RH(t2), RH(t3), ...}.

[0071] The barometer collects air pressure data P(t) at time interval Δt, and the collected data constitutes an air pressure data stream P={P(t1), P(t2), P(t3), ...}.

[0072] S200 selects a sample data stream from the target environmental parameter data stream and the target environmental impact data stream, determines the maximum and minimum points in the sample data stream, and then determines the large and small ranges, and then uses the standard deviation to calculate the data diversity index and calculate the characteristic parameters of the large and small values. By reasonably selecting the sample data stream, it is possible to focus on data with dynamic change characteristics and potentially related to power generation, and conduct more targeted analysis. Determining the large and small ranges and related characteristic parameters helps to gain a deeper understanding of the distribution characteristics of the data, and provides a detailed data basis for subsequent correlation analysis, so as to better grasp the relationship between environmental factors and power generation.

[0073] Please refer to Figure 3 , which shows a flowchart of an exemplary method S200 for optimizing wind farm power generation based on multi-variable association of the present application, and its contents include:

[0074] S210: Analyze the data streams in the target environment parameter data stream and the target environment impact data stream, and select a sample data stream according to a selection principle.

[0075] Select a data stream from the environmental parameter data stream and the environmental impact data stream as the sample data stream. The following principles should be followed when selecting the sample data stream: First, the sample data stream should have obvious dynamic change characteristics and be able to reflect the fluctuation of environmental factors. Second, there should be a potential correlation between the sample data stream and the power generation. Based on existing theoretical knowledge and experience, select those data streams that may have a significant impact on the power generation.

[0076] S220: Determine a large value range and a small value range in the sample data stream.

[0077] Assume that the selected sample data stream is Y = {y1, y2, y3, ..., yi, ..., yn}, where yi represents the i-th data point in the data stream and n is the total number of data points.

[0078] Traverse the entire sample data stream Y and find the maximum value y max and the minimum value y min . That is, ymax=max{y1,y2,y3,...,yi,...,yn}, ymin=min{y1,y2,y3,...,yi,...,yn}.

[0079] The maximum value range is [0.9ymax,ymax] and the minimum value range is [ymin,1.1ymin].

[0080] S230: Calculate the data diversity index of the sample data stream using the standard deviation, that is, the standard deviation σ.

[0081] The data diversity index of the sample data stream is calculated by the standard deviation of the sample data stream, and the sample data stream is Y = {y1, y2, y3, ..., yi, ..., yn}.

[0082] First calculate the average value of the sample data stream Where yi is the i-th sample data stream, and then calculate the standard deviation The larger the standard deviation, the greater the dispersion of the data, that is, the higher the data diversity index.

[0083] S240: Calculate the characteristic parameters of the large value and the small value.

[0084] For the large value y that appears in the sample data stream through the large value range screening Gmax , calculate its frequency f G max, the formula is: Where n G max is the maximum value of y Gmax The number of times it occurs in the sample data stream.

[0085] For the large value y that appears in the sample data stream through the large value range screeningGmax , calculate the maximum value and the average value The degree of deviation d G max, the formula is: Where n G max is the number of times the large value appears in the sample data stream.

[0086] For the small value y that appears in the sample data stream through the small value range screening G min, calculate its frequency f G min, the formula is: Where n G min is the minimum value of y G The number of times min appears in the sample data stream.

[0087] For the small value y that appears in the sample data stream through the small value range screening G min, calculate the minimum value y G min and average The degree of deviation d G min, the formula is:

[0088]

[0089] S300 calculates the correlation index between the large values ​​and the small values ​​of the target environmental parameter data stream and the target environmental impact data stream respectively through the characteristic parameters of the large and small values ​​of the sample data stream, and then calculates the correlation index between the overall target environmental impact data stream and the environmental parameter data set in combination with the data diversity index of the sample data stream. Through the detailed analysis of the large and small value characteristic parameters and the consideration of the data diversity index, the correlation index between different data streams can be calculated comprehensively and accurately. The calculation of this correlation index provides key data support for the subsequent evaluation of the impact of environmental factors on power generation, which helps to have a deeper understanding of the complex relationship between environmental factors and power generation.

