CN110348648A - A kind of predicting power of photovoltaic plant method and device - Google Patents
A kind of predicting power of photovoltaic plant method and device Download PDFInfo
- Publication number
- CN110348648A CN110348648A CN201910712040.1A CN201910712040A CN110348648A CN 110348648 A CN110348648 A CN 110348648A CN 201910712040 A CN201910712040 A CN 201910712040A CN 110348648 A CN110348648 A CN 110348648A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic plant
- network model
- neural network
- meteorological data
- affiliated area
- 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 46
- 238000003062 neural network model Methods 0.000 claims abstract description 64
- 239000000284 extract Substances 0.000 claims abstract description 5
- 238000010248 power generation Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 6
- 210000005036 nerve Anatomy 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
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)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application provides a kind of predicting power of photovoltaic plant method and device, method includes: the meteorological data obtained for the prediction of photovoltaic plant affiliated area, and extracts Meteorological Characteristics from the meteorological data of prediction；By Meteorological Characteristics input for the neural network model of photovoltaic plant building, the generated output of neural network model output, the generated power forecasting value as photovoltaic plant are obtained；Neural network model is to be obtained using the history meteorological data of photovoltaic plant affiliated area and the history generated output training of the corresponding photovoltaic plant of history meteorological data.In this application, the prediction to the generated output of photovoltaic plant may be implemented in the above manner.
Description
Technical field
This application involves technical field of photovoltaic power generation, in particular to a kind of predicting power of photovoltaic plant method and device.
Background technique
Transition formula is presented in recent years and increases as a kind of clean and environmental protection, sustainable, construction period short new energy for photovoltaic power generation
It is long, the following mainstream that gradually traditional energy will be replaced to become electric network source.
Wherein, carrying out accurately generated power forecasting to photovoltaic plant can not only provide for the Optimized Operation decision of power grid
Reliable basis can also provide technical support for the multipotencys energy complementation coordinated control such as wind, light, storage, ensure the safety and stability of power grid
Operation.
But how to carry out prediction to the generated output of photovoltaic plant becomes problem.
Summary of the invention
In order to solve the above technical problems, the embodiment of the present application provides a kind of predicting power of photovoltaic plant method and device, with
Achieve the purpose that realize the prediction to the generated output of photovoltaic plant, technical solution is as follows:
Present invention also provides a kind of retrieval devices, to guarantee the realization and application of the above method in practice.
To solve the above-mentioned problems, this application discloses a kind of search methods, comprising:
This application discloses a kind of retrieval devices, comprising:
Present invention also provides a kind of searching system, which includes:
This block content is similar to claim, fills into again later
Compared with prior art, the application has the beneficial effect that
In this application, since meteorologic factor is to influence the principal element of photovoltaic power station power generation power, can pass through
Meteorological data predicts generated output, especially by the meteorological data obtained for the prediction of photovoltaic plant affiliated area, and from prediction
Meteorological data in extract Meteorological Characteristics, by Meteorological Characteristics input for photovoltaic plant building neural network model, obtain mind
The generated output exported through network model realizes the prediction to the generated output of photovoltaic plant.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for
For those of ordinary skill in the art, without any creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is a kind of flow chart of predicting power of photovoltaic plant embodiment of the method 1 provided by the present application；
Fig. 2 is a kind of flow chart of predicting power of photovoltaic plant embodiment of the method 2 provided by the present application；
Fig. 3 is a kind of flow chart of predicting power of photovoltaic plant embodiment of the method 3 provided by the present application；
Fig. 4 is a kind of flow chart of neural network model training provided by the present application；
Fig. 5 is the flow chart of another neural network model training provided by the present application；
Fig. 6 is a kind of logical construction schematic diagram of predicting power of photovoltaic plant device provided by the present application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
The embodiment of the present application discloses a kind of predicting power of photovoltaic plant method, comprising: obtains for belonging to photovoltaic plant
The meteorological data of regional prediction, and Meteorological Characteristics are extracted from the meteorological data of the prediction；The Meteorological Characteristics are inputted into needle
To the neural network model of photovoltaic plant building, the generated output of the neural network model output is obtained, as described
The generated power forecasting value of photovoltaic plant；The neural network model is meteorological using the history of the photovoltaic plant affiliated area
The training of the history generated output of data and the corresponding photovoltaic plant of the history meteorological data obtains.In this application,
The prediction to the generated output of photovoltaic plant may be implemented.
