Wind farm control methods, devices, equipment and media
By establishing a correspondence between wind speed and power calculation parameter ranges in wind farms, determining active power limit thresholds and implementing power limiting control, the problem of low accuracy in active power control in wind farms is solved, achieving higher grid stability and wind farm control effect.
Patent Information
- Application Number
- CN202110578477.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-05-26
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2041-05-26
AI Technical Summary
Low accuracy of active power control in wind farms, rapid wind speed fluctuations, and uneven distribution of wind resources lead to power curtailment or overload of some units, affecting grid stability.
By acquiring the operating data of each wind turbine generator in the wind farm, a correspondence is established between wind speed range, power calculation parameter range, and predicted change value of active power. The predicted change value is used to determine the active power limit threshold, and power limiting control commands are sent to the generator to ensure that the generator operates under the appropriate threshold.
It improves the accuracy of active power control in wind farms, enhances grid stability, reduces unit overload or power curtailment, and improves the overall control effect of wind farms.
Smart Images

Figure CN115411718B_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of wind power generation, and in particular relates to a wind farm control method, device, equipment and medium. Background Technology
[0002] Wind power generation technology refers to the technology of converting wind energy into electrical energy. A wind farm consists of multiple wind turbine generators. The electrical energy converted by the wind turbine generators in a wind farm can be transmitted to the power grid. As the scale of wind turbine generators increases, the impact of power fluctuations in wind farms on grid stability becomes increasingly significant. In order to ensure the stable operation of the power system, it is necessary to assess and limit the changes in active power of wind farms.
[0003] However, due to factors such as rapid wind speed fluctuations and uneven distribution of wind resources, the active power limitation of wind turbine generators in wind farms results in situations where some wind turbine generators have the ability to generate electricity but are under power curtailment, and some wind turbine generators do not have the ability to generate electricity but require an increase in active power. This leads to low accuracy and poor effectiveness of power control in wind farms. Summary of the Invention
[0004] This application provides a wind farm control method, apparatus, equipment, and medium that can improve the accuracy of wind farm control.
[0005] In a first aspect, embodiments of this application provide a wind farm control method, comprising: acquiring operating data of each wind turbine generator set in a wind farm, the operating data including current wind speed, current power calculation parameters, and current active power, wherein the current power calculation parameters are related to the active power of the wind turbine generator set; determining, within a preset power change relationship, the predicted change value of active power corresponding to the current wind speed and current power calculation parameters of each wind turbine generator set, wherein the power change relationship is used to characterize the correspondence between the wind speed range, power calculation parameter range, and predicted change value of active power of each wind turbine generator set in the wind farm, and the power change relationship is based on multiple acquisitions of data from each wind turbine generator set. The wind speed, power calculation parameters, and active power change values of the generator sets are obtained; based on the predicted active power change values of each wind turbine generator set in the wind farm, the predicted active power change value of the wind farm is determined; when the predicted active power change value of the wind farm is greater than the active power margin threshold, based on the current active power, active power margin threshold, and predicted active power change value of each wind turbine generator set, the active power limit threshold of each wind turbine generator set is determined, and a power limiting control command is sent to each wind turbine generator set. The power limiting control command is used to control the wind turbine generator set to operate when the active power is less than the active power limit threshold corresponding to the wind turbine generator set.
[0006] In some possible embodiments, determining the predicted change value of active power of the wind farm based on the predicted change value of active power of each wind turbine generator in the wind farm includes: calculating a first sum of the predicted change values of active power of each wind turbine generator in the wind farm; correcting the first sum using a preset correction parameter; and determining the corrected first sum as the predicted change value of active power of the wind farm.
[0007] In some possible embodiments, the active power limit threshold for each wind turbine generator set is determined based on the current active power, active power margin threshold, and predicted change in active power. This includes: for each wind turbine generator set, calculating a first product of the margin allocation ratio and the predicted change in active power of the wind turbine generator set, where the margin allocation ratio is the ratio of the active power margin threshold to the predicted change in active power of the wind farm; calculating a second sum of the current active power of the wind turbine generator set and the first product; and determining the second sum as the active power limit threshold for the wind turbine generator set.
[0008] In some possible embodiments, the method further includes controlling the normal operation of each wind turbine generator set when the predicted change in active power of the wind farm is less than or equal to the active power margin threshold.
[0009] In some possible embodiments, the active power margin threshold is the minimum value among the first variation margin threshold, the second variation margin threshold, and the third variation margin threshold. The first variation margin threshold is the difference between a preset maximum active power value and a preset minimum active power value in one minute. The second variation margin threshold is the difference between a preset maximum active power value and a preset minimum active power value in ten minutes. The third variation margin threshold is the difference between a preset planned active power value and the actual active power value obtained.
[0010] In some possible embodiments, the method further includes updating the power change relationship using the current wind speed, current power calculation parameters, and current active power of each wind turbine generator.
[0011] In some possible embodiments, the current power calculation parameters include one or more of the following: the current converter torque of the wind turbine, the current speed of the wind turbine, the current pitch angle of the wind turbine, the current yaw angle of the wind turbine, and the current grid-side current of the wind turbine converter.
[0012] Secondly, embodiments of this application provide a method for predicting active power changes, comprising: acquiring operating data of a wind turbine generator set in each acquisition cycle, the operating data including wind speed, power calculation parameters, and active power, wherein the current power calculation parameters are related to the active power of the wind turbine generator set; grouping the active power change values of multiple acquisition cycles according to wind speed intervals and power calculation parameter intervals divided by wind speed and power calculation parameters, obtaining two or more data groups, wherein the wind speed corresponding to the active power change value in the same data group is in the same wind speed interval, and the power calculation parameters corresponding to the active power change value in the same data group are in the same power calculation parameter interval; and predicting the predicted active power change value of the wind turbine generator set in each wind speed interval and power calculation interval based on the active power change value, the number of active power change values, and the distribution of active power change values in each data group.
[0013] In some possible embodiments, based on the active power change values, the number of active power change values, and the distribution of active power change values in each data group, the predicted active power change value of the wind turbine generator set in each wind speed range and power calculation range is obtained, including: for each data group, if the number of active power change values in the data group is greater than a preset minimum group number threshold, the active power change values in the data group are arranged in ascending order; using a preset quantile parameter and the number of active power change values in the data group, the first active power change value and the second active power change value located on both sides of the quantile position indicated by the quantile parameter in the data group are determined; based on the first active power change value and the second active power change value, the predicted active power change value is obtained.
[0014] In some possible embodiments, using a preset quantile parameter and the number of active power change values in the data group, the determination of the first active power change value and the second active power change value located on both sides of the quantile position indicated by the quantile parameter in the data group includes: calculating a second product of the quantile parameter and a first difference, where the first difference is the difference between the number of active power change values in the data group and 1; obtaining the integer part and the fractional part of the second product; determining the i-th active power change value in the data group in ascending order as the first active power change value, and determining the (i+1)-th active power change value in the data group in ascending order as the second active power change value, where i is equal to the integer part.
[0015] In some possible embodiments, predicting the active power change value based on the first active power change value and the second active power change value includes: calculating a third product of a second difference and the first active power change value, where the second difference is the difference between 1 and the fractional part; calculating a fourth product of the fractional part and the second active power change value; calculating a third sum of the third product and the fourth product, and determining the third sum as the active power change value corresponding to the data set.
[0016] In some possible embodiments, based on the active power change value, the number of active power change values, and the distribution of active power change values in each data group, the predicted active power change value of the wind turbine generator set in each wind speed range and power calculation range is obtained, including: for each data group, if the number of active power change values in the data group is less than or equal to a preset minimum group number threshold, the largest active power change value in the data group is determined as the predicted active power change value.
[0017] In some possible embodiments, before predicting the predicted active power change value of the wind turbine generator in each wind speed range and power calculation range based on the active power change value, the number of active power change values and the distribution of active power change values in each data group, the method further includes: removing active power change values in the data group that meet preset data cleaning conditions.
[0018] In some possible embodiments, the data cleaning conditions include one or more of the following: the wind turbine generator corresponding to the active power change value is in an abnormal operating state; the active power change value is less than zero; the wind speed change value corresponding to the active power change value is less than zero; the duration of the collection period corresponding to the active power change value is greater than a preset duration threshold; and the active power change value is less than a preset minimum power change value threshold.
[0019] In some possible embodiments, the method further includes: for a pair of wind speed zones and power calculation intervals, calculating the average value of the predicted change in active power of each wind turbine generator set corresponding to the pair of wind speed zones and power calculation intervals; and determining the average value as the predicted change in active power of the wind turbine generator set in an abnormal operating state in the pair of wind speed zones and power calculation intervals.
[0020] In some possible embodiments, the method further includes: obtaining the predicted changes in active power of each wind turbine generator set in the wind farm in each wind speed range and power calculation range; and establishing a power change relationship based on the predicted changes in active power of each wind turbine generator set in the wind farm in each wind speed range and power calculation range, wherein the power change relationship is used to characterize the correspondence between the wind speed range, the power calculation parameter range, and the predicted changes in active power of each wind turbine generator set in the wind farm.