[0090] Please refer to Figure 4 , which shows a flowchart of an exemplary method S300 for optimizing wind farm power generation based on multi-variable association of the present application, and its contents include:

[0091] S310: Calculate the correlation index between the maximum values ​​of the target environmental parameter data flow and the target environmental impact data flow in the sample data flow.

[0092] For the target environmental parameter data stream in the sample data stream, the large value y is filtered by the large value range. Gmax1 , get its frequency f G max1, get the degree of deviation from the average value d G max1.

[0093] For the target environment in the sample data stream, the data stream is affected by filtering the large value y that appears in the large value range Gmax2 , get its frequency f G max2, obtain the degree of deviation from the average value dGmax2.

[0094] Count the maximum value y of the target environment parameter data stream in the sample data stream Gmax1 The target environment in the sample data stream affects the maximum value y of the data stream Gmax2 The number of times nst occurs at the same time. Calculate the frequency of large values ​​appearing at the same time fst, Where n G max1 is the number of times the maximum value of the target environment parameter data stream appears in the sample data stream, n G max2 is the number of occurrences of the maximum value of the target environment affecting the data stream in the sample data stream.

[0095] Calculate the correlation index between large values ​​and define the correlation index R between large values G max, calculated as:

[0096] S320: Calculate the correlation index between the minimum values ​​of the target environmental parameter data stream and the target environmental impact data stream in the sample data stream.

[0097] For the target environment parameter data stream in the sample data stream, the small value y is filtered by the small value range. G min1, get its frequency f G min1, get the degree of deviation from the average value d G min1.

[0098] For the target environment in the sample data stream, the data stream is affected by the small value y that appears through the small value range screening G min2, get its frequency f G min2, get the degree of deviation from the average value d G min2.

[0099] Count the minimum value y of the target environment parameter data stream in the sample data stream G min1 and the target environment in the sample data stream affect the small value y of the data stream G min2 appears at the same time, n′st. Calculate the frequency of small values ​​appearing at the same time, f s ' t , Where n G min1 is the number of small values ​​of the target environment parameter data stream in the sample data stream, n Gmin2 is the number of occurrences of the minimum value of the target environment affecting the data stream in the sample data stream.

[0100] Calculate the correlation index between small values ​​and define the correlation index R between small values G min, calculated as:

[0101] S330: Calculate the correlation index between the overall target environmental impact data flow and the environmental parameter data set.

[0102] Get the correlation index R between large values G max, correlation index R between small values G min and the data diversity index of the sample data stream, that is, the standard deviation σ. Calculate the correlation index R of the overall target environmental impact data stream and the environmental parameter data set. The calculation formula of the correlation index R is:

[0103]

[0104] S400 analyzes the impact of the overall target environmental impact data stream and the environmental parameter data set on power generation based on the correlation index, including judging the positive and negative correlation and the strength of the correlation, evaluating the degree of impact of different environmental factors on power generation, and then formulating a power generation optimization strategy. Based on the correlation index, the comprehensive and systematic analysis of the impact of environmental factors on power generation provides a scientific basis and feasible strategic direction for the optimization of wind farm power generation, which helps to improve the power generation efficiency and economic benefits of wind farms.

[0105] Please refer to Figure 5 , which shows a flowchart of an exemplary wind farm power generation optimization method S400 based on multi-variable association of the present application, and its contents include:

[0106] S410: Analyze the impact of correlation indicators on power generation.

[0107] Observe the positive and negative correlation index R between the overall target environmental impact data flow and the environmental parameter data set.

[0108] If R>0, it means that the target environmental impact data stream is positively correlated with the environmental parameter data set, that is, the environmental impact factors are consistent with the changing trends of the environmental parameters that directly affect the power generation, and have a promoting effect on the power generation.

[0109] If R<0, it indicates a negative correlation, that is, the environmental influencing factors have an opposite trend to the environmental parameters that directly affect power generation, and have an inhibitory effect on power generation.

[0110] If R=0, it means there is no obvious linear correlation between the two.

[0111] When |R| is close to 1, it means that the correlation is strong and the environmental factors have a greater impact on power generation.

