Energy-saving control system and method for power loss of a wind farm

Abstract

The application belongs to the technical field of wind farm energy-saving control, and discloses a kind of wind farm power loss energy-saving control system and method;Including: obtaining environmental parameter data and wind generator state data;Obtain historical forecast wind speed and its corresponding historical actual wind speed and historical forecast wind direction and its corresponding historical actual wind direction, construct wind speed prediction model and wind direction prediction model, respectively input forecast wind speed and forecast wind direction in environmental parameter data into wind speed prediction model and wind direction prediction model, obtain predicted wind speed and predicted wind direction;Obtain the wind speed grade of predicted wind speed and its corresponding angle range, whether the blade angle is adjusted according to predicted wind direction, the wind speed grade of predicted wind speed and its corresponding angle range judges, and the blade angle is adjusted according to the judgment result;According to wind generator state data after blade angle adjustment, whether the electric energy transmission loss is abnormal is judged, and early warning is sent;Further reduce the wind farm power loss.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind farm energy-saving control, and more particularly to a wind farm power loss energy-saving control system and method. BACKGROUND

[0002] The patent with the application publication number CN113964845A discloses an energy-saving control method for a wind farm and photovoltaic power station reactive voltage automatic control system, which specifically includes the following steps: first, data communication between the station and the dispatching AVC master station; then, running state and parameter acquisition; finally, station data processing. After receiving the voltage target value issued by the dispatching AVC master station, the station converts the voltage regulation amount into a reactive power regulation amount through analysis and calculation, and then calculates the reactive power regulation target of each device in real time according to the running state and running parameters of each unit and each device, and issues the target value to each platform or device. The energy-saving control method for the wind farm and photovoltaic power station reactive voltage automatic control system optimizes the economic operation of the reactive voltage automatic control system, and further ensures the safe and stable operation of each device in the power plant by more reasonably optimizing and distributing the devices with reactive power output function in the station.

[0003] However, in the process of wind farm energy saving, the traditional method adjusts the blade angle of the wind turbine according to the changes of wind speed and wind direction, so that the power generation of the wind turbine is maximized under the corresponding wind speed. However, in actual process, the wind speed and wind direction may change frequently in a short time, and adjusting the blade angle of the wind turbine consumes the electric energy generated by the wind turbine. Therefore, the power generation of the wind turbine after adjustment may be less than that before adjustment (because adjusting the blade angle of the wind turbine consumes electric energy, so the power generation after adjustment will decrease), thereby increasing the power loss of the wind farm and reducing the power generation of the wind farm.

[0004] In view of this, the present application provides a wind farm power loss energy-saving control system and method to solve the above problems. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned purpose, the present application provides the following technical scheme: a wind farm power loss energy-saving control system, comprising a control center, wherein the control center is communicatively connected with a data acquisition component, a wind speed and wind direction prediction component, a blade angle control component and an abnormal early warning component;

[0006] The data acquisition component is responsible for acquiring environmental parameter data and wind turbine state data in a monitoring time period, and dividing the monitoring time period into m monitoring time points evenly;

[0007] The wind speed and direction prediction component is responsible for obtaining historical predicted wind speed and its corresponding historical actual wind speed and historical predicted wind direction and its corresponding historical actual wind direction in a historical time period, constructing a wind speed prediction model according to the historical predicted wind speed and its corresponding historical actual wind speed, constructing a wind direction prediction model according to the historical predicted wind direction and its corresponding historical actual wind direction, inputting the predicted wind speed and the predicted wind direction at each monitoring time point in the environmental parameter data into the wind speed prediction model and the wind direction prediction model respectively, and obtaining the predicted wind speed and the predicted wind direction at each monitoring time point.

[0008] The blade angle control component is responsible for obtaining the wind speed level of the predicted wind speed at each monitoring time point and its corresponding angle range, adjusting the blade angle of the wind turbine at the first monitoring time point according to the predicted wind direction at the first monitoring time point, the wind speed level of the predicted wind speed and its corresponding angle range, judging whether to adjust the blade angle at the subsequent monitoring time point according to the change of the predicted wind direction and the wind speed level of the predicted wind speed at the subsequent monitoring time point, and making corresponding adjustment to the blade angle at the subsequent monitoring time point according to the judgment result.

[0009] The abnormal early warning component is responsible for judging whether the electric energy transmission loss is abnormal according to the wind turbine state data after the blade angle adjustment, and issuing a warning.

[0010] Further, the environmental parameter data includes predicted wind speed and predicted wind direction.

[0011] The wind turbine state data includes the blade rotation speed and the power generation capacity of the wind turbine.

[0012] Further, the method for constructing the wind speed prediction model comprises:

[0013] Based on the LSTM basic framework, the input layer, the LSTM layer, the full connection layer and the output layer are set, the input of the input layer is set as the predicted wind speed, the activation function of the full connection layer is set as ReLU, and the output of the output layer is set as the predicted wind speed.

[0014] The Adam algorithm is adopted, and the learning rate and the loss function are set.

[0015] The same method is used to construct the wind direction prediction model.

[0016] Further, the method for obtaining the predicted wind speed and the predicted wind direction at each monitoring time point comprises:

[0017] Step A1: evenly divide the historical time period into n historical time points, take the historical predicted wind speed at a historical time point and its corresponding historical actual wind speed as a historical wind speed sample, collect all historical wind speed samples to form a historical wind speed sample set, take the historical predicted wind direction at a historical time point and its corresponding historical actual wind direction as a historical wind direction sample, collect all historical wind direction samples to form a historical wind direction sample set;

[0018] According to the ratio of 9:1, the historical wind speed sample set is divided into a historical wind speed training set and a historical wind speed verification set, and the historical wind direction sample set is divided into a historical wind direction training set and a historical wind direction verification set. The historical wind speed samples in the historical wind speed training set are sequentially input into the wind speed prediction model for forward propagation, and the historical wind direction samples in the historical wind direction training set are sequentially input into the wind direction prediction model for forward propagation.

[0019] Step A2: obtain the predicted wind speed of the historical wind speed sample in the historical wind speed training set and the predicted wind direction of the historical wind direction sample in the historical wind direction training set output by the wind speed prediction model and the wind direction prediction model respectively, calculate the loss value using the corresponding loss function respectively, calculate each parameter in the wind speed prediction model and the wind direction prediction model by the back propagation algorithm, and update the parameters using the gradient descent algorithm.

