Offshore wind power prediction method and system for eliminating boundary effect

Abstract

The invention relates to the technical field of wind power prediction, in particular to an offshore wind power prediction method and system for eliminating a boundary effect, and the method comprises the steps: S1, obtaining power feature data and meteorological feature data of a wind power plant, and carrying out the preprocessing; s2, constructing a power characteristic matrix and a wind speed characteristic matrix; s3, respectively inputting the power characteristic matrix and the wind speed characteristic matrix into a gating circulation unit network, and outputting a power prediction sequence and a wind speed prediction sequence; s4, constructing a boundary effect interval recognition function, inputting the wind speed prediction sequence into the boundary effect interval recognition function, and outputting a boundary effect interval; and S5, constructing a three-dimensional segmentation threshold function, inputting the wind speed prediction sequence, the power prediction sequence and the boundary effect interval into the three-dimensional segmentation threshold function, and outputting a future power sequence. The method can eliminate the influence of the boundary effect on the wind power prediction result, thereby improving the prediction precision of the wind power.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power prediction, and more specifically, to an offshore wind power prediction method and system for eliminating boundary effects. Background Art

[0002] With the continuous development of wind power generation technology, large-capacity wind power grid connection has brought challenges to the safe and stable operation of large power grids. Therefore, accurate prediction of wind power output can dispatch wind power grid connection capacity in advance and reduce the volatility of wind power grid connection power, which is of great significance to the safe and stable operation of the power system. At present, wind power generation is mainly divided into offshore wind power and onshore wind power. In the prediction of wind power, the meteorological differences between offshore wind power and onshore wind power should be considered, and adaptive adjustments should be made to obtain accurate prediction results.

[0003] In the prior art, for example, Chinese patent CN117893361A discloses an offshore wind power prediction method based on a multi-scale analyzer, as follows: the power, wind speed and temperature data of the offshore wind farm obtained are preliminarily processed to obtain wind power time series, wind speed time series and temperature time series; the wind power time series is input into the multi-scale analyzer to obtain trend characteristics, long-periodic characteristics and short-periodic characteristics; the trend characteristics, long-periodic characteristics and short-periodic characteristics, wind power time series, wind speed time series and temperature time series are recombined into a feature vector matrix; the feature vector matrix is ​​input into an offshore wind power prediction model to perform offshore wind power prediction. However, this prediction method does not take into account the fact that due to the high wind speed at sea, there is a boundary effect in the offshore wind power series, and the boundary effect will cause the gradient of the prediction model to disappear during the training process, thereby reducing the accuracy of the wind power prediction results. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the prior art that the accuracy of wind power prediction results is reduced due to the boundary effect, and to provide an offshore wind power prediction method and system for eliminating the boundary effect, so as to eliminate the boundary effect phenomenon in the wind power prediction process, thereby improving the prediction accuracy of offshore wind power.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: A method for predicting offshore wind power for eliminating boundary effects is provided, comprising the following steps: S1. Acquire power characteristic data and meteorological characteristic data of a target wind farm, pre-process the power characteristic data and the meteorological characteristic data to obtain a historical power sequence P, a historical wind speed sequence WS, a historical temperature sequence Tem, and a historical air pressure sequence Pre; S2, using the historical power sequence P, the historical wind speed sequence WS, the historical temperature sequence Tem and the historical air pressure sequence Pre to construct a power feature matrix X power And wind speed feature matrix X wind ; S3, the power characteristic matrix X power And the wind speed characteristic matrix X wind are respectively input into the gated recurrent unit network, and the gated recurrent unit network outputs a power prediction sequence P power And the wind speed prediction sequence P wind ; S4, constructing a boundary effect interval identification function ST according to the wind turbine operation status curve, and converting the wind speed prediction sequence P wind Inputting the boundary effect interval identification function ST, wherein the boundary effect interval identification function ST identifies the boundary effect interval; S5, constructing a three-dimensional segmented threshold function 3DST according to the wind turbine operating state curve and the boundary effect interval, and converting the wind speed prediction sequence P wind , power prediction sequence P power And the boundary effect interval identification function ST inputs the three-dimensional segmented threshold function 3DST, and the three-dimensional segmented threshold function 3DST outputs the future power sequence.

