Wind farm power prediction method and device

Abstract

The present disclosure relates to a wind farm power prediction method and device. The method comprises obtaining wind farm power data, wherein the wind farm power data includes power prediction data and power correction data; inputting the power prediction data into a power prediction model to obtain a first power prediction result; correcting the first power prediction result based on the power correction data and the unit operating status to obtain at least one power correction result; and multiplying the first power prediction result by the at least one power correction result to obtain a target power prediction result. Thus, based on the power prediction model and in combination with the unit operating status, the power prediction result is corrected, thereby improving the accuracy of the power prediction result.

Description

Technical Field

[0001] The present disclosure relates to the technical field of wind power generation, and in particular to a method and device for predicting wind farm power. Background Art

[0002] At present, with the continuous increase in the installed capacity of wind turbines, the impact of wind power output on grid stability is becoming more and more obvious. Therefore, providing timely and accurate wind power prediction methods is an important research direction.

[0003] Related art wind farm power forecasting methods typically use meteorological or power data as time series data to develop prediction models and algorithms, without considering the turbine's own operating conditions. However, in the entire wind power forecasting process, meteorological conditions are only one factor affecting forecast accuracy; the turbine's own operating conditions are more likely to affect the accuracy of the forecast results. Summary of the Invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides a wind farm power prediction method and device.

[0005] According to a first aspect of an embodiment of the present disclosure, a wind farm power prediction method is provided, comprising: obtaining wind farm power data, wherein the wind farm power data comprises: power prediction data and power correction data; inputting the power prediction data into a power prediction model to obtain a first power prediction result; correcting the first power prediction result according to the power correction data and the operating status of the unit to obtain at least one power correction result; and multiplying the first power prediction result and the at least one power correction result to obtain a target power prediction result.

[0006] According to a second aspect of an embodiment of the present disclosure, a wind farm power prediction device is provided, comprising: an acquisition module for acquiring wind farm power data, wherein the wind farm power data comprises: power prediction data and power correction data; an input module for inputting the power prediction data into a power prediction model to obtain a first power prediction result; a correction module for correcting the first power prediction result according to the power correction data and the operating status of the unit to obtain at least one power correction result; and a processing module for multiplying the first power prediction result and the at least one power correction result to obtain a target power prediction result.

[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the steps of the wind farm power prediction method provided in the first aspect of the present disclosure.

[0008] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the wind farm power prediction method provided in the first aspect of the present disclosure are implemented.

[0009] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided. When the computer program is executed by a processor of an electronic device, the electronic device can perform the steps of the wind farm power prediction method provided in the embodiment of the first aspect of the present disclosure as described above.

[0010] The technical solutions provided by the embodiments of the present disclosure may have the following beneficial effects:

[0011] The method involves obtaining wind farm power data, wherein the wind farm power data includes power prediction data and power correction data; inputting the power prediction data into a power prediction model to obtain a first power prediction result; correcting the first power prediction result based on the power correction data and the unit operating status to obtain at least one power correction result; and multiplying the first power prediction result by the at least one power correction result to obtain a target power prediction result. Thus, based on the power prediction model and in combination with the unit operating status, the power prediction result is corrected, thereby improving the accuracy of the power prediction result.

[0012] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0014] Figure 1 is a flow chart showing a method for predicting wind farm power according to an exemplary embodiment;

[0015] Figure 2 is a flow chart showing a method for determining a power correction result corresponding to a fault repair time according to an exemplary embodiment;

[0016] Figure 3 is a schematic diagram of the maintenance assessment module;

[0017] Figure 4 is a flowchart illustrating a method for determining a power correction result corresponding to a scheduled inspection plan according to an exemplary embodiment;

[0018] Figure 5 It is a schematic diagram of the scheduled inspection and evaluation module;

[0019] Figure 6is a flow chart showing a method for determining a power correction result corresponding to a fault prediction situation according to an exemplary embodiment;

[0020] Figure 7 is a schematic diagram of the fault prediction module;

[0021] Figure 8 is a flow chart showing a method for determining a power correction result corresponding to a reduced power operation state according to an exemplary embodiment;

[0022] Figure 9 is a schematic diagram of the power reduction assessment module;

[0023] Figure 10 is a flow chart showing a method for determining a power correction result corresponding to an extreme weather condition according to an exemplary embodiment;

