Power generation information processing method, device and electronic equipment applied to wind power generation

Abstract

Embodiments of the present disclosure disclose a power generation information processing method, device and electronic equipment applied to wind power generation. A specific implementation of the method comprises: inputting a pre-processed wind power generation information set into a wind power generation information calculation model to obtain actual power plant power generation information corresponding to a target wind power plant; in response to determining that the actual power plant power generation information meets a preset adjustment condition, generating wind resource query information corresponding to the target wind power plant; inputting the wind resource query information into a wind resource library; in response to querying a wind resource information set corresponding to the wind resource query information, sorting the wind resource information set to obtain a wind resource information sequence; and sending the actual power plant power generation information and the wind resource information sequence to an associated wind power plant data analysis end. The implementation can mark important wind resource information by sorting the queried wind resource information, so as to facilitate further data analysis.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the field of computer, in particular to a power generation information processing method and device applied to wind power generation and an electronic device. BACKGROUND

[0002] With the continuous development of wind power generation, effective management and control of wind power generation equipment has become one of the main development directions. At present, for the calculation and query of power generation data corresponding to the wind power generation equipment, the commonly used way is: through modeling simulation (CFD model or linear model), the collected power generation data is calculated; through the simple query of the public third-party software (Fremeso).

[0003] However, when the above way is used to calculate and query the power generation data, the following technical problems often exist:

[0004] Through the modeling simulation, the calculation of the collected power generation data is complex in technical route and time-consuming. Through the simple query of the third-party software, the query efficiency is low.

[0005] The above information disclosed in the background section is only intended to enhance the understanding of the background of the present inventive concept, and therefore, it can include information that does not form the prior art known to those of ordinary skill in the art in the country. SUMMARY

[0006] The summary section of the present disclosure is used to introduce the concepts in a brief form, which will be described in detail in the specific embodiments section. The summary section of the present disclosure is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0007] Some embodiments of the present disclosure propose a power generation information processing method and device applied to wind power generation, an electronic device and a computer readable medium, to solve one or more of the technical problems mentioned in the background section.

[0008] In a first aspect, some embodiments of the present disclosure provide a power generation information processing method applied to wind power generation, the method comprising: in response to receiving a wind power generation information set corresponding to a target wind power plant, preprocessing the wind power generation information set to obtain a preprocessed wind power generation information set, wherein the wind power generation information in the wind power generation information set corresponds to a wind power generation device in the target wind power plant; inputting the preprocessed wind power generation information set into a pre-trained wind power generation information calculation model to obtain actual power plant power generation information corresponding to the target wind power plant, wherein the actual power plant power generation information includes total technical reduction information, wind power generation wake information, and actual power generation; in response to determining that the actual power plant power generation information satisfies a preset adjustment condition, generating wind resource query information corresponding to the target wind power plant; inputting the wind resource query information into a wind resource library to query wind resources; in response to querying a wind resource information set corresponding to the wind resource query information, sorting the wind resource information set to obtain a wind resource information sequence; and sending the actual power plant power generation information and the wind resource information sequence to an associated wind power plant data analysis end.

[0009] In a second aspect, some embodiments of the present disclosure provide a power generation information processing device applied to wind power generation, the device comprising: a preprocessing unit configured to, in response to receiving a wind power generation information set corresponding to a target wind power plant, preprocess the wind power generation information set to obtain a preprocessed wind power generation information set, wherein the wind power generation information in the wind power generation information set corresponds to a wind power generation device in the target wind power plant; a first input unit configured to input the preprocessed wind power generation information set into a pre-trained wind power generation information calculation model to obtain actual power plant power generation information corresponding to the target wind power plant, wherein the actual power plant power generation information includes total technical reduction information, wind power generation wake information, and actual power generation; a generation unit configured to, in response to determining that the actual power plant power generation information satisfies a preset adjustment condition, generate wind resource query information corresponding to the target wind power plant; a second input unit configured to input the wind resource query information into a wind resource library to query wind resources; a sorting unit configured to, in response to querying a wind resource information set corresponding to the wind resource query information, sort the wind resource information set to obtain a wind resource information sequence; and a sending unit configured to send the actual power plant power generation information and the wind resource information sequence to an associated wind power plant data analysis end.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the first aspect.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any implementation manner of the first aspect.