[0006] The offshore wind power prediction method for eliminating boundary effects of the present invention first collects power characteristic data and meteorological characteristic data of the wind farm to be predicted, wherein the meteorological characteristic data includes wind speed, temperature and air pressure, and pre-processes the power characteristic data and the meteorological characteristic data to obtain a historical power sequence P, a historical wind speed sequence WS, a historical temperature sequence Tem and a historical air pressure sequence Pre; then, a power characteristic matrix X is constructed according to the historical power sequence P, the historical wind speed sequence WS, the historical temperature sequence Tem and the historical air pressure sequence Pre. power And wind speed feature matrix X wind ; Then the obtained power feature matrix X power And the wind speed characteristic matrix X wind The gated recurrent unit network is input into the gated recurrent unit network, which makes predictions based on the input data and finally outputs two prediction sequences, namely the power prediction sequence P power And the wind speed prediction sequence P wind ; Then, according to the wind turbine operating status curve, the boundary effect interval identification function ST is constructed, and the predicted wind speed prediction sequence P wind The boundary effect discriminant function ST is input to make a judgment, and the wind power boundary effect interval in the future time is obtained; finally, the power prediction sequence P power , wind speed prediction sequence P windAnd the boundary effect interval identification function ST are input into the three-dimensional segmented threshold function 3DST. The three-dimensional segmented threshold function 3DST divides the power prediction sequence into the boundary effect interval and the non-boundary effect interval, and independently processes the power prediction sequences in the two different intervals, so as to eliminate the influence of the boundary effect on the wind power prediction results in the wind power prediction process, avoid the inconsistent coupling relationship between the power sequence and the meteorological characteristic sequence, prevent the prediction model from under-fitting, and thus improve the prediction accuracy of wind power.

[0007] Preferably, in step S1, the meteorological characteristic data includes wind speed, temperature and air pressure data at different heights, and the preprocessing includes performing min-max normalization processing on the power characteristic data and the wind speed, temperature and air pressure data at different heights. Min-max normalization is a data standardization method that linearly maps data to a specific range. During the data collection process, the numerical ranges of different meteorological characteristics may vary greatly. After min-max normalization processing, the numerical ranges of all power characteristic data and meteorological characteristic data are unified, avoiding certain features dominating the prediction results due to large values.

[0008] Preferably, in step S2, the power characteristic matrix X power And wind speed feature matrix X wind for:

[0009]

[0010] in Represents the matrix of power characteristics from time t-1 to time tn at the mth height, The power characteristic matrix X represents the wind speed characteristics from time t-1 to time tn at the mth height. power Mainly provides historical power information, wind speed characteristic matrix X wind It mainly provides meteorological information, reflecting the impact of wind speed and meteorological conditions on power. The synergistic effect of the two can comprehensively describe the operating status of the wind farm and improve the prediction accuracy.

[0011] Preferably, the power characteristic matrix X power And wind speed feature matrix X wind The mathematical expression is:

[0012]

[0013] In the formula, , , , Respectively represent the m The power, wind speed, temperature and air pressure at different heights. Using parameters of multiple dimensions such as power, wind speed, temperature and air pressure at different times and heights to construct a feature matrix can make the collected data more comprehensive, thereby increasing the accuracy of the prediction results.

[0014] Preferably, in step S3, the gated recurrent unit network is a two-layer gated recurrent unit network, the two-layer gated recurrent unit network has different numbers of neurons and is provided with an activation function Setting up a two-layer gated recurrent unit network can enhance the modeling and expression capabilities of the power prediction model, while achieving a good balance between computational efficiency and performance cost, making it easier to maintain stability during deep learning training.

