New energy station electric energy quality evaluation method and device

Abstract

The invention provides a new energy station electric energy quality early warning method and device, and belongs to the technical field of new energy power generation. The method comprises the steps of building a data matrix by collecting power quality evaluation index parameters of a new energy station, converting the data matrix into a normal distribution sample matrix, a normal density value matrix of evaluation indexes and an evaluation index grade probability matrix after data processing, and obtaining a power quality evaluation result based on the normal distribution sample matrix and the evaluation index grade probability matrix. And obtaining a weight value data matrix of the local sensitivity of the evaluation index, carrying out weighted summation on the power quality grade probability matrix to obtain grade scores, finally integrating the grade scores to obtain a new energy station power quality total score, and carrying out grade evaluation and alarm according to the total score. According to the method, data fusion and characteristic display, accurate weight distribution and quantitative evaluation are realized through multivariate Gaussian distribution, and grading alarm is combined, so that the accuracy of power quality evaluation of the new energy station and the operation stability of the new energy station are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of renewable energy power generation, and in particular to a method for evaluating power quality of a renewable energy station, and a device for evaluating power quality of a renewable energy station. Background Art

[0002] With the proposal of the "dual carbon" goal, the installed capacity of new energy and the amount of grid-connected power generation have increased rapidly. However, due to the randomness, volatility and intermittency of the output power of new energy power generation units, when they are incorporated into the large power grid, they will have many negative impacts on the power quality, safe operation and system reliability of the large power grid. In addition, due to the use of a large number of electronic converters inside, power quality problems such as harmonic distortion, voltage deviation, three-phase imbalance, frequency deviation, etc. frequently occur. These power quality problems always affect the safety and stability of new energy sites. Therefore, in order to explore the potential of new energy power generation and improve the power quality and power supply reliability of the distribution network, it is necessary to conduct a scientific and reasonable evaluation of its power quality.

[0003] At present, the more mainstream methods of power quality assessment include the index weighting method, which includes the subjective weighting method and the objective weighting method. The subjective weighting method is a method of weighting the judgment of each index based on expert experience and user needs. It generally does not require original data, but only requires decision makers to make judgments based on their own experience. It is simple to operate, easy to quickly master and apply in practice. However, it focuses on expert experience and does not fully reflect the characteristics of the data itself that constitutes the evaluation index. Therefore, the objective weighting method that weights according to the characteristics of the evaluation index data itself has been proposed by relevant scholars. It starts from the evaluation index data itself and uses the characteristics of the data itself to obtain the weight, so that the final evaluation result can fit the actual situation. Therefore, the objective weighting method is widely used in power quality assessment.

[0004] However, the weight coefficient determined by the traditional objective weighting method does not fully consider the changing process of the power quality evaluation index data of the new energy power station and the distribution characteristics of the evaluation index data itself, which leads to a certain gap between the weighting result and the objective reality, and thus cannot accurately evaluate the power quality of the new energy station. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method and device for evaluating power quality of a new energy station to solve the above problems.

[0006] In order to achieve the above object, an embodiment of the present invention provides a new energy station power quality early warning method, comprising: Obtain multiple parameter values ​​of multiple evaluation indicators of power quality of new energy stations to construct an evaluation indicator data matrix; Performing data conversion processing on the evaluation index data matrix to obtain an evaluation index data matrix that conforms to normal distribution, a probability density data matrix of the evaluation index, and a probability data matrix of the power quality level of the evaluation index; Based on the evaluation index data matrix that conforms to the normal distribution and the probability density data matrix of the evaluation index, a weight value data matrix of the local sensitivity of the evaluation index is obtained; Based on the weight value data matrix of the local sensitivity of the evaluation index, the power quality level probability data matrix of the evaluation index is weighted and summed to obtain the power quality scores of the new energy stations under multiple power quality levels; Based on the power quality scores of new energy stations under various power quality levels, the power quality scores of new energy stations are obtained; The power quality scores of the new energy stations are graded to obtain the assessment level of the power quality of the new energy stations, and the corresponding alarm strategy is executed based on the assessment level of the power quality of the new energy stations.

[0007] Optionally, the multiple evaluation indicators include: voltage deviation, three-phase imbalance, harmonic distortion and frequency deviation.

[0008] Optionally, the evaluation index data matrix is ​​subjected to normal distribution processing to obtain an evaluation index data matrix that conforms to normal distribution, including: Calculate the mean and standard deviation of multiple parameter values ​​of each evaluation indicator in the evaluation indicator data matrix; Calculate the difference between each parameter value of each evaluation index and the mean value of multiple parameter values ​​of each evaluation index to obtain the mean difference of each parameter value of each evaluation index; The ratio of the mean deviation of each parameter value of each evaluation index to the standard deviation of multiple parameter values ​​of each evaluation index is calculated to obtain each parameter value of each evaluation index that conforms to the normal distribution, so as to construct an evaluation index data matrix that conforms to the normal distribution.