[0012] The above various embodiments of the present disclosure have the following beneficial effects: through the application of the power generation information processing method for wind power generation of some embodiments of the present disclosure, the calculation of the collected power generation data is facilitated, and the calculation time is shortened; in addition, by sorting the queried wind resource information, important wind resource information can be marked out to facilitate further data analysis. Specifically, the reason for low query efficiency is that the collected power generation data is calculated by modeling simulation, the technical route is complex, and the time consumed is long; the query efficiency is low through simple query by a third-party software. Based on this, the power generation information processing method for wind power generation of some embodiments of the present disclosure, first, in response to receiving a wind power generation information set corresponding to a target wind power plant, the wind power generation information set is preprocessed to obtain a preprocessed wind power generation information set. The wind power generation information in the wind power generation information set corresponds to a wind power generation device in the target wind power plant. Thus, data support is provided for calculating the actual power plant power generation information. Second, the preprocessed wind power generation information set is input into a pre-trained wind power generation information calculation model to obtain actual power plant power generation information corresponding to the target wind power plant. The actual power plant power generation information includes total technical reduction information, wind power generation wake information, and actual power generation. Thus, the pre-trained wind power generation information calculation model can be used to calculate the power generation data, which speeds up the data calculation efficiency and shortens the calculation time. Then, in response to determining that the actual power plant power generation information meets a preset adjustment condition, wind resource query information corresponding to the target wind power plant is generated. The wind resource query information is input into a wind resource library for wind resource query. Thus, the corresponding wind resource information can be queried through the pre-constructed wind resource library. Then, in response to querying a wind resource information set corresponding to the wind resource query information, the wind resource information set is sorted to obtain a wind resource information sequence. Finally, the actual power plant power generation information and the wind resource information sequence are sent to an associated wind power plant data analysis end. Thus, by sorting the queried wind resource information, important wind resource information can be marked out to facilitate further data analysis. BRIEF DESCRIPTION OF DRAWINGS

[0013] The above and other features, aspects and advantages of the present disclosure will become more apparent with reference to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, similar or same reference numerals are used to denote similar or same elements. It is to be understood that the drawings are schematic, and elements and features are not necessarily to scale.

[0014] Figure 1 is a flow chart of some embodiments of a power generation information processing method applied to wind power generation according to the present disclosure;

[0015] Figure 2 is a structural schematic diagram of some embodiments of a power generation information processing apparatus applied to wind power generation according to the present disclosure;

[0016] Figure 3 is a structural schematic diagram of an electronic device suitable for use to implement some embodiments of the present disclosure;

[0017] Figure 4 is a schematic scenario diagram of a wind resource information sequence in a power generation information processing method applied to wind power generation according to the present disclosure. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described below in greater detail with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be more thoroughly and completely understood. It should be understood that the drawings and embodiments of the present disclosure are only for illustrative purposes and should not be construed as limiting the scope of protection of the present disclosure.

[0019] It should also be noted that, for the sake of brevity, only the parts of the drawings that are relevant to the present application are shown. The embodiments and features in the present disclosure can be combined with each other as long as there is no conflict.

[0020] It should be noted that the terms “first”, “second”, and the like in the present disclosure are only used to distinguish different devices, modules or units, and are not intended to limit the order or interdependence of the functions performed by these devices, modules or units.

[0021] It should be noted that the terms “one”, “multiple” in the present disclosure are illustrative and not restrictive, and those skilled in the art should understand that, unless otherwise explicitly stated in the context, it should be understood as “one or more”.

[0022] Names of messages or information exchanged between multiple devices in embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0023] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0024] Figure 1 is a flowchart of some embodiments of a power generation information processing method for wind power generation according to the present disclosure. Embodiments of a power generation information processing method for wind power generation according to the present disclosure are shown in flowchart 100. The power generation information processing method for wind power generation includes the following steps:

[0025] Step 101, in response to receiving a wind power generation information set corresponding to a target wind power plant, pre-processing the wind power generation information set to obtain a pre-processed wind power generation information set.

[0026] In some embodiments, the execution subject (e.g., a computing device) of the power generation information processing method for wind power generation can respond to receiving a wind power generation information set corresponding to a target wind power plant by pre-processing the wind power generation information set to obtain a pre-processed wind power generation information set. The wind power generation information in the wind power generation information set corresponds to a wind power generation device in the target wind power plant. The wind power generation device can include a wind wheel, a generator, a wind wheel containing blades, a hub, reinforcing members, etc., and has functions such as blade rotation for power generation and generator head rotation. The wind power generation power source is composed of a wind turbine generator set, a tower supporting the generator set, a battery charging controller, an inverter, an unloading device, a grid-connected controller, a battery pack, etc. The wind power generation device can also include a speed-increasing gearbox, a yaw device, a control system, a battery pack, a main transformer and system equipment, a power collection line, a control cabinet and a power distribution device, a power cable, a substation monitoring system device, a direct current system device, a communication system device, an air conditioning system device, and a power station relay protection system device. The target wind power plant can be a power plant where various wind power generation devices are arranged. For example, the pre-processing can include supplementing missing values and removing null values. The wind power generation information includes a wind power generation data sequence of the wind power generation device within a predetermined time period. The wind power generation data can include but is not limited to wind power generation device information, geographic location data, wind power generation device conversion efficiency, open circuit voltage, short circuit current, maximum output power, operating temperature range, rated power, wind wheel diameter, hub height, cut-in wind speed, rated wind speed, cut-out wind speed, survival wind speed, operating temperature.