[0021] In some possible embodiments, the power calculation parameters include one or more of the following: the converter torque of the wind turbine generator set, the rotational speed of the wind turbine generator set, the pitch angle of the wind turbine generator set, the yaw angle of the wind turbine generator set, and the grid-side current of the converter of the wind turbine generator set.
[0022] Thirdly, embodiments of this application provide a wind farm control device, comprising: an acquisition module, configured to acquire operating data of each wind turbine generator set in the wind farm, the operating data including current wind speed, current power calculation parameters, and current active power, wherein the current power calculation parameters are related to the active power of the wind turbine generator set; and a prediction module, configured to determine, within a preset power change relationship, predicted active power change values corresponding to the current wind speed and current power calculation parameters of each wind turbine generator set, wherein the power change relationship characterizes the correspondence between the wind speed range, power calculation parameter range, and predicted active power change values of each wind turbine generator set in the wind farm, and the power change relationship is based on multiple acquisitions of the wind speed of each wind turbine generator set. The system includes: a power calculation module and an active power change module; a field-level calculation module to determine the predicted active power change value of the wind farm based on the predicted active power change value of each wind turbine generator in the wind farm; a threshold determination module to determine the active power limit threshold for each wind turbine generator when the predicted active power change value of the wind farm is greater than the active power margin threshold; and a sending module to send power limiting control commands to each wind turbine generator, which control the wind turbine generator to operate when the active power is less than the active power limit threshold corresponding to the wind turbine generator.
[0023] Fourthly, this application provides an active power change prediction device, comprising: a data acquisition module, used to acquire operating data of a wind turbine generator set in each acquisition cycle, the operating data including wind speed, power calculation parameters, and active power, wherein the current power calculation parameters are related to the active power of the wind turbine generator set; a data grouping module, used to group the active power change values of multiple acquisition cycles according to wind speed intervals and power calculation parameter intervals divided by wind speed and power calculation parameters, to obtain two or more data groups, wherein the wind speed corresponding to the active power change value in the same data group is in the same wind speed interval, and the power calculation parameters corresponding to the active power change value in the same data group are in the same power calculation parameter interval; and a prediction module, used to predict the predicted active power change value of the wind turbine generator set in each wind speed interval and power calculation interval based on the active power change value, the number of active power change values, and the distribution of active power change values in each data group.
[0024] Fifthly, embodiments of this application provide a wind farm control device, including: a processor and a memory storing computer program instructions; the processor executes the computer program instructions to implement the wind farm control method of the first aspect.
[0025] In a sixth aspect, embodiments of this application provide an active power change prediction device, comprising: a processor and a memory storing computer program instructions; the processor executes the computer program instructions to implement the active power change prediction method as described in the second aspect.
[0026] In a seventh aspect, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the wind farm control method of the first aspect and / or the active power change prediction method of the second aspect.
[0027] This application provides a method, apparatus, equipment, and medium for wind farm control and active power change prediction. Based on the current wind speed and current power calculation parameters of each wind turbine generator in the wind farm, and within a power change relationship that characterizes the correspondence between the wind speed range, power calculation parameter range, and predicted active power change value of each wind turbine generator, the predicted active power change value corresponding to the current wind speed and current power calculation parameters of each wind turbine generator is determined. The power change relationship is obtained based on multiple collections of wind speed, power calculation parameters, and active power change values of each wind turbine generator. Through statistical processing of a large amount of data, the accuracy of the power change relationship is improved, thus resulting in higher accuracy of the predicted active power change value of each wind turbine generator determined through the power change relationship. Based on the predicted active power change value corresponding to each wind turbine generator, the predicted active power change value of the wind farm is obtained. When active power limitation is required based on the predicted changes in active power of the wind farm, an appropriate active power limit threshold can be determined for each wind turbine based on its current active power, active power margin threshold, and predicted active power change. This ensures that each wind turbine operates within its designated active power limit threshold. Higher accuracy in the predicted changes in active power of the wind turbines leads to higher accuracy in the overall active power prediction of the wind farm. Consequently, the active power limit threshold determined based on the predicted changes in active power of the wind turbines shows better compatibility with the turbines, resulting in higher accuracy in wind farm control using these predicted changes. Attached Figure Description
[0028] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0029] Figure 1 A schematic diagram of an example architecture for wind farm monitoring provided in an embodiment of this application;
[0030] Figure 2 A flowchart of an embodiment of the active power change prediction method provided in this application;
[0031] Figure 3 A flowchart of another embodiment of the active power change prediction method provided in this application;
[0032] Figure 4 A flowchart of yet another embodiment of the active power change prediction method provided in this application;
[0033] Figure 5 A flowchart of yet another embodiment of the active power change prediction method provided in this application;
[0034] Figure 6 A flowchart of an embodiment of the wind farm control method provided in this application;
[0035] Figure 7 A flowchart of another embodiment of the wind farm control method provided in this application;
[0036] Figure 8 A schematic diagram of the structure of an embodiment of the active power change prediction device provided in this application;
[0037] Figure 9 A schematic diagram of another embodiment of the active power change prediction device provided in this application;
[0038] Figure 10 A schematic diagram of another embodiment of the active power change prediction device provided in this application;
[0039] Figure 11 A schematic diagram of an embodiment of the wind farm control device provided in this application;
[0040] Figure 12 A schematic diagram of another embodiment of the wind farm control device provided in this application;
[0041] Figure 13 A schematic diagram of the structure of an embodiment of the active power change prediction device provided in this application;
[0042] Figure 14 A schematic diagram of an embodiment of the wind farm control equipment provided in this application. Detailed Implementation
[0043] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.
[0044] Wind turbines convert wind energy into electrical energy and transmit it to the power grid. Multiple wind turbines form a wind farm, and overall monitoring of the wind farm can improve wind power generation efficiency. Automatic Generation Control (AGC) technology is an important means of maintaining power system frequency stability and inter-regional stability, and can also assist in power services. Power fluctuations of wind turbines can have a certain impact on the power grid. As the scale of wind turbines in a wind farm increases, the impact of power fluctuations on grid stability becomes increasingly significant, including in wind farms with a large number of turbines. To ensure the stable operation of the power system, it is necessary to assess and limit the active power variations of wind farms.
[0045] Due to natural environmental factors, wind farms experience rapid wind speed fluctuations and uneven distribution of wind resources. This leads to situations where some wind turbines, despite having the capacity to generate electricity, are subject to power limitations, while others, lacking the capacity, are required to increase their active power. Consequently, the power control accuracy and effectiveness of wind farms are low.
[0046] Figure 1 This is a schematic diagram of an example architecture for wind farm monitoring provided in an embodiment of this application. Figure 1 As shown, wind farm 11 may include multiple wind turbine generator sets 111. The number of wind turbine generator sets in wind farm 11 and their locations within the wind farm 11 can be set according to the wind farm site selection and specific needs, and are not limited here. Wind farm 11 can interact with the power grid 12 to realize the flow of electricity between wind farm 11 and power grid 12. Wind farm control device 13 can monitor wind farm 11 and can realize functions such as data acquisition of wind turbine generator sets and operation control of wind turbine generator sets, etc., which are not limited here and will not be illustrated in detail.
[0047] This application provides a method, apparatus, equipment, and medium for wind farm control and active power change prediction. It enables the control of each wind turbine generator to operate at an active power level below its respective suitable active power display threshold when power limiting operation of the wind farm is required. By individually limiting the power of each wind turbine generator in the wind farm, the accuracy of power control in the wind farm is improved. The method, apparatus, equipment, and medium for wind farm control and active power change prediction are described in detail below.
[0048] This application provides a method for predicting changes in active power, which can be executed by an active power prediction device. Figure 2 A flowchart illustrating an embodiment of the active power change prediction method provided in this application. Figure 2 As shown, the active power change prediction method may include steps S201 to S203.
[0049] In step S201, the operating data of the wind turbine generator set is acquired in each acquisition cycle.
[0050] Operating data includes wind speed, power calculation parameters, and active power. Power calculation parameters are related to the active power of the wind turbine generator set, and the active power can be calculated from these parameters. In some examples, power calculation parameters may include, but are not limited to, one or more of the following: the wind turbine generator set's converter torque, the wind turbine generator set's rotational speed, the wind turbine generator set's pitch angle, the wind turbine generator set's yaw angle, and the wind turbine generator set's converter grid-side current. The selection of power calculation parameters can be determined based on the wind turbine generator set's condition and structure, and is not limited here. For example, if the wind turbine generator set's converter torque cannot be obtained, or if the converter cooling is passively triggered by air cooling, or if the wind turbine generator set does not have a converter, the wind turbine generator set's rotational speed can be used as the power calculation parameter.