[0009] Optionally, the evaluation index data matrix is ​​subjected to multi-dimensional Gaussian distribution processing to obtain a probability density data matrix of the evaluation index, including: Determining the number of evaluation indicators and the number of multiple parameter values ​​of the evaluation indicators; Based on the mean deviation of each parameter value of the evaluation index, the evaluation index deviation data matrix is ​​constructed; Transpose the evaluation index deviation data matrix to obtain the evaluation index transposed data matrix; Based on the number of multiple parameter values ​​of the evaluation index, the evaluation index deviation data matrix and the evaluation index transposed data matrix, a covariance data matrix of the evaluation index is obtained; Performing determinant operation and matrix inverse operation on the covariance data matrix of the evaluation index to obtain the covariance determinant value of the evaluation index and the covariance data inverse matrix of the evaluation index; Based on the number of evaluation indicators, the covariance determinant values ​​of the evaluation indicators, the evaluation indicator transposed data matrix, the covariance data inverse matrix of the evaluation indicators and the evaluation indicator deviation data matrix, the probability density data matrix of the evaluation indicators is obtained.

[0010] Optionally, based on the number of multiple parameter values ​​of the evaluation index, the evaluation index deviation data matrix and the evaluation index transposed data matrix, a covariance data matrix of the evaluation index is obtained, including: The following formula is used to calculate the number of multiple parameter values ​​of the evaluation index, the evaluation index deviation data matrix and the evaluation index transposed data matrix to obtain the covariance data matrix of the evaluation index; ;in, Represents the covariance data matrix of the evaluation index, Indicates the number of multiple parameter values ​​of the evaluation index, represents the evaluation index deviation data matrix, Represents the evaluation index transposed data matrix.

[0011] Optionally, based on the number of evaluation indicators, the covariance determinant values ​​of the evaluation indicators, the evaluation indicator transposed data matrix, the covariance data inverse matrix of the evaluation indicators and the evaluation indicator deviation data matrix, a probability density data matrix of the evaluation indicators is obtained, including: The following formula is used to calculate the number of evaluation indicators, the covariance determinant of the evaluation indicators, the transposed data matrix of the evaluation indicators, the inverse covariance data matrix of the evaluation indicators, and the deviation data matrix of the evaluation indicators to obtain the probability density data moment of the evaluation indicators; ;in, Represents the probability density data moment of the evaluation index, represents pi, represents the number of evaluation indicators, represents the covariance determinant of the evaluation index, represents the evaluation index transposed data matrix, Represents the inverse matrix of the covariance data of the evaluation index, Represents the evaluation index deviation data matrix.

[0012] Optionally, the evaluation index data matrix is ​​subjected to power quality level probability statistical processing to obtain a power quality level probability data matrix of the evaluation index, including: Matching each parameter value of each evaluation indicator in the evaluation indicator data matrix with a pre-constructed power quality grade table to obtain the power quality grade of each parameter value of each evaluation indicator; wherein the pre-constructed power quality grade table is used to characterize the mapping relationship between each parameter value of each evaluation indicator and the power quality grade; Determine the number of multiple parameter values ​​of the evaluation index and the number of parameter values ​​of each evaluation index under various power quality conditions; The ratio of the number of parameter values ​​of each evaluation indicator under each power quality level to the number of multiple parameter values ​​of the evaluation indicator is calculated to obtain the probability of each evaluation indicator under each power quality level, so as to construct the power quality level probability data matrix of the evaluation indicator.

[0013] Optionally, based on the evaluation index data matrix conforming to the normal distribution and the probability density data matrix of the evaluation index, a weight value data matrix of the local sensitivity of the evaluation index is obtained, including: Calculate the mean of multiple parameter values ​​of each evaluation indicator in the evaluation indicator data matrix that conforms to the normal distribution, and calculate the difference between the mean of the multiple parameter values ​​of each evaluation indicator and the preset parameter value of each evaluation indicator to obtain a first deviation value of each evaluation indicator; Calculate the mean of multiple probability densities of each evaluation indicator in the probability density data matrix of the evaluation indicator, and calculate the difference between the mean of the multiple probability densities of each evaluation indicator and the preset probability density of each evaluation indicator to obtain a second deviation value of each evaluation indicator; The first deviation value of each evaluation index and the second deviation value of each evaluation index are weighted and summed respectively to obtain the first deviation value of the power quality of the new energy station and the second deviation value of the power quality of the new energy station; Calculate the difference between the first deviation value of the power quality of the new energy station and the second deviation value of the power quality of the new energy station to obtain a change value of the power quality of the new energy station; Respectively calculating the absolute value of the difference between the mean of the multiple parameter values ​​of each evaluation indicator and the mean of the multiple probability densities of each evaluation indicator to obtain a third deviation value of each evaluation indicator; The ratios of the change value of the power quality of the new energy station and the third deviation value of each evaluation index are calculated respectively to obtain the local sensitivity of each evaluation index; The sum of the local sensitivities of each evaluation index is calculated, and the ratio of the local sensitivity of each evaluation index to the sum is calculated respectively to obtain the weight value of the local sensitivity of each evaluation index, so as to construct a weight value data matrix of the local sensitivity of the evaluation index.

[0014] Optionally, based on the power quality scores of the new energy stations at each power quality level, the power quality scores of the new energy stations are obtained, including: The following formula is used to calculate the power quality score of the new energy station under each power quality level to obtain the power quality score of the new energy station; ;in, Indicates the power quality score of the new energy station. Indicates the dth power quality level, Indicates the total number of power quality levels, Represents the power quality score of the new energy station under the dth power quality level.

