CN112613632A - Power prediction model establishing method, prediction method and device and electronic equipment - Google Patents
Power prediction model establishing method, prediction method and device and electronic equipment Download PDFInfo
- Publication number
- CN112613632A CN112613632A CN202010247420.5A CN202010247420A CN112613632A CN 112613632 A CN112613632 A CN 112613632A CN 202010247420 A CN202010247420 A CN 202010247420A CN 112613632 A CN112613632 A CN 112613632A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- power
- predicted
- speed data
- sample
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 79
- 230000005684 electric field Effects 0.000 claims description 23
- 238000001914 filtration Methods 0.000 claims description 20
- 238000005259 measurement Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000003860 storage Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000012896 Statistical algorithm Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011022 operating instruction Methods 0.000 description 2
- 238000000053 physical method Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The embodiment of the application provides a power prediction model establishing method, a prediction device and electronic equipment. The method for establishing the power prediction model comprises the following steps: acquiring sample predicted wind speed data and sample measured wind speed data corresponding to the sample predicted wind speed data; dispersing the sample predicted wind speed data into a plurality of wind speed sections according to a preset wind speed value interval; determining the predicted power of each wind speed section according to the accuracy relation between the predicted power and the actually measured power; and determining a power prediction model according to the predicted power of all the wind speed sections. The power prediction model constructed by the method for establishing the power prediction model provided by the embodiment of the application can effectively improve the power prediction accuracy, is suitable for ultra-short-term prediction and short-term prediction, and obtains a prediction result closer to the reality because the sample is used for predicting the wind speed data.
Description
Technical Field
The application relates to the technical field of wind power, in particular to a power prediction model establishing method, a prediction device and electronic equipment.
Background
The power prediction is implemented by establishing a prediction model of the output power of the electric field according to data such as historical power and historical wind speed of the wind power plant, inputting data such as wind speed, power or numerical weather forecast data serving as sample data of model training, and obtaining the predicted output power of the electric field. The power prediction is divided according to the prediction duration and can be divided into short-term prediction and ultra-short-term prediction, wherein the short-term prediction refers to the prediction of the wind power output power within 1-3 days in the future, and the ultra-short-term prediction refers to the prediction of the wind power output power within 0h-4h (hours) in the future.
By adopting a proper modeling method, the accuracy of power prediction can be improved to a great extent, and important decision support is provided for power scheduling. The power prediction modeling method mainly comprises two main categories of a physical method and a statistical method: the essence of the physical method is that a roughness and terrain change model is utilized to simulate a local effect, and wind speed data of numerical weather forecast is converted into wind speed data at a fan hub, so that the generated power is predicted. The statistical algorithm mainly comprises a time sequence algorithm, a machine learning algorithm and the like, wherein the time sequence algorithm mainly comprises the steps of establishing a mapping relation between input and output, and the machine learning algorithm depends on infinite approximation of a nonlinear relation. Common machine algorithms include neural network algorithms, support vector machines, and the like.
However, time series algorithms are generally only suitable for ultra-short term prediction, and the prediction accuracy decreases greatly as the prediction time increases. Common statistical algorithms such as a neural network algorithm and a support vector machine algorithm are generally stable in a sample adopted in a training process, wind speed data corresponding to abnormal weather is often abandoned in advance and cannot be used as training sample data, so that a prediction result obtained by the statistical algorithm can be disjointed to a certain extent from an actual situation, and the obtained prediction result is not accurate enough.
Disclosure of Invention
The application provides a power prediction model establishing method, a prediction device and electronic equipment aiming at the defects of the existing mode, and aims to solve the technical problems that in the prior art, power prediction is influenced by a prediction period and is inaccurate, and the difference between the power prediction and the actual wind speed is large.
In a first aspect, an embodiment of the present application provides a method for building a power prediction model, including:
acquiring sample predicted wind speed data and sample measured wind speed data corresponding to the sample predicted wind speed data;
dispersing the sample predicted wind speed data into a plurality of wind speed sections according to a preset wind speed value interval;
determining the predicted power of each wind speed section according to the accuracy relation between the predicted power and the actually measured power;
and determining a power prediction model according to the predicted power of all the wind speed sections.
In certain implementations of the first aspect, obtaining the sample predicted wind speed data and the sample measured wind speed data corresponding to the sample predicted wind speed data comprises:
acquiring original predicted wind speed data in a preset time period;
filtering the original predicted wind speed data according to preset data filtering conditions to obtain sample predicted wind speed data;
and determining sample actual measurement wind speed data corresponding to the sample predicted wind speed data in a preset time period according to the sample predicted wind speed data.
With reference to the first aspect and the above-mentioned implementations, in some implementations of the first aspect, the step of obtaining raw predicted wind speed data over a predetermined time period comprises:
acquiring first predicted wind speed data of a first meteorological database and first measured wind speed data corresponding to the first predicted wind speed data, and determining a first wind speed difference value;
acquiring second predicted wind speed data of a second meteorological database and second measured wind speed data corresponding to the second predicted wind speed data, and determining a second wind speed difference value;
and determining the first predicted wind speed data or the second predicted wind speed data corresponding to the minimum value of the first wind speed difference value and the second wind speed difference value as the original predicted wind speed data.
