CN112257938B - Photovoltaic power generation power prediction method and device - Google Patents
Photovoltaic power generation power prediction method and device Download PDFInfo
- Publication number
- CN112257938B CN112257938B CN202011170431.4A CN202011170431A CN112257938B CN 112257938 B CN112257938 B CN 112257938B CN 202011170431 A CN202011170431 A CN 202011170431A CN 112257938 B CN112257938 B CN 112257938B
- Authority
- CN
- China
- Prior art keywords
- level
- sequence
- power
- output power
- generation output
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 28
- 239000011159 matrix material Substances 0.000 claims description 26
- 238000013527 convolutional neural network Methods 0.000 claims description 15
- 238000000354 decomposition reaction Methods 0.000 claims description 12
- 230000003287 optical effect Effects 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 6
- 230000000903 blocking effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a photovoltaic power generation power prediction method and a device, wherein the method takes the second-level power generation output power of the previous time period and the second-level solar shielding sequence of the next time period as input, inputs the input into a power generation power prediction model, and predicts the second-level power generation output power of a photovoltaic power station in the next time period.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation, in particular to a photovoltaic power generation power prediction method and device.
Background
In the conventional photovoltaic power generation power prediction, meteorological factor phasor is established mainly through digital meteorological forecasting, and similar solar irradiation distribution or similar solar photovoltaic power output is obtained through methods such as phasor calculation and the like; however, the environment change in a small space scale cannot be described by the digitized weather forecast data, the solar irradiation change caused by cloud movement may cause hundreds of watts in a few seconds, and the solar irradiation change in the time scale is difficult to be described by the conventional solar irradiation prediction technology, so that the prediction accuracy is low.
Disclosure of Invention
The embodiment of the invention provides a photovoltaic power generation power prediction method and device, which can improve the accuracy of photovoltaic power generation power prediction.
An embodiment of the present invention provides a photovoltaic power generation power prediction method, including:
taking the current moment as a boundary, acquiring second-level power generation output power of the photovoltaic power station in the previous time period to obtain first second-level power generation output power, and calculating a second-level sun shielding sequence in the next time period to obtain a first second-level sun shielding sequence;
and inputting the first second-level generation output power and the first second-level solar shielding sequence into a preset generation power prediction model, so that the generation power prediction model predicts the second-level photovoltaic generation output power of the photovoltaic power station in the next period according to the first second-level generation output power and the first second-level solar shielding sequence.
Further, the generating power prediction model predicts the second-level generating output power of the photovoltaic power station in the next period according to the first-second-level generating output power and the first-second-level sun shading sequence, and specifically includes:
performing wavelet maximum layer decomposition on the first second-level power generation output power to obtain a maximum layer approximate phasor sequence and detail phasor sequences of different levels;
respectively constructing a phasor sequence matrix of each phasor sequence, and then inputting each phasor sequence matrix into a convolutional neural network so that the convolutional neural network generates a predicted phasor sequence of a next time period corresponding to each phasor sequence matrix according to each phasor sequence matrix;
reconstructing each predicted phasor sequence according to a wavelet transformation reconstruction algorithm to generate a second-level power generation output power sequence;
and linearly fusing the first second-level sun shielding sequence and the second-level power generation output power sequence to generate second-level power generation output power of the photovoltaic power station in the next period.
Further, a second-level solar occlusion sequence for the next time period is calculated by:
collecting a second-level foundation cloud picture, and calculating the relative movement speed of a cloud layer relative to the sun through an optical flow method according to the second-level foundation cloud picture;
and calculating whether the sun is shielded in each second-level time interval period in the next time period according to the relative movement speed, and then generating a second-level sun shielding sequence of the next time period according to the condition that the sun is shielded in each second-level time interval period.
And further, the second-level power generation output power of the photovoltaic power station in the last period is collected through the photovoltaic inverter.
