CN115689061B - Wind power ultra-short term power prediction method and related equipment - Google Patents
Wind power ultra-short term power prediction method and related equipment Download PDFInfo
- Publication number
- CN115689061B CN115689061B CN202211706200.XA CN202211706200A CN115689061B CN 115689061 B CN115689061 B CN 115689061B CN 202211706200 A CN202211706200 A CN 202211706200A CN 115689061 B CN115689061 B CN 115689061B
- Authority
- CN
- China
- Prior art keywords
- short
- power
- term
- prediction
- predicted power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
Abstract
The application provides a wind power ultra-short term power prediction method and related equipment, numerical weather forecast, first short term prediction power and actual power of a wind power plant corresponding to each historical moment are obtained, first ultra-short term prediction power is obtained through an ultra-short term power prediction model, a prediction power error and second short term prediction power are obtained through a short term combination prediction model, then a correction prediction error is obtained through the ultra-short term error prediction model, the second short term prediction power is corrected through combining the correction error, second ultra-short term prediction power is obtained, averaging calculation is carried out according to the first ultra-short term prediction power and the second ultra-short term prediction power, the ultra-short term prediction power is obtained, the problem that single algorithm of the wind power plant predicts the ultra-short term power unstability is solved through combining the ultra-short term power prediction model, the short term combination prediction model and the ultra-short term error prediction model, and the stability of a wind power prediction result is improved.
Description
Technical Field
The application relates to the technical field of wind power prediction, in particular to a wind power ultra-short-term power prediction method and related equipment.
Background
The traditional wind power ultra-short-term power prediction algorithm is single in prediction model and prediction method, insufficient in utilization of historical data and weather data of a wind power plant, insufficient in consideration of time correlation of the data, and the traditional prediction model cannot fit high-dimensional time sequence data, so that the problem of unstable predicted ultra-short-term power is caused.
Disclosure of Invention
In view of the above, an object of the present invention is to provide a method for predicting ultra-short term power of wind power and related device, so as to solve or partially solve the above technical problems.
Based on the above purpose, a first aspect of the present application provides a wind power ultra-short term power prediction method, which includes:
acquiring numerical weather forecast, first short-term predicted power and actual power corresponding to each historical moment of the wind power plant, wherein preset time is arranged between every two adjacent historical moments;
respectively carrying out translation processing on the numerical weather forecast and the first short-term prediction power to obtain a translation numerical weather forecast and a first translation short-term prediction power;
inputting the numerical weather forecast, the translational numerical weather forecast, the first short-term predicted power, the first translational short-term predicted power and the actual power into an ultra-short-term power prediction model obtained by training in advance to obtain first ultra-short-term predicted power;
performing combined prediction by adopting a short-term combined prediction model obtained by training in advance based on the numerical weather forecast and the actual power to obtain a predicted power error and a second short-term predicted power;
carrying out translation processing on the second short-term predicted power to obtain second translated short-term predicted power;
inputting the numerical weather forecast, the translational numerical weather forecast, the actual power, the second short-term predicted power, the second translational short-term predicted power and the predicted power error into an ultra-short-term error prediction model obtained through training in advance to obtain a corrected prediction error;
correcting the second short-term predicted power by using the corrected prediction error to obtain a second ultra-short-term predicted power;
and carrying out averaging calculation on the first ultra-short-term prediction power and the second ultra-short-term prediction power to obtain the ultra-short-term prediction power.
Optionally, in response to determining that the numerical weather forecast includes wind speed, wind direction, temperature, and humidity;
the method for carrying out combined prediction by adopting a short-term combined prediction model obtained through training in advance based on the numerical weather forecast and the actual power to obtain a predicted power error and a second short-term predicted power comprises the following steps:
respectively carrying out normalization processing on the wind speed, the wind direction, the temperature and the humidity to obtain normalized wind speed, wind direction, temperature and humidity;
calculating the product of the normalized wind speed and the normalized wind direction to obtain wind speed and wind direction product data;
calculating the ratio of the normalized temperature and humidity to obtain temperature-humidity ratio data;
inputting the wind speed and wind direction product data, the temperature and humidity ratio data and the actual power into the short-term combined prediction model to obtain a plurality of sub short-term prediction powers;
averaging the plurality of sub short-term prediction powers to obtain a second short-term prediction power;
calculating the difference between the second short-term predicted power and the actual power to obtain the predicted power error;
outputting the predicted power error and the second short-term predicted power via the short-term combined prediction model.
Optionally, the normalizing the wind speed, the wind direction, the temperature, and the humidity respectively to obtain normalized wind speed, wind direction, temperature, and humidity includes:
using a normalisation function
Respectively carrying out normalization calculation on the wind speed, the wind direction, the temperature and the humidity to obtain the normalized wind speed, wind direction, temperature and humidity, wherein the normalization calculation is carried out on the wind speed, the wind direction, the temperature and the humidity
Any data which is required to be normalized in wind speed, wind direction, temperature or humidity,
indicating the maximum value of the preset zoom range,
represents the minimum value of the preset set zoom range,
representing normalized wind speed, wind direction, temperature or humidity.
Optionally, the correcting the second short-term predicted power by using the corrected prediction error to obtain a second ultra-short-term predicted power includes:
and performing summation calculation by using the corrected prediction error and the second short-term prediction power to obtain the second ultra-short-term prediction power.