[0015] Preferably, the mathematical expression of the two-layer gated recurrent unit network is:

[0016] In the formula, , , is the weight matrix, corresponding to the update gate , Reset Gate and candidate activation The input part, , , For the current input The corresponding weight matrices are used to calculate the update gate , reset gate and candidate activation The hidden state of , , is the bias parameter matrix, corresponding to the update gate , reset gate and candidate activation The weight bias of is matrix multiplication, is the Sigmod function, To reset the gate, To update the gate, is the candidate state of the hidden layer at the current moment, is the current implicit state, is the implicit state at the previous moment, is the input state at the current moment. In the gated recurrent unit network, the inputs of the reset gate and the update gate are the current time step input and the hidden state of the previous time step. The output is calculated by the fully connected layer whose activation function is the sigmoid function. The reset gate helps to capture the short-term dependencies in the time series, while the update gate helps to capture the long-term dependencies in the time series. Therefore, the gated recurrent unit network shows better computing power than other algorithms in the wind power prediction model.

[0017] Preferably, the number of neurons in the two-layer gated recurrent unit network is 4 and 8 respectively. When selecting the number of neurons, the complexity of the prediction task and the amount of data should be taken into consideration. A smaller number of neurons may result in the inability of the non-gated recurrent unit network to capture dependencies, while a larger number of neurons will increase the computational cost and may cause overfitting, resulting in a decrease in prediction accuracy. The two-layer gated recurrent unit network selects 4 and 8 neurons respectively, which can better adapt to the amount of data in the wind power prediction process without causing overfitting, and can balance computational efficiency and prediction accuracy.

[0018] Preferably, in step S4, the mathematical expression of the boundary effect interval identification function ST is:

[0019] In the formula, is the wind speed prediction sequence P wind , is the cut-in wind speed set in the fan operation status curve, The wind turbine operating state curve corresponds to the operating state of the wind turbine in different wind speed ranges. When the wind speed V is less than the cut-in wind speed V in When the wind turbine is in shutdown state, the output power is 0; when the input wind speed V is at the cut-in wind speed V in and cut-out wind speed V out When the input wind speed V is greater than the cut-out wind speed V out When , the wind turbine protection system starts to run, the wind turbine is in shutdown state, and the output power is 0. The boundary effect interval identification function ST divides the boundary effect interval according to the different input wind speeds. Different input wind speeds correspond to different function output values, thereby reducing the impact of boundary effects on the prediction results.

[0020] Preferably, in step S5, the mathematical expression of the three-dimensional segmentation threshold function 3DST is:

[0021] In the formula, is the maximum rated output power of the fan, The wind speed at which the fan maintains its maximum rated power. in Or greater than the cut-out wind speed V out When the wind speed V is greater than the cut-in wind speed V, the fan remains in shutdown state and the output power is 0. in And it is less than the wind speed V when the fan maintains the maximum rated power operation max When the fan operates normally according to the corresponding relationship between power and wind speed in the fan operating status curve; when the input wind speed V is at the wind speed V at which the fan maintains the maximum rated power max and cut-out wind speed V out The maximum power tracking system inside the fan starts to run, and the fan is in the maximum power tracking state. At this time, the output power is always the maximum rated power P max , the three-dimensional piecewise threshold function 3DST can predict the power sequence P output by the gated recurrent unit network power , wind speed prediction sequence P wind Co-processing is performed to eliminate the impact of offshore wind power boundary effect on the single power prediction model.