[0051] The data acquisition period can be set according to the scenario and requirements, and is not limited here. In some examples, the duration of the acquisition period can be less than 15 minutes. For example, the acquisition period can be set to 5 seconds, acquiring the wind turbine's operating data once every 5 seconds.
[0052] In step S202, the active power change values of multiple acquisition cycles are grouped according to the wind speed interval and power calculation parameter interval, based on the wind speed and power calculation parameter intervals, to obtain two or more data groups.
[0053] The change in active power is the change in active power between two adjacent acquisition cycles. Specifically, the change in active power in the preceding acquisition cycle is the difference in active power between the two adjacent acquisition cycles. For example, if the acquisition cycle is 5 seconds, the first acquisition cycle is from second 1 to second 5, the second acquisition cycle is from second 6 to second 10, the third acquisition cycle is from second 11 to second 15, and the fourth acquisition cycle is from second 16 to second 20. The change in active power in the first acquisition cycle is the difference between the active power acquired in the first acquisition cycle and the active power acquired in the second acquisition cycle; the change in active power in the second acquisition cycle is the difference between the active power acquired in the second acquisition cycle and the active power acquired in the third acquisition cycle, and so on. Four changes in active power can be obtained in four acquisition cycles.
[0054] Wind speed intervals are divided according to wind speed. For example, if the minimum wind speed is V1 and the maximum wind speed is V6, four wind speed intervals can be selected: V2, V3, V4, and V5, where V1 < V2 < V3 < V4 < V5 < V6. This results in five wind speed intervals: [V1, V2), [V2, V3), [V3, V4), [V4, V5), and [V5, V6]. Specifically, the wind speed intervals can be evenly divided.
[0055] Power calculation parameter ranges can be divided according to the power calculation parameters themselves, specifically by the magnitude of the power calculation parameters. For example, if the power calculation parameter includes the rotational speed of the wind turbine generator, multiple rotational speed ranges can be obtained based on the rotational speed, with each range constituting a power calculation parameter range. For instance, the rotational speed range of 0 to 20 rpm can be divided into multiple ranges with a step size of 0.5 rpm. In some cases, the values of the power calculation parameters are large, making direct division of power calculation parameter ranges inconvenient. In such cases, the power calculation parameters can be standardized first, and the ranges can be divided according to the magnitude of the standardized parameters. For example, if the power calculation parameter includes the converter torque of the wind turbine generator, the converter torque can be calculated using the natural logarithm to the base e, yielding the logarithm of the converter torque. Multiple logarithm ranges can then be obtained based on the magnitude of the logarithm, with each range constituting a power calculation parameter range. For instance, the logarithm of the converter torque from 0 to 20 can be divided into multiple logarithm ranges with a step size of 0.2.
[0056] Each data set may include at least one active power change value. The wind speeds corresponding to active power change values within the same data set are in the same wind speed range. The power calculation parameters corresponding to active power change values within the same data set are in the same power calculation parameter range. For example, there are 37 active power change values, from D1 to D37. Based on the wind speeds and power calculation parameters corresponding to D1 to D37, D1 to D37 are divided into multiple data sets. Table 1 shows the data sets corresponding to each wind speed range and power calculation parameter range. As shown in Table 1, each wind speed range and each power calculation parameter range corresponds to one data set. Table 1 includes five wind speed ranges: [V1, V2), [V2, V3), [V3, V4), [V4, V5), and [V5, V6]. Table 1 includes four power calculation parameter ranges: [r1, r2), [r2, r3), [r3, r4), and [r4, r5]. Table 1 includes 20 data sets. The wind speeds corresponding to the active power change values D1 and D2 in the data set {D1, D2} are both within the wind speed range [V1, V2), and the power calculation parameters corresponding to the active power change values D1 and D2 in the data set {D1, D2} are both within the power calculation parameter range [r1, r2).
[0057] Table 1
[0058]
[0059] It should be noted that Table 1 is an example for illustrative purposes. The actual number of active power change values in the data groups obtained will be much greater, but this is not a limitation here.
[0060] In step S203, based on the active power change value, the number of active power change values, and the distribution of active power change values in each data group, the predicted active power change value of the wind turbine generator set in each wind speed range and power calculation range is obtained.
[0061] For a data set corresponding to a wind speed range and a power calculation parameter range, the most likely active power change value under the given wind speed range and power calculation parameter range can be determined based on the active power change values, their quantity, and distribution. This most likely active power change value is then taken as the predicted active power change value for that wind speed range and power calculation parameter range. In other words, the predicted active power change value for a wind speed range and power calculation parameter range is the most likely active power change value predicted under those conditions. The predicted change value of active power in a wind speed range and a power calculation parameter range may include an active power change value in the data set corresponding to the wind speed range and the power calculation parameter range, or it may include an active power change value calculated based on the active power change value in the data set corresponding to the wind speed range and the power calculation parameter range, which is not limited here.
[0062] The predicted change in active power can be used to determine the predicted change in active power of a wind farm in wind farm control, so as to determine whether to implement power limiting control based on the predicted change in active power of the wind farm.
[0063] In this embodiment, operating data of the wind turbine generator is acquired in multiple acquisition cycles. The active power change values obtained using active power are grouped according to the wind speed and power calculation parameters in the operating data. Within the same data group, the wind speed corresponding to the active power change value lies within the same wind speed interval, and the power calculation parameters corresponding to the active power change value within the same data group lie within the same power calculation parameter interval. By analyzing the active power change values, the amount of active power change values, and the distribution of active power change values in each data group, the active power change value with the highest probability of occurrence under the corresponding wind speed interval and power calculation parameter interval can be predicted as the active power prediction change value. The accuracy of the predicted active power change values of the wind turbine generator in each wind speed interval and power calculation interval is higher. The active power prediction change value can be used to determine the active power prediction change value of the wind farm in wind farm control, so as to determine whether to implement power limiting control based on the active power prediction change value of the wind farm. Higher accuracy of the active power prediction change value leads to higher accuracy of wind farm control using the active power prediction change value.
[0064] In the embodiments of this application, the distribution of active power change values can be achieved through multi-dimensional averaging calculation, mode calculation, clustering calculation, etc., and is not limited thereto.
[0065] In some embodiments, different methods may be used to predict the predicted changes in active power of the wind turbine generator set in each wind speed range and power calculation range, depending on the number of active power change values in the data set. Figure 3 A flowchart of another embodiment of the active power change prediction method provided in this application. Figure 3 and Figure 2 The difference is that, Figure 2 The step S203 shown can be further refined into steps S2031 to S2033. Figure 2 The step S203 shown can also be further refined into step S2034.
[0066] In step S2031, for each data group, if the number of active power change values in the data group is greater than the preset minimum threshold, the active power change values in the data group are sorted in ascending order.
[0067] The minimum number threshold within a group is the threshold for the number of samples of active power change values using the cumulative probability distribution algorithm. This threshold can be set according to the scenario and requirements, and is not limited here. If the number of active power change values in a data group is greater than the minimum number threshold within a group, it means that the active power change values in the data group meet the sample size requirement for using the cumulative probability distribution algorithm, and the predicted active power change value can be obtained using the cumulative probability distribution algorithm.
[0068] Sort the active power change values in the data set in ascending order to facilitate determining the percentile position of each value. The predicted active power change value can then be obtained using this percentile position.
[0069] In step S2032, the first active power change value and the second active power change value located on both sides of the quantile position indicated by the quantile parameter are determined using the preset quantile parameter and the number of active power change values in the data group.
[0070] The quantile parameter indicates the quantile position of the active power change value in the data set. It can be set according to the scenario and requirements, and is not limited here. The quantile position is used to determine the first and second active power change values. The first and second active power change values are used to calculate the predicted active power change value. In some examples, the active power change value to the left of the quantile position is the first active power change value, and the active power change value to the right of the quantile position is the second active power change value.
[0071] For example, the quantile parameter can be 0.75. A quantile parameter of 0.75 indicates that the third and fourth quartile positions among the ascending active power change values in the data set are the quantile positions, that is, the positions at three-quarters of the ascending active power change values in the data set are the quantile positions. If the number of active power change values in the data set is 20 and the quantile parameter is 0.75, then the quantile position is the position between the 14th and 15th active power change values in the ascending order of the data set. The 14th active power change value in the ascending order of the data set can be taken as the first active power change value, and the 15th active power change value in the ascending order of the data set can be taken as the second active power change value.
[0072] Specifically, the second product of the quantile parameter and the first difference can be calculated first. The first difference is the difference between the number of active power change values in the data set and 1. Then, the integer and fractional parts of the second product are obtained. For example, if the quantile parameter is p and the number of active power change values in the data set is n, then the second product is (n-1)×p; if the second product (n-1)×p=i+j, where i is the integer part and j is the fractional part, the i-th active power change value in the data set, arranged in ascending order, is determined as the first active power change value, and the (i+1)-th active power change value in the data set, arranged in ascending order, is determined as the second active power change value, where i is equal to the integer part.
