Optimized neural network wind power prediction method based on health assessment

Abstract

The invention discloses an optimized neural network wind power prediction method based on health assessment, and relates to the technical field of wind power prediction methods, and the prediction method comprises the following steps: S1, obtaining fan data, and carrying out health assessment to construct a health matrix; and S2, according to the health matrix in the step S1, calculating an improved power weight, taking a matrix approximation hyper-parameter as a WSA initial value, accelerating an SVR optimization process, and utilizing a neural network to optimize prediction power. The optimized neural network wind power prediction method based on health assessment comprises the following steps: firstly, based on fan data, performing health assessment to obtain a health matrix; then, optimizing a network prediction strategy through a weight calculation result of the matrix; thirdly, the optimization process is accelerated by means of matrix approximation hyper-parameters; and finally, the optimized BP and WSA-SVR neural network is used to predict the wind power, and the prediction precision and speed are improved at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power prediction methods, and in particular to an optimized neural network wind power prediction method based on health assessment. Background Art

[0002] The volatility of wind energy causes instability in wind power, which affects the operation of the power grid after it is connected to the grid. In order to ensure the safety of the power grid, it is necessary to predict wind power and regulate it in a timely manner.

[0003] There have been many studies on the technology of wind power prediction in the world, which can be roughly divided into two types: physical model and statistical model. Among them, the construction of physical model is more complicated, and because the model is affected by environmental factors, climate factors and the status information of the wind turbine itself, it is difficult to build a reasonable and effective prediction model for wind power and cannot guarantee stable prediction accuracy. Therefore, the model based on statistical analysis is widely used in the process of wind power prediction. In the early days of wind power prediction, numerical weather prediction (NWP) and power curve diagrams were often used. Due to the low measurement accuracy of NWP and the large transmission delay, the prediction accuracy of the method is not high. The power curve diagram is derived from the working conditions of the wind turbine. When environmental changes affect the operation of the wind turbine, the actual power deviates from the rated power and the prediction accuracy is reduced.

[0004] In order to improve accuracy, neural networks are often used for power prediction. Neural networks use historical data to train network models.

[0005] Compared with similar methods, the prediction performance of wind power forecasting has been significantly improved, but there are still problems such as slow prediction speed and high data cost. Finding efficient optimization methods to improve the prediction performance of neural networks has become a research hotspot in recent years. Optimization algorithms can enhance network capabilities and improve prediction speed and accuracy at the same time. At present, most optimization algorithms can only improve accuracy or speed alone, and the effect is not ideal. Summary of the invention

[0006] The technical problem to be solved by the present invention is: the present invention provides an optimized neural network wind power prediction method based on health assessment. Through health assessment, the wind turbine health matrix is ​​obtained, the power weight calculation method is improved, and the network prediction strategy is adjusted, which can improve the prediction accuracy and speed at the same time.

[0007] In order to solve the above technical problems, the technical solution proposed by the present invention is:

[0008] A wind power prediction method based on an optimized neural network for health assessment comprises the following steps:

[0009] Step S1, obtaining wind turbine data, performing health assessment and constructing a health matrix;

[0010] Step S2, based on the health matrix of step S1, calculate the improved power weight, use the matrix approximation hyperparameter as the WSA starting value, accelerate the SVR optimization process, and use the neural network to optimize the predicted power.

[0011] As a further improvement of the above technical solution:

[0012] Preferably, the process of constructing the health matrix in step S1 is:

[0013] S1-1, data collection: collect wind speed, temperature, pressure, speed, power and other fan data;

[0014] S1-2, data cleaning: data cleaning is performed for missing values, outliers, and noise to improve data reliability;

[0015] S1-3, feature screening: from the cleaned data, feature data is screened to obtain the approximate hyperparameters of the neural network and the dimensions of the health matrix;

[0016] S1-4, state classification: calculate the power generation efficiency and classify the wind turbine state categories through characteristic data;

[0017] S1-5, matrix generation: Arrange the power generation efficiencies of the same state into a matrix according to their values.

[0018] Preferably, in step S1, the health matrix A is:

[0019] A n×n =Q n×1 V 1×n

[0020] Where n is the dimension of the health matrix, Q n×1 is the efficiency matrix, V 1×n is the characteristic correlation matrix of power.

