Photovoltaic power generation operation control method and system based on data analysis

Abstract

The present invention relates to the field of data processing technology, and specifically to a photovoltaic power generation operation control method and system based on data analysis, including: obtaining the continuity of the light intensity at each moment according to the difference between the light intensities at adjacent moments, obtaining the power generation corresponding to each light intensity in combination with the correlation between the light intensity and the power generation, obtaining the corresponding consistency of each light intensity and the power generation through the difference with the power generation corresponding to other light intensities, correcting the linear relationship of the light intensity, and thus obtaining the corrected power generation; constructing a prediction model according to the difference between the power generation and the corrected power generation, obtaining the predicted power generation at the next moment, and controlling the photovoltaic power generation equipment according to the difference with the actual power generation. The present invention analyzes the relationship between the light intensity and the power generation of historical data, corrects the ARIMA model, and thus obtains the predicted power generation to control the photovoltaic power generation equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a photovoltaic power generation operation control method and system based on data analysis. Background Art

[0002] Photovoltaic power generation is a technology that converts photon energy in sunlight into electrical energy through photovoltaic cells. Maintaining photovoltaic power generation equipment is crucial to ensuring its long-term and efficient operation. Therefore, it is necessary to predict the possible failure time of the equipment based on historical data and models, maintain the photovoltaic power generation equipment, and avoid downtime losses caused by failures.

[0003] When the ARIMA model is used to predict the power generation data of the next moment through historical power generation data, there will be erroneous data in the historical data, and the error with the real data is large, resulting in a large deviation in the prediction of power generation at future moments. It is impossible to accurately determine the time when the photovoltaic power generation equipment may fail, and thus it is impossible to control and adjust the photovoltaic power generation equipment in time. Summary of the invention

[0004] The present invention provides a photovoltaic power generation operation control method and system based on data analysis to solve the existing problems.

[0005] The photovoltaic power generation operation control method and system based on data analysis of the present invention adopts the following technical solutions:

[0006] An embodiment of the present invention provides a photovoltaic power generation operation control method based on data analysis, the method comprising the following steps:

[0007] Get the light intensity and power generation at each moment;

[0008] According to the difference between the light intensity at adjacent moments, the continuity of the light intensity at each moment is obtained; through the correlation between the light intensity and the power generation, as well as the continuity of the light intensity at each moment, the power generation corresponding to each light intensity is obtained;

[0009] According to the difference between the power generation corresponding to each light intensity and the power generation corresponding to other light intensities, the corresponding consistency of each light intensity and the power generation is obtained;

[0010] According to the corresponding consistency of light intensity and power generation, the linear relationship between power generation and light intensity is corrected to obtain the corrected power generation under the light intensity at each moment;

[0011] A prediction model is constructed based on the difference between the power generation at each moment and the corrected power generation to obtain the predicted power generation at the next moment;

[0012] The photovoltaic power generation equipment is controlled according to the difference between the predicted power generation at the next moment and the actual power generation.

[0013] Furthermore, the specific steps of obtaining the continuity of the light intensity at each moment are as follows:

[0014]

[0015] in, Indicates the continuity of light intensity at the Qth moment, represents the light intensity at the Q+1th moment, represents the light intensity at the Qth moment, Represents the light intensity at the Q-1th moment.

[0016] Furthermore, the specific steps of obtaining the power generation corresponding to each light intensity are as follows:

[0017] Arrange all light intensities in order from small to large to construct a light intensity sequence; the calculation method of the power generation corresponding to the Ath light intensity in the light intensity sequence is:

[0018]

[0019] in, Indicates the power generation corresponding to the Ath light intensity in the light intensity sequence, It represents the number of power generation with the same light intensity as the Ath. Indicates the continuity of power generation at the i-th moment with the same light intensity as the A-th moment, represents the power generation at the i-th moment with the same light intensity as the A-th moment, Indicates the continuity of the generated power at the jth moment with the same light intensity as the Ath moment.

