Regional generating capacity prediction method and system of wind turbine generator
By integrating multi-dimensional wind turbine operation data and analyzing its temporal evolution patterns, the problems of insufficient accuracy and efficiency in traditional forecasting methods have been solved, and more accurate regional power generation forecasts have been achieved.
Patent Information
- Application Number
- CN202511336325.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-18
- Publication Date
- 2026-02-10
AI Technical Summary
Traditional wind turbine power generation prediction methods are unable to fully reflect the overall operating status of the unit and lack in-depth analysis of the dynamic trends of data changes, resulting in insufficient prediction accuracy and efficiency.
By integrating multi-dimensional operational data and calculating single-dimensional and multi-dimensional operational data metrics, the temporal evolution patterns of unit operational data are analyzed, and predictions are made in conjunction with actual regional power generation.
It improves the accuracy and efficiency of regional power generation forecasting, providing reliable support for optimized wind farm operation and stable grid dispatch.
Smart Images
Figure CN121507682A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of wind turbine technology, and more specifically, to a method and system for predicting regional power generation of wind turbines. Background Technology
[0002] With the transformation of the global energy structure and the rapid development of renewable energy, wind energy, as a clean and sustainable energy form, is increasingly widely used in power systems. As the core equipment for wind power generation, the power generation efficiency and operational stability of wind turbines directly affect the reliability and economy of the power grid. Therefore, accurate prediction of wind turbine power generation, especially regional power generation prediction, has become a key technical issue in wind farm operation management and grid dispatch.
[0003] Traditional wind turbine power generation prediction methods are mostly based on historical power data, employing machine learning or physical modeling techniques. However, these traditional methods have certain limitations in practical applications: on the one hand, wind turbine operating data is characterized by high dimensionality, nonlinearity, and strong randomness, making single-dimensional data analysis often insufficient to comprehensively reflect the overall operating status of the turbine; on the other hand, the processing of wind turbine operating data often focuses on instantaneous values or simple statistical characteristics (such as mean and variance), lacking in-depth analysis of the dynamic trends of the data and failing to effectively capture the temporal evolution of the operating status. Summary of the Invention
[0004] This invention provides a method and system for predicting regional power generation of wind turbines. This invention can effectively integrate multi-dimensional operating data, effectively analyze the temporal evolution of turbine operating data, improve the accuracy and efficiency of regional power generation prediction, and provide reliable support for the optimized operation of wind farms and the stable dispatch of the power grid.
[0005] To achieve the above objectives, the present invention provides a method for predicting the regional power generation of wind turbine generators, comprising: Receive power generation prediction instructions, obtain the unit operation data of wind turbines at each collection time within a preset time period before the current time, and integrate all the unit operation data to obtain multiple unit operation data sets; The data collection time is divided into multiple time periods, and a single-dimensional operation data metric value of the wind turbine is calculated based on each time period and the unit operation data group. All single-dimensional operational data metrics are analyzed, and multi-dimensional operational data metrics of the wind turbine are calculated based on the analysis results. The actual regional power generation of the wind turbine at the current time is obtained, and the regional predicted power generation of the wind turbine is obtained based on the multi-dimensional operation data metric and the actual regional power generation.
[0006] Furthermore, before receiving the power generation forecast instruction, it also includes: Obtain the previous instruction and determine the instruction type of the previous instruction; The power generation prediction instruction is matched with the instruction category of the previous instruction, and it is determined whether the power generation prediction instruction is the same as the previous instruction. If the power generation prediction instruction matches the instruction category of the previous instruction, then it is determined that the power generation prediction instruction is the same as the previous instruction, the first time node for sending the power generation prediction instruction is collected, and the second time node for sending the previous instruction is collected. Calculate the time node difference between the first time node and the second time node, and determine whether the power generation prediction instruction can be processed based on the relationship between the time node difference and the preset time node difference. If the time node difference is greater than or equal to the preset time node difference, then it is determined that the power generation prediction instruction can be processed. If the time node difference is less than the preset time node difference, it is determined that the power generation prediction instruction cannot be processed, and a log reminder is generated and sent. If the power generation prediction instruction does not match the instruction category of the previous instruction, it is determined that the power generation prediction instruction is different from the previous instruction, and the power generation prediction instruction is processed.
[0007] Furthermore, when calculating the single-dimensional operational data metric of the wind turbine based on each time period and the unit's operational data set, the calculation includes: Each q data collection moments is considered as a time interval; Calculate the variance of unit operation data for all units within each time period; By fitting the variance of all unit operating data, a straight line of unit operating data variance is obtained; Determine all slopes corresponding to the variance line of the unit's operating data, and take the mean of the slopes as the single-dimensional operating data metric of the wind turbine unit.