Next predicting power of photovoltaic plant method disclosed in the embodiment of the present application is introduced, as shown in Figure 1, it is
A kind of flow chart of predicting power of photovoltaic plant embodiment of the method 1 provided by the present application, method includes the following steps:
Step S11, the meteorological data for the prediction of photovoltaic plant affiliated area is obtained, and from the meteorological data of the prediction
Middle extraction Meteorological Characteristics.
Preferably, downloading the meteorological number that photovoltaic plant affiliated area is predicted can be directed to from Global Forecast System (GFS)
According to.It can specifically be downloaded for photovoltaic plant affiliated area 72 hours after current time from GFS, and spatial resolution is
0.25 ° × 0.25 ° of meteorological data.
Meteorological Characteristics are extracted from the meteorological data of prediction, it is possible to understand that are as follows: extracting from the meteorological data of prediction can
Influence the Meteorological Characteristics of photovoltaic power station power generation power.Meteorological Characteristics may include but be not limited to: shortwave radiation, wind speed, wind direction,
Any one or more in temperature and relative humidity.
In the present embodiment, photovoltaic plant may include but be not limited to: photovoltaic power station.
Step S12, Meteorological Characteristics input is obtained described for the neural network model of photovoltaic plant building
The generated output of neural network model output, the generated power forecasting value as the photovoltaic plant.
The neural network model is the history meteorological data and the history gas using the photovoltaic plant affiliated area
What the history generated output training of the corresponding photovoltaic plant of image data obtained.
The neural network model is the history meteorological data and the history gas using the photovoltaic plant affiliated area
What the history generated output training of the corresponding photovoltaic plant of image data obtained, it is ensured that neural network model can pass through
Meteorological data predicts the generated output of photovoltaic plant.
Preferably, neural network model can be BP neural network model.
In this application, since meteorologic factor is to influence the principal element of photovoltaic power station power generation power, can pass through
Meteorological data predicts generated output, especially by the meteorological data obtained for the prediction of photovoltaic plant affiliated area, and from prediction
Meteorological data in extract Meteorological Characteristics, by Meteorological Characteristics input for photovoltaic plant building neural network model, obtain mind
The generated output exported through network model realizes the prediction to the generated output of photovoltaic plant.
As another alternative embodiment of the application, referring to Fig. 2, for a kind of predicting power of photovoltaic plant side provided by the present application
The flow diagram of method embodiment 2, the present embodiment are mainly the predicting power of photovoltaic plant method described to above-described embodiment 1
Refinement scheme, as shown in Fig. 2, this method may include but be not limited to following steps:
Step S21, the first preset time after current time for photovoltaic plant affiliated area prediction is obtained
Meteorological data in section, and extracted in the meteorological data after the current time in first preset time period from prediction meteorological special
Sign.
The process of Meteorological Characteristics is extracted in the meteorological data after the current time in first preset time period from prediction
It may refer to the related introduction for extracting Meteorological Characteristics in embodiment 1 from the meteorological data of prediction, repeated in this step.
First preset time period is i minutes or j hours, and the i is the integer greater than 0, and the j is whole greater than 0
Number.
Preferably, the value range of i can be set to not less than 15 and no more than 240；The value range of j can be set to
Not less than 1 and it is not more than 4.
Step S21 is a kind of specific embodiment of step S11 in embodiment 1.
Step S22, Meteorological Characteristics input is obtained for the first nerves network model of photovoltaic plant building
The generated output of the first nerves network model output, the generated power forecasting value as the photovoltaic plant.
The neural network model is first pre- using the photovoltaic plant affiliated area before each historical juncture
If the meteorological data and the photovoltaic plant in the period are in the first preset time period before each historical time
Generated output training obtains.
Historical juncture can according to need carry out flexible setting, repeat in this step.
Step S22 is a kind of specific embodiment of step S12 in embodiment 1.