[0024] Figure 11 is a schematic diagram of the extreme weather assessment module;

[0025] Figure 12 is a block diagram of a wind farm power prediction device according to an exemplary embodiment;

[0026] Figure 13 It is a block diagram of an electronic device for implementing the method of the embodiment of the present disclosure, according to an exemplary embodiment. DETAILED DESCRIPTION

[0027] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0028] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the corresponding data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0029] Figure 1 This is a flowchart of a wind farm power prediction method according to an exemplary embodiment, wherein it should be noted that the wind farm power prediction method of this embodiment is executed by a wind farm power prediction device, and the wind farm power prediction device can be implemented by software and / or hardware. The wind farm power prediction device can be configured in an electronic device. The following description is given by taking the execution subject as an electronic device as an example.

[0030] like Figure 1 As shown, the wind farm power prediction method includes the following steps:

[0031] In step 101, wind farm power data is acquired, wherein the wind farm power data includes power prediction data and power correction data.

[0032] Among them, power prediction data includes: unit operation data, unit space data, and meteorological data; power correction data includes: unit operation data, meteorological data, faulty units, and maintenance plan data.

[0033] In step 102, power prediction data is input into a power prediction model to obtain a first power prediction result.

[0034] In the disclosed embodiment, the unit operation data and meteorological data are input into a pre-trained power prediction model to obtain the power of all wind turbines in the field for a period of time in the future, that is, the first power prediction result.

[0035] The power prediction data is used as input and the power in a future period is used as output, and the power prediction model is trained to obtain a power prediction model.

[0036] Alternatively, assuming that the power data for the next 4 hours with a time resolution of 15 minutes is predicted, and there are 20 units in the field, a 20×16 power prediction matrix is ​​obtained, where the rows of the matrix represent the units and the columns of the matrix represent the power prediction results for each 15 minutes in the future.

[0037] In step 103, the first power prediction result is corrected according to the power correction data and the unit operating status to obtain at least one power correction result.

[0038] Among them, the operating status of the unit includes: fault repair time, regular inspection plan, fault prediction, reduced power operating status and extreme weather conditions.

[0039] As a possible implementation method, based on the power correction data, the first power prediction result is corrected according to the fault repair time, regular inspection plan, fault prediction situation, reduced power operating status and extreme weather conditions, and the power correction results corresponding to the fault repair time, regular inspection plan, fault prediction situation, reduced power operating status and extreme weather conditions are obtained.

[0040] In step 104, the first power prediction result and at least one power correction result are multiplied to obtain a target power prediction result.

[0041] As a possible implementation, the first power prediction result is multiplied by the power correction result corresponding to the fault repair time to obtain a first power prediction result; the first power prediction result is multiplied by the power correction result corresponding to the scheduled inspection plan to obtain a second power prediction result; the second power prediction result is multiplied by the power correction result corresponding to the fault prediction condition to obtain a third power prediction result; the third power prediction result is multiplied by the power correction result corresponding to the reduced power operation state to obtain a fourth power prediction result; and the fourth power prediction result is multiplied by the power correction result corresponding to the extreme weather condition to obtain a target power prediction result. The order in which the first power prediction result and at least one power correction result are multiplied can be freely selected.

[0042] As a possible implementation method, after obtaining the target power prediction result, it is also possible to: based on the target prediction period, add up all units at different prediction moments to obtain the power prediction result of the entire wind farm in the target prediction period.

[0043] Optionally, taking a total of 20 units in the field and predicting power data for the next 4 hours with a time resolution of 15 minutes as an example, the first power prediction result is a 20×16 matrix, and the power correction results corresponding to the fault repair time, scheduled inspection plan, fault prediction situation, reduced power operation status and extreme weather conditions are 5 20×16 matrices. Multiply the first power prediction result by the power correction result corresponding to the fault repair time to obtain a 20×16 matrix. Similarly, perform 5 multiplications to obtain the target power prediction result, and finally obtain a 20×16 matrix. Add up all the units in the target power prediction result, that is, add up the rows of the matrix to obtain a 1×16 matrix, which is the power prediction result of the entire wind farm for the next 4 hours.