[0020] Step A3: repeat A1 and A2 until the loss value of the wind speed prediction model and the wind direction prediction model no longer changes, respectively import the historical wind speed verification set and the historical wind direction verification set for verification, when the verification is successful, the trained wind speed prediction model and wind direction prediction model are obtained, and when the verification is unsuccessful, repeat A3;

[0021] Step A4: obtain the predicted wind speed and predicted wind direction at each monitoring time point, input the predicted wind speed and predicted wind direction at each monitoring time point into the wind speed prediction model and wind direction prediction model respectively, and the wind speed prediction model and wind direction prediction model output to obtain the predicted wind speed and predicted wind direction at each monitoring time point.

[0022] Further, the method for obtaining the wind speed grade of the predicted wind speed at each monitoring time point and its corresponding angle range comprises:

[0023] The circular plane formed by the rotation of the wind turbine is referred to as the blade circular plane, a first wind speed grade threshold range and a second wind speed grade threshold range are set, when the predicted wind speed is less than the minimum value in the first wind speed grade threshold range, the wind speed grade of the predicted wind speed is recorded as a low wind speed grade, when the predicted wind speed is greater than or equal to the minimum value in the first wind speed grade threshold range and less than or equal to the maximum value in the first wind speed grade threshold range, the wind speed grade of the predicted wind speed is recorded as a medium wind speed grade.

[0024] When the predicted wind speed is greater than or equal to the maximum value in the first wind speed level threshold range and less than or equal to the maximum value in the second wind speed level threshold range, the wind speed level of the predicted wind speed is recorded as a high wind speed level, and when the predicted wind speed is greater than the maximum value in the second wind speed level threshold range, the wind speed level of the predicted wind speed is recorded as an extremely high wind speed level;

[0025] The angle ranges corresponding to the high wind speed level, the medium wind speed level and the low wind speed level are set as (θ1, θ2), (θ2, θ3) and (θ3, θ4) respectively.

[0026] Further, the method for adjusting the blade angle of the wind turbine at the first monitoring time point according to the predicted wind direction, the wind speed level of the predicted wind speed and the corresponding angle range at the first monitoring time point comprises:

[0027] The predicted wind direction and the wind speed level of the predicted wind speed at the first monitoring time point are obtained, and if the wind speed level of the predicted wind speed at the first monitoring time point is an extremely high wind speed level, the operation of the wind turbine is stopped.

[0028] If the wind speed level of the predicted wind speed at the first monitoring time point is not an extremely high wind speed level, the angle range corresponding to the wind speed level of the predicted wind speed at the first monitoring time point is recorded as the first angle range, and the blade angle at the first monitoring time point is adjusted to the middle value of the first angle range.

[0029] Further, the method for adjusting the blade angle at the subsequent monitoring time point according to the judgment result comprises:

[0030] The predicted wind direction and the wind speed level of the predicted wind speed at the second monitoring time point are obtained, if the wind speed level of the predicted wind speed at the second monitoring time point is an extremely high wind speed level, the operation of the wind turbine is stopped, if the wind speed level of the predicted wind speed at the second monitoring time point is the same as the wind speed level of the predicted wind speed at the first monitoring time point and is not an extremely high wind speed level, and the angle between the predicted wind direction at the second monitoring time point and the blade circle plane is within the first angle range, the blade angle at the second monitoring time point is not adjusted.

[0031] If the wind speed level of the predicted wind speed at the second monitoring time point is different from the wind speed level of the predicted wind speed at the first monitoring time point and is not an extremely high wind speed level, and the angle between the predicted wind direction at the second monitoring time point and the blade circle plane is within the angle range corresponding to the wind speed level of the predicted wind speed at the second monitoring time point, the blade angle at the second monitoring time point is not adjusted.

[0032] If the wind speed level of the predicted wind speed at the second monitoring time point is different from the wind speed level of the predicted wind speed at the first monitoring time point and is not the extremely high wind speed level, the predicted wind speed at the second monitoring time point is recorded as a second different-same predicted wind speed, and an angle range corresponding to the wind speed level of the second different-same predicted wind speed is recorded as a second angle range, or the predicted wind direction at the second monitoring time point is out of the first angle range, the predicted wind direction at the second monitoring time point is recorded as a second predicted wind direction, an angle between the second predicted wind direction and the blade circle plane is recorded as a second angle, and the second angle is out of the second angle range, the predicted wind direction and the wind speed level of the predicted wind speed at a third monitoring time point are obtained;

[0033] If the wind speed level of the predicted wind speed at the third monitoring time point is the same as the wind speed level of the predicted wind speed at the second monitoring time point, the blade angle at the second monitoring time point is adjusted to an intermediate value of the second angle range between the blade circle plane and the second predicted wind direction;

[0034] If the wind speed level of the predicted wind speed at the third monitoring time point is different from the wind speed level of the predicted wind speed at the second monitoring time point, a wind turbine operation simulation is performed, and the blade angle at the second monitoring time point is adjusted according to a simulation result;

[0035] The same method is used to determine whether to adjust the blade angle at the third monitoring time point, the blade angle at a fourth monitoring time point,..., and the blade angle at an mth monitoring time point, and the blade angle at the corresponding monitoring time point is adjusted according to a determination result.

[0036] Further, the method of performing a wind turbine operation simulation and adjusting the blade angle at the second monitoring time point according to a simulation result comprises:

[0037] A first simulation condition is that the second different-same predicted wind speed, the second predicted wind direction, the initial rotating speed of the wind turbine is the rotating speed at the second monitoring time point, and the angle between the predicted wind direction and the blade circle plane is the second angle, a simulated power generation amount of the wind turbine from the second monitoring time point to the third monitoring time point under the first simulation condition is obtained and recorded as a first simulated power generation amount;

[0038] A second simulation condition is that the second different-same predicted wind speed, the second predicted wind direction, the initial rotating speed of the wind turbine is the rotating speed at the second monitoring time point, and the angle between the predicted wind direction and the blade circle plane is an intermediate value of the second angle range, a simulated power generation amount of the wind turbine from the second monitoring time point to the third monitoring time point under the second simulation condition is obtained and recorded as a second simulated power generation amount;

[0039] obtaining the second subtraction power generation by subtracting the second simulation power generation from the first simulation power generation;

[0040] If the first simulation power generation is greater than or equal to the second subtraction power generation, the blade angle at the second monitoring time point is not adjusted; if the first simulation power generation is less than the second subtraction power generation, the blade angle at the second monitoring time point is adjusted to the middle value of the second angle range.