[0015] In a second aspect of an embodiment of the present invention, a new energy station power quality early warning device is provided, comprising: A matrix construction module is used to obtain multiple parameter values ​​of multiple evaluation indicators of power quality of new energy stations to construct an evaluation indicator data matrix; A data processing module is used to perform data conversion processing on the evaluation index data matrix to obtain an evaluation index data matrix that conforms to the normal distribution, a probability density data matrix of the evaluation index, and a probability data matrix of the power quality level of the evaluation index; A weight calculation module is used to obtain a weight value data matrix of the local sensitivity of the evaluation index based on the evaluation index data matrix that conforms to the normal distribution and the probability density data matrix of the evaluation index; A scoring calculation module is used to perform weighted summation on the power quality level probability data matrix of the evaluation index based on the weight value data matrix of the local sensitivity of the evaluation index, so as to obtain the power quality scores of the new energy station under multiple power quality levels; A total score calculation module is used to obtain a new energy station power quality score based on the new energy station power quality score at each power quality level; The graded alarm module is used to grade the power quality scores of the new energy stations, obtain the evaluation level of the power quality of the new energy stations, and execute the corresponding alarm strategy based on the evaluation level of the power quality of the new energy stations.

[0016] Beneficial effects of the present invention: (1) Data fusion and characteristic display: By adopting multivariate Gaussian distribution, the present invention can effectively fuse multiple indicator data information together, which can not only intuitively display the data distribution characteristics of each indicator, but also reveal the correlation and independence between indicators. This feature significantly improves the rationality and reliability of power quality assessment of new energy stations.

[0017] (2) Weight determination and evaluation accuracy: By combining the local sensitivity analysis method and the multivariate Gaussian distribution probability density function, the present invention can assign appropriate weights to each indicator in the evaluation sample, thereby making the power quality evaluation results more accurate.

[0018] (3) Quantitative evaluation: By using probability statistics, the present invention can calculate the probability vector of the indicators appearing at different levels, and combine the indicator weights to achieve the quantification of power quality evaluation, making the evaluation results more scientific and operational.

[0019] (4) Gradual alarm: According to the severity of the power quality problem, the present invention provides different alarm modes and treatment measures. This helps the staff to deal with the power quality problem in a timely and accurate manner, thereby improving the operational stability and reliability of the new energy station.

[0020] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 It is a flow chart of a method for evaluating power quality of a new energy station provided by an embodiment of the present invention; Figure 2 It is a structural schematic diagram of a new energy station power quality evaluation device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0024] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0025] Embodiment 1 Please refer to Figure 1 , Figure 1 : is a flow chart of a method for evaluating power quality of a new energy station provided by an embodiment of the present invention, the method comprising the following steps: S100, obtaining multiple parameter values ​​of multiple evaluation indicators of power quality of a new energy station to construct an evaluation indicator data matrix; The evaluation index of power quality of new energy stations refers to a series of technical parameters used to measure and evaluate the output power quality of new energy stations, including but not limited to voltage deviation, three-phase imbalance, harmonic distortion and frequency deviation, etc.

[0026] For ease of understanding, multiple parameter values ​​of multiple evaluation indicators of power quality of new energy stations are given as examples below, as shown in Table 1 below: Table 1 Multiple parameter values ​​of power quality evaluation indicators of new energy stations

[0027] Evaluation index data matrix: .

[0028] S200, performing data conversion processing on the evaluation index data matrix to obtain an evaluation index data matrix that conforms to normal distribution, a probability density data matrix of the evaluation index, and a probability data matrix of the power quality level of the evaluation index; In one embodiment, step S200 includes: S210, performing normal distribution processing on the evaluation index data matrix to obtain an evaluation index data matrix that conforms to normal distribution; Specifically, step S210 includes: S211, calculating the mean and standard deviation of multiple parameter values ​​of each evaluation index in the evaluation index data matrix; For ease of understanding, the following example is given: Mean voltage deviation: (1.02+1.58-1.03-0.16+1.54+1.45+4.22-4.94-2.52+3.90) / 10=0.506.

[0029] The mean of three-phase unbalance is (1.76+1.33+1.24+1.39+0.43+0.48+1.60+0.41+0.15+ 0.77) / 10=0.956.

[0030] Mean value of harmonic distortion: (1.29+1.16+1.35+1.38+1.07+2.39+3.86+1.52+1.22+2.67) / 10=1.791.

[0031] Mean of frequency deviation: (-0.05-0.13+0.18-0.17-0.19-0.14+0.35-0.21+0.16-0.26) / 10=-0.46.

[0032] Standard deviation of voltage deviation: ≈2.6517.

[0033] Standard deviation of three-phase unbalance: ≈0.5537.

[0034] Standard deviation of harmonic distortion: ≈0.8570.

[0035] Standard deviation of frequency deviation: ≈0.4690.

[0036] S212, calculating the difference between each parameter value of each evaluation index and the mean of multiple parameter values ​​of each evaluation index, to obtain the mean difference of each parameter value of each evaluation index; For ease of understanding, the mean deviation of each parameter of each evaluation index data is calculated by combining the data in Table 1 with the mean value of step S211, as shown in Table 2 below: Table 2 The mean deviation of multiple parameter values ​​of power quality evaluation indicators of new energy stations

[0037] Evaluation index deviation data matrix: .

[0038] S213, calculating the ratio of the mean deviation of each parameter value of each evaluation index to the standard deviation of multiple parameter values ​​of each evaluation index, obtaining each parameter value of each evaluation index that conforms to the normal distribution, so as to construct an evaluation index data matrix that conforms to the normal distribution.