On the basis of the above method item embodiment, the present invention correspondingly provides an apparatus item embodiment:
the embodiment of the invention provides a photovoltaic power generation power prediction device, which comprises a data acquisition module and a power prediction module, wherein the data acquisition module is used for acquiring data;
the data acquisition module is used for acquiring second-level power generation output power of the photovoltaic power station in the previous time period by taking the current time as a boundary to obtain first second-level power generation output power, and calculating a second-level sun shielding sequence in the next time period to obtain a first second-level sun shielding sequence;
the power prediction module is used for inputting the first second-level generation output power and the first second-level solar shielding sequence into a preset generation power prediction model so that the generation power prediction model can predict the second-level generation output power of the photovoltaic power station in the next time period according to the first second-level generation output power and the first second-level solar shielding sequence.
Further, the generated power prediction model predicts the second-level generated output power of the photovoltaic power plant in the next period according to the first-second-level generated output power and the first-second-level sun blocking sequence, and specifically includes:
performing wavelet maximum layer decomposition on the first second-level power generation output power to obtain a maximum layer approximate phasor sequence and detail phasor sequences of different levels;
respectively constructing a phasor sequence matrix of each phasor sequence, and then inputting each phasor sequence matrix into a convolutional neural network so that the convolutional neural network generates a predicted phasor sequence of a next time period corresponding to each phasor sequence matrix according to each phasor sequence matrix;
reconstructing each predicted phasor sequence according to a wavelet transformation reconstruction algorithm to generate a second-level power generation output power sequence;
and linearly fusing the first second-level sun shading sequence and the second-level power generation output power sequence to generate second-level power generation output power of the photovoltaic power station in the next period.
Further, the data acquisition module calculates a second-level sun shading sequence of the next time interval by:
acquiring a second-level foundation cloud picture, and calculating the relative movement speed of a cloud layer relative to the sun through an optical flow method according to the second-level foundation cloud picture;
and calculating whether the sun is shielded in each second-level time interval period in the next time period according to the relative movement speed, and then generating a second-level sun shielding sequence of the next time period according to the condition that the sun is shielded in each second-level time interval period.
The embodiment of the invention has the following beneficial effects:
compared with the prior art, the method introduces the condition that the sun is shielded by a cloud layer on a second-level time interval period through the second-level solar shielding sequence of the next time period, corresponds to the condition that the solar irradiation change caused by the movement of the cloud layer in the actual power generation process may cause the solar irradiation change to be hundreds of watts within several seconds, and improves the accuracy of the photovoltaic power generation prediction.
Drawings
Fig. 1 is a schematic flow chart of a photovoltaic power generation power prediction method according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a photovoltaic power generation power prediction apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a method for predicting photovoltaic power generation power, including:
and S101, acquiring second-level power generation output power of the photovoltaic power station in the previous time period by taking the current time as a boundary to obtain first second-level power generation output power, and calculating a second-level sun shielding sequence in the next time period to obtain a first second-level sun shielding sequence.
And S102, inputting the first second-level generation output power and the first second-level solar shielding sequence into a preset generation power prediction model, so that the generation power prediction model predicts the second-level generation output power of the photovoltaic power station in the next time period according to the first second-level generation output power and the first second-level solar shielding sequence.
For step S101, in a preferred embodiment, the second-level generated output power of the photovoltaic power plant in the last period is collected by the photovoltaic inverter. The method comprises the steps that the output power of a high-resolution photovoltaic power station is collected through a photovoltaic inverter, and the second-level power generation output power of the photovoltaic power station in the last period is obtained; preferably, the second-level generated output power of the photovoltaic power plant in the previous period of time refers to the second-level generated output power of the photovoltaic power plant in the past 1 hour with the current time as a boundary.
In a preferred embodiment, the second-order solar-occlusion sequence for the next time period is calculated by:
collecting a second-level foundation cloud picture, and calculating the relative movement speed of a cloud layer relative to the sun through an optical flow method according to the second-level foundation cloud picture; and calculating whether the sun is shielded in each second-level time interval period in the next time period according to the relative movement speed, and then generating a second-level sun shielding sequence of the next time period according to the condition that the sun is shielded in each second-level time interval period.
Specifically, a second-level foundation cloud picture of an area where a photovoltaic power station is located is collected through an all-sky camera, the relative motion speed of a cloud layer relative to the sun is evaluated through an optical flow method, the relative position of the cloud layer and the sun at a future moment (within one hour in the future) is judged, whether the sun is shielded or not in a second-level time interval period is evaluated, if shielding exists, the sun shielding sequence is 1, and if shielding does not exist, the sun shielding sequence related to a time sequence is established, wherein the sun shielding sequence is [0, 0, 1, …,1 ].