[0008] Furthermore, when analyzing all single-dimensional operational data metrics and calculating the multi-dimensional operational data metrics of the wind turbine based on the analysis results, the process includes: Curve fitting is performed on all single-dimensional operational data metrics to obtain single-dimensional operational data metric curves; The multi-dimensional operating data metric of the wind turbine is calculated based on the single-dimensional operating data metric curve.
[0009] Furthermore, when performing curve fitting on all single-dimensional operational data metrics to obtain single-dimensional operational data metric curves, this includes: For each single-dimensional running data metric, a horizontal axis value is generated, wherein the horizontal axis value includes 1, 2, 3, ..., w, where w is the number of single-dimensional running data metrics; Using the single-dimensional operational data metric as the vertical axis and the horizontal axis corresponding to each single-dimensional operational data metric as the horizontal axis, a single-dimensional operational data metric curve is obtained.
[0010] Furthermore, when calculating the multi-dimensional operational data metric of the wind turbine based on the single-dimensional operational data metric curve, the calculation includes: Determine the median dividing line of the single-dimensional operational data metric curve; Collect the single-dimensional operational data metric values on the single-dimensional operational data metric value curve that are greater than the median dividing line, and generate the first single-dimensional operational data metric value sequence. Statistically analyze the single-dimensional operational data metric values on the single-dimensional operational data metric value curve that are less than or equal to the median dividing line, and generate a second single-dimensional operational data metric value sequence. Determine the first sequence mean corresponding to the first single-dimensional running data metric value sequence; A first preset adjustment coefficient and a second preset adjustment coefficient are preset, wherein the first preset adjustment coefficient is less than the second preset adjustment coefficient; Calculate the first product of the first preset adjustment coefficient and the mean of the first sequence, and use it as the first boundary value; Calculate the second product of the second preset adjustment coefficient and the mean of the first sequence, and use it as the second boundary value; The first boundary range is determined based on the first boundary value and the second boundary value, and the first single-dimensional running data metric value sequence is traversed to count the number of first single-dimensional running data metric values falling into the first boundary range. Determine the second sequence mean corresponding to the second single-dimensional running data metric sequence; Calculate the third product of the first preset adjustment coefficient and the mean of the second sequence, and use it as the third boundary value; Calculate the fourth product of the second preset adjustment coefficient and the mean of the second sequence, and use it as the fourth boundary value; The second boundary range is determined based on the third boundary value and the fourth boundary value, and the second single-dimensional running data metric value sequence is traversed to count the number of second single-dimensional running data metric values falling into the second boundary range. The multi-dimensional operation data metric of the wind turbine is calculated based on the number of the first single-dimensional operation data metric and the number of the second single-dimensional operation data metric.
[0011] Further, when calculating the multi-dimensional operational data metric of the wind turbine based on the number of the first single-dimensional operational data metric and the number of the second single-dimensional operational data metric, the calculation includes: A first calculation weight is configured for the number of the first single-dimensional running data metric values, and a second calculation weight is configured for the number of the second single-dimensional running data metric values, wherein the first calculation weight is greater than the second calculation weight; The multi-dimensional operational data metrics of the wind turbine generator are calculated using the following formula: ; Where y represents the multi-dimensional operation data metric of the wind turbine, u1 is the first calculation weight, p1 is the number of the first single-dimensional operation data metric, and s i For the i-th single-dimensional running data metric that falls within the first boundary range, s i+1 For the (i+1)th single-dimensional running data metric falling within the first boundary range, u2 is the second calculated weight, p2 is the number of second single-dimensional running data metrics, and g d For the d-th single-dimensional running data metric that falls within the second boundary range, g d+1 This is the (d+1)th single-dimensional running data metric that falls within the second boundary range.
[0012] Furthermore, when obtaining the regional predicted power generation of the wind turbine based on the multi-dimensional operational data metrics and the actual regional power generation, the process includes: Pre-set the first preset multi-dimensional operational data metric value and the second preset multi-dimensional operational data metric value; Pre-set the first preset adjustment value, the second preset adjustment value, and the third preset adjustment value; When the multi-dimensional operation data metric value is less than the first preset multi-dimensional operation data metric value, the product of the first preset adjustment value and the actual regional power generation is determined as the regional predicted power generation of the wind turbine. When the multi-dimensional operation data metric value is greater than or equal to the first preset multi-dimensional operation data metric value and less than the second preset multi-dimensional operation data metric value, the product of the second preset adjustment value and the actual regional power generation is determined as the regional predicted power generation of the wind turbine. When the multi-dimensional operating data metric is greater than or equal to the second preset multi-dimensional operating data metric, the product of the third preset adjustment value and the actual regional power generation is determined as the regional predicted power generation of the wind turbine.
