CN111932007B - Power prediction method and device for photovoltaic power station and storage medium - Google Patents
Power prediction method and device for photovoltaic power station and storage medium Download PDFInfo
- Publication number
- CN111932007B CN111932007B CN202010775268.8A CN202010775268A CN111932007B CN 111932007 B CN111932007 B CN 111932007B CN 202010775268 A CN202010775268 A CN 202010775268A CN 111932007 B CN111932007 B CN 111932007B
- Authority
- CN
- China
- Prior art keywords
- data sequence
- power
- data
- wavelet
- layer
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 36
- 239000011159 matrix material Substances 0.000 claims abstract description 34
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000013527 convolutional neural network Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 7
- 238000003306 harvesting Methods 0.000 claims 1
- 238000004364 calculation method Methods 0.000 abstract description 16
- 238000013528 artificial neural network Methods 0.000 abstract description 4
- 238000010248 power generation Methods 0.000 description 7
- 238000003062 neural network model Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000009466 transformation Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 241000282414 Homo sapiens Species 0.000 description 1
- HEFNNWSXXWATRW-UHFFFAOYSA-N Ibuprofen Chemical compound CC(C)CC1=CC=C(C(C)C(O)=O)C=C1 HEFNNWSXXWATRW-UHFFFAOYSA-N 0.000 description 1
- 108010076504 Protein Sorting Signals Proteins 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000013519 translation Methods 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)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a power prediction method, a device and a storage medium of a photovoltaic power station, wherein the method comprises the steps of obtaining historical power data of the photovoltaic power station in a first preset time period; calculating the historical power data according to a preset wavelet maximum layer decomposition type to obtain a maximum layer approximate data sequence and a detail data sequence of each layer; constructing a corresponding data sequence matrix by taking the maximum layer approximate data sequence and the detail data sequence of each layer as input quantity; and reconstructing the data sequence matrix of each level according to a wavelet reconstruction algorithm to obtain a corresponding predicted power value. According to the power prediction method, the device and the storage medium for the photovoltaic power station, provided by the embodiment of the invention, the historical photovoltaic power data is processed by adopting the wavelet decomposition algorithm, and then the characteristic learning is performed by combining the neural network modeling, so that the calculation complexity is reduced, and meanwhile, the accuracy of power prediction can be improved.
Description
Technical Field
The invention relates to the technical field of solar energy, in particular to a power prediction method and device of a photovoltaic power station and a storage medium.
Background
Photovoltaic power generation is a technology for directly converting light energy into electric energy by utilizing photovoltaic effect of a semiconductor interface, and because solar illumination has the characteristics of volatility, intermittence, randomness and the like, the access of large-scale solar photovoltaic power generation has a great influence on the stability of a power grid, so that a power dispatching department can timely dispatch according to the change of photovoltaic power generation amount, and in the operation of a photovoltaic power station, the power generation amount of the photovoltaic power station needs to be accurately predicted.
In the prior art, similar solar irradiation distribution or similar solar photovoltaic power output is obtained through numerical weather forecast, but on one hand, more types of weather data (including environmental parameters such as temperature, wind speed and the like) are contained in the weather forecast, so that the calculation complexity of photovoltaic forecast is greatly improved; on the other hand, compared with the actual result, the result of the solar irradiation distribution evaluation on the similar day also has larger inherent error, and the similarity of the solar irradiation space-time distribution cannot be completely represented, so that the existing power prediction method of the photovoltaic power station has higher calculation complexity and lower prediction precision, and is difficult to realize accurate prediction effect.
Disclosure of Invention
The invention provides a power prediction method, a device and a storage medium of a photovoltaic power station, which are used for solving the technical problems of higher calculation complexity and lower prediction accuracy of the existing power prediction method of the photovoltaic power station.
An embodiment of the present invention provides a power prediction method for a photovoltaic power station, including:
Acquiring historical power data of a photovoltaic power station in a first preset time period;
Calculating the historical power data according to a preset wavelet maximum layer decomposition type to obtain a maximum layer approximate data sequence and a detail data sequence of each layer;
Constructing a corresponding data sequence matrix by taking the maximum layer approximate data sequence and the detail data sequence of each layer as input quantity;
And reconstructing the data sequence matrix of each level according to a wavelet reconstruction algorithm to obtain a corresponding predicted power value.