[0044] In summary, wind farm power data is obtained, where the wind farm power data includes power prediction data and power correction data; the power prediction data is input into a power prediction model to obtain a first power prediction result; the first power prediction result is corrected based on the power correction data and the unit operating status to obtain at least one power correction result; and the first power prediction result and the at least one power correction result are multiplied to obtain a target power prediction result. Thus, based on the power prediction model and in combination with the unit operating status, the power prediction result is corrected, thereby improving the accuracy of the power prediction result.

[0045] In the above embodiment, the influence of fault repair time on wind farm power is taken into consideration, so the power prediction result needs to be corrected according to the fault repair time to improve the accuracy of the power prediction result. The specific process of the electronic device performing step 103 is as follows: Figure 2 As shown, this may include:

[0046] In step 201, it is determined whether there is a faulty unit.

[0047] In the embodiment of the present disclosure, fault scanning is performed on the units of the wind farm to obtain the fault conditions of the units and the maintenance status sequence of the units.

[0048] In step 202, when there is no faulty unit, the first power prediction result is not corrected, and the first power prediction result is the corresponding power correction result.

[0049] Alternatively, taking a total of 20 units in the field as an example, if there is no faulty unit, the maintenance status sequence for the next 4 hours is directly output, and all elements in the sequence are 1, that is, no power correction is performed.

[0050] In step 203, when there is a faulty unit, a fault repair sequence is determined, and the first power prediction result is corrected according to the fault repair sequence to obtain a power correction result corresponding to the fault repair time.

[0051] As a possible implementation method, the maintenance experience database is queried according to the fault type to obtain the fault repair time; if the fault repair time is less than or equal to the preset time period, the corresponding value in the fault repair sequence is recorded as 1; if the fault repair time is greater than the preset time period, the corresponding value in the fault repair sequence is recorded as 0.

[0052] like Figure 3 As shown, Figure 3 Figure 1 is a schematic diagram of the maintenance assessment module. Taking the target predicted power for the next four hours as an example, if a faulty unit exists, the fault must be classified to obtain a fault category. The maintenance experience database is then searched based on the fault category to estimate the fault repair time. This results in a sequence of fault repair results for the next four hours. If a unit's fault cannot be repaired within the next four hours, the unit's maintenance status is 0, the corresponding value in the fault repair sequence is recorded as 0, and the first power prediction result at the corresponding time point multiplied by the maintenance status is 0. If a unit's fault can be repaired within the next four hours, the unit's maintenance status is 1, the corresponding value in the fault repair sequence is recorded as 1, and the power correction result at the corresponding time point is the first power prediction result, completing the power correction process.

[0053] Among them, the maintenance experience database estimates the fault repair time based on the maintenance plan, maintenance difficulty, and maintenance personnel ratio of historical similar faults.

[0054] In the above embodiment, the influence of the regular inspection plan on the wind farm power is taken into consideration, so the power prediction result needs to be corrected according to the regular inspection plan to improve the accuracy of the power prediction result. The specific process of the electronic device executing step 103 is as follows: Figure 4As shown, this may include:

[0055] In step 401, it is determined whether there is a scheduled inspection plan for each unit.

[0056] In the disclosed embodiment, each unit of the wind farm is scanned to determine whether there is a regular inspection plan for each unit, wherein the regular inspection plan includes half-year inspection, annual inspection, technical improvement and other plans.

[0057] In step 402, when there is no scheduled inspection plan, the first power prediction result is not corrected, and the first power prediction result is the corresponding power correction result.

[0058] As a possible implementation method, if there is no scheduled inspection plan, the element values ​​in the scheduled inspection status sequence are all 1, and no correction is performed on the prediction result.

[0059] In step 403, if a regular inspection plan exists, a regular inspection state sequence is determined, and the first power prediction result is corrected according to the regular inspection state sequence to obtain a power correction result corresponding to the regular inspection plan.

[0060] As a possible implementation method, if there is a scheduled inspection plan, the specific maintenance time period, maintenance unit, maintenance time and expected completion time are determined, and then the scheduled inspection status sequence is obtained, the first power prediction result of each unit is corrected, and finally the power prediction result of the entire wind farm is corrected.