[0041] Further, the method of judging whether the power transmission loss is abnormal according to the wind turbine state data after the blade angle adjustment and issuing a warning comprises:

[0042] The power generation of the wind turbine after the blade angle adjustment in the monitoring time period is recorded as source power generation, and the power generation of the wind turbine sent by the power receiving end is recorded as received power generation.

[0043] The source power generation is subtracted from the received power generation to obtain a loss power generation, and a loss power generation threshold is set. When the loss power generation is greater than the loss power generation threshold, the power transmission loss is abnormal, and a red warning is issued to remind relevant personnel to handle it. When the loss power generation is less than or equal to the loss power generation threshold, the power transmission loss is normal.

[0044] An energy-saving control method for wind farm power loss, comprising:

[0045] Step S1: obtaining environmental parameter data and wind turbine state data;

[0046] Step S2: obtaining historical predicted wind speed and its corresponding historical actual wind speed, historical predicted wind direction and its corresponding historical actual wind direction, constructing a wind speed prediction model according to the historical predicted wind speed and its corresponding historical actual wind speed, constructing a wind direction prediction model according to the historical predicted wind direction and its corresponding historical actual wind direction, inputting the predicted wind speed and the predicted wind direction in the environmental parameter data into the wind speed prediction model and the wind direction prediction model respectively, and obtaining the predicted wind speed and the predicted wind direction;

[0047] Step S3: obtaining the wind speed grade of the predicted wind speed and its corresponding angle range, judging whether to adjust the blade angle according to the predicted wind direction, the wind speed grade of the predicted wind speed and its corresponding angle range, and adjusting the blade angle according to the judgment result;

[0048] Step S4: judging whether the power transmission loss is abnormal according to the wind turbine state data after the blade angle adjustment and issuing a warning.

[0049] The technical effects and advantages of the energy-saving control system and method for wind farm power loss of the present application are as follows:

[0050] 1. The predicted wind speed and the predicted wind direction are input into the wind speed prediction model and the wind direction prediction model respectively to obtain the predicted wind speed and the predicted wind direction. Instead of directly using the predicted wind speed and the predicted wind direction from the weather forecast as the reference, the predicted wind speed and the predicted wind direction are used as the reference. The predicted wind speed and the predicted wind direction are more close to the actual wind speed and the actual wind direction, so that the data is more targeted, providing a more accurate reference for the subsequent adjustment of the blade angle of the wind turbine, thereby ensuring the accuracy of the adjustment of the blade angle of the wind turbine, further reducing the power loss of the wind farm, and increasing the power generation of the wind farm.

[0051] 2. When the wind speed and the wind direction change each time, the blade angle of the wind turbine is not necessarily adjusted. Instead, the adjusted power generation and the power generation without adjustment are obtained, and the two are compared. If the adjusted power generation is less than or equal to the power generation without adjustment, the blade angle of the wind turbine is not adjusted. If the adjusted power generation is greater than the power generation without adjustment, the blade angle of the wind turbine is adjusted, thereby reducing the power loss of the wind farm and increasing the power generation of the wind farm. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 It is a schematic diagram of the energy-saving control system for wind farm power loss of the present application.

[0053] Figure 2 It is a schematic diagram of the energy-saving control method for wind farm power loss of the present application.

[0054] Figure 3 It is a flowchart of obtaining the wind speed level of the predicted wind speed at each monitoring time point. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0056] Embodiment 1

[0057] Please refer to Figure 1 and Figure 3 shown, the energy-saving control system for wind farm power loss described in the present embodiment includes a control center, the control center is communicatively connected with a data acquisition component, a wind speed and wind direction prediction component, a blade angle control component, and an abnormal early warning component.

[0058] a data acquisition component, responsible for acquiring environmental parameter data and wind turbine state data in a monitoring time period, and dividing the monitoring time period into m monitoring time points evenly;

[0059] a wind speed and direction prediction component, responsible for acquiring historical predicted wind speed and its corresponding historical actual wind speed, and historical predicted wind direction and its corresponding historical actual wind direction in a historical time period, constructing a wind speed prediction model according to the historical predicted wind speed and its corresponding historical actual wind speed, constructing a wind direction prediction model according to the historical predicted wind direction and its corresponding historical actual wind direction, inputting the predicted wind speed and the predicted wind direction at each monitoring time point in the environmental parameter data into the wind speed prediction model and the wind direction prediction model respectively, and obtaining the predicted wind speed and the predicted wind direction at each monitoring time point;

[0060] a blade angle control component, responsible for acquiring a wind speed level of the predicted wind speed at each monitoring time point and its corresponding angle range, adjusting the blade angle of the wind turbine at the first monitoring time point according to the predicted wind direction at the first monitoring time point, the wind speed level of the predicted wind speed and its corresponding angle range, judging whether to adjust the blade angle at the subsequent monitoring time point according to the change of the predicted wind direction and the wind speed level of the predicted wind speed at the subsequent monitoring time point, and adjusting the blade angle at the subsequent monitoring time point according to the judgment result;

[0061] an abnormality warning component, responsible for judging whether the power transmission loss is abnormal according to the wind turbine state data after the blade angle adjustment, and issuing a warning.

[0062] The process of acquiring the environmental parameter data and the wind turbine state data in the monitoring time period includes:

[0063] The environmental parameter data includes predicted wind speed and predicted wind direction;

[0064] The wind turbine state data includes the blade rotation speed and the power generation of the wind turbine;

[0065] The predicted wind speed and the predicted wind direction in the monitoring time period are acquired through weather forecast, the blade rotation speed of the wind turbine in the monitoring time period is acquired through a rotation speed sensor, and the power generation of the wind turbine in the monitoring time period is acquired through an electric energy metering instrument.