Optionally, in response to determining that the numerical weather forecast comprises a predicted wind speed;
the translating the numerical weather forecast and the first short-term prediction power respectively to obtain a translation historical numerical weather forecast and a first translation short-term prediction power includes:
acquiring groups of a preset number of predicted wind speeds, wherein each group of the predicted wind speeds comprises the predicted wind speeds corresponding to the preset number of historical moments;
translating the groups of the predicted wind speeds by a preset number according to the arrangement sequence of the historical moments to obtain the groups of the predicted wind speeds by the preset number after translation, and taking the groups of the predicted wind speeds by the preset number after translation as the weather forecast by the translation value;
the method comprises the steps of obtaining a preset number of groups of first short-term predicted power, wherein each group of the first short-term predicted power comprises a preset number of first short-term predicted power corresponding to historical time;
and translating each group of the first short-term predicted power by a preset number of groups according to the arrangement sequence of historical time to obtain the translated group of the first short-term predicted power by the preset number, and taking the translated group of the first short-term predicted power by the preset number as the first translated short-term predicted power.
Optionally, the performing the translational processing on the second short-term predicted power to obtain a second translated short-term predicted power includes:
acquiring a preset number of groups of second short-term predicted power, wherein each group of the second short-term predicted power comprises a preset number of second short-term predicted power corresponding to historical time;
and translating each group of the second short-term predicted power by a preset number of groups according to the arrangement sequence of the historical time to obtain the translated group of the second short-term predicted power by the preset number, and taking the translated group of the second short-term predicted power by the preset number as the second translated short-term predicted power.
Optionally, after obtaining the numerical weather forecast, the first short-term predicted power, and the actual power corresponding to each historical time of the wind farm, the method further includes:
and respectively carrying out data cleaning on the numerical weather forecast, the first short-term predicted power and the actual power by utilizing a quartile algorithm to obtain the cleaned numerical weather forecast, the first short-term predicted power and the actual power.
A second aspect of the present application provides a wind power ultra-short term power prediction apparatus, including:
the acquisition module is configured to acquire a numerical weather forecast, first short-term predicted power and actual power corresponding to each historical moment of the wind power plant, wherein a preset time is arranged between every two adjacent historical moments;
a first translation module configured to perform translation processing on the numerical weather forecast and the first short-term predicted power respectively to obtain a translated numerical weather forecast and a first translated short-term predicted power;
a first prediction module configured to input the numerical weather forecast, the translational numerical weather forecast, the first short-term prediction power, the first translational short-term prediction power and the actual power into an ultra-short-term power prediction model obtained by training in advance to obtain a first ultra-short-term prediction power;
the second prediction module is configured to perform combined prediction by adopting a short-term combined prediction model obtained by training in advance based on the numerical weather forecast and the actual power to obtain a predicted power error and second short-term predicted power;
a second translation module configured to translate the second short-term predicted power to obtain a second translated short-term predicted power;
a third prediction module configured to input the numerical weather forecast, the translational numerical weather forecast, the actual power, the second short-term predicted power, the second translational short-term predicted power, and the predicted power error into an ultra-short-term error prediction model obtained by training in advance, so as to obtain a corrected prediction error;
a correction module configured to correct the second short-term predicted power by using the corrected prediction error to obtain a second ultra-short-term predicted power;
and the average value calculation module is configured to perform average calculation on the first ultra-short-term prediction power and the second ultra-short-term prediction power to obtain the ultra-short-term prediction power.
A third aspect of the application provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of the first aspect when executing the program.
A fourth aspect of the present application provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of the first aspect.
As can be seen from the above, the wind power ultra-short term power prediction method and the related device provided by the application obtain the numerical weather forecast, the first short term prediction power and the actual power of the wind farm at each historical time, obtain the first ultra-short term prediction power through the ultra-short term power prediction model, obtain the prediction power error and the second short term prediction power through the short term combined prediction model, obtain the corrected prediction error through the ultra-short term error prediction model, correct the second short term prediction power through combining the corrected error to obtain the second ultra-short term prediction power, perform averaging calculation according to the first ultra-short term prediction power and the second ultra-short term prediction power to obtain the ultra-short term prediction power, and solve the problem that the ultra-short term power is predicted to be unstable through a single algorithm of the wind farm in a manner combining the ultra-short term power prediction model, the short term combined prediction model and the ultra-short term error prediction model, so that the stability of the ultra-short term power prediction result is improved, and the probability of occurrence of the error and the extreme abnormal value at the future time is reduced.
Drawings
In order to more clearly illustrate the technical solutions in the present application or the related art, the drawings needed to be used in the description of the embodiments or the related art will be briefly introduced below, and it is obvious that the drawings in the following description are only embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of a wind power ultra-short term power prediction method according to an embodiment of the present application;
FIG. 2A is a schematic diagram of a translation process according to an embodiment of the present application;
fig. 2B is a schematic diagram of ultra-short-term wind power prediction according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a wind power ultra-short-term power prediction apparatus according to an embodiment of the present application;
fig. 4 is a schematic diagram of an electronic device according to an embodiment of the application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described in detail below with reference to the accompanying drawings in combination with specific embodiments.
It should be noted that technical terms or scientific terms used in the embodiments of the present application should have a general meaning as understood by those having ordinary skill in the art to which the present application belongs, unless otherwise defined. The use of "first," "second," and similar terms in the embodiments of the present application do not denote any order, quantity, or importance, but rather the terms are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
In the related technology, most wind power ultra-short term power prediction algorithms adopt a traditional statistical model, and the prediction model and the prediction method are single. The utilization of historical data and weather forecast data of the power station is insufficient, the time correlation of the data is not fully considered, and a traditional model cannot fit high-dimensional time sequence data, so that the problem of unstable predicted ultra-short-term power is caused.
The embodiment of the application provides a wind power ultra-short-term power prediction method, which solves the problem of unstable ultra-short-term power prediction of a single algorithm of a wind power plant by utilizing numerical weather forecast, first short-term prediction power and actual power of the wind power plant corresponding to each historical moment and combining an ultra-short-term power prediction model, a short-term combined prediction model and an ultra-short-term error prediction model, so that the stability of a wind power ultra-short-term power prediction result is improved, and the prediction error and the occurrence probability of extreme abnormal values at future moments are reduced.