[0061] like Figure 5 As shown, Figure 5 Figure 1 is a schematic diagram of the scheduled inspection evaluation module. Taking the target power forecast for the next four hours as an example, the module scans the scheduled inspection plan for each unit to determine whether one exists. If no scheduled inspection plan exists, the first power forecast result is not corrected, and a scheduled inspection status sequence of all 1s is directly output. If a maintenance plan exists, the module determines the specific maintenance time period, unit to be repaired, maintenance time, and expected completion time. This sequence is then used to derive the power forecast for each unit, ultimately correcting the power forecast for the entire wind farm.

[0062] In the above embodiment, since the fault will affect the wind farm power, it is necessary to predict the unit fault and then modify the power prediction result according to the fault prediction to improve the accuracy of the power prediction result. The unit operation status includes: fault prediction status; then, the specific process of the electronic device performing step 103 is as follows: Figure 6 As shown, this may include:

[0063] In step 601, the operating data of each unit is obtained and a characteristic factor library is obtained.

[0064] In the embodiment of the present disclosure, the operating data of the unit is obtained, and features are extracted from the operating data in combination with the accumulated fault case library to generate a feature factor library.

[0065] In step 602, fault prediction is performed on each unit based on the machine learning model to obtain a fault prediction sequence, wherein the input of the machine learning model is a feature factor library, and the output of the machine learning model is the fan parameters.

[0066] Optionally, a machine learning model is trained using the feature factor library as input and wind turbine parameters as output to obtain a trained machine learning model. Wind turbine parameters include temperature, pressure, and the like, such as gearbox oil temperature and generator bearing temperature.

[0067] As a possible implementation method, when the fan parameter is greater than a preset threshold, the corresponding value in the fault prediction sequence is recorded as 0; when the fan parameter is less than or equal to the preset threshold, the corresponding value in the fault prediction sequence is recorded as 1.

[0068] Optionally, when the fan parameter is greater than a preset threshold, it is judged that a fault is about to occur, and the corresponding value in the fault prediction sequence is recorded as 0; when the fan parameter is less than or equal to the preset threshold, it is judged that a fault will not occur, and the corresponding value in the fault prediction sequence is recorded as 1.

[0069] In step 603, the first power prediction result is corrected according to the fault prediction sequence to obtain a power correction result corresponding to the fault prediction situation.

[0070] As a possible implementation manner, the fault prediction sequence is multiplied by the first power prediction result to obtain a power correction result.

[0071] like Figure 7 As shown, Figure 7 This is a schematic diagram of the fault prediction module. Taking the target power forecast for the next four hours as an example, the unit's operating data is obtained. Combined with the accumulated fault case library, this data is feature extracted to generate a feature factor library. A machine learning model is used to predict wind turbine parameters, and trend analysis is performed on the predicted results. When a specific wind turbine parameter exceeds a preset threshold, a fault is determined to be imminent, and the unit cannot continue operating. Based on the trend analysis results, a fault state sequence is generated, which is mapped one-to-one to the first power forecast result. The first power forecast result is then corrected by multiplying the corresponding matrices.

[0072] In the above embodiment, in order to protect the safety of the unit, the unit will reduce power when the vibration is large and the temperature of key components is high. Therefore, it is necessary to correct the power prediction result according to the reduced power operation state to improve the accuracy of the power prediction result. The specific process of the electronic device performing step 103 is as follows: Figure 8 As shown, this may include:

[0073] In step 801, the operating data of each unit is obtained and the power reduction category is obtained.

[0074] In the embodiment of the present disclosure, the operating data of each unit is obtained, and the power reduction category is analyzed based on experience.

[0075] Among them, the power reduction categories include: gearbox oil temperature high temperature power limit, gearbox bearing high temperature power limit, generator bearing high temperature power limit, generator winding high temperature power limit, converter high temperature power limit, unit excessive vibration power limit, etc.

[0076] In step 802, the power reduction release time is evaluated according to the power reduction category to obtain a power reduction state sequence.

[0077] In the embodiment of the present disclosure, if the power reduction release time is less than or equal to the preset time length, it means that the power reduction will be released within the preset time length, and the corresponding value in the power reduction state sequence is recorded as 1; if the power reduction release time is greater than the preset time length, it means that the power reduction will not be released within the preset time length, and the corresponding value in the power reduction state sequence is recorded as 0.

[0078] In step 803, the first power prediction result is corrected according to the power reduction state sequence to obtain a power correction result corresponding to the power reduction operation state.