In the present embodiment, by the first preset time period of setting and using the photovoltaic plant affiliated area in each history
The meteorological data and the photovoltaic plant in the first preset time period before moment before each historical time
Training of the generated output to neural network model in one preset time period, may be implemented first nerves network model to photovoltaic electric
Stand carry out ultra-short term generated output prediction.
As another alternative embodiment of the application, referring to Fig. 3, for a kind of predicting power of photovoltaic plant side provided by the present application
The flow diagram of method embodiment 3, the present embodiment are mainly the predicting power of photovoltaic plant method described to above-described embodiment 1
Refinement scheme, as shown in figure 3, this method may include but be not limited to following steps:
Step S31, the second preset time after current time for photovoltaic plant affiliated area prediction is obtained
Meteorological data in section, and extracted in the meteorological data after the current time in second preset time period from prediction meteorological special
Sign.
Second preset time period is k days, and the k is the integer greater than 0.
Preferably, the value range of k can be set to 1-3.
The process of Meteorological Characteristics is extracted in the meteorological data after the current time in second preset time period from prediction
It may refer to the related introduction for extracting Meteorological Characteristics in embodiment 1 from the meteorological data of prediction, repeated in this step.
Step S31 is a kind of specific embodiment of step S11 in embodiment 1.
Step S32, Meteorological Characteristics input is obtained for the nervus opticus network model of photovoltaic plant building
The generated output of the nervus opticus network model output, the generated power forecasting value as the photovoltaic plant.
The neural network model is second pre- using the photovoltaic plant affiliated area before each historical juncture
If the meteorological data and the photovoltaic plant in the period are in the second preset time period before each historical time
Generated output training obtains.
Step S32 is a kind of specific embodiment of step S12 in embodiment 1.
In the present embodiment, by the second preset time period of setting and using the photovoltaic plant affiliated area in each history
The meteorological data and the photovoltaic plant in the second preset time period before moment before each historical time
Training of the generated output to neural network model in two preset time periods, may be implemented nervus opticus network model to photovoltaic electric
Stand carry out short-term power generation power prediction.
In another embodiment of the application, a kind of training process of neural network model is introduced, Fig. 4 is referred to, it can
With the following steps are included:
Step S41, the history meteorological data of the photovoltaic plant affiliated area is obtained from cloud database and described is gone through
The history generated output of the corresponding photovoltaic plant of history meteorological data.
In the present embodiment, the meteorological data of photovoltaic plant affiliated area can be downloaded from GFS, cloud data are arrived in storage
Library, the history meteorological data as photovoltaic plant affiliated area.Also, the meteorology of photovoltaic plant affiliated area is downloaded from GFS
While data, the generated output of the photovoltaic plant with the period is acquired, is stored into cloud database, as history meteorological data
The history generated output of corresponding photovoltaic plant.
By history meteorological data and the storage of history generated output into cloud database, photovoltaic plant end station grade can be saved
The memory space of server shortens the time of Neural Network model predictive.
Step S42, Meteorological Characteristics are extracted from the history meteorological data, as input training sample, by the history
Generated output is trained neural network model as output training sample.
Meteorological Characteristics are extracted from the history meteorological data, as input training sample, by the history generated output
As output training sample, neural network model is trained, step in the neural network model i.e. embodiment 1 that training obtains
Neural network model used in S12.
In another embodiment of the application, the training process of another neural network model is introduced, Fig. 5 is referred to,
It may comprise steps of:
Step S51, the history meteorological data of the photovoltaic plant affiliated area is obtained from cloud database and described is gone through
The history generated output of the corresponding photovoltaic plant of history meteorological data.
Step S52, Meteorological Characteristics are extracted from the history meteorological data, as input training sample, by the history
Generated output is trained neural network model as output training sample.
The detailed process of step S51-S52 may refer to the related introduction of step S41-S42 in above-described embodiment, herein not
It repeats again.
Step S53, the photovoltaic plant is obtained before current time in third preset time period, and each of output is sent out
The meteorological data of electrical power and the photovoltaic plant affiliated area before current time in third preset time period.
Third preset time period can according to need carry out flexible setting, herein with no restrictions.Such as, third preset time period
It can be set to 15 days.