[0020] Furthermore, the specific method for obtaining the power generation continuity is as follows:

[0021] A time range of length w is constructed with the Qth moment as the center, and the Pearson correlation coefficient between the light intensity at each moment in the time range of the Qth moment and the power generation at each moment is recorded as the neighborhood correlation between the light intensity and the power generation at the Qth moment;

[0022]

[0023] in, Indicates the continuity of power generation at the Qth moment, represents the neighborhood correlation between the light intensity and the power generation at the Qth moment, Indicates the continuity of light intensity at the Qth moment.

[0024] Furthermore, the obtaining of the corresponding consistency between each light intensity and the generated power includes the following specific steps:

[0025] According to all the light intensities and the corresponding power generation, a photoelectric scatter plot is constructed with the light intensity as the horizontal axis and the power generation corresponding to the light intensity as the vertical axis. The calculation method for the corresponding consistency of the light intensity and the power generation of the u-th data point in the photoelectric scatter plot is:

[0026]

[0027] in, Indicates the correspondence between the illumination intensity and the power generation of the u-th data point in the photoelectric scatter plot. represents an exponential function with a natural constant as the base, n represents the number of data points in the photoelectric scatter diagram, represents the power generation of the u-th data point in the photovoltaic scatter plot, represents the power generation of the vth data point except the uth data point in the photoelectric scatter plot, represents the light intensity of the u-th data point in the photoelectric scatter plot, represents the light intensity of the vth data point except the uth data point in the photoelectric scatter plot, Indicates the continuity of the power generation at the i-th moment in the photoelectric scatter diagram, which is equal to the light intensity of the u-th data point. Represents the number of light intensities equal to the light intensity of the u-th data point in the photoelectric scatter plot.

[0028] Furthermore, the obtaining of the corrected power generation under the light intensity at each moment includes the following specific steps:

[0029] The unknown slope parameter k and constant parameter b are preset, and the linear model of light intensity-power generation is constructed using the slope parameter k and constant parameter b:

[0030]

[0031] in, represents the power generation under the light intensity at time t, represents the light intensity at time t;

[0032] Substitute the illumination intensity of all data points in all photoelectric scatter plots into the corrected error square sum formula. When the slope parameter k and the constant parameter b satisfy the corrected error square sum formula, When the value is minimum, the optimal slope parameter is obtained and the optimal constant parameter ;

[0033] Using the optimal slope parameter and the optimal constant parameter Construct a corrected linear model of light intensity-power generation:

[0034]

[0035] represents the corrected power generation under the light intensity at time t, Represents the light intensity at time t.

[0036] Furthermore, the specific method for obtaining the corrected error sum of squares is as follows:

[0037] The formula for constructing the corrected sum of squared errors based on the light intensity-power generation linear model is:

[0038]

[0039] Among them, S represents the sum of square errors of all data points after correction, n represents the number of data points in the photoelectric scatter diagram, Indicates the correspondence between the illumination intensity and the power generation of the u-th data point in the photoelectric scatter plot. represents the power generation of the u-th data point in the photovoltaic scatter plot, Represents the light intensity of the u-th data point in the photoelectric scatter plot.

[0040] Furthermore, the step of obtaining the predicted power generation at the next moment includes the following specific steps:

[0041] The next moment is recorded as the hth moment, and the light intensity at each moment is substituted into the corrected light intensity-power generation linear model to obtain the corrected power generation under the light intensity at each moment;

[0042] Input the autoregressive correction weight and the moving average correction weight into the ARIMA model to obtain the modified ARIMA model. The specific formula is:

[0043]

[0044] in, represents the predicted power generation at time h, represents the autoregressive correction weight at the hi-th moment, represents the moving average correction weight at the hi-th moment, is the prior constant term of the ARIMA model, is the preset number of autoregressive terms, is the preset number of moving average items, is the prior autocorrelation coefficient of the ARIMA model at the i-th moment, is the prior error of the ARIMA model at the hth moment, is the prior error of the ARIMA model at the hith moment, is the prior error parameter of the ARIMA model at the i-th moment.