[0022] The present invention also provides a wind power prediction system for implementing the wind power prediction method, comprising: Data acquisition module: used to acquire power characteristic data and meteorological characteristic data of the target wind farm, and transmit the power characteristic data and the meteorological characteristic data to the data processing module; Data processing module: used to pre-process the power characteristic data and the meteorological characteristic data to obtain the power characteristic matrix X power And wind speed feature matrix X wind ; Gated recurrent unit network prediction module: based on the input power feature matrix X power And wind speed feature matrix X wind , output power prediction sequence P power And the wind speed prediction sequence P wind ; Boundary effect interval identification module: used to construct a boundary effect interval identification function ST, and use the boundary effect interval identification function ST to identify the wind speed prediction sequence P wind Identify and obtain the boundary effect interval; Three-dimensional segmented prediction module: used to construct a three-dimensional segmented threshold function 3DST and convert the wind speed prediction sequence P wind , power prediction sequence P power And the boundary effect interval identification function ST inputs the three-dimensional segmented threshold function 3DST, and finally outputs the future power sequence.

[0023] The wind power prediction system of the present invention collects power characteristic data and meteorological characteristic data of the wind farm through the data acquisition module, and transmits the data to the data processing module, performs preprocessing in the data processing module, and constructs the power characteristic matrix X power And wind speed feature matrix X wind , in the gated recurrent unit network prediction module, the power feature matrix X power And wind speed feature matrix X wind Input the gated recurrent network unit for prediction, and the power prediction sequence P is obtained. power And the wind speed prediction sequence P wind The boundary effect interval recognition module is input, and the boundary effect interval recognition module ST recognizes the boundary effect interval. Finally, the three-dimensional segment prediction module predicts the power sequence P according to the result of the boundary effect interval recognition function ST. power Further coupling and correction are carried out to output the final future power sequence.

[0024] Compared with the prior art, the present invention has the following beneficial effects: 1. It can eliminate the influence of boundary effect on wind power prediction results, keep the coupling relationship between power sequence and meteorological characteristic sequence consistent, and thus improve the prediction accuracy of wind power; 2. Realize separate processing of power prediction sequences in boundary effect intervals and non-boundary effect intervals to prevent under-fitting of the prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A flow chart of an offshore wind power prediction method for eliminating boundary effects; Figure 2 A comparison chart of the prediction effects of offshore wind power prediction methods for eliminating boundary effects; Figure 3 Schematic diagram of a wind power prediction system for eliminating boundary effects. DETAILED DESCRIPTION

[0026] The present invention will be further described below in conjunction with specific implementation modes.

[0027] Embodiment 1 This embodiment is a first embodiment of an offshore wind power prediction method for eliminating boundary effects, including S1, acquiring power characteristic data and meteorological characteristic data of a target wind farm, preprocessing the power characteristic data and the meteorological characteristic data, and obtaining a historical power sequence P, a historical wind speed sequence WS, a historical temperature sequence Tem, and a historical air pressure sequence Pre; S2, using the historical power sequence P, historical wind speed sequence WS, historical temperature sequence Tem and historical pressure sequence Pre to construct the power feature matrix X powerAnd wind speed feature matrix X wind ; S3, the power feature matrix X power And the wind speed feature matrix X wind They are input into the gated recurrent unit network, and the gated recurrent unit network outputs the power prediction sequence P power And the wind speed prediction sequence P wind ; S4. According to the wind turbine operating status curve, a boundary effect interval identification function ST is constructed to convert the wind speed prediction sequence P wind Input a boundary effect interval identification function ST, and the boundary effect interval identification function ST identifies the boundary effect interval; S5. According to the wind turbine operating state curve and boundary effect interval, a three-dimensional segmented threshold function 3DST is constructed to convert the wind speed prediction sequence P wind , power prediction sequence P power And the boundary effect interval identification function ST inputs the three-dimensional piecewise threshold function 3DST, and the three-dimensional piecewise threshold function 3DST outputs the future power sequence.