The photovoltaic plant is obtained before current time in third preset time period, each generated output of output,
And meteorological data of the photovoltaic plant affiliated area before current time in third preset time period, it realizes more fine-grained
The acquisition of training sample.
Step S54, using the photovoltaic plant before current time in third preset time period, each of output is sent out
The meteorological data of electrical power and the photovoltaic plant affiliated area before current time in third preset time period, to described
Neural network model is trained optimization.
Using the photovoltaic plant before current time in third preset time period, each generated output of output,
And meteorological data of the photovoltaic plant affiliated area before current time in third preset time period, to the neural network
Model is trained optimization, and the neural network model after guaranteeing training optimization can more accurately predict the power generation of photovoltaic plant
Power.
Next predicting power of photovoltaic plant device provided by the present application is introduced, the photovoltaic plant function being introduced below
Rate prediction meanss can correspond to each other reference with predicting power of photovoltaic plant method described above.
Fig. 6 is referred to, predicting power of photovoltaic plant device includes: extraction module 11 and prediction module 12.
Extraction module 11, for obtaining the meteorological data for being directed to the prediction of photovoltaic plant affiliated area, and from the prediction
Meteorological Characteristics are extracted in meteorological data；
Prediction module 12, the neural network model for constructing Meteorological Characteristics input for the photovoltaic plant,
Obtain the generated output of the neural network model output, the generated power forecasting value as the photovoltaic plant；
The neural network model is the history meteorological data and the history gas using the photovoltaic plant affiliated area
What the history generated output training of the corresponding photovoltaic plant of image data obtained.
In the present embodiment, the meteorological data for the prediction of photovoltaic plant affiliated area can be with are as follows: is directed to the photovoltaic
Meteorological data in the first preset time period after the current time of power station affiliated area prediction, first preset time period
It is i minutes or j hours, the i is the integer greater than 0, and the j is the integer greater than 0；
Correspondingly, the neural network model are as follows: first nerves network model；
The neural network model is first pre- using the photovoltaic plant affiliated area before each historical juncture
If the meteorological data and the photovoltaic plant in the period are in the first preset time period before each historical time
Generated output training obtains.
In the present embodiment, the meteorological data for the prediction of photovoltaic plant affiliated area can be with are as follows: is directed to the photovoltaic
Meteorological data in the second preset time period after the current time of power station affiliated area prediction, second preset time period
It is k days, the k is the integer greater than 0；
Correspondingly, the neural network model are as follows: nervus opticus network model；
The neural network model is second pre- using the photovoltaic plant affiliated area before each historical juncture
If the meteorological data and the photovoltaic plant in the period are in the second preset time period before each historical time
Generated output training obtains.
In the present embodiment, above-mentioned predicting power of photovoltaic plant device can also include:
Neural network model training module, is used for:
Obtained from cloud database the photovoltaic plant affiliated area history meteorological data and the history meteorology number
According to the history generated output of the corresponding photovoltaic plant；
Meteorological Characteristics are extracted from the history meteorological data, as input training sample, by the history generated output
As output training sample, neural network model is trained.
In the present embodiment, the neural network model training module be can be also used for:
The photovoltaic plant is obtained before current time in third preset time period, each generated output of output,
And meteorological data of the photovoltaic plant affiliated area before current time in third preset time period；
Using the photovoltaic plant before current time in third preset time period, each generated output of output,
And meteorological data of the photovoltaic plant affiliated area before current time in third preset time period, to the neural network
Model is trained optimization.
It should be noted that the same or similar parts between the embodiments can be referred to each other in this specification.It is right
For device class embodiment, since it is basically similar to the method embodiment, so be described relatively simple, related place referring to
The part of embodiment of the method illustrates.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit can be realized in the same or multiple software and or hardware when application.
As seen through the above description of the embodiments, those skilled in the art can be understood that the application can
It realizes by means of software and necessary general hardware platform.Based on this understanding, the technical solution essence of the application
On in other words the part that contributes to existing technology can be embodied in the form of software products, the computer software product
It can store in storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions are used so that a computer equipment
(can be personal computer, server or the network equipment etc.) executes the certain of each embodiment of the application or embodiment
Method described in part.