With reference to the first aspect and the foregoing implementation manners, in some implementation manners of the first aspect, the filtering the condition according to preset data includes: the data difference value is greater than a preset difference value threshold value;
the method comprises the following steps of filtering original predicted wind speed data according to preset data filtering conditions to obtain sample predicted wind speed data, wherein the steps comprise:
determining a wind speed difference value between the original predicted wind speed data and the sample actual measured wind speed data at the same time;
and if the wind speed difference is smaller than or equal to the preset difference threshold, keeping the original predicted wind speed data as sample predicted wind speed data.
With reference to the first aspect and the foregoing implementation manners, in some implementation manners of the first aspect, discretizing the sample predicted wind speed data into a plurality of wind speed segments according to a preset wind speed value interval includes:
uniformly dividing a preset wind speed value interval into a plurality of wind speed subareas according to a preset wind speed value step length;
and determining sample predicted wind speed data corresponding to each wind speed partition according to the speed of the sample predicted wind speed data.
With reference to the first aspect and the foregoing implementation manners, in some implementation manners of the first aspect, determining the predicted power of each wind speed segment according to an accuracy relationship between the predicted power and the measured power includes:
acquiring sample predicted power data corresponding to each sample predicted wind speed data in the wind speed section and sample measured power data corresponding to each sample measured wind speed data;
determining the accuracy corresponding to the actually measured wind speed data of each sample according to the predicted power data of the sample, the installed capacity data of the electric field, the actually measured power data of the sample corresponding to the predicted power data of the sample and the accuracy relation;
determining a power qualified interval corresponding to the actually measured wind speed data of the sample according to the accuracy and the installed capacity data of the electric field;
and determining a superposition interval with the highest interval superposition degree according to the qualified power interval in each wind speed subsection, and determining a power value corresponding to the superposition interval as the predicted power of the wind speed subsection.
With reference to the first aspect and the foregoing implementation manners, in some implementation manners of the first aspect, the step of determining the power value corresponding to the overlap interval as the predicted power of the wind speed segment includes: and determining the average value of the maximum power value and the minimum power value in the coincidence interval as the predicted power.
With reference to the first aspect and the foregoing implementations, in some implementations of the first aspect, determining a power prediction model according to predicted powers of all wind speed segments includes:
according to the predicted power and sample predicted wind speed data corresponding to the predicted power, determining a discrete model of power prediction;
and determining a power prediction model according to an interpolation method and a discrete model.
In a second aspect, the present application provides a power prediction method, including:
acquiring original predicted wind speed data and a power prediction model, wherein the power prediction model is determined by the establishment method of the power prediction model provided by the first aspect of the application;
and inputting the original predicted wind speed data to a power prediction model to obtain the predicted power corresponding to the original predicted wind speed data.
In a third aspect, the present application provides an apparatus for building a power prediction model, including:
the data acquisition module is used for acquiring sample predicted wind speed data and sample measured wind speed data corresponding to the sample predicted wind speed data;
the data dividing module is used for dispersing the sample predicted wind speed data into a plurality of wind speed sections according to a preset wind speed value interval;
the power determination module is used for determining the predicted power of each wind speed section according to the accuracy relation between the predicted power and the actually measured power;
and the model establishing module is used for determining a power prediction model according to the predicted power of all the wind speed sections.
In a fourth aspect, the present application provides a power prediction apparatus, including:
an obtaining module, configured to obtain original predicted wind speed data and a power prediction model, where the power prediction model is determined by a method for establishing the power prediction model according to the first aspect of the present application;
and the prediction module is used for inputting the original predicted wind speed data to the power prediction model to obtain the predicted power corresponding to the original predicted wind speed data.
In a fifth aspect, the present application provides an electronic device, comprising:
a processor, a memory, and a bus;
a bus for connecting the processor and the memory;
a memory for storing operating instructions;
and the processor is used for realizing the establishing method of the power prediction model provided by the first aspect of the application or realizing the power prediction method provided by the second aspect of the application by calling the operation instruction.
The technical scheme provided by the embodiment of the application has the following beneficial technical effects:
according to the method for establishing the power prediction model, after sample predicted wind speed data are dispersed to wind speed sections, the predicted power in each discrete wind speed section is found out according to the accuracy rate relation between the predicted power and the actually measured power, so that the power corresponding to the predicted wind speed in each wind speed section is close to the predicted power, and the variance of the obtained power prediction accuracy rate is smaller. The method for predicting the wind power generation power of the wind power plant by the power prediction model established by the establishing method can effectively improve the power prediction accuracy, is suitable for ultra-short-term prediction and short-term prediction, and obtains a prediction result closer to the reality due to the fact that the sample is used for predicting the wind speed data.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flowchart of a method for establishing a power prediction model according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart of a method for obtaining sample predicted wind speed data and sample measured wind speed data corresponding to the sample predicted wind speed data according to an embodiment of the present disclosure;
FIG. 3 is a schematic flow chart of a method for discretizing sample predicted wind speed data into a plurality of wind speed segments according to a predetermined wind speed value segment according to an embodiment of the present application;
FIG. 4 is a schematic flow chart illustrating a process of determining the predicted power of each wind speed segment according to an accuracy relationship between the predicted power and the measured power according to the embodiment of the present application;
fig. 5 is a schematic flowchart of a method of power prediction according to an embodiment of the present disclosure;
fig. 6 is a schematic structural framework diagram of an apparatus for building a power prediction model according to an embodiment of the present application;
fig. 7 is a schematic structural framework diagram of a power prediction apparatus according to an embodiment of the present application;
fig. 8 is a schematic structural framework diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the present application, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar parts or parts having the same or similar functions throughout. In addition, if a detailed description of the known art is not necessary for illustrating the features of the present application, it is omitted. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.