In a preferred embodiment, the second-level solar occlusion sequence of the next time interval refers to a second-level solar occlusion sequence within one hour in the future, bounded by the current time.
For step S102, in a preferred embodiment, the predicting module of the generated power predicts the second-level generated output power of the photovoltaic power plant in the next period according to the first-second-level generated output power and the first-second-level sun blocking sequence, and specifically includes:
performing wavelet maximum layer decomposition on the first second-level power generation output power to obtain a maximum layer approximate phasor sequence and detail phasor sequences of different levels;
respectively constructing a phasor sequence matrix of each phasor sequence, and then inputting each phasor sequence matrix into a convolutional neural network so that the convolutional neural network generates a predicted phasor sequence of a next time period corresponding to each phasor sequence matrix according to each phasor sequence matrix;
reconstructing each predicted phasor sequence according to a wavelet transformation reconstruction algorithm to generate a second-level power generation output power sequence;
and linearly fusing the first second-level sun shielding sequence and the second-level power generation output power sequence to generate second-level power generation output power of the photovoltaic power station in the next period.
Preferably, the second-level power generation output power of the photovoltaic power generation station in the next period refers to the second-level power generation output power of the photovoltaic power generation station within one hour in the future by taking the current time as a boundary.
According to the method, wavelet decomposition is carried out on second-level photovoltaic power, the second-level photovoltaic power is decomposed into a plurality of high-frequency and low-frequency sequences, a convolutional neural network algorithm is utilized to carry out modeling learning on each characteristic, high-dimensional information on each wavelet segment is extracted, and the extracted high-dimensional information is used as a deep learning framework; and predicting whether the cloud layer on the time axis shields the sun or not by using a foundation cloud picture technology, and establishing a time sequence state phasor as a shallow learning framework. By means of a wi de & Deep model (a model integrating a shallow model and a Deep model), frequency domain signal characteristics and time domain cloud cover state characteristics are integrated, and the model prediction capability is improved by means of the memory capability of the shallow model and the generalization capability of the Deep model.
Specifically, the generated power prediction model of the invention is a model integrating a shallow model and a deep model; the shallow layer input is a sun shielding time state sequence (namely the sun shielding sequence) acquired according to the foundation cloud picture, and is connected with the output layer;
the deep layer model adopts a convolution neural network model, and the second-level power generation output power sequence in the next time period is predicted according to the operations of decomposition, convolution calculation, phasor sequence prediction and reconstruction of the past 1 hour second-level photovoltaic power station output power.
The following is a schematic description of specific processing of the power generation prediction model after the model inputs the second-level power generation output power of the photovoltaic power station and the first-second-level sun blocking sequence in the last period into the power generation prediction model, and the second-level power generation output power of the photovoltaic power station in the past 1 hour is still taken as an example:
firstly, a power generation prediction model decomposes the second-level power generation output power of a past 1 photovoltaic power station according to a Mallat algorithm and a Daubechies wavelet decomposition algorithm according to a wavelet maximum layer, and the calculation method of the decomposition maximum layer is as follows:
wherein ps is a time sequence of the generated power of the photovoltaic power station in the past 1 hour; fs is the data length of the selected wavelet decomposition layer.
The maxL layer approximate phasor sequences (maximum layer approximate phasor sequences) Xa and T with the time label T and the detail phasor sequences of each layer are obtained through the decomposition: the method comprises the following steps of (1) carrying out a maxL layer detail phasor sequence Xdm, a maxL-1 layer detail phasor sequence Xdm-1, … and a first layer phasor detail sequence Xd 1;
establishing phasor sequence matrixes of each layer of phasor sequences (including maxL layer approximate phasor sequences and detail phasor sequences of all levels), and taking a maxL-th layer approximate phasor sequence as an example, establishing an input matrix M of a time sequence, namely [ Xa, T, Xa, T-1, …, Xa, 1 ]; inputting the time-series matrix vector to a convolutional neural network model and a convolutional neural network model, calculating and extracting one-dimensional high-level characteristic phasor of the maxL-th layer approximate phasor sequence, and finally outputting Xa and T +1 of the time tag of the approximate phasor sequence T + 1.