[0027] Step 102, inputting the pre-processed wind power generation information set into a pre-trained wind power generation information calculation model to obtain actual power plant power generation information corresponding to the target wind power plant.

[0028] In some embodiments, the execution subject can input the pre-processed wind power generation information set into a pre-trained wind power generation information calculation model to obtain actual power plant generation information corresponding to the target wind power plant. The actual power plant generation information includes total technical reduction information, wind power wake information, and actual power generation. The wind power generation information calculation model can be a pre-trained time series model for calculating actual power plant generation information corresponding to a wind power generation data sequence included in the wind power generation information. The actual power plant generation information can include a plurality of actual power plant generation sub-information. Each actual power plant generation sub-information corresponds to a wind power generation data sequence. The actual power plant generation sub-information can include a cumulative probability density distribution of wind speed, a power curve (wind speed-power curve), an electric quantity at each wind speed segment, and a cumulative summation. The total technical reduction information can represent the ratio of the actual power generation of the target wind power plant to the preset power generation. The wind power wake information can represent the wind turbine wake. For example, the wind power generation information calculation model can be an autoregressive moving average model (ARMA), an autoregressive integrated moving average model (ARIMA), a seasonal autoregressive integrated moving average model (SARIMA), or a vector autoregressive model (VAR). For another example, the wind power generation information calculation model can also be a CNN convolutional neural network model or an LSTM model.

[0029] The wind power generation information calculation model can be trained by the following steps:

[0030] First, obtain a generation monitoring data set corresponding to each wind power generation device. Each generation monitoring data in the generation monitoring data set can be data collected and recorded by various wind power generation devices about power generation in a preset time period. The generation monitoring data can be data used to determine the type of power generation anomaly. The generation monitoring data can include various generation monitoring sub-data. Each generation monitoring sub-data can be an electric power generation data group sequence and a power loss sequence.

[0031] Secondly, an initial wind power generation information calculation model is determined. The initial wind power generation information calculation model includes an initial power generation information calculation model and an initial power generation abnormal type detection model. The initial power generation information calculation model can be an autoregressive moving average model (ARMA), an autoregressive integrated moving average model (ARIMA), a seasonal autoregressive integrated moving average model (SARIMA), or a vector autoregressive model (VAR). The initial power generation abnormal type detection model can be a recurrent neural network (RNN). For example, the network structure of the initial wind power generation information calculation model can be determined, including which network layers are included, and the loss function involved in the initial wind power generation information calculation model can be determined.

[0032] Thirdly, power generation abnormal type identification is performed on each power generation monitoring data in the power generation monitoring data set to generate a power generation abnormal type identification, thereby obtaining a power generation abnormal type identification set. For example, the execution subject can perform power generation abnormal type identification on each power generation monitoring data in the power generation monitoring data set by using a CNN-LSTM hybrid model multi-class power generation abnormal behavior detection method to generate a power generation abnormal type identification, thereby obtaining a power generation abnormal type identification set. The power generation abnormal type identification can be a name representing a power generation abnormal behavior type. The power generation abnormal type identification can be a bearing fault type identification, a gearbox fault type identification, a blade fault type identification, a generator winding fault type identification, a control system fault type identification, or a converter fault type identification.

[0033] Fourthly, the initial power generation abnormal type detection model is trained based on the power generation monitoring data set and the power generation abnormal type identification set, thereby obtaining a trained power generation abnormal type detection model.

[0034] The fourth step can include the following sub-steps:

[0035] Firstly, for each power generation monitoring data in the power generation monitoring data set, the following processing steps are performed:

[0036] Firstly, the power generation abnormal type identification corresponding to the power generation monitoring data in the power generation abnormal type identification set is determined as a comparison power generation abnormal type identification.

[0037] Secondly, the power generation monitoring data and the comparison power generation abnormal type identification are determined as a power generation abnormal type training sample.

[0038] Secondly, each determined power generation abnormal type training sample is determined as a power generation abnormal type training sample set.

[0039] A third sub-step, based on the power generation anomaly type training sample set, the following training steps are performed:

[0040] First, the power generation monitoring data of at least one power generation anomaly type training sample in the power generation anomaly type training sample set is input into the initial power generation anomaly type detection model, and the detection power generation anomaly type identifier corresponding to each power generation anomaly type training sample in the at least one power generation anomaly type training sample is obtained.