It will be understood by those within the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
The terms referred to in this application will first be introduced and explained:
wind power generation becomes an important component of clean new energy due to the advantages of wind energy, however, wind speed is unstable, and the generated energy is also unstable, so that electric energy is often required to be scheduled to be stably applied to production and life. In order to more accurately schedule the electric energy, the power of the fan in the electric field needs to be predicted in advance according to the wind speed condition. By adopting a proper modeling method, more accurate power prediction can be obtained.
However, the existing modeling method is only suitable for ultra-short term prediction, once the prediction period is increased, the accuracy of power prediction is greatly reduced, or the original data of the predicted wind speed is discarded to a certain extent, and the original real and normal wind speed data is not included in the model as the prediction basis, so that the prediction result is greatly different from the actual situation.
The application provides a power prediction model establishing method, a prediction device and electronic equipment, and aims to solve the technical problems in the prior art.
The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments.
In an embodiment of the first aspect of the present application, a method for building a power prediction model is provided, as shown in fig. 1, including the following steps:
s110: and acquiring sample predicted wind speed data and sample measured wind speed data corresponding to the sample predicted wind speed data.
S120: and dispersing the sample predicted wind speed data into a plurality of wind speed sections according to the preset wind speed value section.
S130: and determining the predicted power of each wind speed section according to the accuracy relation between the predicted power and the actually measured power.
S140: and determining a power prediction model according to the predicted power of all the wind speed sections.
According to the method for establishing the power prediction model, the sample predicted wind speed data are dispersed to the wind speed sections, then the predicted power in each discrete wind speed section is found out according to the accuracy rate relation between the predicted power and the actually measured power, so that the power corresponding to the predicted wind speed in each wind speed section is close to the predicted power, and the variance of the obtained power prediction accuracy rate is smaller.
In S110, the sample predicted wind speed data and the sample actually measured wind speed data have a corresponding relationship, the sample predicted wind speed data in a certain time period is selected, and then the actually measured wind speed data in the wind speed history record is selected according to the predicted time corresponding to the sample predicted wind speed data, so as to obtain the sample actually measured wind speed data corresponding to the sample predicted wind speed data.
Possibly, in some feasible implementation manners of the embodiment of the present application, the obtaining of the sample predicted wind speed data and the sample measured wind speed data corresponding to the sample predicted wind speed data in S110 specifically includes, as shown in fig. 2, the following steps:
s111: raw predicted wind speed data is obtained over a predetermined time period.
The sample predicted wind speed data in S110 is processed raw predicted wind speed data, and this processed process is specifically described in some possible embodiments, and S111 further specifically includes:
and acquiring first predicted wind speed data of the first meteorological database and first measured wind speed data corresponding to the first predicted wind speed data, and determining a first wind speed difference value. And acquiring second predicted wind speed data of a second meteorological database and second measured wind speed data corresponding to the second predicted wind speed data, and determining a second wind speed difference value. And determining the first predicted wind speed data or the second predicted wind speed data corresponding to the minimum value of the first wind speed difference value and the second wind speed difference value as the original predicted wind speed data.
The above process shows that the original predicted wind speed data can be derived from various meteorological databases, and the more sources, the more sufficient the sampled data is, and the more the obtained predicted data is close to the actual production. Currently, there are CMA (central meteorological administration, China), ECMWF (European Centre for Medium-Range Weather forecast center), NWS (National Weather Service, united states Weather bureau), and the like, which can be used as objects of the first Weather database or the second Weather database. The first meteorological database and the second meteorological database are described in this embodiment to indicate different sources of the original predicted wind speed data, but the data source of each meteorological database is not limited.
S112: and filtering the original predicted wind speed data according to preset data filtering conditions to obtain sample predicted wind speed data.
In S112, the obtained original predicted wind speed data, including the first predicted wind speed data and the second predicted wind speed data, needs to be subjected to data cleaning and filtering, and the predicted wind speed data that is more suitable for the actual situation is selected from the original data. In a possible specific implementation manner of this implementation manner, the filtering condition according to the preset data includes: the data difference is greater than a preset difference threshold. The method comprises the following steps of filtering original predicted wind speed data according to preset data filtering conditions to obtain sample predicted wind speed data, wherein the steps comprise: and determining the wind speed difference value of the original predicted wind speed data and the sample measured wind speed data at the same time. And if the wind speed difference is smaller than or equal to the preset difference threshold, keeping the original predicted wind speed data as sample predicted wind speed data.
The preset difference threshold is specifically determined according to the actual engineering production, and the selection of the preset difference threshold is also related to the computing capacity of the existing equipment. And (3) subtracting the original predicted wind speed data and the sample actual measured wind speed data at all corresponding moments to obtain a difference absolute value, wherein the difference absolute value can judge the degree of difference between the original predicted wind speed data and the sample actual measured wind speed data, if the degree of difference is too large, the accuracy of the predicted wind speed data is not in line with the requirement, and the original predicted wind speed data and the sample actual measured wind speed data are removed.
S113: and determining sample actual measurement wind speed data corresponding to the sample predicted wind speed data in a preset time period according to the sample predicted wind speed data.