[0066] The process of acquiring the historical predicted wind speed and its corresponding historical actual wind speed, and the historical predicted wind direction and its corresponding historical actual wind direction in the historical time period includes:

[0067] obtaining historical predicted wind speed and corresponding historical actual wind speed and historical predicted wind direction and corresponding historical actual wind direction in a historical time period through a weather bureau, dividing the historical time period into n historical time points, and obtaining historical predicted wind speed and corresponding historical actual wind speed and historical predicted wind direction and corresponding historical actual wind direction at each historical time point;

[0068] It should be explained that the historical predicted wind speed is the wind speed broadcast by the weather bureau, the historical actual wind speed corresponding to the historical predicted wind speed is the actually measured wind speed, the historical predicted wind direction is the wind direction broadcast by the weather bureau, and the historical actual wind direction corresponding to the historical predicted wind direction is the actually measured wind direction;

[0069] The process of constructing a wind speed prediction model according to historical predicted wind speed and corresponding historical actual wind speed includes:

[0070] Based on the LSTM basic framework, an input layer, an LSTM layer, a full connection layer and an output layer are set, the input of the input layer is set as the predicted wind speed, the activation function of the full connection layer is set as ReLU, and the output of the output layer is set as the predicted wind speed;

[0071] The Adam algorithm is adopted, the learning rate is set as 0.001, and the loss function is: fs(i) represents the predicted wind speed of the i-th historical wind speed sample, fs'(i) represents the historical actual wind speed of the i-th historical wind speed sample, K represents the number of historical wind speed samples, i represents the index of the historical wind speed sample, i = 1, 2, 3, …, K;

[0072] The process of constructing a wind direction prediction model according to historical predicted wind direction and corresponding historical actual wind direction includes:

[0073] Based on the LSTM basic framework, a new input layer, a new LSTM layer, a new full connection layer and a new output layer are set, the input of the new input layer is set as the predicted wind direction, the activation function of the new full connection layer is set as ReLU, and the output of the new output layer is set as the predicted wind direction;

[0074] The Adam algorithm is adopted, the learning rate is set as 0.001, and the loss function is: fx(j) represents the predicted wind direction of the j-th historical wind direction sample, fx'(j) represents the historical actual wind direction of the j-th historical wind direction sample, M represents the number of historical wind direction samples, j represents the index of the historical wind direction sample, j = 1, 2, 3, …, M;

[0075] The process of inputting the predicted wind speed and the predicted wind direction in the environmental parameter data into the wind speed prediction model and the wind direction prediction model respectively to obtain the predicted wind speed and the predicted wind direction at each monitoring time point includes:

[0076] Step A1: Collect n historical wind speed samples and n historical wind direction samples to form a historical wind speed sample set and a historical wind direction sample set respectively, and divide the historical wind speed sample set into a historical wind speed training set and a historical wind speed verification set according to a ratio of 9:1, divide the historical wind direction sample set into a historical wind direction training set and a historical wind direction verification set, input the historical wind speed samples in the historical wind speed training set into the wind speed prediction model in sequence and perform forward propagation, input the historical wind direction samples in the historical wind direction training set into the wind direction prediction model in sequence and perform forward propagation;

[0077] Step A2: Obtain the predicted wind speed of the historical wind speed samples in the historical wind speed training set and the predicted wind direction of the historical wind direction samples in the historical wind direction training set output by the wind speed prediction model and the wind direction prediction model respectively, calculate the loss value using the corresponding loss function, calculate each parameter in the wind speed prediction model and the wind direction prediction model through the back propagation algorithm, and update the parameters using the gradient descent algorithm;

[0078] Step A3: Repeat A1 and A2 until the loss values of the wind speed prediction model and the wind direction prediction model no longer change, and then import the historical wind speed verification set and the historical wind direction verification set for verification, when the verification is successful, the trained wind speed prediction model and wind direction prediction model are obtained, and when the verification is unsuccessful, repeat A3;

[0079] Step A4: Divide the monitoring time period into m monitoring time points, and obtain the predicted wind speed and the predicted wind direction at each monitoring time point, input the predicted wind speed and the predicted wind direction at each monitoring time point into the wind speed prediction model and the wind direction prediction model respectively, and the wind speed prediction model and the wind direction prediction model output to obtain the predicted wind speed and the predicted wind direction at each monitoring time point;

[0080] The process of collecting n historical wind speed samples and n historical wind direction samples to form a historical wind speed sample set and a historical wind direction sample set includes:

[0081] A historical predicted wind speed at a historical time point and its corresponding historical actual wind speed are taken as a historical wind speed sample, all historical wind speed samples are collected to form a historical wind speed sample set, and a historical predicted wind direction at a historical time point and its corresponding historical actual wind direction are taken as a historical wind direction sample, all historical wind direction samples are collected to form a historical wind direction sample set;

[0082] It needs to be explained that the predicted wind speed and the predicted wind direction of the weather forecast are not directly selected as the reference, but a wind speed prediction model and a wind direction prediction model are constructed first, and the predicted wind speed and the predicted wind direction are obtained according to the wind speed prediction model and the wind direction prediction model, and the predicted wind speed and the predicted wind direction are taken as the reference, because the predicted wind speed and the predicted wind direction provided by the weather forecast often cover too large a range, and the predicted wind speed and the predicted wind direction are too different from the actual wind speed and the actual wind direction, and the numerical value is not targeted, and cannot provide more accurate reference for the system, therefore, the wind speed prediction model and the wind direction prediction model are used to more specifically predict the wind speed and the wind direction in the application, the predicted wind speed and the predicted wind direction are more close to the actual wind speed and the actual wind direction, so that the data is more targeted, and more accurate reference is provided for subsequent adjustment of the blade angle of the wind turbine, thereby ensuring the accuracy of the adjustment of the blade angle of the wind turbine, further reducing the power loss of the wind farm, and increasing the power generation of the wind farm.

[0083] The process of obtaining the wind speed level of the predicted wind speed at each monitoring time point and the corresponding angle range includes:

[0084] The circular plane formed by rotating the wind turbine is recorded as the blade circular plane, a first wind speed level threshold range (v1, v2) and a second wind speed level threshold range (v2, v3) are set, the first wind speed level threshold range and the second wind speed level threshold range can be set through experimental data analysis or experience, when the predicted wind speed is less than the minimum value in the first wind speed level threshold range, the wind speed level of the predicted wind speed is recorded as a low wind speed level, when the predicted wind speed is greater than or equal to the minimum value in the first wind speed level threshold range and less than or equal to the maximum value in the first wind speed level threshold range, the wind speed level of the predicted wind speed is recorded as a medium wind speed level, when the predicted wind speed is greater than or equal to the maximum value in the first wind speed level threshold range and less than or equal to the maximum value in the second wind speed level threshold range, the wind speed level of the predicted wind speed is recorded as a high wind speed level, and when the predicted wind speed is greater than the maximum value in the second wind speed level threshold range, the wind speed level of the predicted wind speed is recorded as an extremely high wind speed level;