As one preferable solution, the step of obtaining the historical power data of the photovoltaic power station in the first preset time period specifically includes:
and acquiring second-level output power data of a photovoltaic inverter of the photovoltaic power station in the preset time period, and taking the second-level output power data as the historical power data.
As one preferable mode, the wavelet maximum layer decomposition formula includes:
Wherein p s is the time sequence length of the generated power of the photovoltaic power station in a preset time period, f s is the data length of the selected wavelet decomposition layer, and maxL is the maximum layer of the selected wavelet decomposition.
As one preferable solution, the step of reconstructing the data sequence matrix of each level according to a wavelet reconstruction algorithm to obtain a corresponding predicted power value specifically includes:
Inputting the data sequence matrix of each level into a convolutional neural network, so that the convolutional neural network generates a corresponding predicted data sequence in a second preset time period according to the data sequence matrix of each level;
And reconstructing the predicted data sequence according to a wavelet reconstruction algorithm to obtain the corresponding predicted power value.
The invention further provides a power prediction device of a photovoltaic power station, which comprises an acquisition module and a controller; the acquisition module is connected with the controller;
The controller is configured to:
Acquiring historical power data of a photovoltaic power station in a first preset time period;
Calculating the historical power data according to a preset wavelet maximum layer decomposition type to obtain a maximum layer approximate data sequence and a detail data sequence of each layer;
Constructing a corresponding data sequence matrix by taking the maximum layer approximate data sequence and the detail data sequence of each layer as input quantity;
And reconstructing the data sequence matrix of each level according to a wavelet reconstruction algorithm to obtain a corresponding predicted power value.
As one preferable aspect, the collection module includes a photovoltaic inverter, and the controller is further configured to:
And acquiring second-level output power data of the photovoltaic inverter in the preset time period, and taking the second-level output power data as the historical power data.
As one preferable mode, the wavelet maximum layer decomposition formula includes:
Wherein p s is the time sequence length of the generated power of the photovoltaic power station in a preset time period, f s is the data length of the selected wavelet decomposition layer, and maxL is the maximum layer of the selected wavelet decomposition.
As one preferable aspect, the controller is further configured to:
Inputting the data sequence matrix of each level into a convolutional neural network, so that the convolutional neural network generates a corresponding predicted data sequence in a second preset time period according to the data sequence matrix of each level;
And reconstructing the predicted data sequence according to a wavelet reconstruction algorithm to obtain the corresponding predicted power value.
Yet another embodiment of the present invention provides a computer readable storage medium, which includes a stored computer program, where the computer program when run controls a device in which the computer readable storage medium is located to perform a method for predicting power of a photovoltaic power plant as described above.
Compared with the prior art, the method and the device have the advantages that extra meteorological data parameters are not required to be acquired and calculated, the operation cost of the photovoltaic power station is effectively reduced, the historical power data information of the photovoltaic power station is acquired to predict, and the influence of inherent errors such as high-frequency components in similar days is eliminated. The power prediction method of the whole photovoltaic power station utilizes high-speed calculation processing service, combines discrete wavelet decomposition to construct a neural network model to perform feature learning, and realizes the decomposition, calculation and reconstruction of data signals, so that the system power of the photovoltaic power station in a preset period can be predicted, the calculation complexity is reduced, and the accuracy of power prediction can be improved.
Drawings
FIG. 1 is a flow chart of a method of power prediction for a photovoltaic power plant in one embodiment of the present invention;
Fig. 2 is a signal layer schematic diagram of wavelet decomposition in one embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present application, the terms "first," "second," "third," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first", "a second", "a third", etc. may explicitly or implicitly include one or more such feature. In the description of the present application, unless otherwise indicated, the meaning of "a plurality" is two or more.
In the description of the present application, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present application will be understood in specific cases by those of ordinary skill in the art.
In the description of the present application, it should be noted that all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs unless defined otherwise. The terminology used in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application, as the particular meaning of the terms described above in the present application will be understood to those of ordinary skill in the art in the detailed description of the application.