[0073] For example, if the quantile parameter is 0.75, the number of active power change values in the data set is 20, and the second product is (20-1)×0.75=14.25, then i=14, j=0.25; correspondingly, the 14th active power change value in the data set in ascending order is the first active power change value, and the 15th active power change value in the data set in ascending order is the second active power change value.
[0074] In step S2033, the predicted change value of active power is obtained based on the first change value of active power and the second change value of active power.
[0075] Once the first and second active power change values are determined, the most likely active power change value, i.e., the predicted active power change value, can be obtained from the cumulative probability distribution within the wind speed range and power calculation parameter range corresponding to the data set.
[0076] Specifically, the third product of the second difference and the first active power change value can be calculated first. The second difference is the difference between 1 and the decimal part. Then, the fourth product of the decimal part and the second active power change value can be calculated. Finally, the third sum of the third and fourth products can be calculated, and the third sum is determined as the predicted active power change value corresponding to the data set.
[0077] For example, as described in the example above, i is the integer part and j is the decimal part. The first active power change value is the i-th active power change value array[i] in ascending order in the data set, and the second active power change value is the (i+1)-th active power change value array[i+1] in ascending order in the data set. Then the third product is (1-j)×array[i], the fourth product is j×array[i+1], and the third sum is (1-j)×array[i]+j×array[i+1]. If the quantile parameter is 0.75, the number of active power change values in the data group is 20, the integer part i = 14, the fractional part j = 0.25, the first active power change value is the 14th active power change value in the data group in ascending order array
[14] = 10, the second active power change value is the 15th active power change value in the data group in ascending order array
[15] = 20, and correspondingly, the predicted active power change value is (1-0.25)×10+0.25×20 = 12.5.
[0078] In step S2034, for each data group, if the number of active power change values in the data group is less than or equal to the preset minimum group number threshold, the largest active power change value in the data group is determined as the predicted active power change value.
[0079] If the number of active power change values in a data set is less than or equal to the minimum threshold within the set, it indicates that the number of active power change values in the data set does not meet the sample size requirement for using the cumulative probability distribution algorithm, and is insufficient to support the algorithm. For data sets in this case, the largest active power change value in the data set can be determined as the predicted active power change value to avoid safety risks to the power control of wind turbine generators caused by excessively small predicted active power change values.
[0080] In some embodiments, the active power change values obtained from the acquired wind turbine generator operating data are invalid data. This invalid data not only fails to aid in the calculation of the predicted active power change values but also reduces the accuracy of the predicted active power change values. To further improve the accuracy of the predicted active power change values, the active power change values in the data set can be cleaned first, and the remaining active power change values after data cleaning can be used to predict the predicted active power change values. Figure 4 A flowchart of yet another embodiment of the active power change prediction method provided in this application. Figure 4 and Figure 2 The difference is that, Figure 4 The active power change prediction method shown may also include step S204.
[0081] In step S204, active power change values that meet the preset data cleaning conditions in the data group are removed.
[0082] Data cleaning conditions are used to filter out invalid data, specifically invalid active power change values. Removing invalid data constitutes data cleaning. The remaining valid data after data cleaning, i.e., valid active power change values, are then used in the prediction of active power change values to avoid invalid data being included in the prediction and affecting the accuracy of the active power change values. Data request conditions can be set according to the scenario and requirements, and are not limited here.
[0083] In some examples, data cleaning conditions may include one or more of the following:
[0084] The wind turbine generator unit corresponding to the change in active power is in an abnormal operating state;
[0085] The change in active power is less than zero;
[0086] The change in active power corresponds to a wind speed change that is less than zero;
[0087] The duration of the acquisition period corresponding to the change in active power is greater than the preset duration threshold;
[0088] The change in active power is less than the preset minimum power change threshold.
[0089] The active power change values of wind turbine generators in abnormal operating conditions have very low reference value and will affect the prediction of active power change values. Therefore, the active power change values of wind turbine generators in abnormal operating conditions need to be removed.
[0090] The power safety risk of wind turbine generators is related to excessive active power. The prediction of changes in active power mainly focuses on active power that increases over time. If active power decreases over time, it generally does not pose a power safety risk, so changes in active power less than zero can be removed.
[0091] The power safety risk of wind turbine generators is related to excessively high wind speeds. The prediction of active power change values mainly focuses on the active power at wind speeds that increase over time. If the wind speed decreases over time, it generally will not cause a power safety risk, so active power change values with wind speed changes less than zero can be removed.
[0092] If the duration of the data collection period is too long, the continuity of the collected data will decrease, and the accuracy of the obtained active power change value will also decrease, which will affect the accuracy of the prediction of the active power change value. Therefore, it is necessary to remove the active power change value corresponding to the data collection period with a duration longer than the preset duration threshold.
[0093] The minimum power change threshold is the boundary value for valid active power change values. Active power change values that are less than the minimum power change threshold are considered invalid data and therefore need to be removed.
[0094] Data cleaning can eliminate invalid data, ensuring that the active power change values used in the active power prediction are valid data, thereby further improving the accuracy of the predicted active power change values.
[0095] In some embodiments, wind turbine generators in the wind farm may also exist in abnormal operating conditions. These abnormal operating conditions may include wind turbine generators that have been under long-term power curtailment, wind turbine generators in a faulty state, etc., and are not limited thereto. Since the operating data of these abnormal operating wind turbine generators is not normal operating data, the predicted change in active power of these abnormal operating wind turbine generators cannot be calculated in the manner described in the above embodiments. As a redundant supplement to the active power change prediction method in the embodiments of this application, for a pair of wind speed zones and power calculation intervals, the average value of the predicted change in active power of each wind turbine generator corresponding to this pair of wind speed zones and power calculation intervals can be calculated. It should be noted that the wind turbine generators corresponding to the predicted change in active power participating in the average value calculation are wind turbine generators in normal operating conditions. This average value is determined as the predicted change in active power of the wind turbine generators in abnormal operating conditions within the pair of wind speed zones and power calculation intervals.
[0096] In some embodiments, to facilitate subsequent power control of wind farms including wind turbine generators, a power change relationship can be established that characterizes the correspondence between wind speed ranges, power calculation parameter ranges, and predicted active power changes for each wind turbine generator in the wind farm. During wind farm control, the predicted active power changes for each wind turbine generator in the wind farm within the corresponding wind speed range and power calculation parameter range can be directly obtained using the power change relationship. Figure 5 A flowchart of yet another embodiment of the active power change prediction method provided in this application. Figure 5 and Figure 2 The difference is that, Figure 5 The active power change prediction method shown may also include steps S205 and S206.
[0097] In step S205, the predicted changes in active power of each wind turbine generator set in the wind farm in each wind speed range and power calculation range are obtained.
[0098] A wind farm includes multiple wind turbine generators. The active power change prediction method described in the above embodiments can be used to obtain the predicted active power change values of each wind turbine generator in the wind farm in each wind speed range and power calculation range.
[0099] In step S206, a power change relationship is established based on the predicted changes in active power of each wind turbine generator set in each wind speed range and power calculation range.
[0100] The power change relationship is used to characterize the correspondence between the wind speed range, power calculation parameter range, and active power prediction change value of each wind turbine in a wind farm. It can be used to assess the active power during the power control process of a wind farm.
[0101] Power variation relationships can be represented as a set of tables or matrices, with each wind turbine in the wind farm corresponding to one table or one matrix. For example, Table 2 shows the correspondence between the wind speed range, power calculation parameter range, and predicted active power variation value for a wind turbine A1 in the wind farm.
[0102] Table 2
[0103]
[0104] As shown in Table 2, Table 2 contains the predicted active power change values C1 to C20 for each of the five wind speed intervals [V1, V2), [V2, V3), [V3, V4), [V4, V5), and [V5, V6] and four power calculation parameter intervals [r1, r2), [r2, r3), [r3, r4), and [r4, r5). Based on any wind speed interval and any power calculation parameter interval, the predicted active power change value under the corresponding operating conditions can be found. For example, under the operating conditions of the wind speed interval [V3, V4) and the power calculation parameter interval [r2, r3), the predicted active power change value for wind turbine generator A1 is C10.
[0105] This application provides a wind farm control method, which can be executed by a wind farm control device. The wind farm control device and the active power change prediction device in the above embodiments can be implemented as the same device, or as two independent devices, and are not limited thereto. Figure 6 A flowchart illustrating an embodiment of the wind farm control method provided in this application. Figure 6 As shown, the wind farm control method may include steps S301 to S305.
[0106] In step S301, the operating data of each wind turbine generator set in the wind farm is obtained.
[0107] Operating data includes current wind speed, current power calculation parameters, and current active power. The current power calculation parameters are related to the active power of the wind turbine generator, and the active power of the wind turbine generator can be calculated based on these parameters. In some examples, the current power calculation parameters may include, but are not limited to, one or more of the following: the current converter torque of the wind turbine generator, the current speed of the wind turbine generator, the current pitch angle of the wind turbine generator, the current yaw angle of the wind turbine generator, and the current grid-side current of the converter of the wind turbine generator.