As shown in fig. 1, the method of the present embodiment includes:
In this step, the numerical weather forecast, the first short-term predicted power and the actual power of the wind farm at each historical time may be stored in the cloud, where the storage location is not specifically limited, where the first short-term predicted power represents the short-term predicted power in the stored historical data.
For example, a multi-source Numerical Weather forecast (NWP), a short-term predicted power, and an actual power of a wind farm in one year of history are retrieved from the cloud, for example, the time resolution is 15 minutes, which indicates that the interval between every two adjacent historical moments is 15 minutes.
In some embodiments, after step 101, further comprising:
and respectively carrying out data cleaning on the numerical weather forecast, the first short-term predicted power and the actual power by utilizing a quartile algorithm to obtain the cleaned numerical weather forecast, the first short-term predicted power and the actual power.
In the above scheme, the quartile algorithm equally divides a data sample sequence arranged in order of size into four parts by three data points, and each part contains one fourth of the data quantity of the whole sequence data. Wherein the data samples are divided into samples of a numerical weather forecast, samples of a first short-term predicted power and samples of an actual power.
Abnormal data in the sample data are eliminated by utilizing a quartile algorithm, so that the prediction precision can be improved.
And 102, respectively carrying out translation processing on the numerical weather forecast and the first short-term predicted power to obtain a translation numerical weather forecast and a first translation short-term predicted power.
In the step, the numerical weather forecast and the first short-term prediction power are respectively subjected to translation processing to obtain a translation numerical weather forecast and the first translation short-term prediction power, and sample data required by prediction can be expanded by the mode, so that the accuracy and the stability of the prediction are improved.
In some embodiments, in response to determining that the numerical weather forecast comprises a predicted wind speed;
step 1021, obtaining a preset number of groups of predicted wind speeds, wherein each group of predicted wind speeds comprises a preset number of groups of predicted wind speeds corresponding to historical moments.
And 1022, translating the groups of the predicted wind speeds by a preset number according to the arrangement sequence of historical moments to obtain the groups of the translated predicted wind speeds by the preset number, and taking the groups of the translated predicted wind speeds by the preset number as the translated numerical weather forecast.
Step 1023, obtaining a preset number of first short-term predicted power groups, where each first short-term predicted power group includes a preset number of first short-term predicted powers corresponding to historical times.
Step 1024, translating each group of the first short-term predicted power by a preset number of groups according to the arrangement sequence of the historical time to obtain a translated group of the first short-term predicted power by the preset number, and taking the translated group of the first short-term predicted power by the preset number as the first translated short-term predicted power.
In the above scheme, the specific process of the translation processing for the predicted wind speed is as follows:
for example, as shown in fig. 2A, the original predicted wind speed sequence M and the translated predicted wind speed sequence N are respectively represented, the original predicted wind speed sequence M and the translated predicted wind speed sequence N are the same data sequence, and 1 to N represent data groups (i.e., groups of a preset number of predicted wind speeds), each group consisting of 16 (which may be set according to specific conditions and is not specifically limited herein) data at a resolution of 15 minutes (which may be set according to specific conditions and is not specifically limited herein). The N sequence is constructed by advancing the M sequence data and time by 4 hours. The 1 group of M sequence and the 2 groups of N sequence are combined into 1 data sample, and the 1 group of N sequence is deleted.
Similarly, the specific process of the translation processing of the first short-term predicted power is to translate the first short-term predicted power groups by a preset number of groups according to the arrangement sequence of the historical time to obtain the translated first short-term predicted power groups by the preset number, and the translated first short-term predicted power groups by the preset number are used as the first translated short-term predicted power.
Sample data required by prediction can be expanded through a translation processing mode, so that the accuracy and stability of prediction are improved, and the method can be suitable for wind power plants with different requirements.
And 103, inputting the numerical weather forecast, the translational numerical weather forecast, the first short-term predicted power, the first translational short-term predicted power and the actual power into an ultra-short-term power prediction model obtained by training in advance to obtain first ultra-short-term predicted power.
In this step, for example, a numerical weather forecast, a translational numerical weather forecast, a first short-term predicted power, a first translational short-term predicted power, and an actual power are respectively normalized, and each 16 (which may be set according to specific situations and is not specifically limited herein) normalized sample points are divided into a group: (1) x: the predicted wind speed and the short-term predicted power at 16 points corresponding to the historical time, and the predicted wind speed (translational predicted wind speed) and the translational short-term predicted power at 16 points in the future with respect to these historical times. y: actual power at 16 points is historical.
Inputting x and y into an ultra-short-term power prediction model, and obtaining first ultra-short-term prediction power through the ultra-short-term power prediction model obtained through training, wherein the ultra-short-term power prediction model is a Convolutional Neural Network (CNN).
And step 104, performing combined prediction by adopting a short-term combined prediction model obtained by training in advance based on the numerical weather forecast and the actual power to obtain a predicted power error and second short-term predicted power.
In this step, a short-term combined prediction model obtained through training in advance is used for combined prediction based on a numerical weather forecast and actual power, so that a predicted power error and a second short-term predicted power are obtained through the short-term combined prediction model, the predicted power error represents a difference between the second short-term predicted power and the actual power, and the second short-term predicted power represents new short-term predicted power obtained through prediction of the short-term combined prediction model.
Wherein, the short-term combination prediction model is a Convolutional Neural Network (CNN) model. The prediction power error and the second short-term prediction power are obtained through the short-term combination prediction model, so that all the prediction models can be fused, and the stability and accuracy of prediction are improved.