[0079] As a possible implementation manner, the power reduction state sequence is multiplied by the first power prediction result to obtain a power correction result.

[0080] like Figure 9 As shown, Figure 9 Figure 1 is a schematic diagram of the power reduction assessment module. Taking the target power forecast for the next four hours as an example, the module obtains unit operating data and analyzes component power reduction categories based on expert experience. Different power reduction types are identified, and the power reduction duration and release time are evaluated to obtain a power reduction state sequence for the next four hours. The power reduction state sequence is then mapped one-to-one with the first power forecast result, and the two are multiplied to achieve power correction.

[0081] In the above embodiment, considering the impact of wind farm power caused by unit shutdown due to extreme weather, it is necessary to correct the power prediction results according to the extreme weather conditions to improve the accuracy of the power prediction results. The specific process of the electronic device performing step 103 is as follows: Figure 10 As shown, this may include:

[0082] In step 1001, the operating data and meteorological data of each unit are obtained, wherein the meteorological data includes wind speed data and icing data.

[0083] In step 1002, a storm state sequence is obtained based on the operating data and wind speed data of each unit.

[0084] As a possible implementation method, if the wind speed is greater than the unit's cut-out wind speed, the corresponding value in the storm state sequence is recorded as 0; if the wind speed is less than or equal to the unit's cut-out wind speed, the corresponding value in the storm state sequence is recorded as 1.

[0085] In step 1003, an icing state sequence is obtained based on the operating data and icing data of each unit.

[0086] As a possible implementation method, the operating data and icing data of each unit are input into the meteorological icing prediction model to obtain the meteorological icing prediction result; when the meteorological icing prediction result is icing, the corresponding value in the icing state sequence is recorded as 0; when the meteorological icing prediction result is no icing, the corresponding value in the icing state sequence is recorded as 1.

[0087] The meteorological icing prediction model is trained using turbine operating data and feature data extracted from this data as input, and icing status as output. The turbine operating data includes ambient temperature, humidity, hub temperature, tower bottom temperature, turbine power, speed, pitch angle, and pitch motor temperature. Feature data extracted from this data includes actual power / theoretical power (power ratio), temperature difference (difference between hub temperature and ambient temperature), ambient temperature difference, and power / speed (power-speed ratio).

[0088] In step 1004, the first power prediction result is corrected according to the storm state sequence and / or the icing state sequence to obtain a power correction result corresponding to the extreme weather condition.

[0089] like Figure 11 As shown, Figure 11 This is a schematic diagram of the extreme weather assessment module. Taking the target power forecast for the next four hours as an example, unit operating and meteorological data are obtained. For out-of-range wind speed forecasts, the wind speed state for the next four hours is predicted, and a shutdown decision is made based on the unit's cut-out wind speed as the threshold. This generates a sequence of storm states for the next four hours, and the initial power forecast is corrected. For meteorological icing predictions, a meteorological icing prediction model is trained based on the unit's operating data and feature data extracted from this data. Using this trained icing prediction model, the icing state for the next four hours is predicted, resulting in a sequence of icing states for the next four hours, which is then used to correct the initial power forecast.

[0090] Figure 12 FIG. 1 is a block diagram of a wind farm power prediction device according to an exemplary embodiment. Figure 12The device 1200 includes: an acquisition module 1210, an input module 1220, a first correction module 1230 and a summing module 1240.

[0091] The acquisition module 1210 is configured to acquire wind farm power data, wherein the wind farm power data includes power prediction data and power correction data;

[0092] An input module 1220 is configured to input the power prediction data into a power prediction model to obtain a first power prediction result;

[0093] A correction module 1230 is configured to correct the first power prediction result according to the power correction data and the unit operating status to obtain at least one power correction result;

[0094] The processing module 1240 is configured to multiply the first power prediction result and the at least one power correction result to obtain a target power prediction result.

[0095] As an implementation method of an embodiment of the present disclosure, the unit operating status includes: fault repair time; the correction module 1230 includes: a determination unit, a first correction unit and a second correction unit; wherein the determination unit is used to determine whether there is a faulty unit; the first correction unit is used to not correct the first power prediction result when the faulty unit does not exist, and the first power prediction result is the corresponding power correction result; the second correction unit is used to determine the fault repair sequence when the faulty unit exists, and correct the first power prediction result according to the fault repair sequence to obtain the power correction result corresponding to the fault repair time.