[0013] To achieve the above objectives, the present invention also provides a regional power generation prediction system for wind turbine generators, comprising: The data acquisition module is used to receive power generation prediction instructions, acquire the unit operation data of the wind turbine at each collection time within a preset time before the current time, and integrate all the unit operation data to obtain multiple unit operation data groups. The first calculation module is used to divide the collection time into multiple time periods, and calculate the single-dimensional operation data metric value of the wind turbine based on each time period and the unit operation data group. The second calculation module is used to analyze all single-dimensional operational data metrics and calculate the multi-dimensional operational data metrics of the wind turbine based on the analysis results. The power generation prediction module is used to obtain the actual regional power generation of the wind turbine at the current time, and to obtain the regional predicted power generation of the wind turbine based on the multi-dimensional operation data measurement value and the actual regional power generation.
[0014] Furthermore, it also includes: The instruction judgment module is used for: Obtain the previous instruction and determine the instruction type of the previous instruction; The power generation prediction instruction is matched with the instruction category of the previous instruction, and it is determined whether the power generation prediction instruction is the same as the previous instruction. If the power generation prediction instruction matches the instruction category of the previous instruction, then it is determined that the power generation prediction instruction is the same as the previous instruction, the first time node for sending the power generation prediction instruction is collected, and the second time node for sending the previous instruction is collected. Calculate the time node difference between the first time node and the second time node, and determine whether the power generation prediction instruction can be processed based on the relationship between the time node difference and the preset time node difference. If the time node difference is greater than or equal to the preset time node difference, then it is determined that the power generation prediction instruction can be processed. If the time node difference is less than the preset time node difference, it is determined that the power generation prediction instruction cannot be processed, and a log reminder is generated and sent. If the power generation prediction instruction does not match the instruction category of the previous instruction, it is determined that the power generation prediction instruction is different from the previous instruction, and the power generation prediction instruction is processed.
[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention discloses a method and system for predicting regional power generation of wind turbines. The method involves acquiring wind turbine operation data from various time points within a preset time period prior to the current time, integrating this data to obtain multiple sets of wind turbine operation data; dividing the acquisition time into multiple time periods, and calculating single-dimensional operation data metrics for the wind turbines based on each time period and the wind turbine operation data sets; analyzing all single-dimensional operation data metrics to calculate multi-dimensional operation data metrics for the wind turbines; obtaining the actual regional power generation of the wind turbines at the current time; and obtaining the predicted regional power generation of the wind turbines based on the multi-dimensional operation data metrics and the actual regional power generation. This method effectively integrates multi-dimensional operation data, effectively analyzes the temporal evolution of wind turbine operation data, improves the accuracy and efficiency of regional power generation prediction, and provides reliable support for the optimized operation of wind farms and the stable dispatch of the power grid. Attached Figure Description
[0016] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A flowchart illustrating a method for predicting regional power generation of a wind turbine generator according to an embodiment of the present invention is shown. Figure 2 A schematic diagram of a regional power generation prediction system for a wind turbine generator set is shown in an embodiment of the present invention. Detailed Implementation
[0017] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.
[0018] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.
[0019] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.
[0020] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.
[0021] The following is a description of preferred embodiments of the present invention in conjunction with the accompanying drawings.
[0022] like Figure 1 As shown, an embodiment of the present invention discloses a method for predicting regional power generation of wind turbine units, including: S110: Receives power generation prediction instructions, obtains the unit operation data of the wind turbine at each collection time within the preset time before the current time, and integrates all the unit operation data to obtain multiple unit operation data groups. In this embodiment, the preset duration is pre-set and includes multiple collection times. The preferred number of collection times is 20, specifically including: the 1st hour, the 2nd hour, the 3rd hour, the 4th hour, the 5th hour, the 6th hour, the 7th hour, the 8th hour, the 9th hour, the 10th hour, the 11th hour, the 12th hour, the 13th hour, the 14th hour, the 15th hour, the 16th hour, the 17th hour, the 18th hour, the 19th hour, and the 20th hour.
[0023] In this embodiment, the unit operation data includes wind speed data, nacelle vibration data, and power generation data, which are not shown one by one here.