In some embodiments, responsive to determining that the numerical weather forecast includes wind speed, wind direction, temperature, and humidity;
step 1041, normalizing the wind speed, the wind direction, the temperature and the humidity respectively to obtain normalized wind speed, wind direction, temperature and humidity.
And 1042, calculating a product of the normalized wind speed and the normalized wind direction to obtain wind speed and wind direction product data.
And 1043, calculating a ratio of the normalized temperature and the normalized humidity to obtain temperature-humidity ratio data.
And step 1044, inputting the wind speed and wind direction product data, the temperature and humidity ratio data and the actual power into the short-term combined prediction model to obtain a plurality of sub short-term prediction powers.
And 1045, performing an average calculation on the multiple sub short-term predicted powers to obtain the second short-term predicted power.
And 1046, performing difference calculation on the second short-term predicted power and the actual power to obtain the predicted power error.
Step 1047, outputting the predicted power error and the second short-term predicted power via the short-term combined prediction model.
In the scheme, for example, a wind speed and wind direction product, a temperature-humidity ratio and other meteorological characteristics are constructed for each NWP, and a normalized meteorological characteristic set Di (i is the number of the multiple sources of NWP, and i is more than or equal to 1) is constructed by combining wind speed, wind direction, temperature and humidity data;
the sample data input into the short-term combined prediction model includes: meteorological set Di and actual power data. x: the meteorological set Di. y: the actual power. Inputting x and y into the short-term combined prediction model to obtain new short-term predicted power PF2i (namely sub short-term predicted power), and averaging each PF2i to obtain short-term combined predicted power (namely second short-term predicted power). And calculating the difference value between the short-term combined predicted power and the actual power to obtain absolute errors (errors) (namely predicted power errors), and outputting the absolute errors (namely predicted power errors) and the short-term combined predicted power (namely second short-term predicted power) through the short-term combined prediction model.
In some embodiments, step 1041 comprises:
using a normalisation function
Respectively carrying out normalization calculation on the wind speed, the wind direction, the temperature and the humidity to obtainTo the normalized wind speed, wind direction, temperature and humidity, wherein the
Any data which is required to be normalized in wind speed, wind direction, temperature or humidity,
indicating the maximum value of the preset zoom range,
represents the minimum value of the preset set zoom range,
representing normalized wind speed, wind direction, temperature or humidity.
In the scheme, the wind speed, the wind direction, the temperature and the humidity are respectively subjected to normalization calculation by utilizing the normalization function, so that the normalized wind speed, wind direction, temperature and humidity are obtained, and the prediction speed of the short-term combined prediction model is increased.
And 105, performing translation processing on the second short-term predicted power to obtain second translated short-term predicted power.
In the step, the second short-term predicted power is translated to obtain the second translated short-term predicted power, and the mode can expand sample data required by prediction, so that the accuracy and stability of the prediction are improved.
In some embodiments, step 105 comprises:
step 1051, obtaining a preset number of groups of second short-term predicted power, where each group of second short-term predicted power includes a preset number of second short-term predicted powers corresponding to historical moments.
Step 1052, translating each group of the second short-term predicted power by a preset number of groups according to the arrangement sequence of the historical time to obtain a translated group of the second short-term predicted power by the preset number, and taking the translated group of the second short-term predicted power by the preset number as the second translated short-term predicted power.
In the above-described scheme, as shown in fig. 2A, each of the groups of the second short-term predicted powers may be shifted by a predetermined number of groups in the order of the arrangement of the historical times by using the same shift processing method that shifts the predicted wind speed, so as to obtain the group of the shifted predetermined number of second short-term predicted powers, and the group of the shifted predetermined number of second short-term predicted powers may be used as the second shifted short-term predicted power.
The method can expand sample data required by prediction in a translation processing mode, thereby improving the accuracy and stability of the prediction and being suitable for wind power plants with different requirements.
And 106, inputting the numerical weather forecast, the translational numerical weather forecast, the actual power, the second short-term predicted power, the second translational short-term predicted power and the predicted power error into an ultra-short-term error prediction model obtained by training in advance to obtain a corrected prediction error.
In this step, for example, the numerical weather forecast, the translational numerical weather forecast, the actual power, the second short-term predicted power, the second translational short-term predicted power, and the predicted power error are respectively normalized, and after normalization, each 16 (which may be set according to specific situations and is not specifically limited herein) sample points are divided into a group, and each sample point includes x and y, where x: the predicted wind speed, the short-term combined predicted power and the actual power of 16 points corresponding to the historical moment, and the predicted wind speed (translational predicted wind speed) and the short-term combined predicted power (namely the short-term combined translational predicted power) of 16 points in the future corresponding to the historical moment. y: absolute errors (errors) of 16 points in the future corresponding to historical time;
inputting x and y into an ultra-short term error prediction model, wherein the ultra-short term error prediction model is a Long short-term memory (LSTM) model, and outputting a corrected prediction error through the ultra-short term error prediction model, wherein the corrected prediction error represents the error between the predicted ultra-short term power and the actual power at the future moment.
And 107, correcting the second short-term predicted power by using the corrected predicted error to obtain a second ultra-short-term predicted power.
In this step, the corrected second ultra-short term predicted power is obtained by correcting the second short term predicted power by using the corrected prediction error.
In some embodiments, step 107 comprises:
and performing summation calculation by using the corrected prediction error and the second short-term prediction power to obtain the second ultra-short-term prediction power.
In the scheme, the accuracy and the stability of the second ultra-short-term prediction power are improved by using a mode of carrying out summation calculation on the corrected prediction error and the second short-term prediction power.
And 108, averaging the first ultra-short term prediction power and the second ultra-short term prediction power to obtain the ultra-short term prediction power.