[0041] Second, the detection power generation anomaly type identifier corresponding to each power generation anomaly type training sample in the at least one power generation anomaly type training sample is compared with the corresponding comparison power generation anomaly type identifier. For example, the difference between the detection power generation anomaly type identifier corresponding to each power generation anomaly type training sample and the corresponding comparison power generation anomaly type identifier can be determined by a hinge loss function or a cross-entropy loss function.

[0042] Third, according to the comparison result, it is determined whether the initial power generation anomaly type detection model reaches the preset training target. The comparison result can represent the difference value / loss value. The training target can mean that the difference value / loss value is less than or equal to the preset loss value.

[0043] The fourth sub-step, in response to determining that the initial power generation anomaly type detection model reaches the training target, the initial power generation anomaly type detection model is determined as the trained power generation anomaly type detection model.

[0044] The fifth step, according to the above power generation monitoring data set, the above initial power generation information calculation model is trained to obtain a trained power generation information calculation model. Here, the training method of the power generation anomaly type detection model can be referred to, which will not be repeated here. For example, the training method of the deep neural network model can also be referred to.

[0045] The sixth step, the above power generation anomaly type detection model and the above power generation information calculation model are fused into a wind power generation information calculation model.

[0046] Thus, the processing of the data corresponding to the anomaly identifier with a small power generation anomaly factor is reduced, and the waste of computer computing resources is reduced.

[0047] Step 103, in response to determining that the actual power generation field power generation information satisfies the preset adjustment condition, generating wind resource query information corresponding to the target wind power generation field.

[0048] In some embodiments, the execution subject can generate wind resource query information of the target wind farm in response to determining that the actual power generation information of the actual wind farm meets a preset adjustment condition. The preset adjustment condition can be that the actual power generation amount included in the actual power generation information is less than a preset minimum power generation amount. The wind resource query information can be a query instruction for automatically querying each wind resource information of the target wind farm in a preset time period, and power generation data and operation data of each wind power equipment. The wind resource information can represent weather information of the target wind farm at a certain time node in the preset time period, and can include wind speed, whether it is raining, and the like. The time node can refer to a certain day.

[0049] In step 104, the wind resource query information is input into a wind resource library for wind resource query.

[0050] In some embodiments, the execution subject can input the wind resource query information into the wind resource library for wind resource query. The wind resource library can be a database pre-constructed to store wind resource information of each wind farm and power generation data and operation data of each wind power equipment.

[0051] In step 105, in response to querying a wind resource information set corresponding to the wind resource query information, the wind resource information set is sorted to obtain a wind resource information sequence.

[0052] In some embodiments, the execution subject can sort the wind resource information set corresponding to the wind resource query information to obtain a wind resource information sequence in response to querying the wind resource information set. The wind resource information sorting model can be a pre-trained neural network model for sorting. For example, the wind resource information sorting model can be a BERT model or a RoBERTa model.

[0053] In practice, the execution subject can input the wind resource query information and the wind resource information set into the pre-trained wind resource information sorting model to generate the wind resource information sequence.

[0054] The wind resource information sorting model can be trained by the following steps:

[0055] In a first step, a target wind resource information sample set and a wind resource query information sample set are obtained. The target wind resource information samples in the target wind resource information sample set are wind resource information samples that support association query. The association query can be a query for the target wind resource information sample set that is most associated with the query content of the wind resource query information sample from the target wind resource information sample set. The wind resource query information sample can be information that queries for an association between the target wind resource information sample and the target wind resource information sample set. The target wind resource information sample set and the wind resource query information sample set are pre-set and have content association.

[0056] In a second step, for each wind resource query information sample in the wind resource query information sample set, the following processing steps are performed:

[0057] 1. The initial sorting result corresponding to the wind resource query information sample is determined according to the target wind resource information sample set. The initial sorting result can be a sorting result of each target wind resource information sample that has text content association for the wind resource query information sample. The initial sorting result can be a sorting result of each target wind resource information sample sorted according to the content association degree between the target wind resource information sample and the wind resource query information sample. For example, the initial sorting result can be a result of sorting each target wind resource information sample in descending order of content association degree.

[0058] 2. The initial sorting result is adjusted to generate an initial adjusted sorting result.

[0059] The initial sorting result is adjusted to generate an initial adjusted sorting result, including:

[0060] First, each target wind resource information sample in the target wind resource information sample set is sorted according to the initial sorting result to obtain a target wind resource information sample sequence. For example, each target wind resource information sample in the target wind resource information sample set can be sorted in descending order of matching degree to obtain a target wind resource information sample sequence.