[0108] A wind farm consists of multiple wind turbine generators. It is necessary to obtain the operating data of each wind turbine generator in the wind farm so as to determine the overall operating status of the wind farm based on the operating status of each wind turbine generator in subsequent processes.
[0109] In step S302, based on the preset power change relationship, the predicted change value of active power corresponding to the current wind speed and current power calculation parameters of each wind turbine generator is determined.
[0110] The power variation relationship is used to characterize the correspondence between wind speed ranges, power calculation parameter ranges, and predicted active power changes for each wind turbine generator in a wind farm. The power variation relationship is derived based on multiple data collections of wind speed, power calculation parameters, and active power changes for each wind turbine generator; specifically, the predicted active power changes in the power variation relationship are predicted using the active power variation prediction method described in the above embodiments. Based on the current wind speed of each wind turbine generator, the wind speed range in which the current wind speed falls can be determined. Based on the current power calculation parameters of each wind turbine generator, the power calculation parameter range in which the current power calculation parameters fall can be determined. Based on the determined wind speed range and power calculation parameter range, the predicted active power changes for each wind turbine generator can be obtained. The predicted active power changes corresponding to the current wind speed and current power calculation parameters for each wind turbine generator can characterize the change in active power of each wind turbine generator under the operating conditions of the current wind speed and current power calculation parameters.
[0111] The predicted change value of active power in the power change relationship is the predicted change value of active power obtained by using the active power change prediction method in the above embodiments. The prediction process of the predicted change value of active power can be found in the relevant description in the above embodiments, and will not be repeated here.
[0112] In step S303, the predicted change value of active power of the wind farm is determined based on the predicted change value of active power of each wind turbine generator in the wind farm.
[0113] In some examples, the sum of the predicted changes in active power of each wind turbine in a wind farm can be used as the predicted change in active power of the wind farm.
[0114] In other examples, the sum of the predicted changes in active power of each wind turbine generator in the wind farm can be corrected, and the corrected sum can be used as the predicted change in active power of the wind farm. Specifically, the first sum of the predicted changes in active power of each wind turbine generator in the wind farm can be calculated, and the first sum can be corrected using preset correction parameters. The corrected first sum can then be determined as the predicted change in active power of the wind farm. The correction parameters are wind farm-level correction parameters, which can be set according to the scenario and requirements, and are not limited here. For example, the predicted change in active power of the wind farm can be calculated according to the following formula (1):
[0115]
[0116] Wherein, ΔP rate P represents the predicted change in active power of the wind farm; δ is the correction parameter; rate (i) represents the predicted change in active power of the i-th wind turbine generator in the wind farm.
[0117] In step S304, when the predicted change in active power of the wind farm is greater than the active power margin threshold, the active power limit threshold for each wind turbine generator is determined based on the current active power, the active power margin threshold, and the predicted change in active power of each wind turbine generator.
[0118] The active power margin threshold is the maximum value at which the active power variation at the wind farm level meets safety requirements. If the predicted active power variation of a wind farm exceeds this active power margin threshold, it indicates a significant power safety risk for the wind farm, necessitating measures to mitigate this risk.
[0119] According to wind farm management requirements, the active power of new energy power plants must meet the requirements for the safe and stable operation of the power system. The limits for these limits should be determined by the power dispatching agency based on the frequency regulation characteristics of the connected power system. Correspondingly, the maximum limit for active power variation in wind farms will consider the maximum active power over one minute, the maximum active power over ten minutes, etc.
[0120] In some examples, the active power margin threshold in the embodiments of this application may be the minimum value among the first variation margin threshold, the second variation margin threshold, and the third variation margin threshold.
[0121] The first variation margin threshold is the difference between a preset maximum active power value and a preset minimum active power value over one minute. For example, the first variation margin threshold ΔP one =P omax -P omin , where P omax P represents the maximum active power in one minute.omin This represents the minimum active power over one minute. The maximum and minimum active power over one minute can be determined based on the scenario, requirements, experience, etc., and are not limited here. The difference between the maximum and minimum active power over one minute is the maximum value of the active power variation over one minute that meets safety requirements.
[0122] The second variation margin threshold is the difference between a preset maximum active power value over ten minutes and a preset minimum active power value over ten minutes. For example, the second variation margin threshold ΔP ten =P tmax -P tmin , where P tmax P represents the maximum active power over ten minutes. tmin This represents the minimum active power over ten minutes. The maximum and minimum active power over ten minutes can be determined based on the scenario, requirements, experience, etc., and are not limited here. The difference between the maximum and minimum active power over ten minutes is the maximum value of the active power variation over ten minutes that meets safety requirements.
[0123] The third variation margin threshold is the difference between the preset planned active power and the actual active power obtained. For example, the third variation margin threshold ΔP G =P G -P r , where P G For the planned active power, P r The actual active power is the power output. The planned active power is the active power assigned to the wind farm by the power dispatching agency. The actual active power is the sum of the current active power of each wind turbine in the wind farm, which is the actual active power of the wind farm. The difference between the planned and actual active power is the maximum margin required to meet safety requirements. Here, margin refers to the allowable capacity of the wind farm's active power.
[0124] By selecting the minimum value among the first, second, and third variation margin thresholds as the active power margin threshold, safety requirements can be further guaranteed, thus improving the accuracy of power safety risk assessment for wind farms.
[0125] Based on the current active power, active power margin threshold, and predicted active power change of each wind turbine, a corresponding active power limit threshold can be assigned to each wind turbine according to a certain proportion. It's not that all wind turbines in the wind farm operate under the same active power limit threshold. The active power limit threshold can be set for each wind turbine based on its power generation capacity and operating conditions, thus avoiding situations where power control of wind turbines does not match their power generation capacity, and improving the accuracy of power control in the wind farm.
[0126] In step S305, a power limiting control command is sent to each wind turbine generator set.
[0127] Power limiting control commands are used to control wind turbine generators to operate when their active power is below the active power limit threshold corresponding to the wind turbine generator. The active power limit threshold indicated by the power limiting control commands sent to each wind turbine generator may be different. Upon receiving a power limiting control command, the wind turbine generator may operate at an active power level below the active power limit threshold.
[0128] In this embodiment, based on the current wind speed and current power calculation parameters of each wind turbine in the wind farm, the predicted change value of active power corresponding to the current wind speed and current power calculation parameters of each wind turbine is determined from the power change relationship, which characterizes the correspondence between the wind speed range, power calculation parameter range, and predicted change value of active power for each wind turbine in the wind farm. The power change relationship is obtained based on multiple collections of wind speed, power calculation parameters, and active power change values of each wind turbine. Through statistical processing of a large amount of data, the power change relationship has higher accuracy, thereby making the predicted change value of active power for each wind turbine determined by the power change relationship more accurate. Based on the predicted change value of active power corresponding to each wind turbine, the predicted change value of active power for the wind farm is obtained. When active power limitation is required based on the predicted changes in active power of the wind farm, an appropriate active power limit threshold can be determined for each wind turbine based on its current active power, active power margin threshold, and predicted active power change. This ensures that each wind turbine operates within its designated active power limit threshold. Higher accuracy in the predicted changes in active power of the wind turbines leads to higher accuracy in the overall active power prediction of the wind farm. Consequently, the active power limit threshold determined based on the predicted changes in active power of the wind turbines shows better compatibility with the turbines, resulting in higher accuracy in wind farm control using these predicted changes.
[0129] The wind farm control method of this application embodiment, while satisfying the grid dispatch requirements for active power changes, can maximize the normal operation of the generator set, i.e., it is in a free power generation state, thereby reducing the frequency of wind turbine generator set power limitation, reducing machine fatigue caused by wind turbine generator set pitch, and also reducing the power generation lost due to wind turbine generator set power limitation, thus achieving a balance between power safety and power generation.
[0130] Because the data acquisition period in this embodiment is short, i.e., the data acquisition frequency of the wind turbine generator set is high, the predicted power change value obtained in this embodiment matches the one-minute and ten-minute active power change requirements related to wind farm control. This avoids a large time deviation between the acquired operating data and the one-minute and ten-minute active power change requirements related to wind farm control, thereby improving the accuracy of wind farm control, increasing the response speed of wind farm control, and enhancing the stability of wind farm control.
[0131] In some embodiments, a corresponding active power limit threshold may be allocated to each wind turbine generator set according to a certain ratio, but not all wind turbine generator sets in the wind farm are operated with limited power according to the same active power limit threshold. Figure 7 A flowchart of another embodiment of the wind farm control method provided in this application. Figure 7 and Figure 6 The difference is that, Figure 6 Step S304 can be further refined as follows: Figure 7 Steps S3041 and S3042 in the process.
[0132] In step S3041, for each wind turbine generator set, the first product of the margin allocation ratio and the predicted change in the active power of the wind turbine generator set is calculated.
[0133] The margin allocation ratio is the ratio of the active power margin threshold to the predicted change in active power of the wind farm.