For the whole process of the implementation, the following is exemplified: the adopted strategy is to select all the predicted wind speed data from the CMA and the ECMWF respectively from 24 days in 3 months to 24 days in 4 months in 2017, and certainly, the predicted wind speed data from the NWS in the same time interval can be additionally selected. And selecting the minimum prediction deviation at each moment in the three-atmosphere weather database according to the wind speed prediction deviation | prediction wind speed-actual wind speed |, comparing the minimum prediction deviation value with a preset difference threshold value, and when the minimum prediction deviation is less than or equal to the preset difference threshold value, retaining the data at the moment, otherwise, rejecting the data. The time in the above-mentioned "each time" is specifically selected as the time frequency of wind speed prediction and detection, for example, 9:00, 9:15, 9:30, and the like.
After the raw predicted wind speed data is cleaned, S110 obtains sample predicted wind speed data that can be used for modeling, and further processing is required on the sample predicted wind speed data. Possibly, in an implementation manner of the embodiment of the present application, S120: dispersing the sample predicted wind speed data into a plurality of wind speed segments according to a preset wind speed value section, as shown in fig. 3, specifically including:
s121: and uniformly dividing the preset wind speed value section into a plurality of wind speed sections according to the preset wind speed value step length.
Alternatively, the variation of the wind speed is usually 0-25 m/s (meters per second) in daily production, that is, the preset wind speed value section may be 0-25 m/s. According to the computing capacity of the equipment, a certain preset wind speed value step length can be set, a preset wind speed value section is evenly divided into a plurality of wind speed sections, for example, the preset wind speed value step length is 0.5m/s, the preset wind speed value section can be divided into (0,0.5m/s ], (0.5m/s,1m/s ], …, (24.5m/s,25 m/s), and each section in the sections is a half-open and half-closed section, including an upper limit end point value and not including a lower limit end point value.
S122: and determining sample predicted wind speed data corresponding to each wind speed segment according to the speed of the sample predicted wind speed data.
After the wind speed sections are divided, the sample predicted wind speed data are classified into corresponding wind speed sections according to the speed of the sample predicted wind speed data, further processing of all the obtained sample predicted wind speed data is completed, and convenience is brought to searching for predicted power according to the sample predicted wind speed data.
Feasible, in an implementation manner in the embodiment provided by the first aspect of the present application, S130: determining the predicted power of each wind speed segment according to the accuracy relation between the predicted power and the measured power, as shown in fig. 4, specifically including:
s131: and acquiring sample predicted power data corresponding to each sample predicted wind speed data in the wind speed section and sample measured power data corresponding to each sample measured wind speed data.
Optionally, the generator set for each electric field is determined, and therefore the parameters of the power generation equipment are determined, and from the specific sample predicted wind speed data, the corresponding sample predicted power data can be determined. According to the method provided in the foregoing embodiment, a plurality of wind speed segments, each of which may include a plurality of sample predicted power data, can be acquired. Similarly, for historical data, as long as sample predicted power data exists, sample measured power data can be detected, and each wind speed segment correspondingly comprises a plurality of sample measured power data.
S132: and determining the accuracy corresponding to the actually measured wind speed data of each sample according to the predicted power data of the sample, the installed capacity data of the electric field, the actually measured power data of the sample corresponding to the predicted power data of the sample and the accuracy relation.
The accuracy relationship can be expressed by equation 1:
r is the accuracy, PMtMeasured power data for the sample at time t, PPtAnd predicting power data for the samples at the time t, wherein Cap is the total installed capacity of the electric field, and n is the number of the samples.
And substituting the predicted power data of each sample, the actually measured power data of the sample and the installed capacity data of the electric field in each wind speed section into the formula 1 to obtain the accuracy corresponding to the actually measured wind speed data of each sample in each wind speed section and the accuracy corresponding to the predicted wind speed data of each sample.
S133: and determining a power qualified interval corresponding to the actually measured wind speed data of the sample according to the accuracy and the installed capacity data of the electric field.
After the accuracy corresponding to the predicted wind speed data of each sample is calculated, the accuracy is converted into a power qualified interval by combining the installed capacity data of the electric field, for example, when the installed capacity data of the electric field is 100MW, and the accuracy corresponding to the actually measured wind speed data of a certain sample is calculated to be 80% according to formula 1, then the allowable deviation between the predicted power data corresponding to the actually measured wind speed data of the sample and the actually measured power data is 100MW × (1-80%), that is, the predicted deviation | (predicted power data — actually measured power data | (20 MW), when the actually measured power data is 70MW, the power qualified interval corresponding to the actually measured power data is 70MW ± 20MW, that is, the power qualified interval corresponding to the actually measured wind speed data of the sample is [50MW, 90MW ].
S134: and determining a superposition interval with the highest interval superposition degree according to the qualified power interval in each wind speed subsection, and determining a power value corresponding to the superposition interval as the predicted power of the wind speed subsection.
And obtaining a power qualified interval corresponding to each sample predicted wind speed data in each wind speed section according to the steps, and then obtaining the intersection of the power qualified intervals. For example, a certain wind speed segment includes three sample predicted wind speed data, when the power qualified interval corresponding to the first sample predicted wind speed data is [50MW, 90MW ], the power qualified interval corresponding to the second sample predicted wind speed data is [70MW, 100MW ], the power qualified interval corresponding to the third sample predicted wind speed data is [65MW, 85MW ], the intersection of the three is [70MW, 85MW ], and the intersection is the predicted power of the wind speed segment. Of course, when calculating the power qualified interval, two or more power qualified intervals may be the same, and at this time, the weight of the repeated power qualified interval needs to be increased, and the overlap interval is finally determined.