[0028] The offshore wind power prediction method for eliminating the boundary effect in this embodiment is as follows: Figure 1 As shown in FIG. 1 , firstly, the power characteristic data and meteorological characteristic data of the wind farm to be predicted are collected, wherein the meteorological characteristic data include wind speed, temperature and air pressure. After preprocessing the power characteristic data and the meteorological characteristic data, the historical power sequence P, the historical wind speed sequence WS, the historical temperature sequence Tem and the historical air pressure sequence Pre are obtained; then, the power characteristic matrix X is constructed according to the historical power sequence P, the historical wind speed sequence WS, the historical temperature sequence Tem and the historical air pressure sequence Pre. power And wind speed feature matrix X wind ; Then the obtained power feature matrix X power And the wind speed feature matrix X wind Input the gated recurrent unit network, the gated recurrent unit network predicts according to the input data, and finally outputs two prediction sequences, namely the power prediction sequence P power And the wind speed prediction sequence P wind ; Then, according to the wind turbine operating status curve, the boundary effect interval identification function ST is constructed, and the predicted wind speed prediction sequence P wind The boundary effect discriminant function ST is input to make a judgment, and the wind power boundary effect interval in the future time is obtained; finally, the power prediction sequence P power , wind speed prediction sequence P windThe obtained boundary effect interval identification function ST is input into the three-dimensional segmented threshold function 3DST. The three-dimensional segmented threshold function 3DST divides the power prediction sequence into the boundary effect interval and the non-boundary effect interval, and independently processes the power prediction sequences in the two different intervals, thereby eliminating the influence of the boundary effect on the wind power prediction results in the wind power prediction process.

[0029] In step S1, the meteorological characteristic data includes wind speed, temperature and air pressure data at different heights, and the preprocessing includes min-max normalization of the power characteristic data and wind speed, temperature and air pressure data at different heights. Min-max normalization is a simple and effective standardization method. In wind farm power prediction, normalization can accelerate model training, improve prediction accuracy, and ensure that different features (such as wind speed, temperature, air pressure) have the same weight in the prediction model.

[0030] In step S2, the power characteristic matrix X power And wind speed feature matrix X wind for:

[0031]

[0032] in Represents the matrix of power characteristics from time t-1 to time tn at the mth height, The power characteristic matrix X represents the wind speed characteristics from time t-1 to time tn at the mth height. power Mainly provides historical power information, wind speed characteristic matrix X wind It mainly provides meteorological information, reflecting the impact of wind speed and meteorological conditions on power. The synergistic effect of the two can comprehensively describe the operating status of the wind farm and improve the prediction accuracy.

[0033] Power characteristic matrix X power And wind speed feature matrix X wind The mathematical expression is:

[0034]

[0035] In the formula, , , , Respectively represent the mThe power, wind speed, temperature and air pressure at different heights. Using parameters of multiple dimensions such as power, wind speed, temperature and air pressure at different times and heights to construct a feature matrix can make the collected data more comprehensive, thereby increasing the accuracy of the prediction results.

[0036] In step S4 of this embodiment, the mathematical expression of the boundary effect interval identification function ST is:

[0037] In the formula, is the wind speed prediction sequence P wind , is the cut-in wind speed set in the fan operation status curve, The wind turbine operating state curve corresponds to the operating state of the wind turbine in different wind speed ranges. When the wind speed V is less than the cut-in wind speed V in When the wind turbine is in shutdown state, the output power is 0; when the input wind speed V is at the cut-in wind speed V in and cut-out wind speed V out When the input wind speed V is greater than the cut-out wind speed V out When , the wind turbine protection system starts to run, the wind turbine is in shutdown state, and the output power is 0. The boundary effect interval identification function ST divides the boundary effect interval according to the different input wind speeds. Different input wind speeds correspond to different function output values, thereby reducing the impact of boundary effects on the prediction results.