[0134] In step S3042, the second sum of the current active power of the wind turbine generator set and the first product is calculated, and the second sum is determined as the active power limit threshold of the wind turbine generator set.
[0135] The first product represents the margin of change in active power allocated to the wind turbine generator according to the margin allocation ratio. The margin allocation ratio corresponding to the wind turbine generator characterizes the proportion of the margin of change in active power that matches the power generation capacity of the wind turbine generator. To ensure the power safety of the wind turbine generator, it is necessary to ensure that the wind turbine generator operates within the active power limit threshold of the wind turbine generator.
[0136] For example, the active power limit threshold of the i-th wind turbine generator in a wind farm can be calculated according to the following formulas (2) and (3):
[0137] P set (i)=P r (i)+γ×P rate (i) (2)
[0138]
[0139] Among them, P set (i) represents the active power limit threshold for the i-th wind turbine generator in the wind farm; P r (i) represents the current active power of the i-th wind turbine generator in the wind farm; γ represents the margin allocation ratio; P rate (i) represents the predicted change in active power of the i-th wind turbine generator in the wind farm; ΔP is the active power margin threshold; ΔP rate The value is the predicted change in active power of the wind farm. For specific calculation, please refer to formula (1) in the above embodiment.
[0140] In some embodiments, if the wind farm is not predicted to have a significant power safety risk, each wind turbine in the wind farm can operate freely to generate electricity. Figure 8 A flowchart of yet another embodiment of the wind farm control method provided in this application. Figure 8 and Figure 6 The difference is that, Figure 8 The wind farm control method shown may also include step S306.
[0141] In step S306, when the predicted change in active power of the wind farm is less than or equal to the active power margin threshold, the wind turbine generators are controlled to operate normally.
[0142] If the predicted change in active power of a wind farm is less than or equal to the active power margin threshold, it means that the wind farm is not predicted to have a power safety risk, and each wind turbine in the wind farm can operate normally, i.e., it is in a free power generation state.
[0143] In some embodiments, the power change relationship is updated using the current wind speed, current power calculation parameters, and current active power of each wind turbine generator set. The current wind speed, current power calculation parameters, and current active power of each wind turbine generator set in the wind farm acquired in this study can be used as samples. The active power change prediction method described in the above embodiments is used to obtain the updated predicted active power change values of the wind turbine generator sets in each wind speed interval and power calculation interval. These updated predicted active power change values are then used to update the power change relationship. For example, the current wind speed, current power calculation parameters, and current active power of each wind turbine generator set can be used as the operating data of the wind turbine generator sets in a new acquisition cycle. Steps S201, S202, S203, S205, and S206 in the above embodiments are then executed to obtain the updated power change relationship.
[0144] This application also provides an active power change prediction device, which can execute the active power change prediction method in the above embodiments. Figure 8 This is a schematic diagram of an embodiment of the active power change prediction device provided in this application. Figure 8 As shown, the active power change prediction device 400 may include an acquisition module 401, a data grouping module 402, and a prediction module 403.
[0145] The acquisition module 401 can be used to acquire the operating data of the wind turbine generator set in each acquisition cycle.
[0146] The operating data includes wind speed, power calculation parameters, and active power. The current power calculation parameters are related to the active power of the wind turbine generator.
[0147] In some examples, power calculation parameters include one or more of the following: the converter torque of the wind turbine, the rotational speed of the wind turbine, the pitch angle of the wind turbine, the yaw angle of the wind turbine, and the grid-side current of the converter of the wind turbine.
[0148] The data grouping module 402 can be used to group the active power change values of multiple acquisition cycles according to the wind speed range and power calculation parameter range divided by wind speed and power calculation parameters, and obtain two or more data groups.
[0149] Within the same data set, the wind speeds corresponding to changes in active power fall within the same wind speed range. Furthermore, the power calculation parameters corresponding to changes in active power within the same data set fall within the same power calculation parameter range.
[0150] The prediction module 403 can be used to predict the active power change value of the wind turbine generator set in each wind speed range and power calculation range based on the active power change value, the number of active power change values and the distribution of active power change values in each data group.
[0151] In this embodiment, operating data of the wind turbine generator is acquired in multiple acquisition cycles. The active power change values obtained using active power are grouped according to the wind speed and power calculation parameters in the operating data. Within the same data group, the wind speed corresponding to the active power change value lies within the same wind speed interval, and the power calculation parameters corresponding to the active power change value within the same data group lie within the same power calculation parameter interval. By analyzing the active power change values, the amount of active power change values, and the distribution of active power change values in each data group, the active power change value with the highest probability of occurrence under the corresponding wind speed interval and power calculation parameter interval can be predicted as the active power prediction change value. The accuracy of the predicted active power change values of the wind turbine generator in each wind speed interval and power calculation interval is higher. The active power prediction change value can be used to determine the active power prediction change value of the wind farm in wind farm control, so as to determine whether to implement power limiting control based on the active power prediction change value of the wind farm. Higher accuracy of the active power prediction change value leads to higher accuracy of wind farm control using the active power prediction change value.
[0152] In some examples, the prediction module 403 can be used to: for each data group, if the number of active power change values in the data group is greater than a preset minimum threshold, sort the active power change values in the data group in ascending order; use a preset quantile parameter and the number of active power change values in the data group to determine the first active power change value and the second active power change value located on both sides of the quantile position indicated by the quantile parameter in the data group; and predict the active power change value based on the first active power change value and the second active power change value.
[0153] Specifically, the prediction module 403 can also be used to: calculate the second product of the quantile parameter and the first difference, where the first difference is the difference between the number of active power change values in the data group and 1; obtain the integer part and the fractional part of the second product; determine the i-th active power change value in the data group in ascending order as the first active power change value, and determine the (i+1)-th active power change value in the data group in ascending order as the second active power change value, where i is equal to the integer part.
[0154] Specifically, the prediction module 403 can also be used to: calculate the third product of the second difference and the first active power change value, where the second difference is the difference between 1 and the decimal part; calculate the fourth product of the decimal part and the second active power change value; calculate the third sum of the third product and the fourth product, and determine the third sum as the active power prediction change value corresponding to the data group.
[0155] In some examples, the prediction module 403 can also be used to: for each data group, if the number of active power change values in the data group is less than or equal to a preset minimum group number threshold, determine the largest active power change value in the data group as the predicted active power change value.
[0156] In some examples, the prediction module 403 can also be used to: calculate the average value of the predicted change in active power of each wind turbine corresponding to a pair of wind speed zones and power calculation intervals; and determine the average value as the predicted change in active power of the wind turbine in an abnormal operating state in a pair of wind speed zones and power calculation intervals.
[0157] Figure 9 A schematic diagram of another embodiment of the active power change prediction device provided in this application. Figure 9 and Figure 8 The difference is that, Figure 9 The active power change prediction device 400 shown may also include a data cleaning module 404.
[0158] The data cleaning module 404 is used to remove active power change values in the data group that meet the preset data cleaning conditions.
[0159] In some examples, data cleaning conditions include one or more of the following:
[0160] The wind turbine generator unit corresponding to the change in active power is in an abnormal operating state;
[0161] The change in active power is less than zero;
[0162] The change in active power corresponds to a wind speed change that is less than zero;
[0163] The duration of the acquisition period corresponding to the change in active power is greater than the preset duration threshold;
[0164] The change in active power is less than the preset minimum power change threshold.
[0165] Figure 10 A schematic diagram of another embodiment of the active power change prediction device provided in this application. Figure 10 and Figure 8The difference is that the active power change prediction device 400 may include a field-level data acquisition module 405 and a relationship establishment module 406.
[0166] The data acquisition module 405 can be used to acquire the predicted changes in active power of each wind turbine generator in the wind farm in each wind speed range and power calculation range.
[0167] The relationship establishment module 406 can be used to establish a power change relationship based on the predicted changes in active power of each wind turbine generator in the wind farm in each wind speed range and power calculation range. The power change relationship is used to characterize the correspondence between the wind speed range, power calculation parameter range and predicted changes in active power of each wind turbine generator in the wind farm.
[0168] This application also provides a wind farm control device, which can be used to execute the wind farm control method in the above embodiments. Figure 11 This is a schematic diagram of an embodiment of the wind farm control device provided in this application. Figure 11 As shown, the wind farm control device 500 may include an acquisition module 501, a prediction module 502, a field-level calculation module 503, a limit threshold determination module 504, and a transmission module 505.
[0169] The acquisition module 501 can be used to acquire the operating data of each wind turbine generator in the wind farm.
[0170] The operational data includes current wind speed, current power calculation parameters, and current active power. The current power calculation parameters are related to the active power of the wind turbine generator.
[0171] In some examples, the current power calculation parameters include one or more of the following: the current converter torque of the wind turbine, the current speed of the wind turbine, the current pitch angle of the wind turbine, the current yaw angle of the wind turbine, and the current grid-side current of the wind turbine converter.