[0085] The angle ranges corresponding to the high wind speed level, the medium wind speed level and the low wind speed level are set as (θ1, θ2), (θ2, θ3) and (θ3, θ4) respectively, and the angle ranges corresponding to the high wind speed level, the medium wind speed level and the low wind speed level can be set through experimental data analysis or experience;

[0086] It needs to be explained that the angle range corresponding to the low wind speed level is (θ3, θ4), which indicates that when the wind speed level is the low wind speed level, the wind turbine adjusts the blade angle so that the angle between the blade circle plane and the predicted wind direction is located in (θ3, θ4), the efficiency of using wind energy of the wind turbine is the highest, that is, the power generation of the wind turbine is the largest, the power generation is the most, the lower the wind speed, the larger the angle between the blade circle plane and the predicted wind direction, that is, the wind direction is more directly opposite the blade circle plane, the higher the efficiency of using wind energy, the higher the wind speed, the smaller the angle between the blade circle plane and the predicted wind direction, that is, the wind direction is more oblique to the blade circle plane, to prevent the wind speed from being too high to cause the wind turbine to run overload, cause the wind turbine to be damaged, the angle between the blade circle plane and the predicted wind direction refers to the angle between the blade circle plane and the predicted wind direction when the predicted wind direction is from the front to the back of the blade circle plane or the predicted wind direction is parallel to the blade circle plane, and the angle between the blade circle plane and the predicted wind direction is less than or equal to 90 degrees, when the predicted wind direction is from the back to the front of the blade circle plane, the angle between the blade circle plane and the predicted wind direction is recorded as -90 degrees;

[0087] The process of adjusting the blade angle of the wind turbine at the first monitoring time point according to the predicted wind direction, the wind speed level of the predicted wind speed and the angle range corresponding thereto includes:

[0088] The wind speed level of the predicted wind speed at the first monitoring time point is obtained, if the wind speed level of the predicted wind speed at the first monitoring time point is the extremely high wind speed level, the operation of the wind turbine is stopped, if the wind speed level of the predicted wind speed at the first monitoring time point is not the extremely high wind speed level, the angle range corresponding to the wind speed level of the predicted wind speed at the first monitoring time point is recorded as the first angle range, and the blade angle of the wind turbine at the first monitoring time point is adjusted, so that the angle between the blade circle plane and the predicted wind direction at the first monitoring time point is the middle value of the first angle range;

[0089] For example, if the wind speed level of the predicted wind speed at the first monitoring time point is the low wind speed level, the blade angle of the wind turbine is adjusted so that the angle between the blade circle plane and the predicted wind direction at the first monitoring time point is (θ3+θ4) / 2, if the wind speed level of the predicted wind speed at the first monitoring time point is the medium wind speed level, the blade angle of the wind turbine is adjusted so that the angle between the blade circle plane and the predicted wind direction at the first monitoring time point is (θ2+θ3) / 2, if the wind speed level of the predicted wind speed at the first monitoring time point is the high wind speed level, the blade angle of the wind turbine is adjusted so that the angle between the blade circle plane and the predicted wind direction at the first monitoring time point is (θ1+θ2) / 2;

[0090] The process of determining whether to adjust the blade angle at the subsequent monitoring time point according to the change of the wind speed level of the predicted wind direction and the predicted wind speed at the subsequent monitoring time point, and adjusting the blade angle at the subsequent monitoring time point according to the determination result comprises:

[0091] The wind speed level of the predicted wind direction and the predicted wind speed at the second monitoring time point is obtained, if the wind speed level of the predicted wind speed at the second monitoring time point is the extremely high wind speed level, the operation of the wind turbine is stopped, if the wind speed level of the predicted wind speed at the second monitoring time point is the same as the wind speed level of the predicted wind speed at the first monitoring time point and is not the extremely high wind speed level, and the angle between the predicted wind direction at the second monitoring time point and the blade circle plane is within the first angle range, the blade angle at the second monitoring time point is not adjusted;

[0092] If the wind speed level of the predicted wind speed at the second monitoring time point is different from the wind speed level of the predicted wind speed at the first monitoring time point and is not the extremely high wind speed level, and the angle between the predicted wind direction at the second monitoring time point and the blade circle plane is within the angle range corresponding to the wind speed level of the predicted wind speed at the second monitoring time point, the blade angle at the second monitoring time point is not adjusted;

[0093] It should be explained that the wind speed level changes, the predicted wind direction also changes, and the angle between the changed predicted wind direction and the blade circle plane is just within the angle range corresponding to the wind speed level of the predicted wind speed at the second monitoring time point, so the blade angle at the second monitoring time point does not need to be adjusted;

[0094] If the wind speed level of the predicted wind speed at the second monitoring time point is different from the wind speed level of the predicted wind speed at the first monitoring time point and is not the extremely high wind speed level, the predicted wind speed at the second monitoring time point is recorded as a second different wind speed, and the angle range corresponding to the wind speed level of the second different wind speed is recorded as a second angle range, or the angle between the predicted wind direction at the second monitoring time point and the blade circle plane exceeds the first angle range, the angle between the predicted wind direction at the second monitoring time point and the blade circle plane is recorded as a second angle, the predicted wind direction at the second monitoring time point is recorded as a second predicted wind direction, and the second angle exceeds the second angle range, the wind speed level of the predicted wind direction and the predicted wind speed at a third monitoring time point is obtained, if the wind speed level of the predicted wind speed at the third monitoring time point is the same as the wind speed level of the predicted wind speed at the second monitoring time point, the blade angle of the wind turbine at the second monitoring time point is adjusted, so that the angle between the blade circle plane and the predicted wind direction at the second monitoring time point is the middle value of the second angle range;

[0095] It needs to be explained that the wind speed level changes or the predicted wind direction changes, and the angle between the blade circle plane and the predicted wind direction after the change exceeds the angle range corresponding to the wind speed level of the predicted wind speed at the second monitoring time point, then whether to adjust is judged according to the wind speed level of the predicted wind speed at the third monitoring time point, if the wind speed level of the predicted wind speed at the third monitoring time point and the wind speed level of the predicted wind speed at the second monitoring time point are the same, the blade angle is adjusted, because the wind speed levels of the two continuous monitoring time points are the same, the power generation of the two continuous monitoring time points after adjustment is greater than that before adjustment, because the blade angle of the wind turbine is in the best angle for a long time at the two continuous monitoring time points, the time is long, the power generation is large, although the adjustment of the blade angle needs to consume power, but the time is long, the power generation is large, and the consumed power is small relative to the power generation, so the power generation of the two continuous monitoring time points after adjustment is greater than that before adjustment;