Then reconstructing the phasor sequence predicted by each layer according to a wavelet change reconstruction algorithm to obtain a second-level power generation phasor sequence in the next time period, and establishing a deep full-connection layer
And finally, performing linear fusion on the second-level generated power phasor sequence and the first-second-level sun shielding sequence in the next time period in the output layer, and predicting the second-level generated output power of the photovoltaic power station in the next time period.
On the basis of the embodiment of the method item, the invention correspondingly provides an embodiment of a device item;
as shown in fig. 2, an embodiment of the present invention provides a photovoltaic power generation power prediction apparatus, which includes a data obtaining module and a power prediction module;
the data acquisition module is used for acquiring second-level power generation output power of the photovoltaic power station in the previous time period by taking the current time as a boundary to obtain first second-level power generation output power, and calculating a second-level sun shielding sequence in the next time period to obtain a first second-level sun shielding sequence;
the power prediction module is used for inputting the first second-level generation output power and the first second-level solar shielding sequence into a preset generation power prediction model so that the generation power prediction model can predict the second-level generation output power of the photovoltaic power station in the next time period according to the first second-level generation output power and the first second-level solar shielding sequence.
In a preferred embodiment, the generating power prediction model predicts the second-level generating output power of the photovoltaic power plant in the next time period according to the first-second-level generating output power and the first-second-level solar blocking sequence, and specifically includes:
performing wavelet maximum layer decomposition on the first second-level power generation output power to obtain a maximum layer approximate phasor sequence and detail phasor sequences of different levels;
respectively constructing a phasor sequence matrix of each phasor sequence, and then inputting each phasor sequence matrix into a convolutional neural network so that the convolutional neural network generates a predicted phasor sequence of a next time period corresponding to each phasor sequence matrix according to each phasor sequence matrix;
reconstructing each predicted phasor sequence according to a wavelet transformation reconstruction algorithm to generate a second-level power generation output power sequence;
and linearly fusing the first second-level sun shielding sequence and the second-level power generation output power sequence to generate second-level power generation output power of the photovoltaic power station in the next period.
In a preferred embodiment, the data acquisition module calculates the second-level solar shading sequence for the next time period by:
acquiring a second-level foundation cloud picture, and calculating the relative movement speed of a cloud layer relative to the sun through an optical flow method according to the second-level foundation cloud picture;
and calculating whether the sun is shielded in each second-level time interval period in the next time period according to the relative movement speed, and then generating a second-level sun shielding sequence of the next time period according to the condition that the sun is shielded in each second-level time interval period.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (3)
1. A photovoltaic power generation power prediction method is characterized by comprising the following steps:
the method comprises the steps that the current moment is used as a boundary, second-level power generation output power of a photovoltaic power station in the previous time period is obtained, first second-level power generation output power is obtained, a second-level sun shielding sequence in the next time period is calculated, and a first second-level sun shielding sequence is obtained;
inputting the first second-level generation output power and the first second-level solar shielding sequence into a preset generation power prediction model, so that the generation power prediction model predicts the second-level generation output power of the photovoltaic power station in the next period according to the first second-level generation output power and the first second-level solar shielding sequence;
the generated power prediction model predicts the second-level generated output power of the photovoltaic power station in the next period according to the first-second-level generated output power and the first-second-level sun shielding sequence, and specifically comprises the following steps:
performing wavelet maximum layer decomposition on the first second-level power generation output power to obtain a maximum layer approximate phasor sequence and detail phasor sequences of different levels;
respectively constructing a phasor sequence matrix of each phasor sequence, and then inputting each phasor sequence matrix into a convolutional neural network so that the convolutional neural network generates a predicted phasor sequence of the next time period corresponding to each phasor sequence matrix according to each phasor sequence matrix;
reconstructing each predicted phasor sequence according to a wavelet transformation reconstruction algorithm to generate a second-level power generation output power sequence;
linearly fusing the first second-level sun shielding sequence and the second-level power generation output power sequence to generate second-level power generation output power of the photovoltaic power station in the next period;
calculating a second-level solar occlusion sequence for the next time period by:
collecting a second-level foundation cloud picture, and calculating the relative movement speed of a cloud layer relative to the sun through an optical flow method according to the second-level foundation cloud picture;
and calculating whether the sun is shielded in each second-level time interval period in the next time period according to the relative movement speed, and then generating a second-level sun shielding sequence of the next time period according to the condition that the sun is shielded in each second-level time interval period.