[0021] Preferably, in step S2, the method for obtaining the original predicted power is:

[0022] First, get the weight matrix C n×1 ,Right now:

[0023] C n×1 =A n×n B n×1

[0024] In the formula, B n×1 is the feature matrix;

[0025] Then, the original predicted power P i , expanded to power matrix D 1×n ,Right now:

[0026] D 1×n =

P i P i ···P i

[0027] Next, combine D and C to obtain the reconstructed predicted power Right now:

[0028]

[0029] Wherein, λ is related to characteristic data and fan operating conditions, and takes a value of 0.01 to 0.1.

[0030] Preferably, the improved power weight calculation formula is:

[0031] Δω=α×δ×x i

[0032] In the formula, Δω represents the change in weight, α is the learning rate, δ is the error of the current node, and x i is the input of the current node.

[0033] Preferably, the method to accelerate the SVR optimization process is:

[0034] Assume that the input of the i-th data is x i , the output is y i , the predicted value is f(x i ), define the error variable e i , which represents the gap between the actual value and the predicted value, that is:

[0035] e i =f(x i )-y i

[0036] While minimizing the sum of squared errors, we limit each e i Does not exceed the given threshold ε, and the constraint condition is:

[0037] minimize:0.5×ω T ×ω+T 1 ×∑e i

[0038] subject:|e i |≤ε,i=1,2,…,n

[0039] Where ω is the power weight, which is the same as the element of the weight matrix C, T 1 is the regularization parameter, ω T is the transpose of ω, and the WSA algorithm is used to calculate T 1 Conduct optimization search;

[0040] The SVR prediction value is:

[0041] f(x i )=∑α i ×K(x i ,x)+e i

[0042] In the formula, α i is the Lagrange multiplier, obtained by solving the Lagrange function equation by SVR; K(x i ,x) represents the inner product kernel function, e i Error variable.

[0043] The optimized neural network wind power prediction method based on health assessment provided by the present invention has the following advantages compared with the prior art:

[0044] The wind power prediction method based on health assessment and optimized neural network of the present invention improves the prediction accuracy and speed by optimizing the neural network through health assessment. First, a health assessment is performed based on the wind turbine data to obtain a health matrix. Then, the network prediction strategy is optimized through the weight calculation results of the matrix. Next, the matrix approximation hyperparameters are used to accelerate the optimization process. Finally, the optimized BP and WSA-SVR neural networks are used to predict wind power, while improving the prediction accuracy and speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of the health assessment process diagram of the present invention.

[0046] Figure 2 It is a schematic diagram of the neural network optimization solution based on the health matrix of the present invention.

[0047] Figure 3 It is a diagram of the BP prediction effect of the unoptimized comparative example of the present invention.

[0048] Figure 4 It is a diagram of the BP prediction effect after optimization in the comparative example of the present invention.

[0049] Figure 5 It is a diagram of the prediction effect of the unoptimized WSA-SVR in the comparative example of the present invention.

[0050] Figure 6 It is a diagram of the prediction effect of WSA-SVR after optimization in the comparative example of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] Figure 1 and Figure 2 An implementation of the wind power prediction method based on an optimized neural network for health assessment of the present invention is shown, comprising the following steps:

[0053] Step S1, obtaining wind turbine data, performing health assessment and constructing a health matrix.

[0054] Wind speed and power generation efficiency are positively correlated. When wind speed decreases, the wind turbine rotates slowly and the power generation efficiency is low. When wind speed increases, the wind turbine rotates quickly and the power generation efficiency is high. Applying the multivariate Gaussian distribution model to calculate the power generation efficiency, we can get the health matrix, such as Figure 1 The specific process is as follows:

[0055] S1-1, data collection: collect wind speed, temperature, pressure, speed, power and other fan data.

[0056] S1-2, data cleaning: Perform data cleaning for missing values, outliers, and noise to improve data reliability.

[0057] In order to reduce the order error of data of different magnitudes, data normalization is first performed. Considering that some categories of data have negative values, the maximum-minimum normalization algorithm is as follows:

[0058]

[0059] In the formula, x i Represents the current data, x min Indicates the minimum value of the data, x max Indicates the maximum value of the data.