[0045] Furthermore, the specific method of obtaining the autoregressive correction weight and the moving average correction weight is as follows:

[0046] The calculation method of the autoregressive correction weight at the hi-th moment is:

[0047]

[0048] The calculation method of the moving average correction weight at the hith moment is:

[0049]

[0050] in, represents the autoregressive correction weight at the hi-th moment, represents the moving average correction weight at the hi-th moment, represents the power generation at the hi-th moment, It represents the corrected power generation under the light intensity at the moment hi, is the preset number of autoregressive terms, is the preset number of moving average items.

[0051] The present invention also proposes a photovoltaic power generation operation control system based on data analysis, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of the aforementioned photovoltaic power generation operation control method based on data analysis.

[0052] The beneficial effects of the technical solution of the present invention are as follows: according to the difference between the light intensities at adjacent moments, the continuity of the light intensity at each moment is obtained to show the change of light; since the power generation power changes with the change of light intensity, the power generation power corresponding to each light intensity is obtained in combination with the correlation between the light intensity and the power generation power; through the difference with the power generation power corresponding to other light intensities, the corresponding consistency of each light intensity and the power generation power is obtained; the linear relationship of the light intensity is corrected to obtain the corrected power generation power, and the influence of the error data on the prediction model is eliminated; a prediction model is constructed according to the difference between the power generation power and the corrected power generation power to obtain the predicted power generation power at the next moment; according to the difference with the actual power generation power, the photovoltaic power generation equipment is controlled and adjusted in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 The present invention is a flowchart of the steps of the photovoltaic power generation operation control method based on data analysis. DETAILED DESCRIPTION

[0055] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the photovoltaic power generation operation control method and system based on data analysis proposed by the present invention, its specific implementation method, structure, characteristics and effects are described in detail as follows in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0056] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0057] The specific scheme of the photovoltaic power generation operation control method and system based on data analysis provided by the present invention is described in detail below with reference to the accompanying drawings.

[0058] See also Figure 1 , which shows a flow chart of the steps of a photovoltaic power generation operation control method based on data analysis provided by an embodiment of the present invention, the method comprising the following steps:

[0059] Step S001, obtaining the light intensity and power generation power at each moment.

[0060] The purpose of this embodiment is to analyze the relationship between light intensity and power generation of historical data and to modify the ARIMA model, so as to obtain the predicted power generation and control and adjust the photovoltaic power generation equipment. Therefore, a photoresistor sensor is installed on the photovoltaic solar panel to collect the light intensity at each moment, and a current sensor and a voltage sensor are installed to collect the current and voltage of the photovoltaic solar panel at each moment, and the product of the current data and the voltage data at each moment is used as the power generation of the photovoltaic power generation equipment at each moment. The collection frequency in this embodiment is once per second, and other collection frequencies can be used in other embodiments, which are not specifically limited in this embodiment.

[0061] Step S002, obtain the continuity of light intensity at each moment according to the difference between light intensities at adjacent moments; obtain the continuity of power generation at each moment through the correlation between light intensity and power generation and the continuity of light intensity at each moment, thereby obtaining the power generation corresponding to each light intensity.

[0062] It should be noted that the same light intensity may exist at different times, and the same light intensity is affected by the errors between multiple sensors and environmental factors such as dust on the sensor surface, air humidity refraction, etc., so that the power generation at each moment of the same light intensity may be different, so it is necessary to determine the power generation corresponding to each light intensity. Light intensity changes continuously and slowly in nature, and the difference in light intensity at adjacent moments is small. The light intensity is continuous, and the power generation changes with the change of light intensity. Therefore, the continuity of the obtained light intensity is first obtained through the change of light intensity.

[0063] Specifically, the calculation method of the light intensity continuity at the Qth moment is:

[0064]

[0065] in, Indicates the continuity of light intensity at the Qth moment, represents the light intensity at the Q+1th moment, represents the light intensity at the Qth moment, Represents the light intensity at the Q-1th moment.

[0066] It represents the variation of the light intensity between the Qth moment and the adjacent moments. The smaller the variation, the more the light intensity variation conforms to the natural law and the more continuous the light intensity is in the time series.