[0061] Second, each target wind resource information sample in the target wind resource information sample sequence is window combined according to a pre-set text combination window to obtain a target wind resource information sample group set. The window combination can be a form of combining a target number of adjacent samples to form a sample group.

[0062] Third, sample prompt information representing sample sorting of each target wind resource information sample group in the target wind resource information sample group set is generated.

[0063] Fourth, the above sample prompt information and the above wind resource query information sample are input into a pre-trained ranking model to obtain a group ranking result corresponding to each target wind resource information sample group in the target wind resource information sample group set, and a group ranking result set is obtained.

[0064] Fifth, an initial adjustment ranking result is generated according to the group ranking result set. For example, the individual group ranking results can be combined to obtain the initial adjustment ranking result.

[0065] Third, model training is performed on at least one initial wind resource information ranking reference model according to the individual initial adjustment ranking results, to obtain at least one wind resource information ranking reference model. The initial wind resource information ranking reference model can be a teacher model that has not yet completed training. The teacher model is a teacher model in a teacher-student model. For example, the model structures corresponding to the individual initial wind resource information ranking reference models in the at least one initial wind resource information ranking reference model are different. For example, the at least one initial wind resource information ranking reference model can include multiple different BERT-based teacher models. The at least one initial wind resource information ranking reference model can include a BERT model and a RoBERTa model.

[0066] The third step can include the following sub-steps:

[0067] The first sub-step performs the following processing steps for each initial adjustment ranking result in the individual initial adjustment ranking results:

[0068] First, an initial positive-negative sample set is determined according to the initial adjustment ranking result. The initial positive-negative sample includes positive samples and negative samples whose text order difference satisfies a preset condition. The initial positive-negative sample can include positive samples and negative samples. The preset condition can be that the ranking position corresponding to the positive sample and the ranking position corresponding to the negative sample are separated by a preset number of positions. The ranking position of the positive sample is higher than a preset ranking position, and the ranking position of the negative sample is lower than the preset ranking position. For example, the preset ranking position can be the middle position corresponding to the initial adjustment ranking result.

[0069] Then, a plurality of initial wind resource query information training samples are generated according to the initial positive-negative sample set and the wind resource query information sample corresponding to the initial adjustment ranking result. For example, the execution subject can combine each initial positive-negative sample in the initial positive-negative sample set with the wind resource query information sample to generate an initial wind resource query information training sample, to obtain a plurality of initial wind resource query information training samples.

[0070] Second sub-step, according to each initial wind resource query information sample, model training is performed on the at least one initial wind resource information ranking reference model to obtain at least one wind resource information ranking reference model. For example, the at least one initial wind resource information ranking reference model can be trained by back propagation to update the parameters of the model to obtain at least one wind resource information ranking reference model.

[0071] Fourth step, according to the at least one wind resource information ranking reference model, the initial ranking results corresponding to each wind resource query information sample are adjusted to generate a target adjusted ranking result set. For example, first, the execution subject can randomly select one wind resource information ranking reference model from the at least one wind resource information ranking reference model as a target wind resource information ranking reference model. Then, each initial ranking result in the initial ranking results and the wind resource query information sample can be input into the target wind resource information ranking reference model to generate a target adjusted ranking result to obtain a target adjusted ranking result set.

[0072] Fifth step, according to the target adjusted ranking result set, model training is performed on the initial wind resource information ranking model to obtain a trained wind resource information ranking model. The initial wind resource information ranking model can be a student model that has not completed training. The student model can be a student model in a teacher-student model. The student model is used for real-time online information retrieval ranking. For example, the wind resource information ranking model can be a text ranking model. For example, the wind resource information ranking model can be a BERT model.

[0073] The fifth step can include the following sub-steps:

[0074] First sub-step, for each target adjusted ranking result in the target adjusted ranking result set, the following processing steps are performed:

[0075] First, according to the target adjusted ranking result, a target positive and negative sample set is determined. The target positive and negative sample set includes positive and negative samples whose order difference satisfies a preset condition. The generation method of the initial positive and negative sample set can be referred to.

[0076] Then, according to the target positive and negative sample set and the wind resource query information sample corresponding to the target adjusted ranking result, a plurality of target wind resource query information training samples are generated.

[0077] In a second sub-step, the initial wind resource information ranking model is trained according to the training samples of the respective target wind resource query information, to obtain a trained wind resource information ranking model. For example, the initial wind resource information ranking model can be trained in a manner similar to the training of a deep neural network model, to obtain a trained wind resource information ranking model.

[0078] Thus, the model training of the wind resource information ranking reference model (teacher model) and the wind resource information ranking model (student model) is effectively implemented, and the student model that can accurately implement wind resource information ranking is generated. The problem that the sample information length usually exceeds the upper limit of the input information length that the model can accept is effectively solved, and the generation efficiency of the ranking result is improved.