[0060] S1-3, feature screening: Use the cleaned data to perform principal component analysis (PCA), select the top n highest-scoring data in the analysis results as feature data, perform health assessment based on the feature data, and obtain the approximate hyperparameters of the neural network and the dimensions of the health matrix.

[0061] The dimension of the health matrix can be determined by formula (2):

[0062] n=Kind i (2)

[0063] In the formula, Kind iIndicates the number of features. Each feature data contains 1 feature. Kind i The count is increased by 1.

[0064] S1-4, status classification: Calculate the power generation efficiency through characteristic data, and classify the wind turbine status into normal, minor fault, major fault and other categories according to the efficiency value.

[0065] The power generation efficiency Q is calculated by formula (3): n×1 .

[0066]

[0067] Where i ranges from 1 to n, μ is the mean vector, Σ is the covariance matrix, and i is the feature number.

[0068] S1-5, Matrix generation: Arrange the power generation efficiency of the same state into a matrix according to the value. Each matrix element represents the power generation efficiency of the wind turbine in this state.

[0069] Arrange the calculated power generation efficiency in order of characteristics to obtain the efficiency matrix Q n×1 ,Right now:

[0070] Q n×1 =

f(x 1 ) f(x 2 )··· f(x n )

[0071] In the formula, f(x i ) represents the power generation efficiency of the i-th feature under the same type of state.

[0072] The factor analysis method is used on the measured data to obtain the characteristic correlation matrix V of the power 1×n ,Right now:

[0073] V 1×n =

p 1 p 2 ··· p n

[0074] In the formula, p i represents the correlation coefficient between the ith feature and power.

[0075] Adopt Q T After arranging V, multiply Q by V to get the health matrix A, that is:

[0076] A n×n =Q n×1 V 1×n (6)

[0077] Where n is the dimension of the health matrix, which is usually 6 to 12. When n is greater than 12, dimensionality reduction is required.

[0078] There are two shortcomings in the health assessment process:

[0079] (1) High data cost: When calculating power generation efficiency, a variety of wind turbine data is required, which increases the cost of data collection, processing and analysis;

[0080] (2) High complexity: In order to improve the reliability of evaluation, the feature selection module is introduced, which increases the complexity of the matrix and is not conducive to improvement and maintenance.

[0081] In order to improve the evaluation process and reduce the evaluation cost, firstly, the factor analysis method is used to simplify the feature selection module and reduce the matrix complexity; then, the feature data is dimensional compressed and decoupled to reduce the data processing cost.

[0082] Step S2, according to the health matrix of step S1, design an optimization algorithm, calculate the improved power weight, and use the neural network to output the original predicted power.

[0083] There are currently two shortcomings in optimizing neural network algorithms: first, the prediction speed is not significantly improved and the prediction time is long; second, the optimization is insufficient and the accuracy is not significantly improved.

[0084] Since the power weight has a great influence on the prediction accuracy of the Back Propagation Network (BP), in order to improve the prediction accuracy, the improved power weight of BP is calculated using the health matrix in this embodiment. Since the prediction speed of the Support Vector Regression (SVR) is greatly affected by the parameter optimization, in order to accelerate the optimization process and improve the prediction speed, the Whale Swarm Algorithm (WSA) is introduced as the optimization algorithm of SVR. The matrix approximation hyperparameter is used as the starting value of WSA to accelerate the SVR optimization process.

[0085] According to the health matrix in step S1, the improved power weight is calculated and the predicted power is output by the neural network. Without increasing the data processing cost, the prediction error is reduced and the network prediction accuracy and speed are improved. The following contents are included:

[0086] S2-1, power prediction: After accelerating the optimization process by approximating hyperparameters, a neural network is used to perform power prediction to obtain the original predicted power.

[0087] From equations (2) and (3), we know that n features correspond to the health matrix A n×n Arrange the current data in the order of matrix Q into feature matrix B n×1 ,Right now:

[0088] B n×1 =

q 1 q 2 ···q n

[0089] In the formula, q i Represents the correlation coefficient between the i-th feature and the power at the time to be predicted.