[0096] As an implementation of an embodiment of the present disclosure, the second correction unit is specifically configured to query a maintenance experience database according to the fault type to obtain a fault repair time; if the fault repair time is less than or equal to a preset time period, the corresponding value in the fault repair sequence is recorded as 1; if the fault repair time is greater than the preset time period, the corresponding value in the fault repair sequence is recorded as 0.

[0097] As an implementation method of an embodiment of the present disclosure, the unit operating status includes: a regular inspection plan; the correction module 1230 is specifically used to determine whether each unit has the regular inspection plan; if the regular inspection plan does not exist, the first power prediction result is not corrected, and the first power prediction result is the corresponding power correction result; if the regular inspection plan exists, a regular inspection state sequence is determined, and the first power prediction result is corrected according to the regular inspection state sequence to obtain the power correction result corresponding to the regular inspection plan.

[0098] As an implementation method of an embodiment of the present disclosure, the unit operating status includes: a fault prediction situation; the correction module 1230 includes: a first acquisition unit, a first prediction unit and a third correction unit; wherein, the first acquisition unit is used to obtain the operating data of each unit and obtain a characteristic factor library; the first prediction unit is used to perform fault prediction on each unit based on a machine learning model to obtain a fault prediction sequence, wherein the input of the machine learning model is the characteristic factor library, and the output of the machine learning model is the fan parameter; the third correction unit is used to correct the first power prediction result according to the fault prediction sequence to obtain a power correction result corresponding to the fault prediction situation.

[0099] As an implementation method of an embodiment of the present disclosure, the prediction unit is specifically used to, when the fan parameter is greater than a preset threshold, record the corresponding numerical value in the fault prediction sequence as 0; when the fan parameter is less than or equal to the preset threshold, record the corresponding numerical value in the fault prediction sequence as 1.

[0100] As an implementation method of an embodiment of the present disclosure, the unit operating status includes: a reduced power operating status; the correction module 1230 is specifically used to obtain the operating data of each unit and obtain a reduced power category; evaluate the power reduction release time according to the reduced power category to obtain a reduced power status sequence; according to the reduced power status sequence, correct the first power prediction result to obtain a power correction result corresponding to the reduced power operating status.

[0101] As an implementation method of an embodiment of the present disclosure, the unit operating status includes: extreme weather conditions; the correction module 1230 includes: a second acquisition unit, a second prediction unit, a third prediction unit and a fourth correction unit; wherein, the second acquisition unit is used to obtain the operating data and meteorological data of each unit, wherein the meteorological data includes: wind speed data and icing data; the second prediction unit is used to obtain a storm state sequence based on the operating data of each unit and the wind speed data; the third prediction unit is used to obtain an icing state sequence based on the operating data of each unit and the icing data; the fourth correction unit is used to correct the first power prediction result according to the storm state sequence and / or the icing state sequence to obtain a power correction result corresponding to the extreme weather condition.

[0102] As an implementation method of the embodiment of the present disclosure, the operating data and icing data of each unit are input into a meteorological icing prediction model to obtain a meteorological icing prediction result; when the meteorological icing prediction result is icing, the corresponding value in the icing state sequence is recorded as 0; when the meteorological icing prediction result is no icing, the corresponding value in the icing state sequence is recorded as 1.

[0103] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0104] The wind farm power prediction device of the disclosed embodiment obtains wind farm power data, wherein the wind farm power data includes power prediction data and power correction data; inputs the power prediction data into a power prediction model to obtain a first power prediction result; corrects the first power prediction result based on the power correction data and the unit operating status to obtain at least one power correction result; and multiplies the first power prediction result by the at least one power correction result to obtain a target power prediction result. Thus, based on the power prediction model and in combination with the unit operating status, the power prediction result is corrected, thereby improving the accuracy of the power prediction result.

[0105] To implement the above embodiments, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0106] The electronic device includes: a processor 1320; a memory 1310 for storing instructions executable by the processor 1320; wherein the processor 1320 is configured to execute the wind farm power prediction method proposed in the embodiment of the first aspect of the present disclosure as described above.