An embodiment of the present invention provides a power prediction method of a photovoltaic power station, specifically, referring to fig. 1, fig. 1 is a schematic flow chart of a power prediction method of a photovoltaic power station in one embodiment, which includes:
S1, acquiring historical power data of a photovoltaic power station in a first preset time period;
S2, calculating the historical power data according to a preset wavelet maximum layer decomposition type to obtain a maximum layer approximate data sequence and a detail data sequence of each layer;
S3, constructing a corresponding data sequence matrix by taking the maximum layer approximate data sequence and the detail data sequence of each layer as input quantity;
S4, reconstructing the data sequence matrix of each level according to a wavelet reconstruction algorithm to obtain a corresponding predicted power value.
It should be noted that the photovoltaic power generation change trend features are obvious on a large time scale, the photovoltaic output fluctuation features are obvious on a small time scale, unlike the mode of predicting photovoltaic power generation output power through meteorological parameters, external irradiation, clear sky model, satellite cloud image, similar day calculation and the like in the prior art, the photovoltaic power generation change trend feature prediction method only obtains historical power data and does not depend on additional parameters, so that the number of related sensor assemblies and the calculated load can be reduced, the prediction interval is shortened, meanwhile, the operation cost of a photovoltaic power station is reduced, more importantly, the photovoltaic power station operation cost is reduced, the original solar irradiation signals are decomposed into a plurality of high-frequency and low-frequency sequences through second-level solar irradiation, modeling is conducted on each signal sequence through a neural network algorithm, modeling learning is conducted on each characteristic, the photovoltaic power station output power prediction based on wavelet decomposition-neural network prediction is constructed, and the influence of the photovoltaic power station output power under the condition that no other meteorological parameters is solved, and the fluctuation output of solar irradiation can be effectively predicted.
The multi-resolution analysis of wavelet transformation is to analyze signals according to information of the signals on different scales, so as to simulate the analysis process of human beings on the signals. A signal of a certain scale refers to its best approximation at a certain resolution. The coarse scale is gradually transitioned to the fine scale by the Mallat algorithm, amplified and a more accurate representation of the given signal is obtained. A simple method for implementing multi-resolution analysis using Discrete Wavelet Transform (DWT) is defined as:
a and b are expressed as two integer variables that together determine the scaling and translation parameters of phi, T is a discrete time index, and T is the length of the signal f (T). According to the idea of multi-resolution analysis, the decomposition process of the signal actually reflects the relation between the scale transformation corresponding to the scale multiplication and the wavelet transformation. In the case of wavelet packets, it reflects the relationship between the subdivision of the wideband signal into smaller band signals. Specifically, referring to fig. 2, fig. 2 shows a schematic diagram of a signal layer of wavelet decomposition in one embodiment, where j is denoted as a j-th layer, V is denoted as a j-th layer approximation component, and w is denoted as a j-th layer detail component.
As one preferable scheme, the second-level output power data of the photovoltaic inverter of the photovoltaic power station in the preset time period is obtained, and the second-level output power data is used as the historical power data. The preset time period is preferably second-level power data in the past 1 hour, the output power of the photovoltaic power station of second-level photovoltaic power in the past 1 hour is decomposed according to the maximum layer of wavelets by using a Daubechies wavelet decomposition algorithm according to a Mallat algorithm, and the maximum layer decomposition calculation method comprises the following steps:
Wherein p s is the time sequence length of the generated power of the photovoltaic power station in a preset time period, f s is the data length of the selected wavelet decomposition layer, and maxL is the maximum layer of the selected wavelet decomposition. Of course, the second-level photovoltaic power data of the past N hours may be used as the preset time period, and N may be selected according to the predicted time interval and the predicted time sequence length.
As one preferable scheme, the step S4 is to reconstruct the data sequence matrix of each level according to a wavelet reconstruction algorithm to obtain a corresponding predicted power value, and specifically includes:
s41, inputting the data sequence matrix of each level into a convolutional neural network, so that the convolutional neural network generates a predicted data sequence in a corresponding second preset time period (the second preset time period corresponds to the first preset time period and is the next time interval of the first preset time period) according to the data sequence matrix of each level;
s42, reconstructing the predicted data sequence according to a wavelet reconstruction algorithm to obtain the corresponding predicted power value.