In order to determine the model more conveniently, the number set representing the overlapping interval is processed by a statistical method, and in a feasible implementation manner, the step of determining the power value corresponding to the overlapping interval as the predicted power of the wind speed segment in S134 specifically includes: and determining the average value of the maximum power value and the minimum power value in the coincidence interval as the predicted power. For example, the overlap interval is [70MW, 85MW ] in the foregoing implementation, and the predicted power obtained according to the method of this implementation is 77.5 MW.
In a practical implementation manner of the embodiment provided in the first aspect of the present application, the step S140: according to the predicted power of all wind speed segments, determining a power prediction model, comprising the following steps:
and determining a discrete model of power prediction according to the predicted power and the sample predicted wind speed data corresponding to the predicted power. And determining a power prediction model according to an interpolation method and a discrete model.
After the predicted power is obtained according to the foregoing implementation, a batch of discrete points can be obtained, and at this time, the required predicted power still cannot be obtained by inputting new predicted wind speed data. An approximate curve is obtained by a difference method, interpolation is an important method for approximation of a discrete function, and the approximate values of the function at other points can be estimated by utilizing the value conditions of the function at a limited number of points. According to the data modeling mode, particularly by interpolation, a continuous function is interpolated on the basis of the discrete predicted power data, so that the continuous curve passes through all given discrete predicted power data points. By the method, the electric field power value under the condition of randomly predicting the wind speed can be obtained, and the actual production and the electric energy allocation can be guided.
Based on the same inventive concept, the second aspect of the present application provides a power prediction method, as shown in fig. 5, comprising the following steps:
s210: the method comprises the steps of obtaining original predicted wind speed data and a power prediction model, wherein the power prediction model is determined through a building method of the power prediction model provided by the embodiment of the first aspect of the application.
S220: and inputting the original predicted wind speed data to a power prediction model to obtain the predicted power corresponding to the original predicted wind speed data.
The predicted wind speed acquired from some meteorological databases is input into the established power prediction model, so that the predicted power corresponding to the predicted wind speed can be obtained, and the predicted power can meet the accuracy requirement and can further meet the requirement of actual production. The actual statistical data are used for explaining, 67 wind energy electric fields in a certain area are tested by the power prediction model establishing method provided by the application, the average accuracy is improved to 83.0% from the original 81.0%, wherein the accuracy of 48 electric fields is improved to be 71.6% of the total test number, and particularly the accuracy of 12 electric fields is improved by 4%.
Similarly, 23 electric fields with large installed capacity (100 MW-200 MW) are tested by adopting the power prediction method provided by the application, the average accuracy of data prediction is improved from 80.5% to 82.8%, the accuracy of 18 electric fields is improved and accounts for 78.3% of the total test number, and the accuracy of 7 electric fields is improved by 4%.
In a third aspect, an embodiment of the present application provides a power prediction model building apparatus 10, as shown in fig. 6, including a data obtaining module 11, a data dividing module 12, a power determining module 13, and a model building module 14.
The data obtaining module 11 is configured to obtain sample predicted wind speed data and sample actually measured wind speed data corresponding to the sample predicted wind speed data.
The data dividing module 12 is configured to disperse the sample predicted wind speed data into a plurality of wind speed segments according to a preset wind speed value interval.
The power determining module 13 is configured to determine the predicted power of each wind speed segment according to an accuracy relationship between the predicted power and the measured power.
The model building module 14 is configured to determine a power prediction model according to the predicted power of all wind speed segments.
Feasible, the obtaining of the sample predicted wind speed data and the sample measured wind speed data corresponding to the sample predicted wind speed data by the data obtaining module 11 includes:
acquiring original predicted wind speed data in a preset time period;
filtering the original predicted wind speed data according to preset data filtering conditions to obtain sample predicted wind speed data;
and determining sample actual measurement wind speed data corresponding to the sample predicted wind speed data in a preset time period according to the sample predicted wind speed data.
It is feasible that the step of acquiring the raw predicted wind speed data within the predetermined time period in the data acquisition module 11 includes: and acquiring first predicted wind speed data of the first meteorological database and first measured wind speed data corresponding to the first predicted wind speed data, and determining a first wind speed difference value. And acquiring second predicted wind speed data of a second meteorological database and second measured wind speed data corresponding to the second predicted wind speed data, and determining a second wind speed difference value. And determining the first predicted wind speed data or the second predicted wind speed data corresponding to the minimum value of the first wind speed difference value and the second wind speed difference value as the original predicted wind speed data.
The data obtaining module 11 may filter conditions according to preset data, including: the data difference is greater than a preset difference threshold. The method comprises the following steps of filtering original predicted wind speed data according to preset data filtering conditions to obtain sample predicted wind speed data, wherein the steps comprise: determining a wind speed difference value between the original predicted wind speed data and the sample actual measured wind speed data at the same time; and if the wind speed difference is smaller than or equal to the preset difference threshold, keeping the original predicted wind speed data as sample predicted wind speed data.
Feasible, the data dividing module 12 disperses the sample predicted wind speed data into a plurality of wind speed segments according to the preset wind speed value section, including: and uniformly dividing the preset wind speed value section into a plurality of wind speed sections according to the preset wind speed value step length. And determining sample predicted wind speed data corresponding to each wind speed segment according to the speed of the sample predicted wind speed data.