[0090] First, matrices A and B are multiplied to obtain the weight matrix C n×1 ,Right now:

[0091] C n×1 =A n×n B n×1 (8)

[0092] Then, the original predicted power P i , expanded to power matrix D 1×n All elements in D are the original predicted power P i ,Right now:

[0093] D 1×n =

P i P i ···P i

[0094] Next, combine D and C to obtain the reconstructed predicted power Right now:

[0095]

[0096] Wherein, λ is related to characteristic data and fan operating conditions, and takes a value of 0.01 to 0.1.

[0097] S2-2, design optimization algorithm.

[0098] For BP network, the hidden layer error can be expressed as:

[0099] δ h =f′(x)×∑(ω×δ o ) (11)

[0100] In the formula, δ h represents the hidden layer error; δ o represents the estimated system error, which is a given value; f′ is the derivative of the activation function, x is the hidden layer input, ω is the power weight, which is the same as the element of the weight matrix C, and Σ represents the summation of the output layer nodes.

[0101] The update calculation of BP power weight is as follows:

[0102] Δω=α×δ×xi (12)

[0103] In the formula, Δω represents the change in weight, α is the learning rate, δ is the error of the current node, and x i is the input of the current node.

[0104] In formula (6), the dimension of matrix A is compressed, A is compressed into a matrix of 1 row and n columns, and converted into a vector form, ω is calculated, and the interference term of ω is reduced, so that ω×δ o The value of is significantly reduced, reducing δ h , reduce prediction errors and improve BP prediction accuracy.

[0105] Let the health matrix be x i , through formula (12), the update calculation amount can be reduced, and the weight convergence can be accelerated to obtain the approximate optimal learning rate and improve the BP prediction speed.

[0106] The optimization process of SVR is as follows:

[0107] Assume that the input of the i-th data is x i , the output is y i , the predicted value is f(x i ). Define the error variable e i , which represents the gap between the actual value and the predicted value. That is:

[0108] e i =f(x i )-y i (13)

[0109] During the optimization process, while minimizing the sum of squared errors, each e is limited i Not exceeding the given threshold ε, we obtain the constraint conditions composed of equations (14) and (15):

[0110] minimize:0.5×ω T ×ω+T 1 ×∑e i (14)

[0111] subject:|e i |≤ε,i=1,2,…,n (15)

[0112] Where ω is the power weight, which is the same as the element of the weight matrix C, T 1 is the regularization parameter, ω T is the transpose of ω, and the WSA algorithm is used to calculate T 1 Conduct optimization.

[0113] The calculation of the SVR prediction value is as follows:

[0114] f(xi )=∑α i ×K(x i ,x)+e i (16)

[0115] In the formula, α i is the Lagrange multiplier, obtained by solving the Lagrange function equation by SVR; K(x i ,x) represents the inner product kernel function, e i Error variable.

[0116] The approximate regularization parameters of the health matrix allow WSA to start optimizing from near the global optimal value to obtain the optimal hyperparameters, reduce the optimization time, accelerate the prediction process, and improve the prediction speed of SVR.

[0117] S2-3, optimize predicted power.

[0118] Based on S2-2 and S2-3, according to the health matrix, the weight matrix C calculated by the health matrix in formula (8) is n×1 Take the transpose and get And C T Expressed as a vector form, the improved power weight ω is obtained. Using the improved ω, the steps of equations (13) to (16) are performed, and the optimized predicted power P is obtained from equation (16): 1 .

[0119] Comparative Example

[0120] The data used is from Baidu KDD CUP 2022, Unit 1 of the test data set, with a total of 40 days of data. BP and WSA-SVR networks are selected for optimization. The data preprocessing uses the forward and backward interpolation method to ensure the consistency of the input data. The prediction effect before and after BP network optimization is as follows Figure 3 and Figure 4 shown.

[0121] Using R 2 There are three error indicators: (coefficient of determination), MSE (mean square error), and MAE (mean absolute error), as shown in formulas (17)-(19):

[0122]

[0123]

[0124]

[0125] In the formula, y i is the true value, is the predicted value, is the average of the true values.

[0126] The comparison of prediction errors before and after optimization is shown in Table 1.