[0039] For ease of understanding, Table 2 and the standard deviation of step S211 are combined to calculate the ratio of the two to obtain the parameter values ​​of each evaluation index that conforms to the normal distribution, as shown in Table 3 below: Table 3 Multiple parameter values ​​of power quality evaluation indicators of new energy stations that conform to normal distribution

[0040] S220, performing multi-dimensional Gaussian distribution processing on the evaluation index data matrix to obtain a probability density data matrix of the evaluation index; Specifically, step S220 includes: S221, determining the number of evaluation indicators and the number of multiple parameter values ​​of the evaluation indicators; Taking Table 1 as an example, the number of evaluation indicators is 4, and the number of multiple parameter values ​​of the evaluation indicators is 10.

[0041] S222, constructing an evaluation index deviation data matrix based on the mean deviation of each parameter value of the evaluation index; S223, performing transposition processing on the evaluation index deviation data matrix to obtain an evaluation index transposed data matrix; Transposition processing refers to exchanging the rows and columns of the evaluation index deviation data matrix.

[0042] Specifically, the evaluation index transposes the data matrix: .

[0043] S224, obtaining a covariance data matrix of the evaluation index based on the number of multiple parameter values ​​of the evaluation index, the evaluation index deviation data matrix, and the evaluation index transposed data matrix; In one embodiment, the number of multiple parameter values ​​of the evaluation index, the evaluation index deviation data matrix and the evaluation index transposed data matrix are calculated using the following formula to obtain the covariance data matrix of the evaluation index; ;in, Represents the covariance data matrix of the evaluation index, Indicates the number of multiple parameter values ​​of the evaluation index, represents the evaluation index deviation data matrix, Represents the evaluation index transposed data matrix.

[0044] S225, performing determinant operation and matrix inverse operation on the covariance data matrix of the evaluation index to obtain the covariance determinant value of the evaluation index and the covariance data inverse matrix of the evaluation index; Determinant operation refers to calculating the determinant value of a matrix. The determinant is a numerical value that can be obtained from the elements of the matrix according to specific calculation rules.

[0045] Matrix inverse operation means that for a matrix with equal number of rows and columns, if another matrix with equal number of rows and columns can be found, and the two matrices are multiplied in a specific order, no matter whether the former matrix is ​​multiplied by the latter matrix, or the latter matrix is ​​multiplied by the former matrix, the result is a special matrix with all elements on the main diagonal being 1 and all other elements being 0. In this case, the former matrix can be inverted, and the latter matrix is ​​the inverse matrix of the former matrix.

[0046] S226, based on the number of evaluation indicators, the covariance determinant values ​​of the evaluation indicators, the evaluation indicator transposed data matrix, the covariance data inverse matrix of the evaluation indicators and the evaluation indicator deviation data matrix, the probability density data matrix of the evaluation indicators is obtained.

[0047] In one embodiment, the number of evaluation indicators, the covariance determinant of the evaluation indicators, the evaluation indicator transposed data matrix, the covariance data inverse matrix of the evaluation indicators, and the evaluation indicator deviation data matrix are calculated using the following formula to obtain the probability density data moment of the evaluation indicators; ;in, Represents the probability density data moment of the evaluation index, represents pi, represents the number of evaluation indicators, represents the covariance determinant of the evaluation index, represents the evaluation index transposed data matrix, Represents the inverse matrix of the covariance data of the evaluation index, Represents the evaluation index deviation data matrix.

[0048] S230, performing power quality level probability statistical processing on the evaluation index data matrix to obtain a power quality level probability data matrix of the evaluation index.

[0049] Specifically, step S230 includes: S231, matching each parameter value of each evaluation indicator in the evaluation indicator data matrix with a pre-constructed power quality grade table to obtain the power quality grade of each parameter value of each evaluation indicator; wherein the pre-constructed power quality grade table is used to characterize the mapping relationship between each parameter value of each evaluation indicator and the power quality grade; For ease of understanding, the pre-built power quality level table is exemplarily described below, as shown in Table 4 below: Table 4 Pre-built power quality level table

[0050] S232, determining the number of multiple parameter values ​​of the evaluation index and the number of parameter values ​​of each evaluation index under each power quality, etc.; For ease of understanding, the number of parameter values ​​of each evaluation index under the same power quality level is exemplified below, as shown in Table 5 below: Table 5 Power quality level frequency table

[0051] S233, calculate the ratio of the number of parameter values ​​of each evaluation indicator at each power quality level to the number of multiple parameter values ​​of the evaluation indicator, obtain the probability of each evaluation indicator at each power quality level, and construct a power quality level probability data matrix of the evaluation indicator.

[0052] Specifically, the probability of each evaluation index under each power quality level is calculated in combination with Table 5, as shown in the following Table 6: Table 6 Power quality level probability table of power quality evaluation indicators of new energy stations

[0053] The power quality level probability data matrix of the evaluation index: .

[0054] S300, obtaining a weight value data matrix of local sensitivity of the evaluation index based on the evaluation index data matrix conforming to the normal distribution and the probability density data matrix of the evaluation index; In one embodiment, step S300 includes: S310, calculating the mean of multiple parameter values ​​of each evaluation indicator in the evaluation indicator data matrix that conforms to the normal distribution, and calculating the difference between the mean of the multiple parameter values ​​of each evaluation indicator and the preset parameter value of each evaluation indicator, to obtain a first deviation value of each evaluation indicator; For ease of understanding, the following example is given: Mean voltage deviation: (0.194+0.405-0.579-0.251+0.3899+0.356+1.4-2.054- 1.141+1.28) / 10=0.0999.