[0096] If the wind speed level of the predicted wind speed at the third monitoring time point and the wind speed level of the predicted wind speed at the second monitoring time point are different, the wind turbine operation simulation is carried out, the first simulation condition is the second different prediction wind speed, the second prediction wind direction, the initial speed of the wind turbine is the speed at the second monitoring time point, and the angle between the predicted wind direction and the blade circle plane is the second angle, the simulation power generation of the wind turbine from the second monitoring time point to the third monitoring time point under the first simulation condition is obtained and recorded as the first simulation power generation, the second simulation condition is the second different prediction wind speed, the second prediction wind direction, the initial speed of the wind turbine is the speed at the second monitoring time point, and the angle between the predicted wind direction and the blade circle plane is the middle value of the second angle range, the simulation power generation of the wind turbine from the second monitoring time point to the third monitoring time point under the second simulation condition is obtained and recorded as the second simulation power generation, the power consumed by the adjustment of the blade angle to change the angle between the blade circle plane and the predicted wind direction from the second angle to the middle value of the second angle range is simulated, the second simulation power generation is subtracted from the power consumed by the adjustment of the blade angle to change the angle between the blade circle plane and the predicted wind direction from the second angle to the middle value of the second angle range, and the second subtraction power generation is obtained, if the first simulation power generation is greater than or equal to the second subtraction power generation, the blade angle at the second monitoring time point is not adjusted, if the first simulation power generation is less than the second subtraction power generation, the blade angle of the wind turbine at the second monitoring time point is adjusted, so that the angle between the blade circle plane and the predicted wind direction at the second monitoring time point is the middle value of the second angle range;

[0097] It needs to be explained that the wind speed level of the predicted wind speed at the third monitoring time point is different from the wind speed level of the predicted wind speed at the second monitoring time point, the wind speed level of the predicted wind speed at the third monitoring time point changes immediately, the wind speed level of the predicted wind speed at the second monitoring time point only lasts from the second monitoring time point to the third monitoring time point, the time when the blade angle of the wind turbine is at the optimal angle is short, the time is short, the power generation is small, and adjusting the blade angle consumes power, so that the adjusted power generation may be less than or equal to the power generation without adjustment, therefore, it needs to be discussed in different cases, if the adjusted power generation is less than or equal to the power generation without adjustment, no adjustment is made, if the adjusted power generation is greater than the power generation without adjustment, adjustment is made;

[0098] The same method is used to determine whether to adjust the blade angle at the third monitoring time point, the blade angle at the fourth monitoring time point,..., the blade angle at the mth monitoring time point, and the blade angle at the corresponding monitoring time point is adjusted according to the determination result;

[0099] It needs to be explained that the traditional method adjusts the blade angle of the wind turbine according to the change of wind speed and wind direction, so that the power generation of the wind turbine is maximum under the corresponding wind speed, but in the actual process, the wind speed and wind direction may change frequently in a short time, and adjusting the blade angle of the wind turbine consumes the power generated by the wind turbine, and each change of wind speed and wind direction is adjusted, which may cause the power generation of the wind turbine after adjustment to be less than the power generation of the wind turbine without adjustment, thereby increasing the power loss of the wind farm and reducing the power generation of the wind farm, therefore, the present application does not necessarily adjust the blade angle of the wind turbine every time the wind speed and wind direction change, but compares the adjusted power generation with the power generation without adjustment, if the adjusted power generation is less than or equal to the power generation without adjustment, the blade angle of the wind turbine is not adjusted, if the adjusted power generation is greater than the power generation without adjustment, the blade angle of the wind turbine is adjusted, thereby reducing the power loss of the wind farm and increasing the power generation of the wind farm.

[0100] According to the blade angle adjustment, the wind turbine state data is used to determine whether the power transmission loss is abnormal, and a warning is issued, which includes:

[0101] The power generation amount of the wind turbine after the blade angle adjustment in the monitoring period is recorded as the source power generation amount, the power generation amount sent by the wind turbine and received by the power storage end is recorded as the received power generation amount, the source power generation amount is subtracted from the received power generation amount to obtain the loss power generation amount, and a loss power generation amount threshold is set. The loss power generation amount threshold can be set through experimental data analysis or experience. When the loss power generation amount is greater than the loss power generation amount threshold, the electric energy transmission loss is abnormal, and a red early warning is issued to remind relevant personnel to handle it. When the loss power generation amount is less than or equal to the loss power generation amount threshold, the electric energy transmission loss is normal.

[0102] In the embodiment, the predicted wind speed and the predicted wind direction are respectively input into the wind speed prediction model and the wind direction prediction model to obtain the predicted wind speed and the predicted wind direction. Instead of directly selecting the predicted wind speed and the predicted wind direction from the weather forecast as a reference, the predicted wind speed and the predicted wind direction are used as a reference. The predicted wind speed and the predicted wind direction are more close to the actual wind speed and the actual wind direction, so that the data is more targeted, providing a more accurate reference for subsequent adjustment of the blade angle of the wind turbine, thereby ensuring the accuracy of the adjustment of the blade angle of the wind turbine, further reducing the power loss of the wind farm, and increasing the power generation amount of the wind farm. When the wind speed and the wind direction change each time, the blade angle of the wind turbine is not necessarily adjusted. Instead, the adjusted power generation amount and the power generation amount without adjustment are compared. If the adjusted power generation amount is less than or equal to the power generation amount without adjustment, the blade angle of the wind turbine is not adjusted. If the adjusted power generation amount is greater than the power generation amount without adjustment, the blade angle of the wind turbine is adjusted, thereby reducing the power loss of the wind farm and increasing the power generation amount of the wind farm.

[0103] Embodiment 2

[0104] Please refer to Figure 2 The embodiment does not describe some parts in detail, which can be seen from the description of embodiment 1. The energy-saving control method for power loss of a wind farm includes:

[0105] Step S1: obtaining environmental parameter data and wind turbine state data;

[0106] Step S2: obtaining historical predicted wind speed and its corresponding historical actual wind speed, and historical predicted wind direction and its corresponding historical actual wind direction. A wind speed prediction model is constructed according to the historical predicted wind speed and its corresponding historical actual wind speed, and a wind direction prediction model is constructed according to the historical predicted wind direction and its corresponding historical actual wind direction. The predicted wind speed and the predicted wind direction are obtained by inputting the predicted wind speed and the predicted wind direction in the environmental parameter data into the wind speed prediction model and the wind direction prediction model, respectively.