[0038] In step S5 of this embodiment, the mathematical expression of the three-dimensional segmentation threshold function 3DST is:

[0039] In the formula, is the maximum rated output power of the fan, The wind speed at which the fan maintains its maximum rated power. in Or greater than the cut-out wind speed V out When the wind speed V is greater than the cut-in wind speed V, the fan remains in shutdown state and the output power is 0. in And it is less than the wind speed V when the fan maintains the maximum rated power operation max When the fan operates normally according to the corresponding relationship between power and wind speed in the fan operating status curve; when the input wind speed V is at the wind speed V at which the fan maintains the maximum rated power max and cut-out wind speed V out The maximum power tracking system inside the fan starts to run, and the fan is in the maximum power tracking state. At this time, the output power is always the maximum rated power P max, the three-dimensional piecewise threshold function 3DST can predict the power sequence P output by the gated recurrent unit network power , wind speed prediction sequence P wind Co-processing is performed to eliminate the impact of offshore wind power boundary effect on the single power prediction model.

[0040] The working principle of the offshore wind power prediction method for eliminating boundary effects in this embodiment is as follows: first, the power characteristic data and meteorological characteristic data are preliminarily processed to obtain a power characteristic matrix and a wind speed characteristic matrix, and then the wind speed characteristic matrix sequence is input into the gated cyclic unit network to predict the future wind speed sequence, and then the predicted wind speed sequence is input into the boundary effect discriminant function for discrimination to obtain the boundary effect interval and non-boundary effect interval of the wind power at future moments, and finally the power prediction sequence and the wind speed prediction sequence are input into the three-dimensional segmented threshold activation function together to realize the separate processing of the power prediction sequence in the boundary effect interval and the non-boundary effect interval.

[0041] In this embodiment, according to the wind turbine operating state curve, the cut-in wind speed is set to 3m / s, and the cut-out wind speed is set to 25m / s. The above wind power prediction method is used for prediction. The prediction results are as follows: Figure 2 As shown, the solid line represents the true value of wind power, and the two dotted lines respectively represent the predicted value of the ordinary prediction method without considering the boundary effect of offshore wind power, and the predicted value obtained by considering the boundary effect and using the method in this embodiment for prediction. When the boundary effect is not considered, the mean absolute error MAE is 11.0062, and when the boundary effect is considered and the method in this embodiment is used for prediction, the mean absolute error MAE is reduced to 7.2616. Therefore, the wind power prediction method in this embodiment can significantly eliminate the influence of the boundary effect in the process of offshore wind power prediction, thereby effectively improving the accuracy of short-term wind power prediction.

[0042] Embodiment 2 This embodiment is a second embodiment of an offshore wind power prediction method for eliminating boundary effects. This embodiment is similar to the first embodiment, except that the gated recurrent unit network is a two-layer gated recurrent unit network, the two-layer gated recurrent unit network has different numbers of neurons, and an activation function is provided. Setting up a two-layer gated recurrent unit network can enhance the modeling and expression capabilities of the power prediction model, while achieving a good balance between computational efficiency and performance cost, making it easier to maintain stability during deep learning training.

[0043] The mathematical expression of a two-layer gated recurrent unit network is:

[0044] In the formula, , , is the weight matrix, corresponding to the update gate , Reset Gate and candidate activation The input part, , , For the current input The corresponding weight matrices are used to calculate the update gate , reset gate and candidate activation The hidden state of , , is the bias parameter matrix, corresponding to the update gate , reset gate and candidate activation The weight bias of is matrix multiplication, is the Sigmod function, To reset the gate, To update the gate, is the candidate state of the hidden layer at the current moment, is the current implicit state, is the implicit state at the previous moment, is the input state at the current moment. In the gated recurrent unit network, the inputs of the reset gate and the update gate are the current time step input and the hidden state of the previous time step. The output is calculated by the fully connected layer whose activation function is the sigmoid function. The reset gate helps to capture the short-term dependencies in the time series, while the update gate helps to capture the long-term dependencies in the time series. Therefore, the gated recurrent unit network shows better computing power than other algorithms in the wind power prediction model.