In the step, the first ultra-short-term prediction power and the second ultra-short-term prediction power obtained through correction are subjected to averaging calculation, so that the obtained ultra-short-term prediction model is more accurate and stable.
According to the scheme, numerical weather forecast, first short-term forecast power and actual power of the wind power plant corresponding to each historical moment are obtained, first ultra-short-term forecast power is obtained through an ultra-short-term power forecast model, forecast power errors and second short-term forecast power are obtained through a short-term combined forecast model, then a corrected forecast error is obtained through the ultra-short-term error forecast model, the second short-term forecast power is corrected through the corrected error, second ultra-short-term forecast power is obtained, average calculation is conducted according to the first ultra-short-term forecast power and the second ultra-short-term forecast power, ultra-short-term forecast power is obtained, and the problem that ultra-short-term power is unstable through single algorithm forecast of the wind power plant is solved through the combination of the ultra-short-term power forecast model, the short-term combined forecast model and the ultra-short-term forecast model, the stability of the wind power forecast result is improved, and the probability of occurrence of errors and extreme abnormal values of forecast at future moments is reduced.
The process of wind power ultra-short-term power prediction is specifically described in one embodiment, and specifically described as follows:
as shown in fig. 2B, the database reads the short-term raw forecast data (i.e. numerical weather forecast, first short-term predicted power) and actual power data, and performs data cleansing;
constructing a meteorological characteristic-wind speed and wind direction product (namely wind speed and wind direction product data) and a temperature-humidity ratio (namely temperature-humidity ratio data);
extracting the predicted wind speed, the translational predicted wind speed and the short-term predicted power PF1, and the translational short-term predicted power and the actual power, dividing the extracted predicted wind speed, the translational predicted wind speed and the short-term predicted power into a training set and a testing set through normalization, inputting the ultra-short-term CNN model to train the model until the preset training times are reached, stopping training when the error of the ultra-short-term CNN model is minimum, and obtaining the trained ultra-short-term CNN model. Inputting the trained ultra-short term CNN model (i.e. ultra-short term power prediction model) by using the set feature1 (i.e. predicted wind speed, translational predicted wind speed, short term predicted power PF1, translational short term predicted power and actual power), and outputting the CNN ultra-short term predicted power CDQ1 (i.e. first ultra-short term predicted power).
And dividing the meteorological feature set Di into a training set and a testing set, inputting a short-term CNN model, training the model until reaching a preset training frequency, stopping training when the error of the short-term CNN model is minimum, obtaining the trained short-term CNN model, taking the output short-term combined predicted power and the predicted error as one of input data of the ultra-short-term LSTM model, inputting the trained short-term CNN model (namely the short-term combined predicted model) by using the set Di, and outputting the predicted error (namely the predicted power error) and the average value of the short-term combined predicted power PF2i (namely the short-term combined predicted power) (namely the second short-term predicted power).
And translating the predicted wind speed, the translated predicted wind speed, the actual power, the short-term combined predicted power output by the short-term CNN model training and the predicted error, normalizing the short-term combined predicted power to divide the power into a training set and a test set, inputting the ultra-short-term LSTM model to train the model until the preset training times are reached, and stopping training to obtain the trained ultra-short-term LSTM model when the error of the ultra-short-term LSTM model is minimum. And inputting a trained ultra-short term LSTM model (namely an ultra-short term error prediction model) by using the set feature2 (namely predicted wind speed, translational predicted wind speed, actual power, and short term combined predicted power and predicted error output by the trained short term CNN model, and combining data obtained by performing translational processing on the short term combined predicted power), and outputting a corrected predicted error (namely a corrected predicted error) by the trained ultra-short term LSTM model.
And correcting the short-term combined predicted power (namely, second short-term predicted power) output by the trained short-term CNN model by using the prediction error (namely, corrected prediction error) to obtain LSTM ultra-short-term predicted power CDQ2 (namely, second ultra-short-term predicted power).
And calculating the average value of the CNN ultra-short-term predicted power CDQ1 (namely the first ultra-short-term predicted power) and the LSTM ultra-short-term predicted power CDQ2 (namely the second ultra-short-term predicted power) to obtain the ultra-short-term predicted power.
It should be noted that the method of the embodiment of the present application may be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiment, and the multiple devices interact with each other to complete the method.
It should be noted that the foregoing describes some embodiments of the present application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments described above and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Based on the same inventive concept, corresponding to the method of any embodiment, the application also provides a wind power ultra-short-term power prediction device.
Referring to fig. 3, the wind power ultra-short term power prediction apparatus includes:
the obtaining module 301 is configured to obtain a numerical weather forecast, a first short-term predicted power and an actual power corresponding to each historical time of the wind farm, wherein a preset time is spaced between every two adjacent historical times;
a first translation module 302 configured to perform translation processing on the numerical weather forecast and the first short-term predicted power respectively to obtain a translated numerical weather forecast and a first translated short-term predicted power;
a first prediction module 303, configured to input the numerical weather forecast, the translational numerical weather forecast, the first short-term prediction power, the first translational short-term prediction power, and the actual power into an ultra-short-term power prediction model obtained through training in advance, so as to obtain a first ultra-short-term prediction power;
a second prediction module 304, configured to perform combined prediction by using a short-term combined prediction model obtained through training in advance based on the numerical weather forecast and the actual power, so as to obtain a predicted power error and a second short-term predicted power;
a second translation module 305 configured to translate the second short-term predicted power to obtain a second translated short-term predicted power;
a third prediction module 306, configured to input the numerical weather forecast, the translational numerical weather forecast, the actual power, the second short-term predicted power, the second translational short-term predicted power, and the predicted power error into an ultra-short-term error prediction model obtained through training in advance, so as to obtain a corrected prediction error;
a correcting module 307 configured to correct the second short-term predicted power by using the corrected prediction error to obtain a second ultra-short-term predicted power;
an average calculation module 308 configured to perform an average calculation on the first ultra-short term prediction power and the second ultra-short term prediction power to obtain the ultra-short term prediction power.