[0079] In step 106, the actual power plant power generation information and the wind resource information sequence are sent to the associated wind power plant data analysis terminal.

[0080] In some embodiments, the actual power plant power generation information and the wind resource information sequence can be sent to the associated wind power plant data analysis terminal by the execution subject. The wind power plant data analysis terminal can refer to a terminal for further data analysis of the actual power plant power generation information and the wind resource information sequence. For example, the wind power plant data analysis terminal can be a terminal operated by a technician. Thus, the wind power generation information can be further analyzed.

[0081] As Figure 4 shown in the examples, the wind resource information sequence can be displayed in the form of a table, and can include: wind parameter input, wind turbine selection, evaluation result; wind parameter input, wind turbine selection, evaluation result, corresponding content, input, unit, note / recommended value. The content corresponding to the wind parameter input includes: average wind speed, air density, K value. The content corresponding to the wind turbine selection includes: wind turbine model, single machine capacity, power curve source. The content corresponding to the evaluation result includes: total technical reduction, wake, total reduction, annual equivalent utilization hours.

[0082] It should be noted that Figure 4 the text and numerical values shown in the examples are merely illustrative descriptions and do not represent the fixed limitations of the wind resource information involved in the present application.

[0083] Further referring to Figure 2 , as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a power generation information processing device applied to wind power generation. These embodiments of the power generation information processing device applied to wind power generation correspond to the method embodiments shown in Figure 1 , and the power generation information processing device applied to wind power generation can be applied to various electronic devices.

[0084] As Figure 2 shown, the power generation information processing device 200 for wind power generation of some embodiments includes a preprocessing unit 201, a first input unit 202, a generation unit 203, a second input unit 204, a sorting unit 205, and a sending unit 206. Among them, the preprocessing unit 201 is configured to, in response to receiving a wind power generation information set corresponding to a target wind power plant, preprocess the wind power generation information set to obtain a preprocessed wind power generation information set, wherein the wind power generation information in the wind power generation information set corresponds to a wind power generation device in the target wind power plant; the first input unit 202 is configured to input the preprocessed wind power generation information set into a pre-trained wind power generation information calculation model to obtain actual power plant power generation information corresponding to the target wind power plant, wherein the actual power plant power generation information includes total technical reduction information, wind power generation wake information, and actual power generation; the generation unit 203 is configured to, in response to determining that the actual power plant power generation information meets a preset adjustment condition, generate wind resource query information corresponding to the target wind power plant; the second input unit 204 is configured to input the wind resource query information into a wind resource library for wind resource query; the sorting unit 205 is configured to, in response to querying a wind resource information set corresponding to the wind resource query information, sort the wind resource information set to obtain a wind resource information sequence; and the sending unit 206 is configured to send the actual power plant power generation information and the wind resource information sequence to an associated wind power plant data analysis end.

[0085] It can be understood that the units described in the power generation information processing device 200 for wind power generation correspond to each step in the method described with reference to Figure 1 Thus, the operations, features, and beneficial effects described above for the method also apply to the power generation information processing device 200 for wind power generation and the units contained therein, which will not be described here.

[0086] Reference is made below to Figure 3 which shows a structural schematic diagram of an electronic device 300 (e.g., a computing device) suitable for implementing some embodiments of the present disclosure. The electronic device in some embodiments of the present disclosure can include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet PC), a PMP (Portable Multimedia Player), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like. Figure 3 The electronic device shown is only an example and should not impose any limitation on the functions and use range of embodiments of the present disclosure.

[0087] As Figure 3As shown, the electronic device 300 can include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301 that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 302 or loaded into a random access memory (RAM) 303 from a storage device 308. Various programs and data required for the operation of the electronic device 300 are also stored in the RAM 303. The processing device 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0088] Generally, the following devices can be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 can allow the electronic device 300 to communicate wirelessly or wired with other devices to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that all of the illustrated devices are not required, and more or fewer devices can alternatively be implemented. Figure 3 Each block shown in the flowcharts can represent a device, or multiple devices, as necessary.

[0089] In particular, processes described above with reference to the flowcharts can be implemented as a computer software program according to some embodiments of the present disclosure. For example, some embodiments of the present disclosure include a computer program product including a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In some such embodiments, the computer program can be downloaded and installed from a network through the communication devices 309, or installed from the storage devices 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-described functions defined in the methods of some embodiments of the present disclosure are performed.