[0024] In this embodiment, each data collection moment includes multiple unit operation data.
[0025] In this embodiment, all unit operation data are integrated, that is, unit operation data of the same type are classified, such as wind speed data corresponding to the first hour, wind speed data corresponding to the second hour, wind speed data corresponding to the third hour, etc., and integrated to obtain a unit operation data group for wind speed data. It is also possible to obtain a unit operation data group for engine room vibration data and a unit operation data group for power generation data.
[0026] In some embodiments of this application, before receiving the power generation prediction instruction, the method further includes: Obtain the previous instruction and determine the instruction type of the previous instruction; The power generation prediction instruction is matched with the instruction category of the previous instruction, and it is determined whether the power generation prediction instruction is the same as the previous instruction. If the power generation prediction instruction matches the instruction category of the previous instruction, then it is determined that the power generation prediction instruction is the same as the previous instruction, the first time node for sending the power generation prediction instruction is collected, and the second time node for sending the previous instruction is collected. Calculate the time node difference between the first time node and the second time node, and determine whether the power generation prediction instruction can be processed based on the relationship between the time node difference and the preset time node difference. If the time node difference is greater than or equal to the preset time node difference, then it is determined that the power generation prediction instruction can be processed. If the time node difference is less than the preset time node difference, it is determined that the power generation prediction instruction cannot be processed, and a log reminder is generated and sent. If the power generation prediction instruction does not match the instruction category of the previous instruction, it is determined that the power generation prediction instruction is different from the previous instruction, and the power generation prediction instruction is processed.
[0027] In this embodiment, the previous instruction includes voltage detection, current detection, etc.
[0028] In this embodiment, the preset time node difference is preferably 12 hours, that is, no power generation prediction operation will be performed within 12 hours.
[0029] The beneficial effects of the above technical solution are: the present invention matches the power generation prediction instruction with the instruction category of the previous instruction and determines whether the power generation prediction instruction is the same as the previous instruction. This can not only ensure normal power generation prediction operation, but also avoid repeated power generation prediction and avoid increasing workload.
[0030] S120: Divide the collection time into multiple time periods, and calculate the single-dimensional operation data metric of the wind turbine based on each time period and the unit operation data group; In some embodiments of this application, when calculating the single-dimensional operational data metric of the wind turbine based on each time period and the turbine operation data set, the following is included: Each q data collection moments is considered as a time interval; Calculate the variance of unit operation data for all units within each time period; By fitting the variance of all unit operating data, a straight line of unit operating data variance is obtained; Determine all slopes corresponding to the variance line of the unit's operating data, and take the mean of the slopes as the single-dimensional operating data metric of the wind turbine unit.
[0031] In this embodiment, every 4 acquisition times are taken as a time period, which means 5 time periods can be obtained.
[0032] In this embodiment, a single-dimensional operational data metric value corresponding to each unit's operational data group can be obtained.
[0033] In this embodiment, data with different dimensions can also be eliminated by calculating the single-dimensional running data metric.
[0034] The beneficial effects of the above technical solution are: the present invention determines all slopes corresponding to the variance line of the unit operation data and takes the average slope as the single-dimensional operation data metric of the wind turbine, thereby realizing the analysis of single-dimensional unit operation data and feeding back the fluctuation pattern of the overall unit operation data through the single-dimensional operation data metric.
[0035] S130: Analyze all single-dimensional operational data metrics and calculate the multi-dimensional operational data metrics of the wind turbine based on the analysis results; In some embodiments of this application, when analyzing all single-dimensional operational data metrics and calculating the multi-dimensional operational data metrics of the wind turbine based on the analysis results, the process includes: Curve fitting is performed on all single-dimensional operational data metrics to obtain single-dimensional operational data metric curves; The multi-dimensional operating data metric of the wind turbine is calculated based on the single-dimensional operating data metric curve.
[0036] In some embodiments of this application, when performing curve fitting on all single-dimensional operational data metrics to obtain single-dimensional operational data metric curves, the following steps are included: For each single-dimensional running data metric, a horizontal axis value is generated, wherein the horizontal axis value includes 1, 2, 3, ..., w, where w is the number of single-dimensional running data metrics; Using the single-dimensional operational data metric as the vertical axis and the horizontal axis corresponding to each single-dimensional operational data metric as the horizontal axis, a single-dimensional operational data metric curve is obtained.
[0037] In this embodiment, curve fitting will not be discussed in detail.