[0055] The mean value of three-phase unbalance is (1.452+0.675+0.513+0.783+-0.95-0.86+1.163-0.986- 1.456-0.336) / 10=0.956.

[0056] Mean value of harmonic distortion: (-0.585-0.736-0.515-0.48-0.841+0.7-2.414-0.316-0.667+ 1.026) / 10=1.791.

[0057] The mean of frequency deviation is: (0.874+0.704+1.365+0.619+0.576+0.683+1.728+0.533+ 1.322+0.427) / 10=-0.46.

[0058] It is assumed that the preset value of the voltage deviation, the preset mean value of the three-phase imbalance, the preset mean value of the harmonic distortion, and the preset mean value of the frequency deviation are all zero.

[0059] The first deviation value of the voltage deviation: 0.0999-0=0.0999.

[0060] The first deviation value of three-phase imbalance: 0.956-0=0.956.

[0061] The first deviation value of harmonic distortion: 1.791-0=1.791.

[0062] The first deviation value of the frequency deviation: -0.46-0=-0.46.

[0063] S320, calculating the mean of multiple probability densities of each evaluation indicator in the probability density data matrix of the evaluation indicator, and calculating the difference between the mean of the multiple probability densities of each evaluation indicator and the preset probability density of each evaluation indicator, to obtain a second deviation value of each evaluation indicator; For ease of understanding, the following example is given: In combination with the evaluation index data matrix in step S100, the probability density data moment of the evaluation index is given as an example: .

[0064] The mean of the probability density of voltage deviation is: (0.143+0.136+0.057+0.147+0.138+0.140+ 0.076+0.043+0.064+0.087) / 10=0.1031.

[0065] The mean of the probability density of three-phase unbalance is: (0.077+0.242+0.295+0.217+0.553+0.503 +0.107+0.575+0.747+0.379) / 10=0.3695.

[0066] The mean value of the probability density of harmonic distortion is: (0.422+0.359+0.397+0.392+0.487+0.234+ 0.074+0.370+0.435+0.213) / 10=0.3383.

[0067] The mean of the probability density of frequency deviation is: (1.843+1.574+1.657+1.611+1.528+1.582+ 1.276+1.478+1.685+1.402) / 10=1.5636.

[0068] It is assumed that the preset probability density of voltage deviation, the preset probability density of three-phase imbalance, the preset probability density of harmonic distortion and the preset probability density of frequency deviation are all zero.

[0069] The second deviation value of the voltage deviation: 0.1031-0=0.1031.

[0070] The second deviation value of three-phase imbalance: 0.3695-0=0.3695.

[0071] The second deviation value of harmonic distortion: 0.3383-0=0.3383.

[0072] The second deviation value of the frequency deviation is: 1.5636-0=1.5636.

[0073] S330, performing weighted summation on the first deviation value of each evaluation index and the second deviation value of each evaluation index, respectively, to obtain a first deviation value of the power quality of the new energy station and a second deviation value of the power quality of the new energy station; For ease of understanding, the following example is given: The first deviation value of the power quality of the new energy station: 0.25*0.0999+0.25*0.956+0.25*1.791 -0.25*0.46=0.596725.

[0074] The second deviation value of the power quality of the new energy station: 0.25*0.1031+0.25*0.3695+0.25* 0.3383+0.25*1.5636=0.593625.

[0075] S340, calculating the difference between the first deviation value of the power quality of the new energy station and the second deviation value of the power quality of the new energy station, and obtaining a change value of the power quality of the new energy station; For ease of understanding, the following example is given: The change in power quality of the new energy station = 0.596725-0.593625 = 0.0031.

[0076] S350, respectively calculating the absolute value of the difference between the mean of the multiple parameter values ​​of each evaluation indicator and the mean of the multiple probability densities of each evaluation indicator to obtain a third deviation value of each evaluation indicator; For ease of understanding, the following example is given: The third deviation value of frequency deviation: |0.0999-0.1031|=0.032 The third deviation value of voltage deviation: |0.956-0.3695|=0.5865 The third deviation value of three-phase unbalance: |1.791-0.3383|=1.4527 The third deviation value of harmonic distortion: |-0.46-1.5636|=2.0236 S360, respectively calculating the ratio of the change value of the power quality of the new energy station to the third deviation value of each evaluation index to obtain the local sensitivity of each evaluation index; For ease of understanding, the following example is given: Local sensitivity of frequency deviation: 0.0031 / 0.032=0.96875 Local sensitivity of voltage deviation: 0.0031 / 0.5865=0.0053 Local sensitivity of three-phase unbalance: 0.0031 / 1.4527=0.0021 Local sensitivity of harmonic distortion: 0.0031 / 2.0236=0.0015 S370, calculate the sum of the local sensitivities of the evaluation indicators, and respectively calculate the ratio of the local sensitivity of each evaluation indicator to the sum, to obtain the weight value of the local sensitivity of each evaluation indicator, so as to construct a weight value data matrix of the local sensitivity of the evaluation indicators.

[0077] For ease of understanding, the following example is given: The weight value of the local sensitivity of frequency deviation is: 0.96875 / (0.96875+0.0053+0.0021+ 0.0015)=0.9909.