[0045] The number of neurons in the two-layer gated recurrent unit network is 4 and 8 respectively. When selecting the number of neurons, the complexity of the prediction task and the amount of data should be taken into consideration. A smaller number of neurons may result in the inability of the non-gated recurrent unit network to capture dependencies, while a larger number of neurons will increase the computational cost and may cause overfitting, resulting in a decrease in prediction accuracy. The two-layer gated recurrent unit network selects 4 and 8 neurons respectively, which can better adapt to the amount of data in the wind power prediction process without causing overfitting, and can balance computational efficiency and prediction accuracy.

[0046] Embodiment 3 This embodiment is the first embodiment of the wind power prediction system, comprising: a data acquisition module: used to acquire power characteristic data and meteorological characteristic data of a target wind farm, and transmit the power characteristic data and meteorological characteristic data to a data processing module; Data processing module: used to pre-process the power characteristic data and meteorological characteristic data to obtain the power characteristic matrix X power And wind speed feature matrix X wind ; Gated recurrent unit network prediction module: based on the input power feature matrix X power And wind speed feature matrix X wind , output power prediction sequence P power And the wind speed prediction sequence P wind ; Boundary effect interval identification module: used to construct the boundary effect interval identification function ST, and use the boundary effect interval identification function ST to identify the wind speed prediction sequence P wind Identify and obtain the boundary effect interval; Three-dimensional segmented prediction module: used to construct a three-dimensional segmented threshold function 3DST and convert the wind speed prediction sequence P wind , power prediction sequence P power And the boundary effect interval identification function ST inputs the three-dimensional segmented threshold function 3DST, and finally outputs the future power sequence.

[0047] The wind power prediction system in this embodiment is as follows: Figure 3 As shown in FIG. 1 , the power characteristic data and meteorological characteristic data of the wind farm are collected through the data acquisition module, and the data are passed to the data processing module, where the data are preprocessed to obtain the historical power sequence P, the historical wind speed sequence WS, the historical temperature sequence Tem and the historical pressure sequence Pre; then the power characteristic matrix X is constructed according to the historical power sequence P, the historical wind speed sequence WS, the historical temperature sequence Tem and the historical pressure sequence Pre. power And wind speed feature matrix X wind , in the gated recurrent unit network prediction module, the power feature matrix X power And wind speed feature matrix X wind Input the gated recurrent network unit for prediction, and the power prediction sequence P is obtained. power And the wind speed prediction sequence P wind The boundary effect interval recognition module is input, and the boundary effect interval recognition module ST recognizes the boundary effect interval. Finally, the three-dimensional segment prediction module predicts the power sequence P according to the result of the boundary effect interval recognition function ST. power Further coupling and correction are carried out to output the final future power sequence.

[0048] In the specific contents of the above-mentioned specific implementation methods, the various technical features can be combined in any non-contradictory manner. In order to make the description concise, not all possible combinations of the above-mentioned technical features are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0049] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for predicting offshore wind power to eliminate boundary effects, characterized in that: The following steps are involved: S1. Acquire power characteristic data and meteorological characteristic data of a target wind farm, pre-process the power characteristic data and the meteorological characteristic data to obtain a historical power sequence P, a historical wind speed sequence WS, a historical temperature sequence Tem, and a historical air pressure sequence Pre; S2, using the historical power sequence P, the historical wind speed sequence WS, the historical temperature sequence Tem and the historical air pressure sequence Pre to construct a power feature matrix X power And wind speed feature matrix X wind ; S3, the power characteristic matrix X power And the wind speed characteristic matrix X wind are respectively input into the gated recurrent unit network, and the gated recurrent unit network outputs a power prediction sequence P power And the wind speed prediction sequence P wind ; S4, constructing a boundary effect interval identification function ST according to the wind turbine operation status curve, and converting the wind speed prediction sequence P wind Inputting the boundary effect interval identification function ST, wherein the boundary effect interval identification function ST identifies the boundary effect interval; S5, constructing a three-dimensional segmented threshold function 3DST according to the wind turbine operating state curve and the boundary effect interval, and converting the wind speed prediction sequence P wind , power prediction sequence P power And the boundary effect interval identification function ST inputs the three-dimensional segmented threshold function 3DST, and the three-dimensional segmented threshold function 3DST outputs the future power sequence.