[0172] The prediction module 502 can be used to determine the predicted change value of active power corresponding to the current wind speed and current power calculation parameters of each wind turbine generator set in a preset power change relationship.
[0173] The power variation relationship is used to characterize the correspondence between wind speed ranges, power calculation parameter ranges, and predicted active power variations for each wind turbine generator in a wind farm. The power variation relationship is obtained based on multiple data collections of wind speed, power calculation parameters, and active power variations for each wind turbine generator.
[0174] The field-level calculation module 503 can be used to determine the predicted change value of the active power of the wind farm based on the predicted change value of the active power of each wind turbine generator in the wind farm.
[0175] The threshold determination module 504 can be used to determine the active power limit threshold for each wind turbine generator set when the predicted change value of active power in the wind farm is greater than the active power margin threshold. This threshold is determined based on the current active power, active power margin threshold, and predicted change value of active power for each wind turbine generator set.
[0176] In some examples, the active power margin threshold is the minimum of the first variation margin threshold, the second variation margin threshold, and the third variation margin threshold.
[0177] The first variation margin threshold is the difference between the preset maximum active power value and the preset minimum active power value within one minute. The second variation margin threshold is the difference between the preset maximum active power value and the preset minimum active power value within ten minutes. The third variation margin threshold is the difference between the preset planned active power and the actual active power obtained.
[0178] The transmitting module 505 can be used to send power limiting control commands to each wind turbine generator set.
[0179] The power limiting control command is used to control the operation of wind turbine generators when the active power is less than the active power limit threshold corresponding to the wind turbine generator.
[0180] In this embodiment, based on the current wind speed and current power calculation parameters of each wind turbine in the wind farm, the predicted change value of active power corresponding to the current wind speed and current power calculation parameters of each wind turbine is determined from the power change relationship, which characterizes the correspondence between the wind speed range, power calculation parameter range, and predicted change value of active power for each wind turbine in the wind farm. The power change relationship is obtained based on multiple collections of wind speed, power calculation parameters, and active power change values of each wind turbine. Through statistical processing of a large amount of data, the power change relationship has higher accuracy, thereby making the predicted change value of active power for each wind turbine determined by the power change relationship more accurate. Based on the predicted change value of active power corresponding to each wind turbine, the predicted change value of active power for the wind farm is obtained. When active power limitation is required based on the predicted changes in active power of the wind farm, an appropriate active power limit threshold can be determined for each wind turbine based on its current active power, active power margin threshold, and predicted active power change. This ensures that each wind turbine operates within its designated active power limit threshold. Higher accuracy in the predicted changes in active power of the wind turbines leads to higher accuracy in the overall active power prediction of the wind farm. Consequently, the active power limit threshold determined based on the predicted changes in active power of the wind turbines shows better compatibility with the turbines, resulting in higher accuracy in wind farm control using these predicted changes.
[0181] The wind farm control method of this application embodiment, while satisfying the grid dispatch requirements for active power changes, can maximize the normal operation of the generator set, i.e., it is in a free power generation state, thereby reducing the frequency of wind turbine generator set power limitation, reducing machine fatigue caused by wind turbine generator set pitch, and also reducing the power generation lost due to wind turbine generator set power limitation, thus achieving a balance between power safety and power generation.
[0182] Because the data acquisition period in this embodiment is short, i.e., the data acquisition frequency of the wind turbine generator set is high, the predicted power change value obtained in this embodiment matches the one-minute and ten-minute active power change requirements related to wind farm control. This avoids a large time deviation between the acquired operating data and the one-minute and ten-minute active power change requirements related to wind farm control, thereby improving the accuracy of wind farm control, increasing the response speed of wind farm control, and enhancing the stability of wind farm control.
[0183] In some examples, the field-level calculation module 503 can be used to: calculate the first sum of the predicted changes in active power of each wind turbine generator in the wind farm; correct the first sum using preset correction parameters, and determine the corrected first sum as the predicted changes in active power of the wind farm.
[0184] In some examples, the threshold determination module 504 can be used to: for each wind turbine generator set, calculate a first product of the margin allocation ratio and the predicted change in the active power of the wind turbine generator set, where the margin allocation ratio is the ratio of the active power margin threshold to the predicted change in the active power of the wind farm; calculate a second sum of the current active power of the wind turbine generator set and the first product; and determine the second sum as the active power limit threshold for the wind turbine generator set.
[0185] Figure 12 A schematic diagram of another embodiment of the wind farm control device provided in this application. Figure 12 and Figure 11 The difference is that, Figure 12 The wind farm control device shown may also include a control module 506 and an update module 507.
[0186] The control module 506 can be used to control the normal operation of each wind turbine generator set when the predicted change in active power of the wind farm is less than or equal to the active power margin threshold.
[0187] The update module 507 can be used to update the power change relationship using the current wind speed, current power calculation parameters and current active power of each wind turbine generator set.
[0188] This application also provides an active power change prediction device. Figure 13 This is a schematic diagram of an embodiment of the active power change prediction device provided in this application. Figure 13 As shown, the active power change prediction device 600 includes a memory 601, a processor 602, and a computer program stored in the memory 601 and capable of running on the processor 602.
[0189] In one example, the processor 602 described above may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits that may be configured to implement the embodiments of this application.
[0190] Memory 601 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the active power change prediction method according to this application.
[0191] The processor 602 runs a computer program corresponding to the executable program code stored in the memory 601 to implement the active power change prediction method in the above embodiments.
[0192] In one example, the active power change prediction device 600 may further include a communication interface 603 and a bus 604. Wherein, for example... Figure 13 As shown, the memory 601, processor 602, and communication interface 603 are connected through bus 604 and complete communication with each other.
[0193] The communication interface 603 is mainly used to enable communication between various modules, devices, units, and / or equipment in the embodiments of this application. Input devices and / or output devices can also be connected through the communication interface 603.
[0194] Bus 604 includes hardware, software, or both, that couples the components of the active power change prediction device 600 together. For example, and not limitingly, bus 604 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 604 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.
[0195] This application also provides a wind farm control device. Figure 14 This is a schematic diagram of the structure of an embodiment of the wind farm control equipment provided in this application. Figure 14 As shown, the active power change prediction device 700 includes a memory 701, a processor 702, and a computer program stored in the memory 701 and capable of running on the processor 702.
[0196] In one example, the processor 702 described above may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.
[0197] The memory 701 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the wind farm control method according to this application.
[0198] The processor 702 runs a computer program corresponding to the executable program code by reading the executable program code stored in the memory 701, so as to implement the wind farm control method in the above embodiments.
[0199] In one example, the wind farm control device 700 may also include a communication interface 703 and a bus 704. For example, Figure 14 As shown, the memory 701, processor 702, and communication interface 703 are connected through bus 704 and complete communication with each other.
[0200] The communication interface 703 is mainly used to enable communication between various modules, devices, units, and / or equipment in the embodiments of this application. Input devices and / or output devices can also be connected through the communication interface 703.
[0201] Bus 704 includes hardware, software, or both, that couples the components of wind farm control equipment 700 together. For example, and not limitingly, bus 704 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 704 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.
[0202] The active power change prediction device 600 and the wind farm control device 700 in the above embodiments can be implemented as the same device or as two independent devices, which is not limited here.
[0203] This application also provides a computer-readable storage medium storing computer program instructions. When executed by a processor, these instructions can implement the active power change prediction method and / or wind farm control method described in the above embodiments, achieving the same technical effects. To avoid repetition, these instructions will not be elaborated upon here. The aforementioned computer-readable storage medium may include non-transitory computer-readable storage media, such as read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, etc., and is not limited thereto.
[0204] It should be clarified that the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. For the device embodiments, equipment embodiments, and computer-readable storage medium embodiments, the relevant parts can be referred to the description section of the method embodiments. This application is not limited to the specific steps and structures described above and shown in the figures. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application. Furthermore, for the sake of brevity, detailed descriptions of known methods and techniques are omitted here.
[0205] The aspects of this application have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.
[0206] Those skilled in the art will understand that the above embodiments are exemplary and not restrictive. Different technical features appearing in different embodiments can be combined to achieve beneficial effects. Based on a study of the drawings, specification, and claims, those skilled in the art should be able to understand and implement other variations of the disclosed embodiments. In the claims, the term "comprising" does not exclude other means or steps; the quantifier "a" does not exclude a plurality; the terms "first" and "second" are used to identify names and not to indicate any particular order. No reference numerals in the claims should be construed as limiting the scope of protection. The functionality of multiple parts appearing in the claims can be implemented by a single hardware or software module. The appearance of certain technical features in different dependent claims does not mean that these technical features cannot be combined to achieve beneficial effects.