A kind of predicting power of photovoltaic plant method and device provided herein is described in detail above, herein
In apply specific case the principle and implementation of this application are described, the explanation of above example is only intended to sides
Assistant solves the present processes and its core concept；At the same time, for those skilled in the art, the think of according to the application
Think, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not be construed as pair
The limitation of the application.
Claims (10)
1. a kind of predicting power of photovoltaic plant method characterized by comprising
The meteorological data for the prediction of photovoltaic plant affiliated area is obtained, and extraction is meteorological special from the meteorological data of the prediction
Sign；
By Meteorological Characteristics input for the neural network model of photovoltaic plant building, the neural network model is obtained
The generated output of output, the generated power forecasting value as the photovoltaic plant；
The neural network model is the history meteorological data and the history meteorology number using the photovoltaic plant affiliated area
It is obtained according to the history generated output training of the corresponding photovoltaic plant.
2. the method according to claim 1, wherein the meteorological number for the prediction of photovoltaic plant affiliated area
According to are as follows: for the meteorological data in the first preset time period after the current time of photovoltaic plant affiliated area prediction,
First preset time period is i minutes or j hours, and the i is the integer greater than 0, and the j is the integer greater than 0；
The neural network model are as follows: first nerves network model；
The neural network model be using the photovoltaic plant affiliated area before each historical juncture first it is default when
Between the power generation of meteorological data and the photovoltaic plant in the first preset time period before each historical time in section
Power training obtains.
3. the method according to claim 1, wherein the meteorological number for the prediction of photovoltaic plant affiliated area
According to are as follows: for the meteorological data in the second preset time period after the current time of photovoltaic plant affiliated area prediction,
Second preset time period is k days, and the k is the integer greater than 0；
The neural network model are as follows: nervus opticus network model；
The neural network model be using the photovoltaic plant affiliated area before each historical juncture second it is default when
Between the power generation of meteorological data and the photovoltaic plant in the second preset time period before each historical time in section
Power training obtains.
4. the method according to claim 1, wherein the training process of the neural network model, comprising:
The history meteorological data and the history meteorological data pair of the photovoltaic plant affiliated area are obtained from cloud database
The history generated output for the photovoltaic plant answered；
Extract Meteorological Characteristics from the history meteorological data, as input training sample, using the history generated output as
Training sample is exported, neural network model is trained.
5. according to the method described in claim 4, it is characterized in that, the method also includes:
The photovoltaic plant is obtained before current time in third preset time period, each generated output of output and institute
State meteorological data of the photovoltaic plant affiliated area before current time in third preset time period；
Using the photovoltaic plant before current time in third preset time period, each generated output of output and institute
Meteorological data of the photovoltaic plant affiliated area before current time in third preset time period is stated, to the neural network model
It is trained optimization.
6. a kind of predicting power of photovoltaic plant device characterized by comprising
Extraction module, for obtaining the meteorological data for being directed to the prediction of photovoltaic plant affiliated area, and from the meteorological number of the prediction
According to middle extraction Meteorological Characteristics；
Prediction module, for Meteorological Characteristics input for the neural network model of photovoltaic plant building, to be obtained institute
State the generated output of neural network model output, the generated power forecasting value as the photovoltaic plant；
The neural network model is the history meteorological data and the history meteorology number using the photovoltaic plant affiliated area
It is obtained according to the history generated output training of the corresponding photovoltaic plant.
7. device according to claim 6, which is characterized in that the meteorological number for the prediction of photovoltaic plant affiliated area
According to are as follows: for the meteorological data in the first preset time period after the current time of photovoltaic plant affiliated area prediction,
First preset time period is i minutes or j hours, and the i is the integer greater than 0, and the j is the integer greater than 0；
The neural network model are as follows: first nerves network model；
The neural network model be using the photovoltaic plant affiliated area before each historical juncture first it is default when
Between the power generation of meteorological data and the photovoltaic plant in the first preset time period before each historical time in section
Power training obtains.