[0107] Step S3: Obtain the wind speed level and its corresponding angle range of the predicted wind speed. Based on the predicted wind direction, the wind speed level and its corresponding angle range, determine whether to adjust the blade angle. Adjust the blade angle accordingly based on the determination result.

[0108] Step S4: Determine whether the power transmission loss is abnormal based on the wind turbine status data after the blade angle is adjusted, and issue an early warning.

[0109] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0110] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only one method, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0111] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

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

Claims

1. An energy-saving control system for power loss in a wind farm, comprising a control center, characterized in that, The control center is connected to a data acquisition component, a wind speed and direction prediction component, a blade angle control component, and an anomaly early warning component. The data acquisition component is responsible for acquiring environmental parameter data and wind turbine status data within the monitoring period, and dividing the monitoring period evenly into... The monitoring time points; the environmental parameter data include forecast wind speed and forecast wind direction; the wind turbine status data includes wind turbine blade speed and power generation; The wind speed and direction prediction component is responsible for acquiring historical forecast wind speeds and their corresponding historical actual wind speeds and historical forecast wind directions and their corresponding historical actual wind directions within a historical time period. Based on the historical forecast wind speeds and their corresponding historical actual wind speeds, it constructs a wind speed prediction model, and based on the historical forecast wind directions and their corresponding historical actual wind directions, it constructs a wind direction prediction model. The forecast wind speed and forecast wind direction at each monitoring time point in the environmental parameter data are input into the wind speed prediction model and the wind direction prediction model, respectively, to obtain the predicted wind speed and predicted wind direction at each monitoring time point. The method for constructing the wind speed prediction model includes: Based on the basic LSTM framework, an input layer, an LSTM layer, a fully connected layer, and an output layer are set up. The input of the input layer is the forecast wind speed, the activation function of the fully connected layer is ReLU, and the output of the output layer is the predicted wind speed. The Adam algorithm is used, and the learning rate and loss function are set. The same method is used to build the wind direction prediction model. The method for obtaining the predicted wind speed and predicted wind direction at each monitoring time point includes: Step A1: Divide the historical time period evenly into For each historical time point, the historical forecast wind speed and its corresponding historical actual wind speed are taken as a historical wind speed sample. All historical wind speed samples are collected to form a historical wind speed sample set. Similarly, the historical forecast wind direction and its corresponding historical actual wind direction are taken as a historical wind direction sample. All historical wind direction samples are collected to form a historical wind direction sample set. The historical wind speed sample set is divided into a historical wind speed training set and a historical wind speed validation set in a 9:1 ratio. The historical wind direction sample set is divided into a historical wind direction training set and a historical wind direction validation set. The historical wind speed samples in the historical wind speed training set are sequentially input into the wind speed prediction model for forward propagation. The historical wind direction samples in the historical wind direction training set are sequentially input into the wind direction prediction model for forward propagation. Step A2: Obtain the predicted wind speed from the historical wind speed samples in the historical wind speed training set and the predicted wind direction from the historical wind direction samples in the historical wind direction training set, respectively, and calculate the loss value using the corresponding loss function. Calculate each parameter in the wind speed prediction model and the wind direction prediction model using the backpropagation algorithm, and update the parameters using the gradient descent algorithm. Step A3: Repeat A1 and A2 until the loss values ​​of the wind speed prediction model and the wind direction prediction model no longer change. Then, import the historical wind speed validation set and the historical wind direction validation set for validation. If the validation is successful, the trained wind speed prediction model and the wind direction prediction model are obtained. If the validation is unsuccessful, repeat A3. Step A4: Obtain the forecast wind speed and forecast wind direction at each monitoring time point. Input the forecast wind speed and forecast wind direction at each monitoring time point into the wind speed prediction model and the wind direction prediction model respectively. The wind speed prediction model and the wind direction prediction model output to obtain the forecast wind speed and forecast wind direction at each monitoring time point. The blade angle control component is responsible for acquiring the wind speed level and its corresponding angle range of the predicted wind speed at each monitoring time point. Based on the predicted wind direction, wind speed level and its corresponding angle range at the first monitoring time point, it adjusts the blade angle of the wind turbine at the first monitoring time point. Based on the changes in the predicted wind direction and wind speed level at subsequent monitoring time points, it determines whether to adjust the blade angle at subsequent monitoring time points and adjusts the blade angle at subsequent monitoring time points accordingly based on the determination result. The anomaly warning component is responsible for determining whether the power transmission loss is abnormal based on the wind turbine status data after the blade angle is adjusted, and issuing an early warning.

2. The energy-saving control system and method for wind farm power loss according to claim 1, characterized in that, The method for obtaining the wind speed level and its corresponding angle range for the predicted wind speed at each monitoring time point includes: The circular plane formed by the rotation of the wind turbine is denoted as the blade circular plane. A first wind speed level threshold range and a second wind speed level threshold range are set. When the predicted wind speed is less than the minimum value in the first wind speed level threshold range, the wind speed level of the predicted wind speed is denoted as low wind speed level. When the predicted wind speed is greater than or equal to the minimum value in the first wind speed level threshold range and less than or equal to the maximum value in the first wind speed level threshold range, the wind speed level of the predicted wind speed is denoted as medium wind speed level. When the predicted wind speed is greater than or equal to the maximum value in the first wind speed level threshold range and less than or equal to the maximum value in the second wind speed level threshold range, the predicted wind speed level is recorded as a high wind speed level. When the predicted wind speed is greater than the maximum value in the second wind speed level threshold range, the predicted wind speed level is recorded as an extremely high wind speed level. Set the angle ranges corresponding to high wind speed level, medium wind speed level and low wind speed level as (θ1, θ2), (θ2, θ3) and (θ3, θ4) respectively.