[0038] The beneficial effects of the above technical solution are: the present invention uses the single-dimensional operational data metric as the vertical axis and the horizontal axis corresponding to each single-dimensional operational data metric as the horizontal axis to obtain the single-dimensional operational data metric curve, which lays the foundation for the analysis of multi-dimensional operational data metric.
[0039] In some embodiments of this application, calculating the multi-dimensional operational data metric of the wind turbine based on the single-dimensional operational data metric curve includes: Determine the median dividing line of the single-dimensional operational data metric curve; Collect the single-dimensional operational data metric values on the single-dimensional operational data metric value curve that are greater than the median dividing line, and generate the first single-dimensional operational data metric value sequence. Statistically analyze the single-dimensional operational data metric values on the single-dimensional operational data metric value curve that are less than or equal to the median dividing line, and generate a second single-dimensional operational data metric value sequence. Determine the first sequence mean corresponding to the first single-dimensional running data metric value sequence; A first preset adjustment coefficient and a second preset adjustment coefficient are preset, wherein the first preset adjustment coefficient is less than the second preset adjustment coefficient; Calculate the first product of the first preset adjustment coefficient and the mean of the first sequence, and use it as the first boundary value; Calculate the second product of the second preset adjustment coefficient and the mean of the first sequence, and use it as the second boundary value; The first boundary range is determined based on the first boundary value and the second boundary value, and the first single-dimensional running data metric value sequence is traversed to count the number of first single-dimensional running data metric values falling into the first boundary range. Determine the second sequence mean corresponding to the second single-dimensional running data metric sequence; Calculate the third product of the first preset adjustment coefficient and the mean of the second sequence, and use it as the third boundary value; Calculate the fourth product of the second preset adjustment coefficient and the mean of the second sequence, and use it as the fourth boundary value; The second boundary range is determined based on the third boundary value and the fourth boundary value, and the second single-dimensional running data metric value sequence is traversed to count the number of second single-dimensional running data metric values falling into the second boundary range. The multi-dimensional operation data metric of the wind turbine is calculated based on the number of the first single-dimensional operation data metric and the number of the second single-dimensional operation data metric.
[0040] In this embodiment, the minimum bounding rectangle of the single-dimensional running data metric curve is determined. The minimum bounding rectangle is the smallest rectangle that can completely enclose the single-dimensional running data metric curve. The four sides of the minimum bounding rectangle are extended to obtain two sides perpendicular to the horizontal axis, and the median of these two sides is determined as the median dividing line.
[0041] In this embodiment, the first preset adjustment coefficient is preferably 0.9, and the second preset adjustment coefficient is preferably 1.1.
[0042] The beneficial effects of the above technical solution are: the present invention calculates the multi-dimensional operating data measurement value of the wind turbine based on the number of first single-dimensional operating data measurement values and the number of second single-dimensional operating data measurement values, which ensures the calculation accuracy of the multi-dimensional operating data measurement value, integrates the unit operating data of multiple dimensions, and thus ensures the prediction accuracy and prediction efficiency of regional power generation.
[0043] In some embodiments of this application, when calculating the multi-dimensional operational data metric of the wind turbine based on the number of the first single-dimensional operational data metric and the number of the second single-dimensional operational data metric, the calculation includes: A first calculation weight is configured for the number of the first single-dimensional running data metric values, and a second calculation weight is configured for the number of the second single-dimensional running data metric values, wherein the first calculation weight is greater than the second calculation weight; The multi-dimensional operational data metrics of the wind turbine generator are calculated using the following formula: ; Where y represents the multi-dimensional operation data metric of the wind turbine, u1 is the first calculation weight, p1 is the number of the first single-dimensional operation data metric, and s i For the i-th single-dimensional running data metric that falls within the first boundary range, s i+1 For the (i+1)th single-dimensional running data metric falling within the first boundary range, u2 is the second calculated weight, p2 is the number of second single-dimensional running data metrics, and g d For the d-th single-dimensional running data metric that falls within the second boundary range, g d+1 This is the (d+1)th single-dimensional running data metric that falls within the second boundary range.
[0044] In this embodiment, the first calculation weight and the second calculation weight can be assigned according to the subjective weighting method and the objective weighting method. Here, the first calculation weight is preferably 0.7 and the second calculation weight is preferably 0.3.
[0045] S140: Obtain the actual regional power generation of the wind turbine at the current time, and obtain the regional predicted power generation of the wind turbine based on the multi-dimensional operation data metric and the actual regional power generation.