[0127] Table 1 Comparison of neural network prediction errors

[0128]

[0129] From Table 1 and Figure 3 , Figure 4 It can be seen that after BP network optimization, the prediction accuracy is improved by 40% and the prediction time is reduced by 20%. Figure 5 , Figure 6 It can be seen that after the WSA-SVR network is optimized, the prediction accuracy is improved by 10% and the prediction time is reduced by 45%.

[0130] The optimization algorithm of the present invention simplifies the BP neural network weight correction step and significantly improves the hysteresis of prediction. The matrix approximation regularization parameter is used as the optimization starting value to improve the optimization efficiency.

[0131] During the WSA-SVR optimization process, the approximate regularization parameters of the health matrix are passed to the WSA-SVR network, allowing WSA to start from the approximate global optimal value to reduce the WSA-SVR prediction time. After optimization, the accuracy of WSA-SVR is significantly improved.

[0132] The above implementation cases are only preferred embodiments of the present invention and are not intended to limit the present invention in any form. Although the present invention has been disclosed as above with preferred embodiments, they are not intended to limit the present invention. Therefore, any simple modification, equivalent changes and modifications made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention shall fall within the scope of protection of the technical solution of the present invention.

Claims

1. A wind power prediction method based on an optimized neural network for health assessment, characterized in that: The following steps are involved: Step S1, obtaining wind turbine data, performing health assessment and constructing a health matrix; In step S2, based on the health matrix of step S1, the improved power weight is calculated, and the matrix approximation hyperparameter is used as the starting value of WSA to accelerate the SVR optimization process and optimize the predicted power using the neural network.

2. The wind power prediction method based on optimized neural network of health assessment according to claim 1 is characterized in that: The process of constructing the health matrix in step S1 is as follows: S1-1, data collection: collect wind speed, temperature, pressure, speed, power and other fan data; S1-2, data cleaning: data cleaning is performed for missing values, outliers, and noise to improve data reliability; S1-3, feature screening: from the cleaned data, feature data is screened to obtain the approximate hyperparameters of the neural network and the dimensions of the health matrix; S1-4, state classification: calculate the power generation efficiency and classify the wind turbine state categories through characteristic data; S1-5, matrix generation: Arrange the power generation efficiencies of the same state into a matrix according to their values.

3. The wind power prediction method based on optimized neural network for health assessment according to claim 2 is characterized in that: In step S1, the health matrix A is: A n×n =Q n×1 V 1×n Where n is the dimension of the health matrix, Q n×1 is the efficiency matrix, V 1×n is the characteristic correlation matrix of power.

4. The method for wind power prediction based on optimized neural network based on health assessment according to claim 3 is characterized in that: In step S2, the method for obtaining the original predicted power is: First, get the weight matrix C n×1 ,Right now: C n×1 =A n×n B n×1 In the formula, B n×1 is the feature matrix; Then, the original predicted power P i , expanded to power matrix D 1×n ,Right now: D 1×n =【P i P i ··· P i 】 Next, combine D and C to obtain the reconstructed predicted power Right now: Wherein, λ is related to characteristic data and fan operating conditions, and takes a value of 0.01 to 0.

1.

5. The method for wind power prediction based on optimized neural network based on health assessment according to claim 4 is characterized in that: The improved power weight calculation formula is: Dω=α×δ×x i In the formula, Δω represents the change in weight, α is the learning rate, δ is the error of the current node, and x i is the input of the current node.

6. The method for wind power prediction based on optimized neural network of health assessment according to claim 4 is characterized in that: The method for accelerating the SVR optimization process is: Assume that the input of the i-th data is x i , the output is y i , the predicted value is f(x i ), define the error variable e i , which represents the gap between the actual value and the predicted value, that is: e i =f(x i )-y i While minimizing the sum of squared errors, we limit each e i Does not exceed the given threshold ε, and the constraint condition is: minimize:0.5×ω T ×ω+T1×∑e i subject:|e i |≤ε,i=1,2,…,n Where ω is the power weight, which is the same as the element of the weight matrix C, T1 is the regularization parameter, and ω T is the transpose of ω, and the WSA algorithm is used to optimize T1; The SVR prediction value is: f(x i )=∑α i ×K(x i ,x)+e i In the formula, α i is the Lagrange multiplier, obtained by solving the Lagrange function equation by SVR; K(x i ,x) represents the inner product kernel function, e i Error variable.

Images