8. device according to claim 6, which is characterized in that the meteorological number for the prediction of photovoltaic plant affiliated area
According to are as follows: for the meteorological data in the second preset time period after the current time of photovoltaic plant affiliated area prediction,
Second preset time period is k days, and the k is the integer greater than 0；
The neural network model are as follows: nervus opticus network model；
The neural network model be using the photovoltaic plant affiliated area before each historical juncture second it is default when
Between the power generation of meteorological data and the photovoltaic plant in the second preset time period before each historical time in section
Power training obtains.
9. device according to claim 6, which is characterized in that further include: neural network model training module is used for:
The history meteorological data and the history meteorological data pair of the photovoltaic plant affiliated area are obtained from cloud database
The history generated output for the photovoltaic plant answered；
Extract Meteorological Characteristics from the history meteorological data, as input training sample, using the history generated output as
Training sample is exported, neural network model is trained.
10. device according to claim 9, which is characterized in that the neural network model training module is also used to:
The photovoltaic plant is obtained before current time in third preset time period, each generated output of output and institute
State meteorological data of the photovoltaic plant affiliated area before current time in third preset time period；
Using the photovoltaic plant before current time in third preset time period, each generated output of output and institute
Meteorological data of the photovoltaic plant affiliated area before current time in third preset time period is stated, to the neural network model
It is trained optimization.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910712040.1A CN110348648A (en) | 2019-08-02 | 2019-08-02 | A kind of predicting power of photovoltaic plant method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910712040.1A CN110348648A (en) | 2019-08-02 | 2019-08-02 | A kind of predicting power of photovoltaic plant method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110348648A true CN110348648A (en) | 2019-10-18 |
Family
ID=68183810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910712040.1A Pending CN110348648A (en) | 2019-08-02 | 2019-08-02 | A kind of predicting power of photovoltaic plant method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110348648A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932007A (en) * | 2020-08-04 | 2020-11-13 | 广州发展新能源股份有限公司 | Power prediction method and device for photovoltaic power station and storage medium |
| CN112101626A (en) * | 2020-08-14 | 2020-12-18 | 安徽继远软件有限公司 | Distributed photovoltaic power generation power prediction method and system |
| CN113570126A (en) * | 2021-07-15 | 2021-10-29 | 远景智能国际私人投资有限公司 | Method, device and system for predicting power generation power of photovoltaic power station |
| CN114936640A (en) * | 2022-07-04 | 2022-08-23 | 中北大学 | Online training method for new energy power generation intelligent prediction model |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521670A (en) * | 2011-11-18 | 2012-06-27 | 中国电力科学研究院 | Power generation output power prediction method based on meteorological elements for photovoltaic power station |
| CN102930358A (en) * | 2012-11-28 | 2013-02-13 | 江西九江供电公司 | Neural network prediction method for generated output of photovoltaic power station |
| CN103390200A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power station electricity generation output power forecasting method based on similar days |
| CN105404937A (en) * | 2015-11-26 | 2016-03-16 | 北京国电通网络技术有限公司 | Photovoltaic plant short-term power prediction method and system |
| CN107220723A (en) * | 2017-04-20 | 2017-09-29 | 华北电力大学 | A kind of predicting power of photovoltaic plant method |
| CN109002915A (en) * | 2018-07-13 | 2018-12-14 | 福州大学 | Photovoltaic plant short term power prediction technique based on Kmeans-GRA-Elman model |
| JP2018207727A (en) * | 2017-06-08 | 2018-12-27 | 清水建設株式会社 | Excess power evaluation device and excess power evaluation method |
| CN109657881A (en) * | 2019-01-14 | 2019-04-19 | 南京国电南自电网自动化有限公司 | A kind of neural network photovoltaic power generation prediction technique and system suitable for small sample |
| CN109978284A (en) * | 2019-04-25 | 2019-07-05 | 中国人民解放军国防科技大学 | Photovoltaic power generation power time-sharing prediction method based on hybrid neural network model |
-
2019