[0107] As an example, Figure 13 is a block diagram of an electronic device for implementing the method of the embodiment of the present disclosure according to an exemplary embodiment. Figure 13 As shown, the electronic device 1300 may include:

[0108] The memory 1310 and the processor 1320, a bus 1330 connecting different components (including the memory 1310 and the processor 1320), the memory 1310 stores a computer program, and when the processor 1320 executes the program, the wind farm power prediction method proposed in the embodiment of the first aspect of the present disclosure as described above is implemented.

[0109] Bus 1330 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0110] The electronic device 1300 typically includes a variety of computer-readable media. These media can be any available media that can be accessed by the electronic device 1300, including volatile and non-volatile media, removable and non-removable media.

[0111] The memory 1310 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 1340 and / or cache 1350. The electronic device 1300 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 1360 may be used to read and write non-removable, non-volatile magnetic media ( Figure 13 Not shown, often called a "hard drive"). Although Figure 13 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 1330 via one or more data medium interfaces. Memory 1310 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present disclosure.

[0112] A program / utility 1380 having a set (at least one) of program modules 1370 may be stored, for example, in memory 1310. Such program modules 1370 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 1370 generally implement the functions and / or methods described in the embodiments of the present disclosure.

[0113] The electronic device 1300 may also communicate with one or more external devices 1390 (e.g., a keyboard, a pointing device, a display 1391, etc.), and may also communicate with one or more devices that enable a user to interact with the electronic device 1300, and / or any device that enables the electronic device 1300 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed through an input / output (I / O) interface 1392. Furthermore, the electronic device 1300 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 1393. Figure 13 As shown, the network adapter 1393 communicates with other modules of the electronic device 1300 via the bus 1330. Figure 13 Not shown, other hardware and / or software modules may be used in conjunction with electronic device 1300, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0114] The processor 1320 executes various functional applications and data processing by running programs stored in the memory 1310 .

[0115] It should be noted that the implementation process and technical principles of the electronic device of this embodiment can be found in the aforementioned explanation of the wind farm power prediction method of the embodiment of the present disclosure, and will not be repeated here.

[0116] The electronic device provided in an embodiment of the present disclosure obtains wind farm power data, wherein the wind farm power data includes power prediction data and power correction data; inputs the power prediction data into a power prediction model to obtain a first power prediction result; corrects the first power prediction result based on the power correction data and the unit operating status to obtain at least one power correction result; and multiplies the first power prediction result by the at least one power correction result to obtain a target power prediction result. Thus, based on the power prediction model and in combination with the unit operating status, the power prediction result is corrected, thereby improving the accuracy of the power prediction result.

[0117] In order to implement the above embodiments, the present disclosure also proposes a computer-readable storage medium, wherein, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the wind farm power prediction method proposed in any of the above embodiments.

[0118] In order to implement the above embodiments, the present disclosure further provides a computer program product. When the computer program is executed by a processor of an electronic device, the electronic device can execute the wind farm power prediction method proposed in any of the above embodiments.

[0119] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and features of different embodiments or examples, unless they are mutually inconsistent.

[0120] Furthermore, 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 being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0121] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present disclosure belong.

[0122] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0123] It should be understood that various parts of the present disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0124] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0125] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0126] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present disclosure have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. A person of ordinary skill in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

[0127] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the present disclosure. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0128] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A wind farm power prediction method, characterized in that: include: Acquiring wind farm power data, wherein the wind farm power data includes: power prediction data and power correction data; Inputting the power prediction data into a power prediction model to obtain a first power prediction result; Correcting the first power prediction result according to the power correction data and the unit operating status to obtain at least one power correction result; multiplying the first power prediction result and the at least one power correction result to obtain a target power prediction result; Among them, the power prediction data includes: unit operation data, unit space data, and meteorological data; the power correction data includes: unit operation data, meteorological data, faulty units, and maintenance plan data; the unit operation status includes: fault repair time, scheduled inspection plan, fault prediction situation, reduced power operation status and extreme weather conditions.

2. The method according to claim 1, wherein the unit operating status comprises: Fault repair time; The step of correcting the first power prediction result according to the power correction data and the unit operating status to obtain at least one power correction result includes: Determine whether there is a faulty unit; In the absence of the faulty unit, the first power prediction result is not corrected, and the first power prediction result is the corresponding power correction result; In the case where the faulty unit exists, a fault repair sequence is determined, and the first power prediction result is corrected according to the fault repair sequence to obtain a power correction result corresponding to the fault repair time.