2. The photovoltaic generated power prediction method according to claim 1, wherein the generation output power of the photovoltaic power plant in the second order in the last period is collected by the photovoltaic inverter.
3. The photovoltaic power generation power prediction device is characterized by comprising a data acquisition module and a power prediction module;
the data acquisition module is used for acquiring second-level power generation output power of the photovoltaic power station in the previous time period by taking the current time as a boundary to obtain first second-level power generation output power, and calculating a second-level sun shielding sequence in the next time period to obtain a first second-level sun shielding sequence;
the power prediction module is used for inputting the first second-level generation output power and the first second-level solar shielding sequence into a preset generation power prediction model so that the generation power prediction model can predict the second-level generation output power of the photovoltaic power station in the next time period according to the first second-level generation output power and the first second-level solar shielding sequence;
the method for predicting the second-level generation output power of the photovoltaic power station in the next period of time according to the first-second-level generation output power and the first-second-level sun shielding sequence includes the following steps:
performing wavelet maximum layer decomposition on the first second-level power generation output power to obtain a maximum layer approximate phasor sequence and detail phasor sequences of different levels;
respectively constructing a phasor sequence matrix of each phasor sequence, and then inputting each phasor sequence matrix into a convolutional neural network so that the convolutional neural network generates a predicted phasor sequence of the next time period corresponding to each phasor sequence matrix according to each phasor sequence matrix;
reconstructing each predicted phasor sequence according to a wavelet transformation reconstruction algorithm to generate a second-level power generation output power sequence;
linearly fusing the first second-level sun shielding sequence and the second-level power generation output power sequence to generate second-level power generation output power of the photovoltaic power station in the next period;
the data acquisition module calculates a second-level sun shielding sequence of the next time interval in the following mode:
collecting a second-level foundation cloud picture, and calculating the relative movement speed of a cloud layer relative to the sun through an optical flow method according to the second-level foundation cloud picture;
and calculating whether the sun is shielded in each second-level time interval period in the next time period according to the relative movement speed, and then generating a second-level sun shielding sequence of the next time period according to the condition that the sun is shielded in each second-level time interval period.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011170431.4A CN112257938B (en) | 2020-10-28 | 2020-10-28 | Photovoltaic power generation power prediction method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011170431.4A CN112257938B (en) | 2020-10-28 | 2020-10-28 | Photovoltaic power generation power prediction method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112257938A CN112257938A (en) | 2021-01-22 |
CN112257938B true CN112257938B (en) | 2022-07-08 |
Family
ID=74261398
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011170431.4A Active CN112257938B (en) | 2020-10-28 | 2020-10-28 | Photovoltaic power generation power prediction method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112257938B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112801413A (en) * | 2021-03-02 | 2021-05-14 | 国网电子商务有限公司 | Photovoltaic power station generated power prediction method and device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105335560A (en) * | 2015-10-29 | 2016-02-17 | 中国电力科学研究院 | Photovoltaic generation power volatility and automatic generation control reserve demand computing method thereof |
CN107563903A (en) * | 2016-06-30 | 2018-01-09 | 中国电力科学研究院 | A kind of cloud layer blocks method for establishing model to ground photovoltaic plant |
CN108280551A (en) * | 2018-02-02 | 2018-07-13 | 华北电力大学 | A kind of photovoltaic power generation power prediction method using shot and long term memory network |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180373827A1 (en) * | 2012-03-23 | 2018-12-27 | Power Analytics Corporation | Systems and methods for model-based solar power management |