In some embodiments, in response to determining that the numerical weather forecast includes wind speed, wind direction, temperature, and humidity;
a second prediction module 304, comprising:
the normalization unit is configured to perform normalization processing on the wind speed, the wind direction, the temperature and the humidity respectively to obtain normalized wind speed, wind direction, temperature and humidity;
a product calculation unit configured to perform product calculation by using the normalized wind speed and wind direction to obtain wind speed and wind direction product data;
a ratio calculation unit configured to perform a ratio calculation on the normalized temperature and the normalized humidity to obtain temperature-humidity ratio data;
a sub-short-term prediction power calculation unit configured to input the wind speed and wind direction product data, the temperature-humidity ratio data and the actual power into the short-term combined prediction model to obtain a plurality of sub-short-term prediction powers;
an average calculation unit configured to perform an average calculation on the plurality of sub-short-term prediction powers to obtain the second short-term prediction power;
a difference calculation unit configured to perform difference calculation on the second short-term predicted power and the actual power to obtain the predicted power error;
an output unit configured to output the predicted power error and the second short-term predicted power via the short-term combined prediction model.
In some embodiments, the normalization unit is specifically configured to:
using a normalisation function
Respectively carrying out normalization calculation on the wind speed, the wind direction, the temperature and the humidity to obtain the normalized wind speed, wind direction, temperature and humidity, wherein the normalization calculation is carried out on the wind speed, the wind direction, the temperature and the humidity
Any data which is required to be normalized in wind speed, wind direction, temperature or humidity,
indicating the maximum value of the preset zoom range,
represents the minimum value of the preset set zoom range,
representing normalized wind speed, wind direction, temperature or humidity.
In some embodiments, the modification module 307 is specifically configured to:
and performing summation calculation by using the corrected prediction error and the second short-term prediction power to obtain the second ultra-short-term prediction power.
In some embodiments, in response to determining that the numerical weather forecast comprises a predicted wind speed;
the first translation module 302 is specifically configured to:
acquiring groups of a preset number of predicted wind speeds, wherein each group of predicted wind speeds comprises the predicted wind speeds corresponding to a preset number of historical moments;
translating the groups of each predicted wind speed by a preset number according to the arrangement sequence of historical moments to obtain the groups of the translated predicted wind speeds by the preset number, and taking the groups of the translated predicted wind speeds by the preset number as the translation numerical weather forecast;
the method comprises the steps of obtaining a preset number of groups of first short-term predicted power, wherein each group of the first short-term predicted power comprises a preset number of first short-term predicted power corresponding to historical time;
and translating each group of the first short-term predicted power by a preset number of groups according to the arrangement sequence of historical time to obtain the translated group of the first short-term predicted power by the preset number, and taking the translated group of the first short-term predicted power by the preset number as the first translated short-term predicted power.
In some embodiments, the second translation module 305 is specifically configured to:
acquiring a preset number of groups of second short-term predicted power, wherein each group of the second short-term predicted power comprises a preset number of second short-term predicted power corresponding to historical time;
and translating each group of the second short-term predicted power by a preset number of groups according to the arrangement sequence of the historical time to obtain the translated group of the second short-term predicted power by the preset number, and taking the translated group of the second short-term predicted power by the preset number as the second translated short-term predicted power.
In some embodiments, the wind power ultra-short term power prediction apparatus further includes a data cleansing module specifically configured to:
and respectively carrying out data cleaning on the numerical weather forecast, the first short-term predicted power and the actual power by utilizing a quartile algorithm to obtain the cleaned numerical weather forecast, the first short-term predicted power and the actual power.
For convenience of description, the above devices are described as being divided into various modules by functions, which are described separately. Of course, the functionality of the various modules may be implemented in the same one or more pieces of software and/or hardware in the practice of the present application.
The device of the above embodiment is used to implement the corresponding wind power ultra-short term power prediction method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, corresponding to the method of any embodiment, the application further provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor, and when the processor executes the program, the wind power ultra-short term power prediction method of any embodiment is implemented.
Fig. 4 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 401, a memory 402, an input/output interface 403, a communication interface 404, and a bus 405. Wherein the processor 401, the memory 402, the input/output interface 403 and the communication interface 404 are communicatively connected to each other within the device via a bus 405.
The processor 401 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present specification.
The Memory 402 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 402 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 402 and called to be executed by the processor 401.
The input/output interface 403 is used for connecting an input/output module to realize information input and output. The i/o module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 404 is used to connect a communication module (not shown in the figure) to implement communication interaction between the present device and other devices. The communication module can realize communication in a wired mode (for example, USB, network cable, etc.), and can also realize communication in a wireless mode (for example, mobile network, WIFI, bluetooth, etc.).
The bus 405 includes a path to transfer information between various components of the device, such as the processor 401, memory 402, input/output interface 403, and communication interface 404.
It should be noted that although the above-mentioned device only shows the processor 401, the memory 402, the input/output interface 403, the communication interface 404 and the bus 405, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.
The electronic device of the foregoing embodiment is used to implement the corresponding wind power ultra-short term power prediction method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application further provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the wind power ultra-short term power prediction method according to any of the above-mentioned embodiments.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, for storing information may be implemented in any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device.
The computer instructions stored in the storage medium of the foregoing embodiment are used to enable the computer to execute the wind power ultra-short term power prediction method according to any of the foregoing embodiments, and have the beneficial effects of corresponding method embodiments, which are not described herein again.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the context of the present application, technical features in the above embodiments or in different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application described above, which are not provided in detail for the sake of brevity.