[0067] It should be further explained that, since the power generation power is mainly caused by the change of light intensity, the continuity of the power generation power in time series is positively correlated with the continuity of the light intensity in time series. Therefore, the continuity of the power generation power is obtained through the continuity of the light intensity. Specifically, a time range with a length of w is constructed with the Qth moment as the center, and the Pearson correlation coefficient between the light intensity at each moment in the time range of the Qth moment and the power generation power at each moment is recorded as the neighborhood correlation between the light intensity and the power generation power at the Qth moment. In this embodiment, the preset time range is 10, and other values ​​can be set in other embodiments. This embodiment does not make a specific limitation.

[0068] The calculation method of the power generation continuity at the Qth moment is:

[0069]

[0070] in, Indicates the continuity of power generation at the Qth moment, represents the neighborhood correlation between the light intensity and the power generation at the Qth moment, Indicates the continuity of light intensity at the Qth moment.

[0071] Since light intensity is positively correlated with power generation, the Pearson correlation coefficient between light intensity and its surrounding data and between power generation and its surrounding data is The larger the value is, the greater the light intensity is, and the higher the continuity of the power generation at the Qth moment is.

[0072] At this point, the continuity of the generated power at each moment is obtained, and the generated power corresponding to each light intensity is obtained according to the continuity of the generated power at each moment and the generated power at each moment under the same light intensity.

[0073] Specifically, all light intensities are arranged in order from small to large to construct a light intensity sequence; the calculation method of the power generation corresponding to the Ath light intensity in the light intensity sequence is:

[0074]

[0075] in, Indicates the power generation corresponding to the Ath light intensity in the light intensity sequence, It represents the number of power generation with the same light intensity as the Ath. Indicates the continuity of power generation at the i-th moment with the same light intensity as the A-th moment, represents the power generation at the i-th moment with the same light intensity as the A-th moment, Indicates the continuity of the generated power at the jth moment with the same light intensity as the Ath moment.

[0076] It represents the continuous sum of the power generation at all times equal to the Ath light intensity. It represents the ratio of the continuity of the power generation at the i-th moment, which is equal to the A-th light intensity, to the sum of the continuity of the power generation at all moments. The larger the ratio is, the stronger the correlation with the light intensity is, and the more likely it is the power generation corresponding to the A-th light intensity.

[0077] Step S003, according to the difference between the power generation power corresponding to each light intensity and the power generation power corresponding to other light intensities, obtain the corresponding consistency of each light intensity and the power generation power; according to the corresponding consistency of the light intensity and the power generation power, correct the linear relationship between the power generation power and the light intensity to obtain the corrected power generation power under the light intensity at each moment.

[0078] It should be noted that when using the ARIMA model to predict power generation, the impact of each data in the data used to construct the model on the accuracy of the model is the same, so that unreliable data also performs well in the prediction. When the error of the power generation is too large, it will affect the prediction result. Therefore, the authenticity of the power generation corresponding to each light intensity can be analyzed to adjust the power generation with possible errors. Under normal circumstances, there is a linear proportional relationship between light intensity and power generation. Therefore, the more similar the ratio between the power generation corresponding to each light intensity and the power generation corresponding to other light intensities is, the higher the authenticity of the power generation corresponding to the light intensity is.

[0079] Specifically, according to all the light intensities and the corresponding power generation, a photoelectric scatter plot is constructed with the light intensity as the horizontal axis and the power generation corresponding to the light intensity as the vertical axis; the calculation method for the corresponding consistency of the light intensity and the power generation of the u-th data point in the photoelectric scatter plot is:

[0080]

[0081] in, Indicates the correspondence between the illumination intensity and the power generation of the u-th data point in the photoelectric scatter plot. represents an exponential function with a natural constant as the base, n represents the number of data points in the photoelectric scatter diagram, represents the power generation of the u-th data point in the photovoltaic scatter plot, represents the power generation of the vth data point except the uth data point in the photoelectric scatter plot, represents the light intensity of the u-th data point in the photoelectric scatter plot, represents the light intensity of the vth data point except the uth data point in the photoelectric scatter plot, Indicates the continuity of the power generation at the i-th moment in the photoelectric scatter diagram, which is equal to the light intensity of the u-th data point. Represents the number of light intensities equal to the light intensity of the u-th data point in the photoelectric scatter plot.