- 2019-08-02 CN CN201910712040.1A patent/CN110348648A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521670A (en) * | 2011-11-18 | 2012-06-27 | 中国电力科学研究院 | Power generation output power prediction method based on meteorological elements for photovoltaic power station |
| CN102930358A (en) * | 2012-11-28 | 2013-02-13 | 江西九江供电公司 | Neural network prediction method for generated output of photovoltaic power station |
| CN103390200A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power station electricity generation output power forecasting method based on similar days |
| CN105404937A (en) * | 2015-11-26 | 2016-03-16 | 北京国电通网络技术有限公司 | Photovoltaic plant short-term power prediction method and system |
| CN107220723A (en) * | 2017-04-20 | 2017-09-29 | 华北电力大学 | A kind of predicting power of photovoltaic plant method |
| JP2018207727A (en) * | 2017-06-08 | 2018-12-27 | 清水建設株式会社 | Excess power evaluation device and excess power evaluation method |
| CN109002915A (en) * | 2018-07-13 | 2018-12-14 | 福州大学 | Photovoltaic plant short term power prediction technique based on Kmeans-GRA-Elman model |
| CN109657881A (en) * | 2019-01-14 | 2019-04-19 | 南京国电南自电网自动化有限公司 | A kind of neural network photovoltaic power generation prediction technique and system suitable for small sample |
| CN109978284A (en) * | 2019-04-25 | 2019-07-05 | 中国人民解放军国防科技大学 | Photovoltaic power generation power time-sharing prediction method based on hybrid neural network model |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932007A (en) * | 2020-08-04 | 2020-11-13 | 广州发展新能源股份有限公司 | Power prediction method and device for photovoltaic power station and storage medium |
| CN112101626A (en) * | 2020-08-14 | 2020-12-18 | 安徽继远软件有限公司 | Distributed photovoltaic power generation power prediction method and system |
| CN113570126A (en) * | 2021-07-15 | 2021-10-29 | 远景智能国际私人投资有限公司 | Method, device and system for predicting power generation power of photovoltaic power station |
| CN114936640A (en) * | 2022-07-04 | 2022-08-23 | 中北大学 | Online training method for new energy power generation intelligent prediction model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110348648A (en) | A kind of predicting power of photovoltaic plant method and device | |
| Zhou et al. | Deep Learning Enhanced Solar Energy Forecasting with AI‐Driven IoT | |
| Sarwat et al. | Weather-based interruption prediction in the smart grid utilizing chronological data | |
| Theocharides et al. | Machine learning algorithms for photovoltaic system power output prediction | |
| Constantinescu et al. | A computational framework for uncertainty quantification and stochastic optimization in unit commitment with wind power generation | |
| KR102405282B1 (en) | Method for predicting of solar power generation using prediction model | |
| Dubey et al. | Optimization of solar photovoltaic plant and economic analysis | |
| CN103208037B (en) | A kind of power forecasting method based on on-line correction being applied to new energy power station | |
| CN106651007A (en) | Method and device for GRU-based medium and long-term prediction of irradiance of photovoltaic power station | |
| Ciapessoni et al. | Risk-based dynamic security assessment for power system operation and operational planning | |
| Fidan et al. | Harmonic analysis based hourly solar radiation forecasting model | |
| CN113408785B (en) | Method, device, equipment and storage medium for predicting optical power | |
| Zhang et al. | Robust classification model for PMU‐based on‐line power system DSA with missing data | |
| Li et al. | Multivariable time series prediction for the icing process on overhead power transmission line | |
| CN106934191A (en) | A kind of WRF pattern correction wind methods based on self-similarity | |
| CN109657874A (en) | A kind of electric power Mid-long term load forecasting method based on long memory models in short-term | |
| Michiorri et al. | Forecasting real-time ratings for electricity distribution networks using weather forecast data | |
| Corne et al. | Short term wind speed forecasting with evolved neural networks | |
| Tran et al. | Short-term solar power generation forecasting using edge ai | |
| Ceferino et al. | Hurricane Risk of Solar Generation in the United States | |
| Kassim et al. | Harmony search-based optimization of artificial neural network for predicting AC power from a photovoltaic system | |
| WO2020125984A1 (en) | System and method for power outage prediction | |
| Zheng et al. | Offshore wind power ramp prediction based on optimal combination model | |
| Kumar et al. | Forecasting wind power using Optimized Recurrent Neural Network strategy with time‐series data | |
| CN110743111B (en) | Real-time evacuation guide system based on regional field |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191018 |
|
| RJ01 | Rejection of invention patent application after publication |