JP6255251B2 (en) * | 2014-01-22 | 2017-12-27 | 株式会社日立製作所 | Output estimation method and apparatus for photovoltaic power generation apparatus and power system monitoring apparatus using the same |
CN111815038B (en) * | 2020-06-24 | 2022-05-13 | 山东大学 | Photovoltaic ultra-short term prediction method and system |
-
2020
- 2020-10-28 CN CN202011170431.4A patent/CN112257938B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105335560A (en) * | 2015-10-29 | 2016-02-17 | 中国电力科学研究院 | Photovoltaic generation power volatility and automatic generation control reserve demand computing method thereof |
CN107563903A (en) * | 2016-06-30 | 2018-01-09 | 中国电力科学研究院 | A kind of cloud layer blocks method for establishing model to ground photovoltaic plant |
CN108280551A (en) * | 2018-02-02 | 2018-07-13 | 华北电力大学 | A kind of photovoltaic power generation power prediction method using shot and long term memory network |
Non-Patent Citations (3)
Title |
---|
基于多尺度聚类分析的光伏功率特性建模及预测应用;管霖等;《电力系统自动化》;20180810;第42卷(第15期);第24-28页 * |
基于小波分解和卷积神经网络的光伏发电功率预测方法;易海燕;《中国优秀硕士学位论文全文数据库工程科技II辑》;20190715(第7期);第C042-307页 * |
基于相位相关的天空图像云团运动速度计算方法研究;王飞等;《无机太阳能学报》;20161031;第37卷(第10期);第2539-2541页 * |
Also Published As
Publication number | Publication date |
---|---|
CN112257938A (en) | 2021-01-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Huang et al. | Forecasting hourly solar irradiance using hybrid wavelet transformation and Elman model in smart grid | |
Agoua et al. | Short-term spatio-temporal forecasting of photovoltaic power production | |
Oh et al. | Real-time forecasting of wave heights using EOF–wavelet–neural network hybrid model | |
Rodríguez et al. | Forecasting intra-hour solar photovoltaic energy by assembling wavelet based time-frequency analysis with deep learning neural networks | |
CN112651290A (en) | Hydroelectric generating set vibration trend prediction method and system | |
CN106803128B (en) | Photovoltaic power generation prediction method and device | |
CN116128170B (en) | Photovoltaic power station power ultra-short-term prediction method and device and related equipment | |
Perpiñán et al. | Analysis and synthesis of the variability of irradiance and PV power time series with the wavelet transform | |
CN109711622A (en) | A kind of method and system based on space-time multi-dimensional factors prediction alert | |
CN112257938B (en) | Photovoltaic power generation power prediction method and device | |
Rebouças Filho et al. | Energy production predication via Internet of Thing based machine learning system | |
Wang et al. | A novel wind power prediction model improved with feature enhancement and autoregressive error compensation | |
Hatanaka et al. | Diffusion models for high-resolution solar forecasts | |
Yin et al. | Inception-embedded attention memory fully-connected network for short-term wind power prediction | |
Song et al. | Sea level simulation with signal decomposition and machine learning | |
Wei et al. | Cloudprednet: an ultra-short-term movement prediction model for ground-based cloud image | |
Khan et al. | DSPM: Dual sequence prediction model for efficient energy management in micro-grid | |
CN116451873B (en) | Wind power generation power prediction method and system based on multi-scale double space-time network area | |
Phan et al. | Application of a new Transformer-based model and XGBoost to improve one-day-ahead solar power forecasts | |
CN116706903A (en) | Photovoltaic power generation amount prediction method, device, equipment and medium | |
CN111932007B (en) | Power prediction method and device for photovoltaic power station and storage medium | |
Wan et al. | Turbine location wind speed forecast using convolutional neural network | |
CN116975611B (en) | High-frequency load data generation method and system based on diffusion model ODE form | |
Kustiyo et al. | Analysis on Dimensionality Reduction Techniques for Sub-Seasonal to Seasonal Rainfall Prediction | |
Singh et al. | Power forecasting in photovoltaic system using hybrid ANN and wavelet transform based method |
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 | ||
TR01 | Transfer of patent right |
Effective date of registration: 20231030 Address after: 510000 room 2901, No.3 Linjiang Avenue, Tianhe District, Guangzhou City, Guangdong Province Patentee after: GUANGZHOU DEVELOPMENT NEW ENERGY Co.,Ltd. Patentee after: GUANGFA HUIDONG WIND POWER CO.,LTD. Address before: 510000 29th floor, development center, No.3 Linjiang Avenue, Tianhe District, Guangzhou City, Guangdong Province Patentee before: GUANGZHOU DEVELOPMENT NEW ENERGY Co.,Ltd. |
|
TR01 | Transfer of patent right |