[0082] It represents the difference between the ratio of power generation to light intensity of the u-th data point and the ratio of power generation to light intensity of other data points. The smaller the difference, the more likely the u-th data is to be in a linear relationship. The higher the consistency of the corresponding light intensity and power generation, the higher the authenticity of the data. It represents the temporal authenticity of the light intensity of the u-th data point in the photoelectric scatter diagram. The greater the continuity of the power generation at all moments when the light intensity is equal to that of the u-th data point, the greater the authenticity.

[0083] It should be further explained that when correcting the relationship between light intensity and power generation, since there is a linear relationship between light intensity and power generation, the data points in the photoelectric scatter diagram can be fitted by the least squares method to obtain a light intensity-power generation linear model. When using the sum of squared errors in the least squares method to determine the parameters in the linear model, the authenticity of the data will affect the calculation of the parameters. Therefore, it is necessary to correct the sum of squared errors in the least squares method, and then use the corrected sum of squared errors to construct a corrected light intensity-power generation linear model.

[0084] The unknown slope parameter k and constant parameter b are preset, and the linear model of light intensity-power generation is constructed using the slope parameter k and constant parameter b:

[0085]

[0086] in, represents the power generation under the light intensity at time t, Represents the light intensity at time t.

[0087] The formula for constructing the corrected sum of squared errors based on the light intensity-power generation linear model is:

[0088]

[0089] Among them, S represents the sum of square errors of all data points after correction, n represents the number of data points in the photoelectric scatter diagram, Indicates the correspondence between the illumination intensity and the power generation of the u-th data point in the photoelectric scatter plot. represents the power generation of the u-th data point in the photovoltaic scatter plot, Represents the light intensity of the u-th data point in the photoelectric scatter plot.

[0090] Substitute the illumination intensity of all data points in all photoelectric scatter plots into the corrected error square sum formula. When the slope parameter k and the constant parameter b satisfy the corrected error square sum formula, When the value is minimum, the optimal slope parameter is obtained and the optimal constant parameter .

[0091] Furthermore, using the optimal slope parameter and the optimal constant parameter Construct a corrected linear model of light intensity-power generation:

[0092]

[0093] represents the corrected power generation under the light intensity at time t, Represents the light intensity at time t.

[0094] It should be noted that the least square method and the method of obtaining the minimum sum of squared errors therein are well-known techniques and will not be described in detail in this embodiment.

[0095] Step S004: construct a prediction model based on the difference between the generated power at each moment and the corrected generated power to obtain the predicted generated power at the next moment.

[0096] It should be noted that the ARIMA model uses the power generation at historical moments to predict the power generation, but the data at historical moments contain errors, which reduces the authenticity. Therefore, the weight of the power generation at historical moments is adjusted through the relationship between the corrected light intensity and the power generation to better reflect the true situation of the historical data and obtain accurate predicted power generation. If the error between the actual power generation and the corrected power generation is larger, it is necessary to reduce the error between the actual power generation and the corrected power generation and increase the weight.

[0097] Specifically, the next moment is recorded as the hth moment, and the light intensity at each moment is substituted into the corrected light intensity-power generation linear model to obtain the corrected power generation under the light intensity at each moment. The calculation method of the autoregressive correction weight at the hith moment is:

[0098]

[0099] The calculation method of the moving average correction weight at the hith moment is:

[0100]

[0101] in, represents the autoregressive correction weight at the hi-th moment, represents the moving average correction weight at the hi-th moment, represents the power generation at the hi-th moment, It represents the corrected power generation under the light intensity at the moment hi, is the preset number of autoregressive terms, is the preset number of moving average items. In this embodiment, p is preset to be 3 and q is preset to be 3. This is taken as an example for description. Other values ​​may be set in other implementation modes, and this embodiment does not specifically limit this.