Claims
1. A wind farm control method, characterized in that, include: The system acquires the operating data of each wind turbine generator in the wind farm. The operating data includes the current wind speed, current power calculation parameters, and current active power. The current power calculation parameters are related to the active power of the wind turbine generator. In the preset power change relationship, the predicted change value of active power corresponding to the current wind speed and the current power calculation parameters of each wind turbine generator is determined. The power change relationship is used to characterize the correspondence between the wind speed range, power calculation parameter range and the predicted change value of active power of each wind turbine generator in the wind farm. The power change relationship is obtained based on the wind speed, power calculation parameters and active power change value of each wind turbine generator multiple times. The predicted change value of active power in the power change relationship is the active power change value with the highest probability of occurrence under the corresponding wind speed range and power calculation parameter range conditions. The active power change value is the change value of active power in two adjacent acquisition cycles. Based on the predicted change in active power of each wind turbine generator in the wind farm, the predicted change in active power of the wind farm is determined. If the predicted change in active power of the wind farm exceeds the active power margin threshold, the active power limit threshold for each wind turbine generator set is determined based on the current active power, the active power margin threshold, and the predicted change in active power. A power limiting control command is sent to each wind turbine generator set. The power limiting control command is used to control the wind turbine generator set to operate when the active power is less than the active power limit threshold corresponding to the wind turbine generator set.
2. The method according to claim 1, characterized in that, Based on the predicted changes in active power of each wind turbine generator in the wind farm, the predicted changes in active power of the wind farm are determined, including: Calculate the first sum of the predicted changes in active power of each wind turbine generator unit in the wind farm; The first sum is corrected using preset correction parameters, and the corrected first sum is determined as the predicted change value of the active power of the wind farm.
3. The method according to claim 1, characterized in that, The step of determining the active power limit threshold for each wind turbine generator set based on its current active power, active power margin threshold, and predicted active power change includes: For each wind turbine generator, calculate the first product of the margin allocation ratio and the predicted change in active power of the wind turbine generator, where the margin allocation ratio is the ratio of the active power margin threshold to the predicted change in active power of the wind farm. Calculate a second sum of the current active power of the wind turbine generator set and the first product, and determine the second sum as the active power limit threshold of the wind turbine generator set.
4. The method according to claim 1, characterized in that, Also includes: When the predicted change in active power of the wind farm is less than or equal to the active power margin threshold, the wind turbine generators are controlled to operate normally.
5. The method according to claim 1, characterized in that, The active power margin threshold is the minimum value among the first variation margin threshold, the second variation margin threshold, and the third variation margin threshold. The first change margin threshold is the difference between the preset maximum active power in one minute and the preset minimum active power in one minute; the second change margin threshold is the difference between the preset maximum active power in ten minutes and the preset minimum active power in ten minutes; and the third change margin threshold is the difference between the preset planned active power and the obtained actual active power.
6. The method according to claim 1, characterized in that, Also includes: The power change relationship is updated using the current wind speed, current power calculation parameters, and current active power of each wind turbine generator set.
7. The method according to any one of claims 1 to 6, characterized in that, The current power calculation parameters include one or more of the following: The current converter torque, current speed, current pitch angle, current yaw angle, and current grid-side current of the wind turbine generator set.
8. The method according to claim 1, characterized in that, Also includes: The operating data of the wind turbine generator set is acquired in each acquisition cycle; Based on the wind speed and power calculation parameter intervals, the active power change values from multiple acquisition cycles are grouped into two or more data sets. Within the same data set, the wind speed corresponding to the active power change value is in the same wind speed interval, and the power calculation parameter corresponding to the active power change value is in the same power calculation parameter interval. Based on the active power change value, the number of active power change values, and the distribution of active power change values in each data group, the predicted active power change value of the wind turbine generator set in each wind speed range and power calculation range is obtained.
9. The method according to claim 8, characterized in that, The step of predicting the active power change value of the wind turbine generator set in each wind speed range and power calculation range based on the active power change value, the number of active power change values, and the distribution of the active power change values in each data group includes: For each data group, if the number of active power change values in the data group is greater than a preset minimum group size threshold, the active power change values in the data group are sorted in ascending order. Using preset quantile parameters and the number of active power change values in the data group, determine the first active power change value and the second active power change value located on both sides of the quantile position indicated by the quantile parameters in the data group; The predicted change value of active power is obtained based on the first change value of active power and the second change value of active power.
10. The method according to claim 9, characterized in that, The step of determining the first and second active power change values located on either side of the quantile position indicated by the quantile parameter in the data set, using a preset quantile parameter and the number of active power change values in the data set, includes: Calculate the second product of the quantile parameter and the first difference, where the first difference is the difference between the number of active power change values in the data set and 1; Obtain the integer and fractional parts of the second product; The i-th active power change value in the data set, arranged in ascending order, is determined as the first active power change value, and the (i+1)-th active power change value in the data set, arranged in ascending order, is determined as the second active power change value, where i is equal to the integer part.
11. The method according to claim 10, characterized in that, The step of predicting the predicted change value of active power based on the first change value of active power and the second change value of active power includes: Calculate the third product of the second difference and the first active power change value, where the second difference is the difference between 1 and the decimal part; Calculate the fourth product of the fractional part and the second active power change value; Calculate the third sum of the third product and the fourth product, and determine the third sum as the predicted change value of active power corresponding to the data set.
12. The method according to claim 8, characterized in that, The step of predicting the active power change value of the wind turbine generator set in each wind speed range and power calculation range based on the active power change value, the number of active power change values, and the distribution of the active power change values in each data group includes: For each data group, if the number of active power change values in the data group is less than or equal to a preset minimum group size threshold, the largest active power change value in the data group is determined as the predicted active power change value.
13. The method according to claim 8, characterized in that, Before predicting the predicted change in active power of the wind turbine generator set in each wind speed range and power calculation range based on the active power change value, the number of active power change values, and the distribution of the active power change values in each of the data sets, the method further includes: Remove the active power change values from the data set that meet the preset data cleaning conditions.
14. The method according to claim 13, characterized in that, The data cleaning conditions include one or more of the following: The wind turbine generator set corresponding to the change in active power is in an abnormal operating state; The change in active power is less than zero; The wind speed change corresponding to the change in active power is less than zero; The duration of the acquisition period corresponding to the active power change value is greater than the preset duration threshold. The change in active power is less than a preset minimum power change threshold.
15. The method according to claim 8, characterized in that, Also includes: For a pair of wind speed zones and power calculation intervals, calculate the average value of the predicted change in active power of each wind turbine generator corresponding to the pair of wind speed zones and power calculation intervals; The average value is determined as the predicted change in active power of the wind turbine generator set in an abnormal operating state in the pair of wind speed zones and power calculation intervals.
16. The method according to claim 8, characterized in that, Also includes: Obtain the predicted changes in active power of each wind turbine generator unit in the wind farm in each wind speed range and power calculation range; Based on the predicted changes in active power of each wind turbine generator set in the wind farm in each wind speed range and power calculation range, a power change relationship is established. This power change relationship is used to characterize the correspondence between the wind speed range, power calculation parameter range, and the predicted changes in active power of each wind turbine generator set in the wind farm.
17. The method according to any one of claims 8 to 16, characterized in that, The power calculation parameters include one or more of the following: The converter torque of the wind turbine generator set, the speed of the wind turbine generator set, the pitch angle of the wind turbine generator set, the yaw angle of the wind turbine generator set, and the grid-side current of the converter of the wind turbine generator set.
18. A wind farm control device, characterized in that, include: The acquisition module is used to acquire the operating data of each wind turbine generator in the wind farm. The operating data includes the current wind speed, the current power calculation parameters, and the current active power. The current power calculation parameters are related to the active power of the wind turbine generator. The prediction module is used to determine the predicted change value of active power corresponding to the current wind speed and the current power calculation parameters of each wind turbine generator set in a preset power change relationship. The power change relationship is used to characterize the correspondence between the wind speed range, power calculation parameter range and predicted change value of active power of each wind turbine generator set in the wind farm. The power change relationship is obtained based on the wind speed, power calculation parameters and active power change value of each wind turbine generator set collected multiple times. The predicted change value of active power in the power change relationship is the active power change value with the highest probability of occurrence under the corresponding wind speed range and power calculation parameter range conditions. The active power change value is the change value of active power between two adjacent collection cycles. The field-level calculation module is used to determine the predicted change value of the active power of the wind farm based on the predicted change value of the active power of each wind turbine generator in the wind farm. The threshold determination module is used to determine the active power limit threshold for each wind turbine generator set based on the current active power, the active power margin threshold, and the active power prediction change value when the predicted change value of the active power of the wind farm is greater than the active power margin threshold. The sending module is used to send power limiting control commands to each wind turbine generator set. The power limiting control commands are used to control the wind turbine generator set to operate when the active power is less than the active power limit threshold corresponding to the wind turbine generator set.
19. A wind farm control device, characterized in that, include: Processor and memory storing computer program instructions; When the processor executes the computer program instructions, it implements the wind farm control method as described in any one of claims 1 to 17.
20. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the wind farm control method as described in any one of claims 1 to 17.
Citation Information
Patent Citations
Wind farm power scheduling method, device, and storage medium
CN110311401A