It should be noted that, after the step of wavelet decomposition is completed, maxL-layer approximate sequence X a,T, maxL-layer detail sequence X dm, maxL-1-layer detail sequence X dm-1, …, first-layer detail sequence X d1 with time tag T are obtained; then, respectively establishing a sequence matrix of each layer of sequence, taking maxL layers of approximate sequences as an example, and establishing an input matrix M= [ X a,T,Xa,T-1,…,Xa,1 ] of a time sequence, and taking X a,T+1 of a T+1 time tag as an output matrix; finally, feature learning is carried out through neural network modeling, a neural network model is built by taking maxL-layer approximate sequences as an example, M is input, X a,T+1 is output, a data set which is shaped like M-X is built according to the past second data accumulated in the preset time period of the power of the photovoltaic system, the neural network model is trained, and modeling training is carried out on detail parameters (V and other W layers) of other layers respectively.
For convenience of explanation, taking second-level power data of an inverter of a photovoltaic power station in a 60 second period as an example, a photovoltaic power second-level matrix is input:
the matrix after wavelet transformation is exemplified by a V j-p layer:
AC＝[ACT0,ACT1,ACT2,ACT3,ACT4]
So after calculation by the convolutional neural network, the calculation process is that
Wherein D is the latitude of V j-p, CNN model is 3 layers of convolution+pooling layers, 4 layers of full-connection layers, dropoutrate is 0.1, adam optimized gradient learning rate is 0.0001, and error loss is defined as absolute error.
The predicted photovoltaic power is reconstructed according to the wavelet transformation inverse process, and the calculation process is as follows:
Therefore, the output data of the photovoltaic power station for the past 1 hour is input, and the output data is subjected to wavelet decomposition to realize prediction calculation to the neural network model, so that the system power of the photovoltaic power station in a preset period can be predicted.
Another embodiment of the present invention provides a power prediction apparatus (not shown) of a photovoltaic power station, including an acquisition module and a controller; the acquisition module is connected with the controller;
The controller is configured to:
Acquiring historical power data of a photovoltaic power station in a first preset time period;
Calculating the historical power data according to a preset wavelet maximum layer decomposition type to obtain a maximum layer approximate data sequence and a detail data sequence of each layer;
Constructing a corresponding data sequence matrix by taking the maximum layer approximate data sequence and the detail data sequence of each layer as input quantity;
And reconstructing the data sequence matrix of each level according to a wavelet reconstruction algorithm to obtain a corresponding predicted power value.
As one preferable aspect, the collection module includes a photovoltaic inverter, and the controller is further configured to:
and acquiring second-level output power data of the photovoltaic inverter of the photovoltaic power station in the preset time period, and taking the second-level output power data as the historical power data.
As one preferable mode, the wavelet maximum layer decomposition formula includes:
Wherein p s is the time sequence length of the generated power of the photovoltaic power station in a preset time period, f s is the data length of the selected wavelet decomposition layer, and maxL is the maximum layer of the selected wavelet decomposition.
As one preferable aspect, the controller is further configured to:
Inputting the data sequence matrix of each level into a convolutional neural network, so that the convolutional neural network generates a corresponding predicted data sequence in a second preset time period according to the data sequence matrix of each level;
And reconstructing the predicted data sequence according to a wavelet reconstruction algorithm to obtain the corresponding predicted power value.
Yet another embodiment of the present invention provides a computer readable storage medium, which includes a stored computer program, where the computer program when run controls a device in which the computer readable storage medium is located to perform a method for predicting power of a photovoltaic power plant as described above.
According to the power prediction method, the power prediction device and the storage medium of the photovoltaic power station, which are provided by the embodiment of the invention, additional meteorological data parameters are not required to be acquired and calculated, so that the operation cost of the photovoltaic power station is effectively reduced, the historical power data information of the photovoltaic power station is acquired to predict, and the influence of inherent errors such as high-frequency components in similar days is eliminated. The power prediction method of the whole photovoltaic power station utilizes high-speed calculation processing service, combines discrete wavelet decomposition to construct a neural network model to perform feature learning, and realizes the decomposition, calculation and reconstruction of data signals, so that the system power of the photovoltaic power station in a preset period can be predicted, the calculation complexity is reduced, and the accuracy of power prediction can be improved.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random-access Memory (Random Access Memory, RAM), or the like.