[0046] In some embodiments of this application, when obtaining the regional predicted power generation of the wind turbine based on the multi-dimensional operational data metrics and the actual regional power generation, the following steps are included: Pre-set the first preset multi-dimensional operational data metric value and the second preset multi-dimensional operational data metric value; Pre-set the first preset adjustment value, the second preset adjustment value, and the third preset adjustment value; When the multi-dimensional operation data metric value is less than the first preset multi-dimensional operation data metric value, the product of the first preset adjustment value and the actual regional power generation is determined as the regional predicted power generation of the wind turbine. When the multi-dimensional operation data metric value is greater than or equal to the first preset multi-dimensional operation data metric value and less than the second preset multi-dimensional operation data metric value, the product of the second preset adjustment value and the actual regional power generation is determined as the regional predicted power generation of the wind turbine. When the multi-dimensional operating data metric is greater than or equal to the second preset multi-dimensional operating data metric, the product of the third preset adjustment value and the actual regional power generation is determined as the regional predicted power generation of the wind turbine.
[0047] In this embodiment, the first preset multi-dimensional operation data metric value is preferably 8, and the second preset multi-dimensional operation data metric value is preferably 12. The specific values can be adjusted according to actual needs.
[0048] In this embodiment, the first preset adjustment value is preferably 0.85, the second preset adjustment value is preferably 1.15, and the third preset adjustment value is preferably 1.25. The specific values can be adjusted according to actual needs.
[0049] The beneficial effects of the above technical solution are: the present invention selects the corresponding preset adjustment value based on the multi-dimensional operation data measurement value, the first preset multi-dimensional operation data measurement value and the second preset multi-dimensional operation data measurement value, so as to realize the dynamic adjustment of the actual regional power generation, improve the prediction accuracy and prediction efficiency of regional power generation, and provide reliable support for the optimized operation of wind farms and the stable dispatch of power grid.
[0050] To further illustrate the technical concept of this invention, the technical solution of this invention will now be described in conjunction with specific application scenarios.
[0051] Correspondingly, such as Figure 2 As shown, this application also provides a regional power generation prediction system for wind turbine generators, comprising: The data acquisition module is used to receive power generation prediction instructions, acquire the unit operation data of the wind turbine at each collection time within a preset time before the current time, and integrate all the unit operation data to obtain multiple unit operation data groups. The first calculation module is used to divide the collection time into multiple time periods, and calculate the single-dimensional operation data metric value of the wind turbine based on each time period and the unit operation data group. The second calculation module is used to analyze all single-dimensional operational data metrics and calculate the multi-dimensional operational data metrics of the wind turbine based on the analysis results. The power generation prediction module is used to obtain the actual regional power generation of the wind turbine at the current time, and to obtain the regional predicted power generation of the wind turbine based on the multi-dimensional operation data measurement value and the actual regional power generation.
[0052] In some embodiments of this application, it also includes: The instruction judgment module is used for: Obtain the previous instruction and determine the instruction type of the previous instruction; The power generation prediction instruction is matched with the instruction category of the previous instruction, and it is determined whether the power generation prediction instruction is the same as the previous instruction. If the power generation prediction instruction matches the instruction category of the previous instruction, then it is determined that the power generation prediction instruction is the same as the previous instruction, the first time node for sending the power generation prediction instruction is collected, and the second time node for sending the previous instruction is collected. Calculate the time node difference between the first time node and the second time node, and determine whether the power generation prediction instruction can be processed based on the relationship between the time node difference and the preset time node difference. If the time node difference is greater than or equal to the preset time node difference, then it is determined that the power generation prediction instruction can be processed. If the time node difference is less than the preset time node difference, it is determined that the power generation prediction instruction cannot be processed, and a log reminder is generated and sent. If the power generation prediction instruction does not match the instruction category of the previous instruction, it is determined that the power generation prediction instruction is different from the previous instruction, and the power generation prediction instruction is processed.
[0053] In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.
[0054] Although the invention has been described above with reference to embodiments, various modifications can be made and components can be replaced with equivalents without departing from the scope of the invention. In particular, as long as there is no structural conflict, the features in the embodiments disclosed in this invention can be combined with each other in any way. The fact that not all of these combinations are described in this specification is merely for the sake of brevity and resource conservation.