[0090] Note that the computer readable medium in some embodiments of the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination thereof. The computer readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program used by an instruction execution system, apparatus or device, or that can be used by or in connection with an instruction execution system, apparatus or device. In some embodiments of the present disclosure, the computer readable signal medium can include a computer readable program code propagated in or on a carrier medium, in which the computer readable program code is embodied. Such propagated computer readable program code can take many forms, including but not limited to, an electromagnetic signal, an optical signal or any suitable combination of the foregoing. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device. Program code embodied on a computer readable medium can be transmitted using any suitable medium, including but not limited to, wire, cable, wireless, RF, infrared or any suitable combination of the foregoing.

[0091] In some embodiments, the client, server, or both can communicate using any current known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet, and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any current known or future developed networks.

[0092] The computer readable medium can be included in the electronic device, or can exist separately from the electronic device. The computer readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: in response to receiving a wind power generation information set corresponding to a target wind farm, pre-process the wind power generation information set to obtain a pre-processed wind power generation information set, wherein the wind power generation information in the wind power generation information set corresponds to a wind power generation device in the target wind farm; input the pre-processed wind power generation information set into a pre-trained wind power generation information calculation model to obtain actual power plant generation information corresponding to the target wind farm, wherein the actual power plant generation information includes total technical reduction information, wind power generation wake information, and actual power generation; in response to determining that the actual power plant generation information meets a preset adjustment condition, generate wind resource query information corresponding to the target wind farm; input the wind resource query information into a wind resource library to query wind resources; in response to querying a wind resource information set corresponding to the wind resource query information, sort the wind resource information set to obtain a wind resource information sequence; and send the actual power plant generation information and the wind resource information sequence to an associated wind farm data analysis end.

[0093] Computer program code for carrying out operations of some embodiments of the disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0094] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0095] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor can be described as including: a preprocessing unit, a first input unit, a generation unit, a second input unit, a sorting unit, and a sending unit. The names of these units do not necessarily limit the specific unit; for example, the sending unit can also be described as "a unit that sends the above-mentioned actual power generation information from the wind farm and the above-mentioned wind resource information sequence to an associated wind farm data analysis terminal."

[0096] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0097] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A power generation information processing method applied to wind power generation, comprising: in response to receiving a wind power generation information set corresponding to a target wind power plant, preprocessing the wind power generation information set to obtain a preprocessed wind power generation information set, wherein the wind power generation information in the wind power generation information set corresponds to a wind power generation device in the target wind power plant; inputting the preprocessed wind power generation information set into a pre-trained wind power generation information calculation model to obtain actual power plant power generation information corresponding to the target wind power plant; in response to determining that the actual power plant power generation information meets a preset adjustment condition, generating wind resource query information corresponding to the target wind power plant, the wind resource query information being an automatically generated query instruction for querying each wind resource information of the target wind power plant within a preset time period, and power generation data and operation data of each wind power generation device; inputting the wind resource query information into a wind resource library for wind resource query; in response to querying a wind resource information set corresponding to the wind resource query information, sorting the wind resource information set to obtain a wind resource information sequence, comprising: obtaining a target wind resource information sample set and a wind resource query information sample set; for each wind resource query information sample in the wind resource query information sample set, performing the following processing steps: determining an initial sorting result corresponding to the wind resource query information sample from the target wind resource information sample set, the initial sorting result being a result of sorting each target wind resource information sample in descending order of content correlation degree; adjusting the initial sorting result to generate an initial adjusted sorting result, comprising: sorting each target wind resource information sample in the target wind resource information sample set in descending order of matching degree according to the initial sorting result to obtain a target wind resource information sample sequence; performing window combination on each target wind resource information sample in the target wind resource information sample sequence according to a pre-set text combination window to obtain a target wind resource information sample group set; generating sample prompt information representing sample sorting of each target wind resource information sample group in the target wind resource information sample group set; inputting the sample prompt information and the wind resource query information sample into a pre-trained sorting model to obtain a group sorting result corresponding to each target wind resource information sample group in the target wind resource information sample group set, and obtaining a group sorting result set; generating an initial adjusted sorting result according to the group sorting result set; performing model training on at least one initial wind resource information sorting reference model according to each initial adjusted sorting result to obtain at least one wind resource information sorting reference model; adjusting the sorting result of each initial sorting result corresponding to the wind resource query information sample set according to the at least one wind resource information sorting reference model to generate a target adjusted sorting result set; According to the target adjustment sorting result set, the initial wind resource information sorting model is trained to obtain a trained wind resource information sorting model; The wind resource query information and the wind resource information set are input into the pre-trained wind resource information sorting model to generate a wind resource information sequence; The actual power plant power generation information and the wind resource information sequence are sent to an associated wind power plant data analysis terminal, which is a terminal operated by a technician, to further analyze the wind power generation information.