[0078] The weight value of the local sensitivity of voltage deviation is: 0.0053 / (0.96875+0.0053+0.0021+ 0.0015)=0.0054.

[0079] The weight value of the local sensitivity of three-phase unbalance is: 0.0053 / (0.96875+0.0053+0.0021+ 0.0015)=0.0021.

[0080] The weight value of the local sensitivity of harmonic distortion is: 0.0053 / (0.96875+0.0053+0.0021+ 0.0015)=0.0015.

[0081] The weight value data matrix of the local sensitivity of the evaluation index is: .

[0082] S400, obtaining a power quality score of a new energy station based on the power quality scores of the new energy station at each power quality level; For ease of understanding, the following example is given: The power quality level probability data matrix of the evaluation index: , the weight value data matrix of the evaluation index local sensitivity: .

[0083] The power quality score of new energy stations under Level I: 0.9909*0.6+0.0054*0+0.0021*0.1 +0.0015*0=0.59475.

[0084] Power quality score of new energy stations under Level II: 0.9909*0.2+0.0054*0.4+0.0021* 0.4+0.0015*0.7=0.20223.

[0085] The power quality score of new energy stations under level III: 0.9909*0.2+0.0054*0.1+0.0021*0 +0.0015*0.2=0.19902.

[0086] The power quality score of new energy stations under Level IV: 0.9909*0+0.0054*0.2+0.0021*0.3 +0.0015*0.1=0.00186.

[0087] The power quality score of new energy stations under level V: 0.9909*0+0.0054*0.3+0.0021*0.2 +0.0015*0=0.00204.

[0088] The power quality score of new energy stations under level VI is: 0.9909*0+0.0054*0.3+0.0021*0 +0.0015*0=0.00162.

[0089] S500, performing a weighted summation of the power quality scores of the new energy stations at each power quality level by relative importance to obtain the power quality scores of the new energy stations; Specifically, the following formula is used to calculate the power quality score of the new energy station under each power quality level to obtain the power quality score of the new energy station; ;in, Indicates the power quality score of the new energy station. Indicates the dth power quality level, Indicates the total number of power quality levels, Represents the power quality score of the new energy station under the dth power quality level.

[0090] For example: New energy station power quality score: (6*0.59475+5*0.20223+4*0.19902+ 3*0.00186+2*0.00204+1*0.00162) / 0.59475+0.20223+0.1990+0.0018+0.00204+0.00162=5.38.

[0091] For ease of understanding, the following is a score table for the power quality of new energy stations, as shown in Table 7: Table 7 Power quality rating table

[0092] S600, grading the power quality score of the new energy station to obtain the evaluation grade of the power quality of the new energy station, and executing the corresponding alarm strategy based on the evaluation grade of the power quality of the new energy station.

[0093] Specifically, the power quality score of the new energy station is matched with a pre-constructed power quality assessment grade table for the new energy station to obtain the assessment grade of the power quality of the new energy station.

[0094] For ease of understanding, the following is an exemplary table of pre-built power quality assessment levels for new energy stations, as shown in Table 8 below: Table 8 Power quality assessment level table

[0095] For example, the power quality score of the new energy station calculated in step S500 is 5.38. From Table 8, it can be seen that the evaluation level of the power quality of the new energy station is normal.

[0096] For ease of understanding, the following is an exemplary table of power quality alarm strategies for new energy stations, as shown in Table 9 below: Table 9 Power quality alarm strategy table

[0097] For example: If the assessment level of the power quality of a new energy station is normal, an early warning will be sent to the operation and maintenance team, and an inspection and optimization plan will be formulated within 24 hours, with real-time monitoring and expert evaluation and suggestions.

[0098] Beneficial effects of the present invention: (1) Data fusion and characteristic display: By adopting multivariate Gaussian distribution, the present invention can effectively fuse multiple indicator data information together, which can not only intuitively display the data distribution characteristics of each indicator, but also reveal the correlation and independence between indicators. This feature significantly improves the rationality and reliability of power quality assessment of new energy stations.

[0099] (2) Weight determination and evaluation accuracy: By combining the local sensitivity analysis method and the multivariate Gaussian distribution probability density function, the present invention can assign appropriate weights to each indicator in the evaluation sample, thereby making the power quality evaluation results more accurate.

[0100] (3) Quantitative evaluation: By using probability statistics, the present invention can calculate the probability vector of the indicators appearing at different levels, and combine the indicator weights to achieve the quantification of power quality evaluation, making the evaluation results more scientific and operational.

[0101] (4) Gradual alarm: According to the severity of the power quality problem, the present invention provides different alarm modes and treatment measures. This helps the staff to deal with the power quality problem in a timely and accurate manner, thereby improving the operational stability and reliability of the new energy station.