3. The method according to claim 2, characterized in that The method of determining a fault repair sequence when the faulty unit exists and correcting the first power prediction result according to the fault repair sequence to obtain a corresponding power correction result includes: Query the maintenance experience database according to the fault type to obtain the fault repair time; If the fault repair time is less than or equal to the preset time period, the corresponding value in the fault repair sequence is recorded as 1; If the fault repair time is greater than the preset time period, the corresponding value in the fault repair sequence is recorded as 0.

4. The method according to claim 1, wherein The unit operation status includes: a scheduled inspection plan; and the first power prediction result is corrected according to the power correction data and the unit operation status to obtain at least one power correction result, including: Determine whether the scheduled inspection plan exists for each unit; In the absence of the scheduled inspection plan, the first power prediction result is not corrected, and the first power prediction result is the corresponding power correction result; In the case where the regular inspection plan exists, a regular inspection state sequence is determined, and the first power prediction result is corrected according to the regular inspection state sequence to obtain a power correction result corresponding to the regular inspection plan.

5. The method according to claim 1, wherein The unit operating status includes: a fault prediction condition; and the first power prediction result is corrected according to the power correction data and the unit operating status to obtain at least one power correction result, including: Obtain the operating data of each unit and obtain the characteristic factor library; Performing fault prediction on each of the units based on a machine learning model to obtain a fault prediction sequence, wherein the input of the machine learning model is the characteristic factor library, and the output of the machine learning model is the fan parameters; The first power prediction result is corrected according to the fault prediction sequence to obtain a power correction result corresponding to the fault prediction situation.

6. The method according to claim 5, characterized in that The fault prediction of each unit based on the machine learning model to obtain a fault prediction sequence includes: When the fan parameter is greater than a preset threshold, the corresponding value in the fault prediction sequence is recorded as 0; When the fan parameter is less than or equal to the preset threshold, the corresponding value in the fault prediction sequence is recorded as 1.

7. The method according to claim 1, characterized in that The unit operating state includes: a reduced power operating state; and the correcting the first power prediction result according to the power correction data and the unit operating state to obtain at least one power correction result includes: Obtain the operating data of each unit and obtain the power reduction category; Evaluate the power reduction release time according to the power reduction category to obtain a power reduction state sequence; The first power prediction result is corrected according to the power reduction state sequence to obtain a power correction result corresponding to the power reduction operation state.

8. The method according to claim 1, characterized in that The unit operating state includes: extreme weather conditions; the first power prediction result is corrected according to the power correction data and the unit operating state to obtain at least one power correction result, including: Acquiring operating data and meteorological data of each unit, wherein the meteorological data includes wind speed data and icing data; Obtaining a storm state sequence according to the operating data of each unit and the wind speed data; Obtaining an icing state sequence according to the operating data of each unit and the icing data; The first power prediction result is corrected according to the storm state sequence and / or the icing state sequence to obtain a power correction result corresponding to the extreme weather condition.

9. The method according to claim 8, characterized in that The step of obtaining an icing state sequence according to the operating data of each unit and the icing data includes: Inputting the operating data and icing data of each unit into a meteorological icing prediction model to obtain a meteorological icing prediction result; When the meteorological icing prediction result is icing, the corresponding value in the icing state sequence is recorded as 0; When the meteorological icing prediction result is no icing, the corresponding value in the icing state sequence is recorded as 1.

10. A wind farm power prediction device, characterized in that: include: An acquisition module, configured to acquire wind farm power data, wherein the wind farm power data includes power prediction data and power correction data; An input module, configured to input the power prediction data into a power prediction model to obtain a first power prediction result; a correction module, configured to correct the first power prediction result according to the power correction data and the unit operating status to obtain at least one power correction result; a processing module, configured to multiply the first power prediction result and the at least one power correction result to obtain a target power prediction result; Among them, the power prediction data includes: unit operation data, unit space data, and meteorological data; the power correction data includes: unit operation data, meteorological data, faulty units, and maintenance plan data; the unit operation status includes: fault repair time, scheduled inspection plan, fault prediction situation, reduced power operation status and extreme weather conditions.

Images