If applicable, the power determining module 13 determines the predicted power of each wind speed segment according to the accuracy relationship between the predicted power and the measured power, including: and acquiring sample predicted power data corresponding to each sample predicted wind speed data in the wind speed section and sample measured power data corresponding to each sample measured wind speed data. And determining the accuracy corresponding to the actually measured wind speed data of each sample according to the predicted power data of the sample, the installed capacity data of the electric field, the actually measured power data of the sample corresponding to the predicted power data of the sample and the accuracy relation. And determining a power qualified interval corresponding to the actually measured wind speed data of the sample according to the accuracy and the installed capacity data of the electric field. And determining a superposition interval with the highest interval superposition degree according to the qualified power interval in each wind speed subsection, and determining a power value corresponding to the superposition interval as the predicted power of the wind speed subsection.
Possibly, the step of determining, by the power determination module 13, the power value corresponding to the overlap interval as the predicted power of the wind speed segment includes: and determining the average value of the maximum power value and the minimum power value in the coincidence interval as the predicted power.
If applicable, the model building module 14 determines a power prediction model according to the predicted power of all wind speed segments, including: and determining a discrete model of power prediction according to the predicted power and the sample predicted wind speed data corresponding to the predicted power. And determining a power prediction model according to an interpolation method and a discrete model.
Based on the same inventive concept, the embodiment of the fourth aspect of the present application further provides a power prediction apparatus 20, as shown in fig. 7, including an obtaining module 21 and a prediction module 22.
The obtaining module 21 is configured to obtain raw predicted wind speed data and a power prediction model, which is determined by a method for establishing the power prediction model as provided in the first aspect of the present application.
The prediction module 22 is configured to input the original predicted wind speed data to the power prediction model to obtain a predicted power corresponding to the original predicted wind speed data.
The power prediction device provided by the application can effectively improve the power prediction accuracy through the establishment method of the power prediction model provided by the application, is suitable for ultra-short-term prediction and short-term prediction, and obtains a prediction result closer to the reality because the sample is used for predicting the wind speed data.
Based on the same inventive concept, an embodiment of the present application provides an electronic device, including:
a processor, a memory, and a bus;
a bus for connecting the processor and the memory;
a memory for storing operating instructions;
a processor, configured to implement, by calling an operation instruction, a method for building a power prediction model as described in the above first aspect of the present application or implement a power prediction method as described in the above second aspect of the present application.
Those skilled in the art will appreciate that the electronic devices provided by the embodiments of the present application may be specially designed and manufactured for the required purposes, or may comprise known devices in general-purpose computers. These devices have stored therein computer programs that are selectively activated or reconfigured. Such a computer program may be stored in a device (e.g., computer) readable medium or in any type of medium suitable for storing electronic instructions and respectively coupled to a bus.
Compared with the prior art, the method can realize that: the power prediction accuracy is effectively improved, the method is suitable for ultra-short-term prediction and short-term prediction, and the obtained prediction result is closer to reality due to the fact that the sample is used for predicting the wind speed data.
In an alternative embodiment, the present application provides an electronic device, as shown in fig. 8, the electronic device 1000 shown in fig. 8 comprising: a processor 1001 and a memory 1003. The processor 1001 and the memory 1003 are electrically coupled, such as by a bus 1002.
The Processor 1001 may be a CPU (Central Processing Unit), a general-purpose Processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array) or other Programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 1001 may also be a combination of computing functions, e.g., comprising one or more microprocessors, DSPs and microprocessors, and the like.
The Memory 1003 may be a ROM (Read-Only Memory) or other type of static storage device that can store static information and instructions, a RAM (random access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read-Only Memory), a CD-ROM (Compact Disc Read-Only Memory) or other optical Disc storage, optical Disc storage (including Compact Disc, laser Disc, optical Disc, digital versatile Disc, blu-ray Disc, etc.), a magnetic Disc storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to these.
Optionally, the electronic device 1000 may also include a transceiver 1004. The transceiver 1004 may be used for reception and transmission of signals. The transceiver 1004 may allow the electronic device 1000 to communicate wirelessly or wiredly with other devices to exchange data. It should be noted that the transceiver 1004 is not limited to one in practical application.
Optionally, the electronic device 1000 may further include an input unit 1005. The input unit 1005 may be used to receive input numeric, character, image, and/or sound information, or to generate key signal inputs related to user settings and function control of the electronic apparatus 1000. The input unit 1005 may include, but is not limited to, one or more of a touch screen, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, a camera, a microphone, and the like.
Optionally, the electronic device 1000 may further include an output unit 1006. Output unit 1006 may be used to output or show information processed by processor 1001. The output unit 1006 may include, but is not limited to, one or more of a display device, a speaker, a vibration device, and the like.
While fig. 8 illustrates an electronic device 1000 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
Optionally, the memory 1003 is used for storing application program codes for executing the scheme of the present application, and the processor 1001 controls the execution. The processor 1001 is configured to execute the application program codes stored in the memory 1003 to implement any one of the power prediction model establishing methods or the power prediction methods provided in the embodiments of the present application.
Based on the same inventive concept, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the computer program implements any one of the power prediction model establishment methods or the power prediction methods provided by the present application.