In addition, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown in the provided figures for simplicity of illustration and discussion, and so as not to obscure the embodiments of the application. Furthermore, devices may be shown in block diagram form in order to avoid obscuring embodiments of the application, and this also takes into account the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the embodiments of the application are to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the application, it should be apparent to one skilled in the art that the embodiments of the application can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present application has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures, such as Dynamic RAM (DRAM), may use the discussed embodiments.
The present embodiments are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of the embodiments of the present application are intended to be included within the scope of the present application.
Claims (9)
1. A wind power ultra-short-term power prediction method is characterized by comprising the following steps:
acquiring numerical weather forecast, first short-term predicted power and actual power corresponding to each historical moment of the wind power plant, wherein preset time is arranged between every two adjacent historical moments;
respectively carrying out translation processing on the numerical weather forecast and the first short-term prediction power to obtain a translation numerical weather forecast and a first translation short-term prediction power;
inputting the numerical weather forecast, the translational numerical weather forecast, the first short-term predicted power, the first translational short-term predicted power and the actual power into an ultra-short-term power prediction model obtained by training in advance to obtain first ultra-short-term predicted power;
performing combined prediction by adopting a short-term combined prediction model obtained by training in advance based on the numerical weather forecast and the actual power to obtain a predicted power error and second short-term predicted power;
performing translation processing on the second short-term predicted power to obtain a second translated short-term predicted power, and performing translation processing on the second short-term predicted power to obtain a second translated short-term predicted power, including:
obtaining a preset number of groups of second short-term predicted power, wherein each group of the second short-term predicted power comprises a preset number of second short-term predicted power corresponding to historical time;
translating each group of the second short-term predicted power by a preset number of groups according to the arrangement sequence of the historical time to obtain the translated group of the second short-term predicted power by the preset number, and taking the translated group of the second short-term predicted power by the preset number as the second translated short-term predicted power;
inputting the numerical weather forecast, the translational numerical weather forecast, the actual power, the second short-term predicted power, the second translational short-term predicted power and the predicted power error into an ultra-short-term error prediction model obtained through training in advance to obtain a corrected prediction error;
correcting the second short-term predicted power by using the corrected prediction error to obtain second ultra-short-term predicted power;
and carrying out averaging calculation on the first ultra-short-term prediction power and the second ultra-short-term prediction power to obtain the ultra-short-term prediction power.
2. The method of claim 1, wherein in response to determining that the numerical weather forecast comprises a wind speed, a wind direction, a temperature, and a humidity;
the method for carrying out combined prediction by adopting a short-term combined prediction model obtained through training in advance based on the numerical weather forecast and the actual power to obtain a predicted power error and a second short-term predicted power comprises the following steps:
respectively carrying out normalization processing on the wind speed, the wind direction, the temperature and the humidity to obtain normalized wind speed, wind direction, temperature and humidity;
calculating the product of the normalized wind speed and the normalized wind direction to obtain wind speed and wind direction product data;
calculating the ratio of the normalized temperature and the normalized humidity to obtain temperature-humidity ratio data;
inputting the wind speed and wind direction product data, the temperature and humidity ratio data and the actual power into the short-term combined prediction model to obtain a plurality of sub short-term prediction powers;
averaging the plurality of sub short-term prediction powers to obtain a second short-term prediction power;
calculating the difference between the second short-term predicted power and the actual power to obtain the predicted power error;
outputting the predicted power error and the second short-term predicted power via the short-term combined prediction model.
3. The method of claim 2, wherein the normalizing the wind speed, the wind direction, the temperature and the humidity respectively to obtain normalized wind speed, wind direction, temperature and humidity comprises:
using a normalisation function
Respectively carrying out normalization calculation on the wind speed, the wind direction, the temperature and the humidity to obtain the normalized wind speed, wind direction, temperature and humidity, wherein the normalized wind speed, wind direction, temperature and humidity are obtained
Any data which is required to be normalized in wind speed, wind direction, temperature or humidity,
indicating the maximum value of the preset zoom range,
represents the minimum value of the preset set zoom range,
representing normalized wind speed, wind direction, temperature or humidity.
4. The method of claim 1, wherein said modifying the second short-term predicted power with the modified prediction error to obtain a second ultra-short-term predicted power comprises:
and performing summation calculation by using the corrected prediction error and the second short-term prediction power to obtain the second ultra-short-term prediction power.
5. The method of claim 1, wherein in response to determining that the numerical weather forecast comprises a predicted wind speed;
the translating the numerical weather forecast and the first short-term prediction power respectively to obtain a translation historical numerical weather forecast and a first translation short-term prediction power includes:
acquiring groups of a preset number of predicted wind speeds, wherein each group of predicted wind speeds comprises the predicted wind speeds corresponding to a preset number of historical moments;
translating the groups of each predicted wind speed by a preset number according to the arrangement sequence of historical moments to obtain the groups of the translated predicted wind speeds by the preset number, and taking the groups of the translated predicted wind speeds by the preset number as the translation numerical weather forecast;
the method comprises the steps of obtaining a preset number of groups of first short-term predicted power, wherein each group of the first short-term predicted power comprises a preset number of first short-term predicted power corresponding to historical time;
and translating each group of the first short-term predicted power by a preset number of groups according to the arrangement sequence of historical time to obtain the translated group of the first short-term predicted power by the preset number, and taking the translated group of the first short-term predicted power by the preset number as the first translated short-term predicted power.
6. The method of claim 1, wherein after obtaining the numerical weather forecast, the first short-term predicted power and the actual power corresponding to the wind farm at each historical time, the method further comprises:
and respectively carrying out data cleaning on the numerical weather forecast, the first short-term predicted power and the actual power by utilizing a quartile algorithm to obtain the cleaned numerical weather forecast, the first short-term predicted power and the actual power.