3. The energy-saving control system and method for wind farm power loss according to claim 2, characterized in that, The method for adjusting the blade angle of the wind turbine at the first monitoring time point based on the predicted wind direction, predicted wind speed, wind speed level, and corresponding angle range at the first monitoring time point includes: Obtain the predicted wind direction and wind speed level at the first monitoring time point. If the predicted wind speed level at the first monitoring time point is extremely high, then stop the operation of the wind turbine. If the wind speed level of the predicted wind speed at the first monitoring time point is not an extremely high wind speed level, then the angle range corresponding to the wind speed level of the predicted wind speed at the first monitoring time point is recorded as the first angle range, and the blade angle at the first monitoring time point is adjusted so that the angle between the blade circular plane and the predicted wind direction at the first monitoring time point is the midpoint of the first angle range.

4. The energy-saving control system and method for wind farm power loss according to claim 3, characterized in that, The method for adjusting the blade angle at subsequent monitoring time points based on the judgment result includes: Obtain the predicted wind direction and wind speed level at the second monitoring time point. If the predicted wind speed level at the second monitoring time point is an extremely high wind speed level, then stop the operation of the wind turbine. If the predicted wind speed level at the second monitoring time point is the same as the predicted wind speed level at the first monitoring time point and is not an extremely high wind speed level, and the angle between the predicted wind direction at the second monitoring time point and the blade circular plane is within the first angle range, then do not adjust the blade angle at the second monitoring time point. If the wind speed level of the predicted wind speed at the second monitoring time point is different from that at the first monitoring time point and is not an extremely high wind speed level, and the angle between the predicted wind direction at the second monitoring time point and the blade circular plane is within the angle range corresponding to the wind speed level of the predicted wind speed at the second monitoring time point, then the blade angle at the second monitoring time point will not be adjusted. If the wind speed level of the predicted wind speed at the second monitoring time point is different from that at the first monitoring time point and is not an extremely high wind speed level, the predicted wind speed at the second monitoring time point is recorded as the second different predicted wind speed, and the angle range corresponding to the wind speed level of the second different predicted wind speed is recorded as the second angle range. Alternatively, if the angle between the predicted wind direction at the second monitoring time point and the circular plane of the blade exceeds the first angle range, the predicted wind direction at the second monitoring time point is recorded as the second predicted wind direction, and the angle between the second predicted wind direction and the circular plane of the blade is recorded as the second included angle. If the second included angle exceeds the second angle range, then the predicted wind direction and the wind speed level of the predicted wind speed at the third monitoring time point are obtained. If the wind speed level of the predicted wind speed at the third monitoring time point is the same as that of the predicted wind speed at the second monitoring time point, then the blade angle at the second monitoring time point will be adjusted so that the angle between the blade circular plane and the second predicted wind direction is the midpoint of the second angle range. If the wind speed level of the predicted wind speed at the third monitoring time point is different from that at the second monitoring time point, a wind turbine operation simulation will be performed, and the blade angle at the second monitoring time point will be adjusted accordingly based on the simulation results. The same method was used to determine whether the blade angle at the third monitoring time point, the fourth monitoring time point, and so on, should be adjusted. The blade angles at each monitoring time point are adjusted, and the blade angles at the corresponding monitoring time points are adjusted based on the judgment results.

5. The energy-saving control system and method for wind farm power loss according to claim 4, characterized in that, The method for simulating wind turbine operation and adjusting the blade angle at the second monitoring time point based on the simulation results includes: The first simulation conditions are the second predicted wind speed, the second predicted wind direction, the initial rotational speed of the wind turbine at the second monitoring time point, and the angle between the predicted wind direction and the blade circular plane as the second angle. The simulated power generation of the wind turbine from the second monitoring time point to the third monitoring time point under the first simulation conditions is obtained and recorded as the first simulated power generation. The second simulation conditions are the second predicted wind speed, the second predicted wind direction, the initial rotational speed of the wind turbine at the second monitoring time point, and the angle between the predicted wind direction and the blade circular plane at the midpoint of the second angle range. The simulated power generation of the wind turbine from the second monitoring time point to the third monitoring time point under the second simulation conditions is obtained and recorded as the second simulated power generation. The amount of electricity consumed when the angle between the blade circular plane and the predicted wind direction changes from the second angle to the midpoint of the second angle range is obtained by simulating the adjustment of the blade angle. The amount of electricity consumed when the angle between the blade circular plane and the predicted wind direction changes from the second angle to the midpoint of the second angle range is subtracted from the second simulated power generation to obtain the second phase subtraction power generation. If the first simulated power generation is greater than or equal to the second phase subtraction power generation, the blade angle at the second monitoring time point will not be adjusted. If the first simulated power generation is less than the second phase subtraction power generation, the blade angle at the second monitoring time point will be adjusted so that the angle between the blade circular plane and the second predicted wind direction is the midpoint of the second angle range.

6. The energy-saving control system and method for wind farm power loss according to claim 5, characterized in that, The method for determining whether power transmission loss is abnormal and issuing an early warning based on the wind turbine status data after blade angle adjustment includes: The power generation of the wind turbine after the blade angle is adjusted during the monitoring period is recorded as the source power generation, and the power generation received by the storage terminal from the wind turbine is recorded as the received power generation. The power loss is obtained by subtracting the power received from the power generated at the source. A power loss threshold is set. When the power loss exceeds the power loss threshold, the power transmission loss is abnormal and a red warning is issued to remind relevant personnel to handle the situation. When the power loss is less than or equal to the power loss threshold, the power transmission loss is normal.

7. An energy-saving control method for power loss in a wind farm, used to implement the energy-saving control system for power loss in a wind farm as described in any one of claims 1 to 6, characterized in that, include: Step S1: Obtain environmental parameter data and wind turbine status data; Step S2: Obtain historical forecast wind speed and its corresponding historical actual wind speed and historical forecast wind direction and its corresponding historical actual wind direction. Construct a wind speed prediction model based on the historical forecast wind speed and its corresponding historical actual wind speed. Construct a wind direction prediction model based on the historical forecast wind direction and its corresponding historical actual wind direction. Input the forecast wind speed and forecast wind direction from the environmental parameter data into the wind speed prediction model and the wind direction prediction model respectively to obtain the predicted wind speed and predicted wind direction. Step S3: Obtain the wind speed level and its corresponding angle range of the predicted wind speed. Based on the predicted wind direction, the wind speed level and its corresponding angle range, determine whether to adjust the blade angle. Adjust the blade angle accordingly based on the determination result. Step S4: Determine whether the power transmission loss is abnormal based on the wind turbine status data after the blade angle is adjusted, and issue an early warning.

Images