Those of skill in the art will appreciate that the various operations, methods, steps in the processes, acts, or solutions discussed in this application can be interchanged, modified, combined, or eliminated. Further, other steps, measures, or schemes in various operations, methods, or flows that have been discussed in this application can be alternated, altered, rearranged, broken down, combined, or deleted. Further, steps, measures, schemes in the prior art having various operations, methods, procedures disclosed in the present application may also be alternated, modified, rearranged, decomposed, combined, or deleted.
The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless otherwise specified.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The foregoing is only a partial embodiment of the present application, and it should be noted that, for those skilled in the art, several modifications and decorations can be made without departing from the principle of the present application, and these modifications and decorations should also be regarded as the protection scope of the present application.
Claims (12)
1. A method for establishing a power prediction model is characterized by comprising the following steps:
acquiring sample predicted wind speed data and sample measured wind speed data corresponding to the sample predicted wind speed data;
dispersing the sample predicted wind speed data into a plurality of wind speed sections according to a preset wind speed value section;
determining the predicted power of each wind speed segment according to the accuracy relation between the predicted power and the actually measured power;
and determining a power prediction model according to the predicted power of all the wind speed sections.
2. The method for building a power prediction model according to claim 1, wherein the obtaining of the sample predicted wind speed data and the sample measured wind speed data corresponding to the sample predicted wind speed data comprises:
acquiring original predicted wind speed data in a preset time period;
filtering the original predicted wind speed data according to preset data filtering conditions to obtain sample predicted wind speed data;
and determining sample actual measurement wind speed data corresponding to the sample predicted wind speed data in the preset time period according to the sample predicted wind speed data.
3. The method of building a power prediction model according to claim 2, wherein the step of obtaining raw predicted wind speed data over a predetermined time period comprises:
acquiring first predicted wind speed data of a first meteorological database and first measured wind speed data corresponding to the first predicted wind speed data, and determining a first wind speed difference value;
acquiring second predicted wind speed data of a second meteorological database and second measured wind speed data corresponding to the second predicted wind speed data, and determining a second wind speed difference value;
and determining first predicted wind speed data or second predicted wind speed data corresponding to the minimum value of the first wind speed difference value and the second wind speed difference value as the original predicted wind speed data.
4. The method for building a power prediction model according to claim 2, wherein the filtering condition according to the preset data comprises: the data difference value is greater than a preset difference value threshold value;
the step of filtering the original predicted wind speed data according to preset data filtering conditions to obtain sample predicted wind speed data comprises the following steps:
determining the wind speed difference value of the original predicted wind speed data and the sample actual measured wind speed data at the same moment;
and if the wind speed difference is smaller than or equal to a preset difference threshold value, reserving the original predicted wind speed data as sample predicted wind speed data.
5. The method for building a power prediction model according to claim 1, wherein the discretizing the sample predicted wind speed data into a plurality of wind speed segments according to a preset wind speed value section comprises:
uniformly dividing the preset wind speed value section into a plurality of wind speed sections according to a preset wind speed value step length;
and determining the sample predicted wind speed data corresponding to each wind speed segment according to the speed of the sample predicted wind speed data.
6. The method for building the power prediction model according to claim 1, wherein the determining the predicted power of each wind speed segment according to the accuracy relation between the predicted power and the measured power comprises:
acquiring sample predicted power data corresponding to each sample predicted wind speed data in the wind speed section and sample measured power data corresponding to each sample measured wind speed data;
determining the accuracy corresponding to the actually measured wind speed data of each sample according to the sample predicted power data, the installed capacity data of the electric field, the actually measured sample power data corresponding to the sample predicted power data and the accuracy relation;
determining a power qualified interval corresponding to the sample actually-measured wind speed data according to the accuracy and the electric field installed capacity data;
and determining a coincidence interval with the highest interval coincidence degree according to the qualified power interval in each wind speed subsection, and determining a power value corresponding to the coincidence interval as the predicted power of the wind speed subsection.
7. The method for building the power prediction model according to claim 6, wherein the step of determining the power value corresponding to the overlap interval as the predicted power of the wind speed segment includes: and determining the average value of the maximum power value and the minimum power value in the coincidence interval as the predicted power.
8. The method for building a power prediction model according to claim 1, wherein the determining a power prediction model according to the predicted power of all wind speed segments comprises:
determining a discrete model of power prediction according to the predicted power and sample predicted wind speed data corresponding to the predicted power;
and determining the power prediction model according to an interpolation method and the discrete model.
9. A method of power prediction, comprising:
acquiring raw predicted wind speed data and a power prediction model, wherein the power prediction model is determined by the establishment method of the power prediction model provided by any one of claims 1-8;
and inputting the original predicted wind speed data to the power prediction model to obtain the predicted power corresponding to the original predicted wind speed data.
10. An apparatus for building a power prediction model, comprising:
the data acquisition module is used for acquiring sample predicted wind speed data and sample measured wind speed data corresponding to the sample predicted wind speed data;
the data dividing module is used for dispersing the sample predicted wind speed data into a plurality of wind speed sections according to a preset wind speed value interval;
the power determination module is used for determining the predicted power of each wind speed segment according to the accuracy relation between the predicted power and the actually measured power;
and the model establishing module is used for determining a power prediction model according to the predicted power of all the wind speed sections.
11. A power prediction apparatus, comprising:
an obtaining module for obtaining raw predicted wind speed data and a power prediction model, the power prediction model being determined by a method of establishing a power prediction model as provided in any one of claims 1 to 8;
and the prediction module is used for inputting the original predicted wind speed data to the power prediction model to obtain the predicted power corresponding to the original predicted wind speed data.