[0055] It will be understood by those skilled in the art that the above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A method for predicting regional power generation of wind turbine units, characterized in that, include: Receive power generation prediction instructions, obtain the unit operation data of wind turbines at each collection time within a preset time period before the current time, and integrate all the unit operation data to obtain multiple unit operation data sets; The data collection time is divided into multiple time periods, and a single-dimensional operation data metric value of the wind turbine is calculated based on each time period and the unit operation data group. All single-dimensional operational data metrics are analyzed, and multi-dimensional operational data metrics of the wind turbine are calculated based on the analysis results; The actual regional power generation of the wind turbine at the current time is obtained, and the regional predicted power generation of the wind turbine is obtained based on the multi-dimensional operation data metric and the actual regional power generation.
2. The regional power generation prediction method for wind turbine units according to claim 1, characterized in that, Before receiving the power generation forecast instruction, it also includes: Obtain the previous instruction and determine the instruction type of the previous instruction; The power generation prediction instruction is matched with the instruction category of the previous instruction, and it is determined whether the power generation prediction instruction is the same as the previous instruction. If the power generation prediction instruction matches the instruction category of the previous instruction, then it is determined that the power generation prediction instruction is the same as the previous instruction, the first time node for sending the power generation prediction instruction is collected, and the second time node for sending the previous instruction is collected. Calculate the time node difference between the first time node and the second time node, and determine whether the power generation prediction instruction can be processed based on the relationship between the time node difference and the preset time node difference. If the time node difference is greater than or equal to the preset time node difference, then it is determined that the power generation prediction instruction can be processed. If the time node difference is less than the preset time node difference, it is determined that the power generation prediction instruction cannot be processed, and a log reminder is generated and sent. If the power generation prediction instruction does not match the instruction category of the previous instruction, it is determined that the power generation prediction instruction is different from the previous instruction, and the power generation prediction instruction is processed.
3. The regional power generation prediction method for wind turbine units according to claim 1, characterized in that, When calculating the single-dimensional operational data metric of the wind turbine based on each time period and the turbine's operational data set, the following is included: Each q data collection moments is considered as a time interval; Calculate the variance of unit operation data for all units within each time period; By fitting the variance of all unit operating data, a straight line of unit operating data variance is obtained; Determine all slopes corresponding to the variance line of the unit's operating data, and take the mean of the slopes as the single-dimensional operating data metric of the wind turbine unit.
4. The regional power generation prediction method for wind turbine units according to claim 1, characterized in that, When analyzing all single-dimensional operational data metrics and calculating the multi-dimensional operational data metrics of the wind turbine based on the analysis results, the following are included: Curve fitting is performed on all single-dimensional operational data metrics to obtain single-dimensional operational data metric curves; The multi-dimensional operating data metric of the wind turbine is calculated based on the single-dimensional operating data metric curve.
5. The regional power generation prediction method for wind turbine units according to claim 4, characterized in that, When performing curve fitting on all single-dimensional operational data metrics to obtain single-dimensional operational data metric curves, the following are included: For each single-dimensional running data metric, a horizontal axis value is generated, wherein the horizontal axis value includes 1, 2, 3, ..., w, where w is the number of single-dimensional running data metrics; Using the single-dimensional operational data metric as the vertical axis and the horizontal axis corresponding to each single-dimensional operational data metric as the horizontal axis, a single-dimensional operational data metric curve is obtained.
6. The regional power generation prediction method for wind turbine units according to claim 4, characterized in that, When calculating the multi-dimensional operational data metric of the wind turbine based on the single-dimensional operational data metric curve, the following steps are included: Determine the median dividing line of the single-dimensional operational data metric curve; Collect the single-dimensional operational data metric values on the single-dimensional operational data metric value curve that are greater than the median dividing line, and generate the first single-dimensional operational data metric value sequence. Statistically analyze the single-dimensional operational data metric values on the single-dimensional operational data metric value curve that are less than or equal to the median dividing line, and generate a second single-dimensional operational data metric value sequence. Determine the first sequence mean corresponding to the first single-dimensional running data metric value sequence; A first preset adjustment coefficient and a second preset adjustment coefficient are preset, wherein the first preset adjustment coefficient is less than the second preset adjustment coefficient; Calculate the first product of the first preset adjustment coefficient and the mean of the first sequence, and use it as the first boundary value; Calculate the second product of the second preset adjustment coefficient and the mean of the first sequence, and use it as the second boundary value; The first boundary range is determined based on the first boundary value and the second boundary value, and the first single-dimensional running data metric value sequence is traversed to count the number of first single-dimensional running data metric values falling into the first boundary range. Determine the second sequence mean corresponding to the second single-dimensional running data metric sequence; Calculate the third product of the first preset adjustment coefficient and the mean of the second sequence, and use it as the third boundary value; Calculate the fourth product of the second preset adjustment coefficient and the mean of the second sequence, and use it as the fourth boundary value; The second boundary range is determined based on the third boundary value and the fourth boundary value, and the second single-dimensional running data metric value sequence is traversed to count the number of second single-dimensional running data metric values falling into the second boundary range. The multi-dimensional operation data metric of the wind turbine is calculated based on the number of the first single-dimensional operation data metric and the number of the second single-dimensional operation data metric.