[0102] Embodiment 2 Based on the same inventive concept, Figure 2 As shown, the embodiment of the present invention further provides a new energy station power quality evaluation device 200, comprising: A matrix construction module 210 is used to obtain multiple parameter values ​​of multiple evaluation indicators of power quality of new energy stations to construct an evaluation indicator data matrix; The data processing module 220 is used to perform data conversion processing on the evaluation index data matrix to obtain an evaluation index data matrix that conforms to the normal distribution, a probability density data matrix of the evaluation index, and a probability data matrix of the power quality level of the evaluation index; A weight calculation module 230, for obtaining a weight value data matrix of local sensitivity of the evaluation index based on the evaluation index data matrix conforming to the normal distribution and the probability density data matrix of the evaluation index; The scoring calculation module 240 is used to perform weighted summation on the power quality level probability data matrix of the evaluation index based on the weight value data matrix of the local sensitivity of the evaluation index to obtain the power quality scores of the new energy station under multiple power quality levels; A total score calculation module 250 is used to obtain a new energy station power quality score based on the new energy station power quality score at each power quality level; The graded alarm module 260 is used to grade the power quality scores of the new energy stations, obtain the evaluation grade of the power quality of the new energy stations, and execute the corresponding alarm strategy based on the evaluation grade of the power quality of the new energy stations.

[0103] It should be understood that the device corresponds to the above-mentioned embodiment of the method for evaluating the power quality of a new energy station, and can execute the various steps involved in the above-mentioned method embodiment. The specific functions of the device can be found in the description above. To avoid repetition, the detailed description is appropriately omitted here. The device includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the operating system (OS) of the device.

[0104] Embodiment 3 Based on the same inventive concept, an embodiment of the present invention also provides an electronic device, including: a processor and a memory, the memory storing machine-readable instructions executable by the processor, and the machine-readable instructions executing the above-mentioned new energy station power quality evaluation method when executed by the processor.

[0105] In a typical configuration, an electronic device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0106] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0107] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0108] Embodiment 4 Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium storing computer instructions. When the computer instructions are executed on a computer, the computer executes the above-mentioned method for evaluating power quality of a new energy station.

[0109] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0110] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0113] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0114] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0115] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0116] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A new energy station power quality early warning method, characterized in that: include: Obtain multiple parameter values ​​of multiple evaluation indicators of power quality of new energy stations to construct an evaluation indicator data matrix; Performing data conversion processing on the evaluation index data matrix to obtain an evaluation index data matrix that conforms to normal distribution, a probability density data matrix of the evaluation index, and a probability data matrix of the power quality level of the evaluation index; Based on the evaluation index data matrix that conforms to the normal distribution and the probability density data matrix of the evaluation index, a weight value data matrix of the local sensitivity of the evaluation index is obtained; Based on the weight value data matrix of the local sensitivity of the evaluation index, the power quality level probability data matrix of the evaluation index is weighted and summed to obtain the power quality scores of the new energy stations under multiple power quality levels; Based on the power quality scores of new energy stations under various power quality levels, the power quality scores of new energy stations are obtained; The power quality scores of the new energy stations are graded to obtain the assessment level of the power quality of the new energy stations, and the corresponding alarm strategy is executed based on the assessment level of the power quality of the new energy stations.

2. The method for early warning of power quality of a new energy station according to claim 1 is characterized in that: Multiple evaluation indicators include: voltage deviation, three-phase imbalance, harmonic distortion and frequency deviation.

3. The method for early warning of power quality of a new energy station according to claim 1 is characterized in that: The evaluation index data matrix is ​​processed for normal distribution to obtain an evaluation index data matrix that conforms to normal distribution, including: Calculate the mean and standard deviation of multiple parameter values ​​of each evaluation indicator in the evaluation indicator data matrix; Calculate the difference between each parameter value of each evaluation index and the mean value of multiple parameter values ​​of each evaluation index to obtain the mean difference of each parameter value of each evaluation index; The ratio of the mean deviation of each parameter value of each evaluation index to the standard deviation of multiple parameter values ​​of each evaluation index is calculated to obtain each parameter value of each evaluation index that conforms to the normal distribution, so as to construct an evaluation index data matrix that conforms to the normal distribution.

4. The method for early warning of power quality of a new energy station according to claim 3 is characterized in that: The evaluation index data matrix is ​​processed by multi-dimensional Gaussian distribution to obtain the probability density data matrix of the evaluation index, including: Determining the number of evaluation indicators and the number of multiple parameter values ​​of the evaluation indicators; Based on the mean deviation of each parameter value of the evaluation index, the evaluation index deviation data matrix is ​​constructed; Transpose the evaluation index deviation data matrix to obtain the evaluation index transposed data matrix; Based on the number of multiple parameter values ​​of the evaluation index, the evaluation index deviation data matrix and the evaluation index transposed data matrix, a covariance data matrix of the evaluation index is obtained; Performing determinant operation and matrix inverse operation on the covariance data matrix of the evaluation index to obtain the covariance determinant value of the evaluation index and the covariance data inverse matrix of the evaluation index; Based on the number of evaluation indicators, the covariance determinant values ​​of the evaluation indicators, the evaluation indicator transposed data matrix, the covariance data inverse matrix of the evaluation indicators and the evaluation indicator deviation data matrix, the probability density data matrix of the evaluation indicators is obtained.

5. The method for early warning of power quality of a new energy station according to claim 3 is characterized in that: Based on the number of multiple parameter values ​​of the evaluation index, the evaluation index deviation data matrix and the evaluation index transposed data matrix, the covariance data matrix of the evaluation index is obtained, including: The following formula is used to calculate the number of multiple parameter values ​​of the evaluation index, the evaluation index deviation data matrix and the evaluation index transposed data matrix to obtain the covariance data matrix of the evaluation index; ;in, Represents the covariance data matrix of the evaluation index, Indicates the number of multiple parameter values ​​of the evaluation index, represents the evaluation index deviation data matrix, Represents the evaluation index transposed data matrix.