[0112] When |R| is close to 0, it means that the correlation is weak and the environmental factors have little impact on power generation.

[0113] S420: Evaluate the impact of different environmental factors on power generation.

[0114] For the temperature, humidity and air pressure in the target environment impact data stream, the correlation index with the environmental parameter data set is analyzed respectively. The correlation index of temperature is R T , the correlation index of humidity is R RH , the correlation index of air pressure is R P By comparing R T , R RH , R P The absolute value of the environmental factors is used to determine the relative importance of the impact of different environmental factors on power generation.

[0115] For example, if R T >R RH >R P , it means that temperature has a relatively large impact on power generation, followed by humidity, and air pressure is the smallest.

[0116] S430: Formulate a power generation optimization strategy.

[0117] If an environmental factor is positively correlated with the environmental parameter data set and the correlation is strong, the favorable impact of the environmental factor should be appropriately increased within a certain range.

[0118] For example, for temperature factors, if temperature increase is conducive to increased power generation and the correlation is strong, we can consider taking some measures (such as adjusting the heat dissipation facilities around the wind farm) to appropriately increase the temperature environment in the appropriate season or time period.

[0119] If an environmental factor is negatively correlated with the environmental parameter data set and the correlation is strong (such as humidity and the humidity is close to 1), measures are taken to reduce the adverse effects of the environmental factor.

[0120] For example, for the humidity factor, if increased humidity is not conducive to increased power generation and the correlation is strong, measures such as installing dehumidification equipment in the wind farm are taken to reduce humidity.

[0121] If the correlation between an environmental factor and the environmental parameter data set is weak (such as air pressure close to 0), no special adjustment will be considered for the time being.

[0122] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0123] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0124] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0125] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features of the present invention.

[0126] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A wind farm power generation optimization method based on multi-variable correlation, characterized in that: include: A wind farm is selected as the research object, and the environmental parameters that directly affect the power generation are collected by wind farm monitoring equipment and recorded as the target environmental parameter data flow, and other environmental factors that may affect the power generation are recorded as the target environmental impact data flow; Select a data stream from the target environmental parameter data stream and the target environmental impact data stream as a sample data stream, determine the maximum value point and the minimum value point in the sample data stream, determine the large value range and the small value range through the maximum value point and the minimum value point, and then calculate the data diversity index of the sample data stream and the characteristic parameters of the large value and the small value in the sample data stream; The correlation index between the large values ​​and the correlation index between the small values ​​of the target environmental parameter data stream and the target environmental impact data stream in the sample data stream is calculated by using the characteristic parameters of the large values ​​and the small values ​​of the sample data stream, and the correlation index between the large values ​​and the small values ​​and the data diversity index of the sample data stream is used to calculate the correlation index between the overall target environmental impact data stream and the environmental parameter data set; According to the correlation indicators between the overall target environmental impact data flow and the environmental parameter data set, the impact of the correlation indicators on power generation is analyzed, including judging the positive and negative correlation and the strength of the correlation, evaluating the impact of different environmental factors on power generation, and then formulating power generation optimization strategies.

2. A wind farm power generation optimization method based on multi-variable correlation according to claim 1, characterized in that: The wind farm selection method is to select a wind farm with the highest comprehensive evaluation value from multiple wind farms as a research object based on the scale, geographical location and operation time of the wind farm; Among them, the comprehensive evaluation value S of the wind farm is calculated as follows: Among them, ω1 is the wind farm scale weight, ω2 is the geographical location weight, ω3 is the operation time weight, and ω1+ω2+ω3=1, C is the installed capacity, C max is the maximum installed capacity of all candidate wind farms; D is the distance between the wind farm and the main power consumption area, V is the local annual average wind speed, T is the operating time, T max is the maximum operating time among all candidate wind farms.

3. The method for optimizing wind farm power generation based on multi-variable correlation according to claim 1, characterized in that: The target environmental parameter data stream includes wind speed and wind direction, and the corresponding data is collected through an anemometer and a wind vane; The target environment impact data stream includes temperature, humidity and air pressure, and the corresponding data are collected by a thermometer, a hygrometer and a barometer respectively.