12. An electronic device, comprising:
a processor, a memory, and a bus;
the bus is used for connecting the processor and the memory;
the memory is used for storing operation instructions;
the processor is configured to implement the method for building a power prediction model according to any one of claims 1 to 8 or implement the method for power prediction according to claim 9 by calling the operation instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010247420.5A CN112613632A (en) | 2020-03-31 | 2020-03-31 | Power prediction model establishing method, prediction method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010247420.5A CN112613632A (en) | 2020-03-31 | 2020-03-31 | Power prediction model establishing method, prediction method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112613632A true CN112613632A (en) | 2021-04-06 |
Family
ID=75224840
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010247420.5A Pending CN112613632A (en) | 2020-03-31 | 2020-03-31 | Power prediction model establishing method, prediction method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112613632A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512766A (en) * | 2015-12-11 | 2016-04-20 | 中能电力科技开发有限公司 | Wind power plant power predication method |
| CN106229972A (en) * | 2016-08-16 | 2016-12-14 | 北京国能日新系统控制技术有限公司 | A kind of integrated based on many meteorological sources and the wind power forecasting method of segmentation modeling |
| CN107992970A (en) * | 2017-12-06 | 2018-05-04 | 北京金风慧能技术有限公司 | The output power predicting method and equipment of wind power generating set |
| US20180340515A1 (en) * | 2017-05-25 | 2018-11-29 | Hitachi, Ltd. | Adaptive power generation management |
| CN110298511A (en) * | 2019-07-02 | 2019-10-01 | 辽宁科技大学 | A kind of novel wind power power forecasting method and device |
| CN110363354A (en) * | 2019-07-16 | 2019-10-22 | 上海交通大学 | Wind field wind power prediction method, electronic device and storage medium |
| CN110705772A (en) * | 2019-09-26 | 2020-01-17 | 国家电网公司华北分部 | Regional power grid wind power generation power prediction optimization method and device |
-
2020
- 2020-03-31 CN CN202010247420.5A patent/CN112613632A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512766A (en) * | 2015-12-11 | 2016-04-20 | 中能电力科技开发有限公司 | Wind power plant power predication method |
| CN106229972A (en) * | 2016-08-16 | 2016-12-14 | 北京国能日新系统控制技术有限公司 | A kind of integrated based on many meteorological sources and the wind power forecasting method of segmentation modeling |
| US20180340515A1 (en) * | 2017-05-25 | 2018-11-29 | Hitachi, Ltd. | Adaptive power generation management |
| CN107992970A (en) * | 2017-12-06 | 2018-05-04 | 北京金风慧能技术有限公司 | The output power predicting method and equipment of wind power generating set |
| CN110298511A (en) * | 2019-07-02 | 2019-10-01 | 辽宁科技大学 | A kind of novel wind power power forecasting method and device |
| CN110363354A (en) * | 2019-07-16 | 2019-10-22 | 上海交通大学 | Wind field wind power prediction method, electronic device and storage medium |
| CN110705772A (en) * | 2019-09-26 | 2020-01-17 | 国家电网公司华北分部 | Regional power grid wind power generation power prediction optimization method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111898691B (en) | River burst water pollution early warning and tracing method, system, terminal and medium | |
| CN107622308B (en) | Power generation equipment parameter early warning method based on DBN (database-based network) | |
| CN105740991A (en) | Climate change prediction method and system for fitting various climate modes based on modified BP neural network | |
| CN116150897A (en) | Machine tool spindle performance evaluation method and system based on digital twin | |
| CN111104736B (en) | Abnormal data detection method, device, medium and equipment based on time sequence | |
| CN112418921A (en) | Power demand prediction method, device, system and computer storage medium | |
| CN113868953B (en) | Multi-unit operation optimization method, device and system in industrial system and storage medium | |
| CN108256693B (en) | Photovoltaic power generation power prediction method, device and system | |
| CN110097205A (en) | A kind of building load prediction weather forecast data preprocessing method | |
| CN116413604A (en) | Battery parameter monitoring method, system, device and storage medium | |
| CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
| CN111025041A (en) | Electric vehicle charging pile monitoring method and system, computer equipment and medium | |
| CN116187552A (en) | Abnormality detection method, computing device, and computer storage medium | |
| CN111415027A (en) | Method and device for constructing component prediction model | |
| CN117029968A (en) | Traffic data diagnosis method, system, storage medium and electronic equipment | |
| CN112580844A (en) | Meteorological data processing method, device, equipment and computer readable storage medium | |
| CN113868948A (en) | User-oriented dynamic threshold model training system and method | |
| CN113268929A (en) | Short-term load interval prediction method and device | |
| CN115422263B (en) | Multifunctional universal fault analysis method and system for electric power field | |
| CN112884197A (en) | Water bloom prediction method and device based on double models | |
| CN116777281A (en) | ARIMA model-based power equipment quality trend prediction method and device | |
| CN112613632A (en) | Power prediction model establishing method, prediction method and device and electronic equipment | |
| CN111080037A (en) | Short-term power load prediction method and device based on deep neural network | |
| CN116011281A (en) | Method and device for analyzing seismic vulnerability of electric power facility | |
| CN113780356B (en) | Water quality prediction method and system based on integrated learning model |
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 |