6. The method for early warning of power quality of a new energy station according to claim 3 is characterized in that: Based on the number of evaluation indicators, the covariance determinant values ​​of the evaluation indicators, the evaluation indicator transposed data matrix, the covariance data inverse matrix of the evaluation indicators and the evaluation indicator deviation data matrix, the probability density data matrix of the evaluation indicators is obtained, including: The following formula is used to calculate the number of evaluation indicators, the covariance determinant of the evaluation indicators, the transposed data matrix of the evaluation indicators, the inverse covariance data matrix of the evaluation indicators, and the deviation data matrix of the evaluation indicators to obtain the probability density data moment of the evaluation indicators; ;in, Represents the probability density data moment of the evaluation index, represents pi, represents the number of evaluation indicators, represents the covariance determinant of the evaluation index, represents the evaluation index transposed data matrix, Represents the inverse matrix of the covariance data of the evaluation index, Represents the evaluation index deviation data matrix.

7. The method for early warning of power quality of a new energy station according to claim 1 is characterized in that: Perform power quality level probability statistical processing on the evaluation index data matrix to obtain the power quality level probability data matrix of the evaluation index, including: Matching each parameter value of each evaluation indicator in the evaluation indicator data matrix with a pre-constructed power quality grade table to obtain the power quality grade of each parameter value of each evaluation indicator; wherein the pre-constructed power quality grade table is used to characterize the mapping relationship between each parameter value of each evaluation indicator and the power quality grade; Determine the number of multiple parameter values ​​of the evaluation index and the number of parameter values ​​of each evaluation index under various power quality conditions; The ratio of the number of parameter values ​​of each evaluation indicator under each power quality level to the number of multiple parameter values ​​of the evaluation indicator is calculated to obtain the probability of each evaluation indicator under each power quality level, so as to construct the power quality level probability data matrix of the evaluation indicator.

8. The method for early warning of power quality of a new energy station according to claim 1 is characterized in that: Based on the evaluation index data matrix that conforms to the normal distribution and the probability density data matrix of the evaluation index, the weight value data matrix of the local sensitivity of the evaluation index is obtained, including: Calculate the mean of multiple parameter values ​​of each evaluation indicator in the evaluation indicator data matrix that conforms to the normal distribution, and calculate the difference between the mean of the multiple parameter values ​​of each evaluation indicator and the preset parameter value of each evaluation indicator to obtain a first deviation value of each evaluation indicator; Calculate the mean of multiple probability densities of each evaluation indicator in the probability density data matrix of the evaluation indicator, and calculate the difference between the mean of the multiple probability densities of each evaluation indicator and the preset probability density of each evaluation indicator to obtain a second deviation value of each evaluation indicator; The first deviation value of each evaluation index and the second deviation value of each evaluation index are weighted and summed respectively to obtain the first deviation value of the power quality of the new energy station and the second deviation value of the power quality of the new energy station; Calculate the difference between the first deviation value of the power quality of the new energy station and the second deviation value of the power quality of the new energy station to obtain a change value of the power quality of the new energy station; Respectively calculating the absolute value of the difference between the mean of the multiple parameter values ​​of each evaluation indicator and the mean of the multiple probability densities of each evaluation indicator to obtain a third deviation value of each evaluation indicator; The ratios of the change value of the power quality of the new energy station and the third deviation value of each evaluation index are calculated respectively to obtain the local sensitivity of each evaluation index; The sum of the local sensitivities of each evaluation index is calculated, and the ratio of the local sensitivity of each evaluation index to the sum is calculated respectively to obtain the weight value of the local sensitivity of each evaluation index, so as to construct a weight value data matrix of the local sensitivity of the evaluation index.

9. The method for early warning of power quality of a new energy station according to claim 1 is characterized in that: Based on the power quality scores of new energy stations under each power quality level, the power quality scores of new energy stations are obtained, including: The following formula is used to calculate the power quality score of the new energy station under each power quality level to obtain the power quality score of the new energy station; ;in, Indicates the power quality score of the new energy station. Indicates the dth power quality level, Indicates the total number of power quality levels, Represents the power quality score of the new energy station under the dth power quality level.

10. A new energy station power quality early warning device, characterized in that: include: A matrix construction module is used to obtain multiple parameter values ​​of multiple evaluation indicators of power quality of new energy stations to construct an evaluation indicator data matrix; A data processing module is used to perform data conversion processing on the evaluation index data matrix to obtain an evaluation index data matrix that conforms to the normal distribution, a probability density data matrix of the evaluation index, and a probability data matrix of the power quality level of the evaluation index; A weight calculation module is used to obtain a weight value data matrix of the local sensitivity of the evaluation index based on the evaluation index data matrix that conforms to the normal distribution and the probability density data matrix of the evaluation index; A scoring calculation module is used to perform weighted summation on the power quality level probability data matrix of the evaluation index based on the weight value data matrix of the local sensitivity of the evaluation index, so as to obtain the power quality scores of the new energy station under multiple power quality levels; A total score calculation module is used to obtain a new energy station power quality score based on the new energy station power quality score at each power quality level; The graded alarm module is used to grade the power quality scores of the new energy stations, obtain the evaluation level of the power quality of the new energy stations, and execute the corresponding alarm strategy based on the evaluation level of the power quality of the new energy stations.

Images