4. The method for optimizing wind farm power generation based on multi-variable correlation according to claim 1, characterized in that: The sample data stream selection follows the following principles: the sample data stream can reflect the fluctuation of environmental factors; the sample data stream should have a potential correlation with the power generation.

5. The method for optimizing wind farm power generation based on multi-variable correlation according to claim 1, characterized in that: The maximum value range in the sample data stream is [0.9y max ,y max ], the minimum value range is [y min ,1.1y min ]; Among them, y max and min are the maximum and minimum values ​​in the sample data stream respectively.

6. A wind farm power generation optimization method based on multi-variable correlation according to claim 5, characterized in that: The data diversity index of the sample data stream is calculated by standard deviation, and the calculation steps are as follows: the sample data stream is Y = {y1, y2, y3, ..., y i ,...,y n }, calculate the average value of the sample data stream Calculate standard deviation where y i is the i-th sample data stream, and n is the total number of data points.

7. The method for optimizing wind farm power generation based on multi-variable correlation according to claim 5, characterized in that: The characteristic parameters of the large and small values ​​in the sample data stream include: The frequency of large values ​​f Gmax , Maximum value and average value The degree of deviation d Gmax , the formula is: Where n Gmax is a large value y Gmax The number of times it appears in the sample data stream; The frequency of small values ​​f Gmin , Small value y Gmin With the average The degree of deviation d Gmin , Where n Gmin is a small value of y Gmin The number of times it occurs in the sample data stream.

8. The method for optimizing wind farm power generation based on multi-variable correlation according to claim 1, characterized in that: The calculation formula for the correlation index between the maximum values ​​of the target environmental parameter data stream and the target environmental impact data stream in the sample data stream is: Among them, R Gmax is the correlation index between large values, f st is the frequency of large values ​​appearing simultaneously, f Gmax1 and d Gmax1 They are respectively the target environmental parameter data stream in the sample data stream that is filtered through the large value range and the large value y Gmax1 Frequency and maximum value y Gmax1 The degree of deviation from the mean, f Gmax2 and d Gmax2 They are respectively the target environment in the sample data stream that affects the large value y that appears after filtering the data stream through the large value range Gmax2 Frequency and maximum value y Gmax2 the degree of deviation from the mean; The calculation formula of the correlation index between the minimum values ​​of the target environmental parameter data stream and the target environmental impact data stream is: Among them, R Gmin is the correlation index between small values, f′ st is the frequency of small values ​​appearing simultaneously, f Gmin1 and d Gmin1 They are the target environmental parameter data stream in the sample data stream that is filtered through the large value range to appear the small value y Gmin1 Frequency of occurrence and minimum value y Gmin1 The degree of deviation from the mean, f Gmin2 and d Gmin2 The target environment in the sample data stream affects the data stream through the small value range screening of the small value y Gmin2 Frequency of occurrence and minimum value y Gmin2 The degree of deviation from the mean.

9. The method for optimizing wind farm power generation based on multi-variable correlation according to claim 8, characterized in that: The calculation formula for the correlation index between the overall target environmental impact data stream and the environmental parameter data set is: Among them, R Gmax is the correlation index between large values, R Gmin is the correlation index between small values, σ is the standard deviation of the sample data stream, and represents the data diversity index of the sample data stream.

10. The method for optimizing wind farm power generation based on multi-variable correlation according to claim 1, characterized in that: The impact of the correlation index on power generation includes: If R>0, it means that the target environmental impact data stream is positively correlated with the environmental parameter data set, that is, the environmental impact factors are consistent with the environmental parameters that directly affect power generation, and have a promoting effect on power generation; If R < 0, it indicates a negative correlation, that is, the environmental factors and the environmental parameters that directly affect power generation have opposite trends, which have an inhibitory effect on power generation; If R = 0, it means there is no obvious linear correlation between the two; When |R| is close to 1, it means that the correlation is strong and the environmental factors have a greater impact on power generation; When |R| is close to 0, it means that the correlation is weak and the environmental factors have little impact on power generation.

Images