2. The offshore wind power prediction method for eliminating boundary effects according to claim 1, characterized in that: In step S1, the meteorological characteristic data includes wind speed, temperature and air pressure data at different heights, and the preprocessing includes performing min-max normalization processing on the power characteristic data and the wind speed, temperature and air pressure data at different heights.

3. The offshore wind power prediction method for eliminating boundary effects according to claim 1, characterized in that: In step S2, the power characteristic matrix X power And wind speed feature matrix X wind for: In the formula, Indicates The matrix composed of the power characteristics from time t-1 to time tn at each height, Indicates The matrix consists of the wind speed characteristics at each height from time t-1 to time tn.

4. The offshore wind power prediction method for eliminating boundary effects according to claim 3, characterized in that: The power characteristic matrix X power And wind speed feature matrix X wind The mathematical expression is: In the formula, , , , Respectively represent Time Power, wind speed, temperature and air pressure at each altitude.

5. The offshore wind power prediction method for eliminating boundary effects according to any one of claims 1 to 4, characterized in that: In step S3, the gated recurrent unit network is a two-layer gated recurrent unit network, the two-layer gated recurrent unit network has different numbers of neurons and is provided with an activation function .

6. The offshore wind power prediction method for eliminating boundary effects according to claim 5, characterized in that: The mathematical expression of the two-layer gated recurrent unit network is: In the formula, , , is the weight matrix, corresponding to the update gate , Reset Gate and candidate activation The input part, , , For the current input The corresponding weight matrices are used to calculate the update gate , reset gate and candidate activation The hidden state of , , is the bias parameter matrix, corresponding to the update gate , reset gate and candidate activation The weight bias of is matrix multiplication, is the Sigmod function, To reset the gate, To update the gate, is the candidate state of the hidden layer at the current moment, is the current implicit state, is the implicit state at the previous moment, The input status at the current moment.

7. The offshore wind power prediction method for eliminating boundary effects according to claim 5, characterized in that: The number of neurons in the two-layer gated recurrent unit network is 4 and 8 respectively.

8. The offshore wind power prediction method for eliminating boundary effects according to claim 1, characterized in that: In step S4, the mathematical expression of the boundary effect interval identification function ST is: In the formula, is the wind speed prediction sequence P wind , is the cut-in wind speed set in the fan operation status curve, It is the cut-out wind speed set in the fan operation status curve.

9. The offshore wind power prediction method for eliminating boundary effects according to claim 8, characterized in that: In step S5, the mathematical expression of the three-dimensional segmentation threshold function 3DST is: In the formula, is the maximum rated output power of the fan, The wind speed is maintained at the maximum rated power of the fan.

10. A wind power prediction system, used to implement the wind power prediction method according to any one of claims 1 to 9, characterized in that: include: Data acquisition module: used to acquire power characteristic data and meteorological characteristic data of the target wind farm, and transmit the power characteristic data and the meteorological characteristic data to the data processing module; Data processing module: used to pre-process the power characteristic data and the meteorological characteristic data to obtain the power characteristic matrix X power And wind speed feature matrix X wind ; Gated recurrent unit network prediction module: based on the input power feature matrix X power And wind speed feature matrix X wind , output power prediction sequence P power And the wind speed prediction sequence P wind ; Boundary effect interval identification module: used to construct a boundary effect interval identification function ST, and use the boundary effect interval identification function ST to identify the wind speed prediction sequence P wind Identify and obtain the boundary effect interval; Three-dimensional segmented prediction module: used to construct a three-dimensional segmented threshold function 3DST and convert the wind speed prediction sequence P wind , power prediction sequence P power And the boundary effect interval identification function ST inputs the three-dimensional segmented threshold function 3DST, and finally outputs the future power sequence.

Images