7. The regional power generation prediction method for wind turbine units according to claim 6, characterized in that, When calculating the multi-dimensional operational data metric of the wind turbine based on the number of the first single-dimensional operational data metric and the number of the second single-dimensional operational data metric, the calculation includes: A first calculation weight is configured for the number of the first single-dimensional running data metric values, and a second calculation weight is configured for the number of the second single-dimensional running data metric values, wherein the first calculation weight is greater than the second calculation weight; The multi-dimensional operational data metrics of the wind turbine generator are calculated using the following formula: ； Where y represents the multi-dimensional operation data metric of the wind turbine, u1 is the first calculation weight, p1 is the number of the first single-dimensional operation data metric, and s i For the i-th single-dimensional running data metric that falls within the first boundary range, s i+1 For the (i+1)th single-dimensional running data metric falling within the first boundary range, u2 is the second calculated weight, p2 is the number of second single-dimensional running data metrics, and g d For the d-th single-dimensional running data metric that falls within the second boundary range, g d+1 This is the (d+1)th single-dimensional running data metric that falls within the second boundary range.
8. The regional power generation prediction method for wind turbine units according to claim 1, characterized in that, When obtaining the regional predicted power generation of the wind turbine based on the multi-dimensional operational data metrics and the actual regional power generation, the following steps are included: Pre-set the first preset multi-dimensional operational data metric value and the second preset multi-dimensional operational data metric value; Pre-set the first preset adjustment value, the second preset adjustment value, and the third preset adjustment value; When the multi-dimensional operation data metric value is less than the first preset multi-dimensional operation data metric value, the product of the first preset adjustment value and the actual regional power generation is determined as the regional predicted power generation of the wind turbine. When the multi-dimensional operation data metric value is greater than or equal to the first preset multi-dimensional operation data metric value and less than the second preset multi-dimensional operation data metric value, the product of the second preset adjustment value and the actual regional power generation is determined as the regional predicted power generation of the wind turbine. When the multi-dimensional operating data metric is greater than or equal to the second preset multi-dimensional operating data metric, the product of the third preset adjustment value and the actual regional power generation is determined as the regional predicted power generation of the wind turbine.
9. A regional power generation prediction system for wind turbine generators, applied to the regional power generation prediction method for wind turbine generators as described in any one of claims 1-8, characterized in that, include: The data acquisition module is used to receive power generation prediction instructions, acquire the unit operation data of the wind turbine at each collection time within a preset time before the current time, and integrate all the unit operation data to obtain multiple unit operation data groups. The first calculation module is used to divide the collection time into multiple time periods, and calculate the single-dimensional operation data metric value of the wind turbine based on each time period and the unit operation data group. The second calculation module is used to analyze all single-dimensional operational data metrics and calculate the multi-dimensional operational data metrics of the wind turbine based on the analysis results. The power generation prediction module is used to obtain the actual regional power generation of the wind turbine at the current time, and to obtain the regional predicted power generation of the wind turbine based on the multi-dimensional operation data measurement value and the actual regional power generation.
10. The regional power generation prediction system for wind turbine units according to claim 9, characterized in that, Also includes: The instruction judgment module is used for: Obtain the previous instruction and determine the instruction type of the previous instruction; The power generation prediction instruction is matched with the instruction category of the previous instruction, and it is determined whether the power generation prediction instruction is the same as the previous instruction. If the power generation prediction instruction matches the instruction category of the previous instruction, then it is determined that the power generation prediction instruction is the same as the previous instruction, the first time node for sending the power generation prediction instruction is collected, and the second time node for sending the previous instruction is collected. Calculate the time node difference between the first time node and the second time node, and determine whether the power generation prediction instruction can be processed based on the relationship between the time node difference and the preset time node difference. If the time node difference is greater than or equal to the preset time node difference, then it is determined that the power generation prediction instruction can be processed. If the time node difference is less than the preset time node difference, it is determined that the power generation prediction instruction cannot be processed, and a log reminder is generated and sent. If the power generation prediction instruction does not match the instruction category of the previous instruction, it is determined that the power generation prediction instruction is different from the previous instruction, and the power generation prediction instruction is processed.