[0102] It represents the error between the actual power generation and the corrected power generation. The larger the error, the greater the difference between the actual power generation at the historical moment and the corrected power generation. In order to make the power generation at the hi moment closer to the true value, the larger the weight required.

[0103] Input the autoregressive correction weight and the moving average correction weight into the ARIMA model to obtain the modified ARIMA model. The specific formula is:

[0104]

[0105] in, represents the predicted power generation at time h, represents the autoregressive correction weight at the hi-th moment, represents the moving average correction weight at the hi-th moment, is the prior constant term of the ARIMA model, is the preset number of autoregressive terms, is the preset number of moving average items, is the prior autocorrelation coefficient of the ARIMA model at the i-th moment, is the prior error of the ARIMA model at the hth moment, is the prior error of the ARIMA model at the hith moment, is the prior error parameter of the ARIMA model at the i-th moment.

[0106] It should be noted that the calculation formula of the ARIMA model is a known technology and will not be described in detail in this embodiment.

[0107] Step S005: Compare the predicted power generation with the actual power generation to control and adjust the photovoltaic power generation equipment.

[0108] The predicted power generation at the next moment is compared with the actual power generation. If the actual power generation at the next moment is less than the preset percentage of the predicted power generation, the photovoltaic power generation equipment may fail, and it is necessary to maintain the photovoltaic power generation equipment in advance to avoid downtime losses caused by the failure. The preset percentage in this embodiment is 75%, and other values ​​can be set in other implementation modes, which are not specifically limited in this embodiment.

[0109] It should be noted that the The model only shows negative correlation and the output of the constraint model is in In the range, As the input of this model, it can be replaced by other models with the same purpose in specific implementation. The model is used as an example for description without any specific limitation.

[0110] The present invention also provides a photovoltaic power generation operation control system based on data analysis, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of the aforementioned photovoltaic power generation operation control method based on data analysis.

[0111] So far, the present invention is completed.