Claims (5)
1. A method for predicting power of a photovoltaic power plant, comprising:
Acquiring historical power data of a photovoltaic power station in a first preset time period;
Calculating the historical power data according to a preset wavelet maximum layer decomposition type to obtain a maximum layer approximate data sequence and a detail data sequence of each layer;
Constructing a corresponding data sequence matrix by taking the maximum layer approximate data sequence and the detail data sequence of each layer as input quantity;
reconstructing the data sequence matrix of each level according to a wavelet reconstruction algorithm to obtain a corresponding predicted power value;
The wavelet maximum layer decomposition comprises:
Wherein p s is the time sequence length of the generated power of the photovoltaic power station in a preset time period, f s is the data length of the selected wavelet decomposition layer, and maxL is the maximum layer of the selected wavelet decomposition;
The step of reconstructing the data sequence matrix of each level according to a wavelet reconstruction algorithm to obtain a corresponding predicted power value specifically comprises the following steps:
Inputting the data sequence matrix of each level into a convolutional neural network, so that the convolutional neural network generates a corresponding predicted data sequence in a second preset time period according to the data sequence matrix of each level;
And reconstructing the predicted data sequence according to a wavelet reconstruction algorithm to obtain the corresponding predicted power value.
2. The method for predicting power of a photovoltaic power plant according to claim 1, wherein the step of obtaining historical power data of the photovoltaic power plant in the first preset time period specifically comprises:
and acquiring second-level output power data of a photovoltaic inverter of the photovoltaic power station in the preset time period, and taking the second-level output power data as the historical power data.
3. The power prediction device of the photovoltaic power station is characterized by comprising an acquisition module and a controller;
the acquisition module is connected with the controller;
The controller is configured to:
Acquiring historical power data of a photovoltaic power station in a first preset time period;
Calculating the historical power data according to a preset wavelet maximum layer decomposition type to obtain a maximum layer approximate data sequence and a detail data sequence of each layer;
Constructing a corresponding data sequence matrix by taking the maximum layer approximate data sequence and the detail data sequence of each layer as input quantity;
reconstructing the data sequence matrix of each level according to a wavelet reconstruction algorithm to obtain a corresponding predicted power value;
The wavelet maximum layer decomposition comprises:
Wherein p s is the time sequence length of the generated power of the photovoltaic power station in a preset time period, f s is the data length of the selected wavelet decomposition layer, and maxL is the maximum layer of the selected wavelet decomposition;
The controller is further configured to:
Inputting the data sequence matrix of each level into a convolutional neural network, so that the convolutional neural network generates a corresponding predicted data sequence in a second preset time period according to the data sequence matrix of each level;
And reconstructing the predicted data sequence according to a wavelet reconstruction algorithm to obtain the corresponding predicted power value.
4. The power prediction device of a photovoltaic power plant of claim 3, wherein the harvesting module comprises a photovoltaic inverter, the controller further configured to:
And acquiring second-level output power data of the photovoltaic inverter in the preset time period, and taking the second-level output power data as the historical power data.
5. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the power prediction method of a photovoltaic power plant according to any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010775268.8A CN111932007B (en) | 2020-08-04 | 2020-08-04 | Power prediction method and device for photovoltaic power station and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010775268.8A CN111932007B (en) | 2020-08-04 | 2020-08-04 | Power prediction method and device for photovoltaic power station and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111932007A CN111932007A (en) | 2020-11-13 |
| CN111932007B true CN111932007B (en) | 2024-06-18 |
Family
ID=73307883
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010775268.8A Active CN111932007B (en) | 2020-08-04 | 2020-08-04 | Power prediction method and device for photovoltaic power station and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111932007B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734125A (en) * | 2021-01-15 | 2021-04-30 | 国网山西省电力公司晋城供电公司 | Photovoltaic output prediction method and device and electronic equipment |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109840633A (en) * | 2019-01-29 | 2019-06-04 | 合肥工业大学 | Photovoltaic output power predicting method, system and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408529A (en) * | 2014-11-21 | 2015-03-11 | 广东工业大学 | Short-term load predicting method of power grid |
| CN105528517B (en) * | 2015-12-01 | 2019-02-26 | 北京国电通网络技术有限公司 | Based on neural network, wavelet decomposition predicting power of photovoltaic plant method, system |
| CN106909985B (en) * | 2017-01-11 | 2021-02-09 | 沃太能源南通有限公司 | Prediction method of photovoltaic power generation prediction system |
| CN107194496A (en) * | 2017-04-25 | 2017-09-22 | 甘肃省电力公司风电技术中心 | The Forecasting Methodology and prediction meanss of photovoltaic power |
| CN107341569B (en) * | 2017-06-26 | 2020-04-24 | 清华大学 | Photovoltaic power prediction method combining photovoltaic power physical model and data driving |
| CN110348648A (en) * | 2019-08-02 | 2019-10-18 | 国网电子商务有限公司 | A kind of predicting power of photovoltaic plant method and device |
-
2020
- 2020-08-04 CN CN202010775268.8A patent/CN111932007B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109840633A (en) * | 2019-01-29 | 2019-06-04 | 合肥工业大学 | Photovoltaic output power predicting method, system and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111932007A (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Accurate solar PV power prediction interval method based on frequency-domain decomposition and LSTM model | |
| De Giorgi et al. | Assessment of the benefits of numerical weather predictions in wind power forecasting based on statistical methods | |
| CN111950793A (en) | Comprehensive energy system load prediction method considering multivariate load coupling characteristics | |
| Rodríguez et al. | Forecasting intra-hour solar photovoltaic energy by assembling wavelet based time-frequency analysis with deep learning neural networks | |
| Liu et al. | Heating load forecasting for combined heat and power plants via strand-based LSTM | |
| Perpiñán et al. | Analysis and synthesis of the variability of irradiance and PV power time series with the wavelet transform | |
| CN112668611B (en) | Kmeans and CEEMD-PE-LSTM-based short-term photovoltaic power generation power prediction method | |
| CN105760961A (en) | Photovoltaic output power prediction method and system | |
| CN114201924B (en) | Solar irradiance prediction method and system based on transfer learning | |
| Zhang et al. | Photovoltaic power prediction based on hybrid modeling of neural network and stochastic differential equation | |
| CN116128170B (en) | Photovoltaic power station power ultra-short-term prediction method and device and related equipment | |
| Mathew et al. | EMD-Att-LSTM: a data-driven strategy combined with deep learning for short-term load forecasting | |
| El Bakali et al. | Data-Based Solar Radiation Forecasting with Pre-Processing Using Variational Mode Decomposition | |
| CN111932007B (en) | Power prediction method and device for photovoltaic power station and storage medium | |
| CN116561567A (en) | Short-term photovoltaic power prediction model based on variation modal decomposition, construction method and application method | |
| Tuyen et al. | A combination of novel hybrid deep learning model and quantile regression for short‐term deterministic and probabilistic PV maximum power forecasting | |
| CN113361782B (en) | Photovoltaic power generation power short-term rolling prediction method based on improved MKPLS | |
| CN116523145A (en) | Photovoltaic power ultra-short-term prediction method and device, computer equipment and storage medium | |
| CN116826727A (en) | Ultra-short-term wind power prediction method and prediction system based on time sequence representation and multistage attention | |
| CN116402194A (en) | Multi-time scale load prediction method based on hybrid neural network | |
| CN116805782A (en) | New energy output scene generation method and device and computer equipment | |
| CN115936238A (en) | Method, system, equipment and medium for predicting middle and long term output of global wind power | |
| CN113779861B (en) | Photovoltaic Power Prediction Method and Terminal Equipment | |
| CN115630731A (en) | Image-based wind power short-term prediction method and system with self-attention mechanism and gating | |
| CN112257938B (en) | Photovoltaic power generation power prediction method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |