CN113033910A - Photovoltaic power generation power prediction method, storage medium and terminal equipment - Google Patents
Photovoltaic power generation power prediction method, storage medium and terminal equipment Download PDFInfo
- Publication number
- CN113033910A CN113033910A CN202110383624.6A CN202110383624A CN113033910A CN 113033910 A CN113033910 A CN 113033910A CN 202110383624 A CN202110383624 A CN 202110383624A CN 113033910 A CN113033910 A CN 113033910A
- Authority
- CN
- China
- Prior art keywords
- data
- prediction
- power generation
- photovoltaic power
- meteorological
- 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.)
- Granted
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000012549 training Methods 0.000 claims abstract description 48
- 238000013145 classification model Methods 0.000 claims abstract description 29
- 238000012795 verification Methods 0.000 claims abstract description 25
- 238000005096 rolling process Methods 0.000 claims abstract description 6
- 238000010219 correlation analysis Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 5
- 239000006185 dispersion Substances 0.000 claims description 4
- 238000002790 cross-validation Methods 0.000 abstract description 9
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 3
- 238000012417 linear regression Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001052 transient effect 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention discloses a method for predicting photovoltaic power generation power, a storage medium and terminal equipment, wherein the method for predicting the photovoltaic power generation power comprises the following steps: inputting the historical meteorological data sample set into a classification model, and obtaining a first meteorological type training set through the classification model; inputting the real-time meteorological data sample set into a classification model, and performing rolling verification on a first meteorological type training set by the classification model according to the real-time meteorological data sample set to obtain a second meteorological type training set; inputting the second meteorological type training set into a dynamic combination prediction model, and obtaining first prediction data through the dynamic combination prediction model; inputting the first prediction data into a verification model, and obtaining second prediction data through the verification model; the second prediction data is prediction data of photovoltaic power generation power; the meteorological types are classified according to the historical data and the real-time data, accuracy of classified data is improved, and accuracy of prediction is improved by performing cross validation on a plurality of predicted values.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation, in particular to a method for predicting photovoltaic power generation power, a storage medium and terminal equipment.
Background
In the process of building a photovoltaic power station, designers need to predict the photovoltaic power generation power according to the geographical position and the meteorological conditions of the area in the early period, but the photovoltaic power generation power is greatly influenced by the meteorological conditions, so that the photovoltaic power generation power has different characteristics under the conditions of different areas and different meteorological conditions, even under the conditions of the same area and different seasons, and the difficulty in predicting the photovoltaic power generation power is high.
The existing photovoltaic power generation power prediction method mainly comprises the following steps: the method comprises an indirect prediction method and a direct prediction method, wherein the indirect prediction method firstly predicts environmental parameters related to the photovoltaic system, such as solar radiation, environmental temperature and other parameters, and then predicts the photovoltaic power generation power by using the existing physical model based on the photovoltaic power generation system; the direct prediction method is to obtain a prediction result by using historical data such as the existing photovoltaic power generation amount and meteorological data, however, various prediction models have certain limitations in the prediction process, if the prediction models are not used properly, an unsatisfactory prediction result may be obtained, and for special complex weather conditions such as rainy and humid weather in Guangdong, accurate photovoltaic power generation power prediction cannot be made for such weather conditions by adopting the traditional prediction method.
It is seen that improvements and enhancements to the prior art are needed.
Disclosure of Invention
In view of the defects of the prior art, the invention aims to provide a photovoltaic power generation power prediction method, a storage medium and a terminal device, so that the accuracy of power generation power prediction in complex weather is improved.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for predicting photovoltaic power generation power comprises the following steps:
inputting the historical meteorological data sample set into a classification model, and obtaining a first meteorological type training set through the classification model;
inputting the real-time meteorological data sample set into a classification model, and performing rolling verification on a first meteorological type training set by the classification model according to the real-time meteorological data sample set to obtain a second meteorological type training set;
inputting the second meteorological type training set into a dynamic combination prediction model, and obtaining first prediction data through the dynamic combination prediction model;
inputting the first prediction data into a verification model, and obtaining second prediction data through the verification model; the second prediction data is prediction data of photovoltaic power generation power.
In the method for predicting photovoltaic power generation power, the step of inputting the historical meteorological data sample set into the classification model, and obtaining the first meteorological type training set through the classification model further includes the steps of:
acquiring historical meteorological data and historical photovoltaic power generation data in the same time period;
and performing parameter characteristic correlation analysis on the historical meteorological data and the historical photovoltaic power generation data in the same time period, and obtaining a historical meteorological data sample set.
In the method for predicting photovoltaic power generation power, the parameter characteristic correlation analysis is performed on the historical meteorological data and the historical photovoltaic power generation amount data in the same time period, and a historical meteorological data sample set is obtained, which specifically includes:
performing dispersion standardization processing on historical meteorological data and historical photovoltaic power generation data to obtain a first training set;
and selecting the average value of the generated energy in the same time period as a classification standard, calibrating a classification label for the first training set, and obtaining a second training set, wherein the second training set is a historical meteorological data sample set.
In the method for predicting photovoltaic power generation, the dynamic combination prediction model comprises a plurality of prediction models.
In the method for predicting photovoltaic power generation power, the inputting of the second meteorological type training set to the dynamic combined prediction model, and the obtaining of the first prediction data through the dynamic combined prediction model specifically include:
and respectively inputting the second meteorological type training set into the plurality of prediction models, and obtaining a plurality of first prediction data through the plurality of prediction models.
In the method for predicting photovoltaic power generation power, the inputting of the first prediction data into the verification model and the obtaining of the second prediction data by the verification model specifically include:
and inputting the plurality of first prediction data into a verification model, and performing cross verification on the plurality of first prediction data to obtain second prediction data.
In the method for predicting photovoltaic power generation power, the parameter characteristic correlation analysis is performed on the historical meteorological data and the historical photovoltaic power generation amount data in the same time period, and a historical meteorological data sample set is obtained, which specifically includes:
and performing parameter characteristic correlation analysis on the historical meteorological data and the historical photovoltaic power generation amount data in the same time period by a Pearson correlation coefficient method, and obtaining a historical meteorological data sample set.
In the photovoltaic power generation power prediction method, the classification model adopts a ridge regression classification model to train a historical meteorological data sample set, so as to obtain a first meteorological type training set.
The present invention also provides a computer readable storage medium storing one or more programs, which are executable by one or more processors to implement the steps in the photovoltaic power generation power prediction method as described in any above.
The invention also provides a terminal device correspondingly, which comprises: a processor, a memory, and a communication bus; the memory has stored thereon a computer readable program executable by the processor;
the communication bus realizes connection communication between the processor and the memory;
the processor, when executing the computer readable program, implements the steps in the photovoltaic power generation power prediction method as described in any one of the above.
Has the advantages that:
the invention provides a method for predicting photovoltaic power generation power, a storage medium and a terminal device, wherein the method for predicting photovoltaic power generation power comprises the steps of classifying historical data according to the characteristics of weather types, and performing rolling verification on classification results by combining real-time data, so that the accuracy of the classification results of complex weather types is improved, and the influence of the complex weather on the photovoltaic power generation power is reduced; further training photovoltaic power generation power data by dynamically combining the prediction models according to data included in various meteorological types to obtain a plurality of predicted values of photovoltaic power generation power, so that a large number of prediction results can be obtained by the models as samples even under the condition of limited weather data; and further performing cross validation on the plurality of predicted values, and selecting a prediction result with higher score and a model with better performance at a certain moment to be used for predicting the photovoltaic power generation power at the moment, so that the predicted value of the photovoltaic power generation power is closer to the actual power generation power, and the accuracy of prediction is improved.
Drawings
FIG. 1 is a schematic flow chart of a method for predicting photovoltaic power generation provided by the present invention;
fig. 2 is a schematic flow chart of step S200 in the photovoltaic power generation power prediction method provided in the present invention;
fig. 3 is a schematic flowchart of steps S500 and S600 in the photovoltaic power generation power prediction method provided by the present invention;
fig. 4 is a schematic structural diagram of a terminal device provided in the present invention.
Detailed Description
The invention provides a photovoltaic power generation power prediction method, a storage medium and a terminal device, and in order to make the purpose, technical scheme and effect of the invention clearer and clearer, the invention is further described in detail below by referring to the attached drawings and embodiments.
In the description of the present invention, it is to be understood that the terms "mounted," "connected," and the like are to be interpreted broadly, and those skilled in the art can understand the specific meanings of the above terms in the present invention according to specific situations.
Referring to fig. 1, the present invention provides a method for predicting photovoltaic power generation power, including:
s300, inputting the historical meteorological data sample set into a classification model, and obtaining a first meteorological type training set through the classification model; as the meteorological conditions in the plum rain season are complex and changeable, and the influence of the changeable meteorological conditions on the photovoltaic power generation power is different, the meteorological data need to be classified, similar weather types are distinguished and correspond to the photovoltaic power generation power, the follow-up photovoltaic power generation power is predicted in a more targeted manner, and the prediction accuracy is improved.
In one embodiment, the historical meteorological data sample set includes historical temperature data, historical humidity data, historical wind speed data, historical radiant quantity data, historical power generation data, and the like.
In one embodiment, the classification model trains a historical meteorological data sample set by using a ridge regression classification model to obtain a first meteorological type training set; the ridge regression is an improved least square estimation method, and by abandoning the unbiased property of the least square method, the regression coefficient obtained at the cost of losing part of information and reducing precision is more consistent with a practical and reliable regression method.
Assuming that the target to be predicted is a weather type of 10:00 am at 3/6/2020, the historical weather data sample set adopts historical data of 9:00 am to 10:45 am in the same time period of 2017, 2018 and 2019 at 3/6/2019 and days before and after (preset as required, such as five days before and after), and historical data of 9:00 am to 10:45 am in the same time period of days before 3/6/2020 (preset as required, such as five days before) as a sample set, the ridge regression classification model is trained through the historical weather data sample set, and the weather type of 10:00 am at 6/2020 at 3/6/2020 is predicted after training.
Further, referring to fig. 1, the method for predicting the photovoltaic power generation power further includes the steps of:
s400, inputting the real-time meteorological data sample set into a classification model, and performing rolling verification on a first meteorological type training set by the classification model according to the real-time meteorological data sample set to obtain a second meteorological type training set;
in one embodiment, the real-time change conditions of temperature, humidity, wind speed, radiation capacity and power generation capacity are tracked by collecting meteorological data and photovoltaic power generation capacity data every 15 minutes through a monitoring mechanism; and meteorological data and photovoltaic power generation capacity data collected every 15 minutes are used as a real-time meteorological data sample set and are added into a database as historical data, the classification model performs rolling verification on the first meteorological type training set according to the real-time meteorological data sample set, the classification accuracy of the classification model is improved, and therefore the second meteorological type training set which is classified accurately is obtained.
Further, referring to fig. 1, the method for predicting the photovoltaic power generation power further includes the steps of:
and S500, inputting the second meteorological type training set into the dynamic combined prediction model, and obtaining first prediction data through the dynamic combined prediction model.
Further, referring to fig. 3, in an embodiment, the step S500 specifically includes the steps of:
and S510, respectively inputting the second meteorological type training set into a plurality of prediction models, and obtaining a plurality of first prediction data through the prediction models.
In one embodiment, the dynamically combined predictive model includes a number of predictive models; in this embodiment, the dynamic combined prediction model is composed of a bayesian ridge regression model, a linear regression model, a gaussian regression model, a multi-layer perceptron model, and a support vector machine model.
Supposing that one day in the plum rain season is selected randomly, because the same prediction model has different prediction results at different moments, a second meteorological type training set at a certain moment needs to be input into the dynamic combination prediction model, a plurality of prediction models in the dynamic combination prediction model are trained according to the second meteorological type training set, so that a plurality of prediction results used at the moment are obtained, a large number of prediction results can be obtained as samples under the condition that weather data are limited, a plurality of prediction results at the moment are cross-verified through a verification model, a prediction result with higher score and a model with better performance at the moment are selected and used for predicting the photovoltaic power generation power at the moment, the reliability of the prediction results can be improved through the dynamic combination of a plurality of models, particularly, the prediction system can be automatically matched according to the performance of the models under the condition that the special weather data amount is limited, to improve prediction accuracy.
Examples are as follows: assuming that the target to be predicted is 3/6/2020, if the prediction result of the Bayesian ridge regression model in the time period from 7:00 to 9:00 is high in score and the model is good in performance, taking the prediction result as the prediction result of the photovoltaic power generation power in the time period from 7:00 to 9:00, and if the prediction result of the Gaussian process regression model in the time period from 9:00 to 11:00 is high in score and the model is good in performance, taking the prediction result as the prediction result of the photovoltaic power generation power in the time period from 9:00 to 11:00, and similarly, the prediction results in other time periods are also selected by the method; and the optimal prediction result of each time interval is automatically matched by performing cross validation on the prediction results of the models, so that the prediction accuracy is improved.
The Bayesian ridge regression model is a supervised learning algorithm based on Bayesian theorem, and is characterized in that feature vectors are assumed to be independent from each other, and the probability obeys normal distribution.
A linear regression model is a model that models the relationship between one or more independent variables and dependent variables using a least squares function called a linear regression equation.
The gaussian process regression model is a non-parametric model that uses gaussian process priors to perform regression analysis on the data.
The multilayer perceptron model is a model with full connection between middle layers (full connection is that any neuron in the upper layer is connected with all neurons in the lower layer).
The support vector regression model is a model pursuing maximum separation, and the kernel function in the constraint condition enables the model to find a strip region instead of a simple line.
Further, referring to fig. 1, the method for predicting the photovoltaic power generation power further includes the steps of:
s600, inputting the first prediction data into a verification model, and obtaining second prediction data through the verification model; the second prediction data is prediction data of photovoltaic power generation power.
Further, referring to fig. 3, in an embodiment, the step S600 specifically includes a step S610 of inputting a plurality of first prediction data into a verification model, and performing cross-validation on the plurality of first prediction data to obtain second prediction data; and performing cross validation on the plurality of first prediction data through the validation model, scoring each first prediction data, and automatically selecting a model with higher score and better performance at a certain moment as the photovoltaic power generation power prediction at the moment so as to improve the prediction accuracy of the dynamic combination prediction model.
The process of cross-validation is as follows: the first prediction data are scrambled, then the scrambled data are evenly divided into k parts, k-1 parts are selected as a training set in turn, the remaining part is used for verification, the error square sum of the model is calculated, and after k times of iteration, the error square sum of k times is averaged to be used as a basis for selecting the optimal model.
Because most of the data in the dataset is used for training, there is a potential for reduced overfitting, therefore, cross-validation uses k average performances as scores for the entire model after k cross-validations, each data appearing once in the validation set and k-1 times in the training, thereby reducing under-fitting.
In this embodiment, the value of k may be 5 or 10; sufficient quality differences and different optimal parameters of the model can be obtained when performing k cross-validations to produce a test error estimate that is neither too highly biased nor too highly biased.
Further, referring to fig. 1, the method for predicting the photovoltaic power generation power further includes the steps of:
s100, historical meteorological data and historical photovoltaic power generation data in the same time period are obtained.
S200, performing parameter characteristic correlation analysis on the historical meteorological data and the historical photovoltaic power generation amount data in the same time period, and obtaining a historical meteorological data sample set.
In one embodiment, parameter characteristic correlation analysis is carried out on historical meteorological data and historical photovoltaic power generation amount data in the same time period through a Pearson correlation coefficient method, and a historical meteorological data sample set is obtained.
Further, referring to fig. 2, in an embodiment, the step S200 specifically includes the steps of:
s210, performing dispersion standardization processing on historical meteorological data and historical photovoltaic power generation amount data to obtain a first training set; similar data in a historical period are selected, the meteorological data and the generating capacity data are standardized, dispersion standardization is adopted, the original data are subjected to linear transformation, the result falls into a [0,1] interval, and normalization processing is carried out on the original data.
S220, selecting the average value of the generated energy in the same time period as a classification standard, calibrating a classification label for the first training set, and obtaining a second training set, wherein the second training set is a historical meteorological data sample set.
In one embodiment, with the power generation amount as the average as the classification criterion, it is assumed that the time periods of 2 to 5 months per day are divided into 6 groups, one group every 2 hours, such as 7:00 to 9:00, 9:00 to 11:00, 11:00 to 13:00, 13:00 to 15:00, 15:00 to 17:00, 17:00 to 19:00, and then weather classification tags are added in each time period, it is assumed that the weather conditions in the time period are divided into two types, and the power generation amount average in the time period is used as a boundary, the weather tags above the average are set as type a, and the weather tags below the average are set as type B.
Furthermore, the classification tags can be flexibly set according to the meteorological data and the power generation amount, for example, the classification tags are classified into four classes or six classes, namely the classification tags are not limited to 2 classes, and corresponding tags are added into the training set.
The present invention also provides, accordingly, a computer readable storage medium storing one or more programs, the one or more programs being executable by one or more processors for implementing the steps in the photovoltaic power generation power prediction method as described in any one of the above; for example, the computer readable storage medium may be a ROM, a random access memory, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
Referring to fig. 4, the present invention further provides a terminal device, including: a processor, a memory, and a communication bus; the memory has stored thereon a computer readable program executable by the processor;
the communication bus realizes connection communication between the processor and the memory;
the processor, when executing the computer readable program, implements the steps in the photovoltaic power generation power prediction method as described in any one of the above.
In addition, the logic instructions in the memory may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand-alone product.
The memory, which is a computer-readable storage medium, may be configured to store a software program, a computer-executable program; the processor executes the functional application and data processing by executing the software program, instructions or modules stored in the memory, that is, implements the method in the above embodiments.
The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal device, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory. For example, various media that can store program codes, such as a usb disk, a removable hard disk, a read-only memory, a random access memory, a magnetic disk, or an optical disk, may also be transient storage media.
It should be understood that equivalents and modifications of the technical solution and inventive concept thereof may occur to those skilled in the art, and all such modifications and alterations should fall within the protective scope of the present invention.
Claims (10)
1. A method for predicting photovoltaic power generation power is characterized by comprising the following steps:
inputting the historical meteorological data sample set into a classification model, and obtaining a first meteorological type training set through the classification model;
inputting the real-time meteorological data sample set into a classification model, and performing rolling verification on a first meteorological type training set by the classification model according to the real-time meteorological data sample set to obtain a second meteorological type training set;
inputting the second meteorological type training set into a dynamic combination prediction model, and obtaining first prediction data through the dynamic combination prediction model;
inputting the first prediction data into a verification model, and obtaining second prediction data through the verification model; the second prediction data is prediction data of photovoltaic power generation power.
2. The method for predicting photovoltaic power generation according to claim 1, wherein the step of inputting the historical meteorological data sample set into a classification model, and obtaining a first meteorological type training set through the classification model further comprises the steps of:
acquiring historical meteorological data and historical photovoltaic power generation data in the same time period;
and performing parameter characteristic correlation analysis on the historical meteorological data and the historical photovoltaic power generation data in the same time period, and obtaining a historical meteorological data sample set.
3. The method for predicting photovoltaic power generation according to claim 2, wherein the performing parameter feature correlation analysis on the historical meteorological data and the historical photovoltaic power generation amount data in the same time period to obtain a historical meteorological data sample set specifically comprises:
performing dispersion standardization processing on historical meteorological data and historical photovoltaic power generation data to obtain a first training set;
and selecting the average value of the generated energy in the same time period as a classification standard, calibrating a classification label for the first training set, and obtaining a second training set, wherein the second training set is a historical meteorological data sample set.
4. The method according to claim 1, wherein the dynamic combination prediction model comprises a plurality of prediction models.
5. The method for predicting photovoltaic power generation according to claim 4, wherein the inputting the second meteorological type training set into the dynamic combined prediction model, and the obtaining the first prediction data by the dynamic combined prediction model specifically includes:
and respectively inputting the second meteorological type training set into the plurality of prediction models, and obtaining a plurality of first prediction data through the plurality of prediction models.
6. The method for predicting photovoltaic power generation according to claim 5, wherein the inputting the first prediction data into the verification model and the obtaining the second prediction data by the verification model specifically include:
and inputting the plurality of first prediction data into a verification model, and performing cross verification on the plurality of first prediction data to obtain second prediction data.
7. The method for predicting photovoltaic power generation according to claim 2, wherein the performing parameter feature correlation analysis on the historical meteorological data and the historical photovoltaic power generation amount data in the same time period to obtain a historical meteorological data sample set specifically comprises:
and performing parameter characteristic correlation analysis on the historical meteorological data and the historical photovoltaic power generation amount data in the same time period by a Pearson correlation coefficient method, and obtaining a historical meteorological data sample set.
8. The method of claim 1, wherein the classification model uses a ridge regression classification model to train a historical meteorological data sample set, so as to obtain a first meteorological type training set.
9. A computer readable storage medium, storing one or more programs, the one or more programs being executable by one or more processors to implement the steps in the photovoltaic power generation power prediction method according to any one of claims 1-8.
10. A terminal device, comprising: a processor, a memory, and a communication bus; the memory has stored thereon a computer readable program executable by the processor;
the communication bus realizes connection communication between the processor and the memory;
the processor, when executing the computer readable program, implements the steps in the photovoltaic power generation power prediction method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110383624.6A CN113033910B (en) | 2021-04-09 | 2021-04-09 | Photovoltaic power generation power prediction method, storage medium and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110383624.6A CN113033910B (en) | 2021-04-09 | 2021-04-09 | Photovoltaic power generation power prediction method, storage medium and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113033910A true CN113033910A (en) | 2021-06-25 |
| CN113033910B CN113033910B (en) | 2023-06-09 |
Family
ID=76456177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110383624.6A Active CN113033910B (en) | 2021-04-09 | 2021-04-09 | Photovoltaic power generation power prediction method, storage medium and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113033910B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114048896A (en) * | 2021-10-27 | 2022-02-15 | 国核自仪系统工程有限公司 | Method, system, equipment and medium for predicting photovoltaic power generation data |
| CN114548571A (en) * | 2022-02-25 | 2022-05-27 | 国网山东省电力公司潍坊供电公司 | Photovoltaic power generation prediction method and device based on Bayesian ridge regression |
| CN116520046A (en) * | 2023-04-10 | 2023-08-01 | 广东永光新能源设计咨询有限公司 | Renewable energy power generation grid-connected test method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503386A (en) * | 2016-11-07 | 2017-03-15 | 上海思源弘瑞自动化有限公司 | The good and bad method and device of assessment luminous power prediction algorithm performance |
| CN107766990A (en) * | 2017-11-10 | 2018-03-06 | 河海大学 | A kind of Forecasting Methodology of photovoltaic power station power generation power |
| CN111695601A (en) * | 2020-05-15 | 2020-09-22 | 特变电工西安电气科技有限公司 | Photovoltaic power prediction method, device, equipment and readable storage medium |
| CN112070311A (en) * | 2020-09-10 | 2020-12-11 | 天津大学 | Day-ahead light power prediction method based on similar day clustering and meteorological factor weighting |
| CN112577745A (en) * | 2020-12-02 | 2021-03-30 | 上海应用技术大学 | Rolling bearing fault diagnosis method based on 1D-CNN |
-
2021
- 2021-04-09 CN CN202110383624.6A patent/CN113033910B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503386A (en) * | 2016-11-07 | 2017-03-15 | 上海思源弘瑞自动化有限公司 | The good and bad method and device of assessment luminous power prediction algorithm performance |
| CN107766990A (en) * | 2017-11-10 | 2018-03-06 | 河海大学 | A kind of Forecasting Methodology of photovoltaic power station power generation power |
| CN111695601A (en) * | 2020-05-15 | 2020-09-22 | 特变电工西安电气科技有限公司 | Photovoltaic power prediction method, device, equipment and readable storage medium |
| CN112070311A (en) * | 2020-09-10 | 2020-12-11 | 天津大学 | Day-ahead light power prediction method based on similar day clustering and meteorological factor weighting |
| CN112577745A (en) * | 2020-12-02 | 2021-03-30 | 上海应用技术大学 | Rolling bearing fault diagnosis method based on 1D-CNN |
Non-Patent Citations (1)
| Title |
|---|
| 王小杨 等: "基于ABC-SVM和PSO-RF的光伏微电网日发电功率组合预测方法研究", 《太阳能学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114048896A (en) * | 2021-10-27 | 2022-02-15 | 国核自仪系统工程有限公司 | Method, system, equipment and medium for predicting photovoltaic power generation data |
| CN114048896B (en) * | 2021-10-27 | 2023-02-03 | 国核自仪系统工程有限公司 | Method, system, equipment and medium for predicting photovoltaic power generation data |
| CN114548571A (en) * | 2022-02-25 | 2022-05-27 | 国网山东省电力公司潍坊供电公司 | Photovoltaic power generation prediction method and device based on Bayesian ridge regression |
| CN116520046A (en) * | 2023-04-10 | 2023-08-01 | 广东永光新能源设计咨询有限公司 | Renewable energy power generation grid-connected test method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113033910B (en) | 2023-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kannan et al. | Prediction of daily rainfall state in a river basin using statistical downscaling from GCM output | |
| CN113033910A (en) | Photovoltaic power generation power prediction method, storage medium and terminal equipment | |
| Gu et al. | Neural network soil moisture model for irrigation scheduling | |
| CN113496104B (en) | Precipitation prediction correction method and system based on deep learning | |
| WO2022039675A1 (en) | Method and apparatus for forecasting weather, electronic device and storage medium thereof | |
| CN106526710A (en) | Haze prediction method and device | |
| CN113240153A (en) | Photovoltaic power generation data prediction method and device, computing equipment and storage medium | |
| Hudnurkar et al. | Binary classification of rainfall time-series using machine learning algorithms. | |
| CN116205508A (en) | Distributed photovoltaic power generation abnormality diagnosis method and system | |
| CN115036922A (en) | Distributed photovoltaic power generation electric quantity prediction method and system | |
| CN116760017A (en) | Prediction method for photovoltaic power generation | |
| Kajbaf et al. | Temporal downscaling of precipitation from climate model projections using machine learning | |
| CN118364865A (en) | Method for predicting visibility of highway traffic meteorological environment in minute level and early warning system | |
| Georgoulas et al. | Examining nominal and ordinal classifiers for forecasting wind speed | |
| CN117290673A (en) | Ship energy consumption high-precision prediction system based on multi-model fusion | |
| CN115905997B (en) | Wind turbine generator meteorological disaster early warning method and system based on prediction deviation optimization | |
| Lu et al. | Uncertainty quantification of machine learning models to improve streamflow prediction under changing climate and environmental conditions | |
| CN115600498A (en) | Wind speed forecast correction method based on artificial neural network | |
| Li et al. | Performance assessment of cross office building energy prediction in the same region using the domain adversarial transfer learning strategy | |
| Tahsin et al. | Comparative analysis of weather prediction using ensemble learning models and neural network | |
| CN113723670A (en) | Photovoltaic power generation power short-term prediction method with variable time window | |
| Obisesan | Machine Learning Models for Prediction of Meteorological Variables for Weather Forecasting | |
| Gutiérrez et al. | Evaluating nominal and ordinal classifiers for wind speed prediction from synoptic pressure patterns | |
| CN111507495A (en) | Method and device for predicting missing wind measurement data | |
| CN118393612B (en) | Cloud information prediction method and device, storage medium and electronic equipment |
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 |