[0112] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A photovoltaic power generation operation control method based on data analysis, characterized in that: The method comprises the following steps: Get the light intensity and power generation at each moment; According to the difference between the light intensity at adjacent moments, the continuity of the light intensity at each moment is obtained; through the correlation between the light intensity and the power generation, as well as the continuity of the light intensity at each moment, the power generation corresponding to each light intensity is obtained; According to the difference between the power generation corresponding to each light intensity and the power generation corresponding to other light intensities, the corresponding consistency of each light intensity and the power generation is obtained; According to the corresponding consistency of light intensity and power generation, the linear relationship between power generation and light intensity is corrected to obtain the corrected power generation under the light intensity at each moment; A prediction model is constructed based on the difference between the power generation at each moment and the corrected power generation to obtain the predicted power generation at the next moment; Control the photovoltaic power generation equipment according to the difference between the predicted power generation at the next moment and the actual power generation; The specific steps of obtaining the corrected power generation under the light intensity at each moment are as follows: The unknown slope parameter k and constant parameter b are preset, and the linear model of light intensity-power generation is constructed using the slope parameter k and constant parameter b: in, represents the power generation under the light intensity at time t, represents the light intensity at time t; Substitute the illumination intensity of all data points in all photoelectric scatter plots into the corrected error square sum formula. When the slope parameter k and the constant parameter b satisfy the corrected error square sum formula, When the value is minimum, the optimal slope parameter is obtained and the optimal constant parameter ; Using the optimal slope parameter and the optimal constant parameter Construct a corrected linear model of light intensity-power generation: represents the corrected power generation under the light intensity at time t, represents the light intensity at time t; The specific method for obtaining the corrected error sum of squares is as follows: The formula for constructing the corrected sum of squared errors based on the light intensity-power generation linear model is: Among them, S represents the sum of square errors of all data points after correction, n represents the number of data points in the photoelectric scatter diagram, Indicates the correspondence between the illumination intensity and the power generation of the u-th data point in the photoelectric scatter plot. represents the power generation of the u-th data point in the photovoltaic scatter plot, Represents the light intensity of the u-th data point in the photoelectric scatter plot; The specific steps of obtaining the continuity of the light intensity at each moment are as follows: in, Indicates the continuity of light intensity at the Qth moment, represents the light intensity at the Q+1th moment, represents the light intensity at the Qth moment, represents the light intensity at the Q-1th moment; The specific steps of obtaining the power generation corresponding to each light intensity are as follows: Arrange all light intensities in order from small to large to construct a light intensity sequence; the calculation method of the power generation corresponding to the Ath light intensity in the light intensity sequence is: in, Indicates the power generation corresponding to the Ath light intensity in the light intensity sequence, It represents the number of power generation with the same light intensity as the Ath. Indicates the continuity of power generation at the i-th moment with the same light intensity as the A-th moment, represents the power generation at the i-th moment with the same light intensity as the A-th moment, Indicates the continuity of power generation at the jth moment with the same light intensity as the Ath moment; The specific method of obtaining the continuity of the power generation is as follows: A time range of length w is constructed with the Qth moment as the center, and the Pearson correlation coefficient between the light intensity at each moment in the time range of the Qth moment and the power generation at each moment is recorded as the neighborhood correlation between the light intensity and the power generation at the Qth moment; in, Indicates the continuity of power generation at the Qth moment, represents the neighborhood correlation between the light intensity and the power generation at the Qth moment, Indicates the continuity of light intensity at the Qth moment; The specific steps of obtaining the corresponding consistency of each light intensity and the generated power are as follows: According to all the light intensities and the corresponding power generation, a photoelectric scatter plot is constructed with the light intensity as the horizontal axis and the power generation corresponding to the light intensity as the vertical axis. The calculation method for the corresponding consistency of the light intensity and the power generation of the u-th data point in the photoelectric scatter plot is: in, Indicates the correspondence between the illumination intensity and the power generation of the u-th data point in the photoelectric scatter plot. represents an exponential function with a natural constant as the base, n represents the number of data points in the photoelectric scatter diagram, represents the power generation of the u-th data point in the photovoltaic scatter plot, represents the power generation of the vth data point except the uth data point in the photoelectric scatter plot, represents the light intensity of the u-th data point in the photoelectric scatter plot, represents the light intensity of the vth data point except the uth data point in the photoelectric scatter plot, Indicates the continuity of the power generation at the i-th moment in the photoelectric scatter diagram, which is equal to the light intensity of the u-th data point. Represents the number of light intensities equal to the light intensity of the u-th data point in the photoelectric scatter plot; The specific steps of obtaining the predicted power generation at the next moment are as follows: The next moment is recorded as the hth moment, and the light intensity at each moment is substituted into the corrected light intensity-power generation linear model to obtain the corrected power generation under the light intensity at each moment; Input the autoregressive correction weight and the moving average correction weight into the ARIMA model to obtain the modified ARIMA model. The specific formula is: in, represents the predicted power generation at time h, represents the autoregressive correction weight at the hi-th moment, represents the moving average correction weight at the hi-th moment, is the prior constant term of the ARIMA model, is the preset number of autoregressive terms, is the preset number of moving average items, is the prior autocorrelation coefficient of the ARIMA model at the i-th moment, is the prior error of the ARIMA model at the hth moment, is the prior error of the ARIMA model at the hith moment, is the prior error parameter of the ARIMA model at the i-th moment.

2. The photovoltaic power generation operation control method based on data analysis according to claim 1 is characterized in that: The specific method of obtaining the autoregressive correction weight and the moving average correction weight is as follows: The calculation method of the autoregressive correction weight at the hi-th moment is: The calculation method of the moving average correction weight at the hi-th moment is: in, represents the autoregressive correction weight at the hi-th moment, represents the moving average correction weight at the hi-th moment, represents the power generation at the hi-th moment, It represents the corrected power generation under the light intensity at the moment hi, is the preset number of autoregressive terms, is the preset number of moving average items.

3. A photovoltaic power generation operation control system based on data analysis, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of the photovoltaic power generation operation control method based on data analysis as described in any one of claims 1-2 are implemented.

Images