2. The method of claim 1, wherein, The at least one wind resource information sorting reference model is obtained by training the at least one initial wind resource information sorting reference model according to each initial adjustment sorting result, including: For each initial adjustment sorting result in the initial adjustment sorting result set, the following processing steps are performed: According to the initial adjustment sorting result, an initial positive and negative sample set is determined; According to the initial positive and negative sample set and the wind resource query information sample corresponding to the initial adjustment sorting result, a plurality of initial wind resource query information training samples are generated; According to each initial wind resource query information training sample, the at least one initial wind resource information sorting reference model is trained to obtain at least one wind resource information sorting reference model.

3. The method of claim 1, wherein, Before the preprocessed wind power generation information set is input into the pre-trained wind power generation information calculation model to obtain the actual power plant power generation information corresponding to the target wind power plant, the method further includes: Obtain a power generation monitoring data set corresponding to each wind power generation device; Determine an initial wind power generation information calculation model, wherein the initial wind power generation information calculation model includes an initial power generation information calculation model and an initial power generation anomaly type detection model; Perform power generation anomaly type identification processing on each power generation monitoring data in the power generation monitoring data set to generate a power generation anomaly type identification, and obtain a power generation anomaly type identification set; Based on the power generation monitoring data set and the power generation anomaly type identification set, the initial power generation anomaly type detection model is trained to obtain a trained power generation anomaly type detection model; According to the power generation monitoring data set, the initial power generation information calculation model is trained to obtain a trained power generation information calculation model; The power generation anomaly type detection model and the power generation information calculation model are fused into a wind power generation information calculation model.

4. A power generation information processing device applied to wind power generation, comprising: a preprocessing unit configured to, in response to receiving a wind power generation information set corresponding to a target wind power plant, preprocess the wind power generation information set to obtain a preprocessed wind power generation information set, wherein the wind power generation information in the wind power generation information set corresponds to a wind power generation device in the target wind power plant; a first input unit configured to input the preprocessed wind power generation information set into a pre-trained wind power generation information calculation model to obtain actual power plant power generation information corresponding to the target wind power plant; The generating unit is configured to, in response to determining that the actual power generation field power generation information meets preset adjustment conditions, generate wind power resource query information corresponding to the target wind power generation field, the wind power resource query information being automatically generated query instructions for querying each wind power resource information of the target wind power generation field within a preset time period and power generation data and operation data of each wind power equipment; The second input unit is configured to input the wind power resource query information into a wind power resource library for wind power resource query; The sorting unit is configured to, in response to querying a wind power resource information set corresponding to the wind power resource query information, sort the wind power resource information set to obtain a wind power resource information sequence, including: obtaining a target wind power resource information sample set and a wind power resource query information sample set; For each wind power resource query information sample in the wind power resource query information sample set, the following processing steps are performed: According to the target wind power resource information sample set, determine the initial sorting result corresponding to the wind power resource query information sample, and the initial sorting result is the result of sorting each target wind power resource information sample in descending order of content correlation degree; adjusting the initial sorting result to generate an initial adjusted sorting result, including: According to the initial sorting result, sort each target wind power resource information sample in the target wind power resource information sample set in descending order of matching degree to obtain a target wind power resource information sample sequence; According to a pre-set text combination window, window combination is performed on each target wind power resource information sample in the target wind power resource information sample sequence to obtain a target wind power resource information sample group set; generate sample prompt information representing sample sorting of each target wind power resource information sample group in the target wind power resource information sample group set; input the sample prompt information and the wind power resource query information sample into a pre-trained sorting model to obtain a group sorting result corresponding to each target wind power resource information sample group in the target wind power resource information sample group set, and obtain a group sorting result set; According to the group sorting result set, generate an initial adjusted sorting result; According to each initial adjusted sorting result, model training is performed on at least one initial wind power resource information sorting reference model to obtain at least one wind power resource information sorting reference model; According to the at least one wind power resource information sorting reference model, adjust the sorting result of each initial sorting result corresponding to the wind power resource query information sample set to generate a target adjusted sorting result set; According to the target adjusted sorting result set, model training is performed on the initial wind power resource information sorting model to obtain a trained wind power resource information sorting model; input the wind power resource query information and the wind power resource information set into a pre-trained wind power resource information sorting model to generate a wind power resource information sequence; a sending unit configured to send the actual power plant power generation information and the wind power resource information sequence to an associated wind power plant data analysis terminal, which is a terminal operated by a technician to further analyze the wind power generation information. 5.An electronic device, comprising: one or more processors; a memory device having stored thereon one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-3.

6. A computer readable medium having stored thereon a computer program, wherein, the program is executed by the processor to implement the method according to any one of claims 1-3.

Images