7. A wind power ultra-short term power prediction device is characterized by comprising:
the acquiring module is configured to acquire a numerical weather forecast, first short-term predicted power and actual power corresponding to each historical moment of the wind power plant, wherein a preset time is arranged between every two adjacent historical moments;
a first translation module configured to perform translation processing on the numerical weather forecast and the first short-term predicted power respectively to obtain a translated numerical weather forecast and a first translated short-term predicted power;
a first prediction module configured to input the numerical weather forecast, the translational numerical weather forecast, the first short-term prediction power, the first translational short-term prediction power and the actual power into an ultra-short-term power prediction model obtained by training in advance to obtain a first ultra-short-term prediction power;
the second prediction module is configured to perform combined prediction by adopting a short-term combined prediction model obtained by training in advance based on the numerical weather forecast and the actual power to obtain a predicted power error and second short-term predicted power;
a second translation module configured to translate the second short-term predicted power to obtain a second translated short-term predicted power, and translate the second short-term predicted power to obtain a second translated short-term predicted power, including:
acquiring a preset number of groups of second short-term predicted power, wherein each group of the second short-term predicted power comprises a preset number of second short-term predicted power corresponding to historical time;
translating each group of the second short-term predicted power by a preset number of groups according to the arrangement sequence of historical time to obtain the translated group of the second short-term predicted power by the preset number, and taking the translated group of the second short-term predicted power by the preset number as the second translated short-term predicted power;
a third prediction module configured to input the numerical weather forecast, the translational numerical weather forecast, the actual power, the second short-term predicted power, the second translational short-term predicted power, and the predicted power error into an ultra-short-term error prediction model obtained by training in advance, so as to obtain a corrected prediction error;
a correction module configured to correct the second short-term predicted power by using the corrected prediction error to obtain a second ultra-short-term predicted power;
and the average value calculation module is configured to perform average calculation on the first ultra-short-term prediction power and the second ultra-short-term prediction power to obtain the ultra-short-term prediction power.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 6 when executing the program.
9. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211706200.XA CN115689061B (en) | 2022-12-29 | 2022-12-29 | Wind power ultra-short term power prediction method and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211706200.XA CN115689061B (en) | 2022-12-29 | 2022-12-29 | Wind power ultra-short term power prediction method and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115689061A CN115689061A (en) | 2023-02-03 |
| CN115689061B true CN115689061B (en) | 2023-03-17 |
Family
ID=85056109
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211706200.XA Active CN115689061B (en) | 2022-12-29 | 2022-12-29 | Wind power ultra-short term power prediction method and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115689061B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117272827B (en) * | 2023-10-13 | 2024-04-12 | 辽宁天成联合科技有限公司 | Ultra-short-term wind speed prediction method of wind measuring system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102102626B (en) * | 2011-01-30 | 2012-08-29 | 华北电力大学 | Method for forecasting short-term power in wind power station |
| CN102880810B (en) * | 2012-10-25 | 2015-07-15 | 山东电力集团公司电力科学研究院 | Wind power prediction method based on time sequence and neural network method |
| CN113516318A (en) * | 2021-08-06 | 2021-10-19 | 北京东润环能科技股份有限公司 | Short-term power prediction method for deep learning |
| CN115456289A (en) * | 2022-09-22 | 2022-12-09 | 华润电力技术研究院有限公司 | Wind power ultra-short-term power prediction method, system, equipment and medium |
-
2022
- 2022-12-29 CN CN202211706200.XA patent/CN115689061B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115689061A (en) | 2023-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008080B (en) | Business index anomaly detection method and device based on time sequence and electronic equipment | |
| CN115689061B (en) | Wind power ultra-short term power prediction method and related equipment | |
| CN110838075A (en) | Training and predicting method and device for prediction model of transient stability of power grid system | |
| KR20210017342A (en) | Time series prediction method and apparatus based on past prediction data | |
| CN113255792B (en) | Data anomaly point detection method, device, system and storage medium | |
| CN111079944A (en) | Method and device for realizing interpretation of transfer learning model, electronic equipment and storage medium | |
| CN111931345A (en) | Monitoring data prediction method, device, equipment and readable storage medium | |
| CN109814101B (en) | Method and device for predicting position of aircraft | |
| CN114742234A (en) | Fault diagnosis model training method, fault diagnosis method and related device | |
| CN116523145B (en) | Photovoltaic power ultra-short-term prediction method and device, computer equipment and storage medium | |
| CN112100869B (en) | Power line point supplementing method and device and electronic equipment | |
| CN111798263A (en) | Transaction trend prediction method and device | |
| CN115423159A (en) | Photovoltaic power generation prediction method and device and terminal equipment | |
| CN115186751A (en) | CVT metering error prediction method and device based on s transformation and storage medium | |
| CN113988491B (en) | Photovoltaic short-term power prediction method and device, electronic equipment and storage medium | |
| CN113568067A (en) | Numerical weather forecasting method and device, computer storage medium and electronic equipment | |
| CN111563078A (en) | Data quality detection method and device based on time sequence data and storage device | |
| CN116248959B (en) | Network player fault detection method, device, equipment and storage medium | |
| CN113902228A (en) | Wind power prediction method based on stepwise regression and deep learning and related equipment | |
| CN115906368A (en) | Temperature signal real-time load spectrum calculation method and related equipment | |
| CN115640336B (en) | Business big data mining method, system and cloud platform | |
| CN117851820A (en) | Sample expansion method, device, electronic equipment and storage medium | |
| CN117033352A (en) | Data restoration method and device, terminal equipment and storage medium | |
| CN114528907B (en) | Industrial abnormal data detection method and device | |
| CN110942196B (en) | Predicted irradiation correction method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |