CN117117849A - Photovoltaic power prediction method, device, equipment and storage medium - Google Patents
Photovoltaic power prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117117849A CN117117849A CN202311081650.9A CN202311081650A CN117117849A CN 117117849 A CN117117849 A CN 117117849A CN 202311081650 A CN202311081650 A CN 202311081650A CN 117117849 A CN117117849 A CN 117117849A
- Authority
- CN
- China
- Prior art keywords
- data
- historical
- photovoltaic
- power
- irradiation
- 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 45
- 238000003062 neural network model Methods 0.000 claims abstract description 68
- 238000012549 training Methods 0.000 claims abstract description 35
- 238000012937 correction Methods 0.000 claims abstract description 13
- 230000002159 abnormal effect Effects 0.000 claims description 20
- 238000013523 data management Methods 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 17
- 239000013598 vector Substances 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 9
- 230000003213 activating effect Effects 0.000 claims description 3
- 238000010248 power generation Methods 0.000 claims description 2
- 238000009472 formulation Methods 0.000 claims 1
- 239000000203 mixture Substances 0.000 claims 1
- 238000004590 computer program Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 230000007613 environmental effect Effects 0.000 description 6
- 230000000717 retained effect Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000033228 biological regulation Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000005067 remediation Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/381—Dispersed generators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
-
- 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)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Power Engineering (AREA)
- Development Economics (AREA)
- Medical Informatics (AREA)
- Game Theory and Decision Science (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention provides a photovoltaic power prediction method, a photovoltaic power prediction device, photovoltaic power prediction equipment and a storage medium. Obtaining second historical actual photovoltaic power and second historical irradiation data according to the first historical actual photovoltaic power and the first historical irradiation data; respectively retaining second historical temperature data, second historical cloud amount data and second historical humidity data corresponding to the second historical actual photovoltaic power; determining an initial historical photovoltaic predicted power according to the second historical irradiation data and the second historical temperature data; training and setting a neural network model by using all the reserved data and the initial historical photovoltaic predicted power; acquiring irradiation prediction data and temperature prediction data, and determining initial photovoltaic prediction power; and inputting the initial photovoltaic predicted power into the trained set neural network model for error correction to obtain the target photovoltaic predicted power. The photovoltaic power prediction method and the device can improve accuracy of photovoltaic power prediction.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of photovoltaic power generation, in particular to a photovoltaic power prediction method, a device, equipment and a storage medium.
Background
The accuracy of the distributed photovoltaic power prediction has important significance for safe and stable operation of the power system. The current data driving prediction method based on photovoltaic historical data and meteorological data is widely applied, and the quality of the data is very important for a data driving model. Current photovoltaic prediction methods often employ some complex large models, and the anomaly data processing is performed only for one dimension of the photovoltaic power data. This can lead to difficult model training, resulting in poor accuracy of the photovoltaic power prediction model.
Disclosure of Invention
The embodiment of the disclosure provides a photovoltaic power prediction method, a device, equipment and a storage medium, which can improve the accuracy of photovoltaic power prediction.
In a first aspect, an embodiment of the present disclosure provides a photovoltaic power prediction method, which obtains a first historical actual photovoltaic power, a first historical irradiation data, a first historical temperature data, a first historical cloud cover data, and a first historical humidity data; obtaining second historical actual photovoltaic power and second historical irradiation data according to the first historical actual photovoltaic power and the first historical irradiation data; respectively retaining second historical temperature data, second historical cloud amount data and second historical humidity data corresponding to the second historical actual photovoltaic power; determining an initial historical photovoltaic predicted power from the second historical irradiance data and the second historical temperature data; training a set neural network model according to the second historical irradiation data, the second historical temperature data, the second historical cloud amount data, the second historical humidity data, the initial historical photovoltaic predicted power and the second historical actual photovoltaic power to obtain a trained set neural network model; acquiring irradiation prediction data and temperature prediction data; determining an initial photovoltaic predicted power from the irradiance prediction data and the temperature prediction data; and inputting the initial photovoltaic predicted power into the trained set neural network model to correct errors, so as to obtain the target photovoltaic predicted power.
In a second aspect, an embodiment of the present disclosure further provides a photovoltaic power prediction apparatus, where the history data obtaining module is configured to obtain a first historical actual photovoltaic power, first historical irradiation data, first historical temperature data, first historical cloud amount data, and first historical humidity data; the data management module is used for obtaining second historical actual photovoltaic power and second historical irradiation data according to the first historical actual photovoltaic power and the first historical irradiation data; the reservation module is used for respectively reserving second historical temperature data, second historical cloud amount data and second historical humidity data corresponding to the second historical actual photovoltaic power; the initial historical photovoltaic predicted power determining module is used for determining initial historical photovoltaic predicted power according to the second historical irradiation data and the second historical temperature data; the training module is used for training a set neural network model according to the second historical irradiation data, the second historical temperature data, the second historical cloud cover data, the second historical humidity data, the initial historical photovoltaic predicted power and the second historical actual photovoltaic power to obtain a trained set neural network model; the predicted data acquisition module is used for acquiring irradiation predicted data and temperature predicted data; the initial photovoltaic predicted power determining module is used for determining initial photovoltaic predicted power according to the irradiation predicted data and the temperature predicted data; and the target photovoltaic predicted power obtaining module is used for inputting the initial photovoltaic predicted power into the trained set neural network model for error correction to obtain the target photovoltaic predicted power.
In a third aspect, embodiments of the present disclosure further provide an electronic device, including:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the photovoltaic power prediction methods as described in embodiments of the present disclosure.
In a fourth aspect, the disclosed embodiments also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are for performing the photovoltaic power prediction method as described in the disclosed embodiments.
According to the technical scheme, first historical actual photovoltaic power, first historical irradiation data, first historical temperature data, first historical cloud cover data and first historical humidity data are obtained; obtaining second historical actual photovoltaic power and second historical irradiation data according to the first historical actual photovoltaic power and the first historical irradiation data; respectively retaining second historical temperature data, second historical cloud amount data and second historical humidity data corresponding to the second historical actual photovoltaic power; determining an initial historical photovoltaic predicted power from the second historical irradiance data and the second historical temperature data; training a set neural network model according to the second historical irradiation data, the second historical temperature data, the second historical cloud amount data, the second historical humidity data, the initial historical photovoltaic predicted power and the second historical actual photovoltaic power to obtain a trained set neural network model; acquiring irradiation prediction data and temperature prediction data; determining an initial photovoltaic predicted power from the irradiance prediction data and the temperature prediction data; and inputting the initial photovoltaic predicted power into the trained set neural network model to correct errors, so as to obtain the target photovoltaic predicted power. According to the embodiment of the disclosure, the data management module is used for removing abnormal data, so that the accuracy of determining the initial historical photovoltaic predicted power can be improved; and the initial photovoltaic predicted power is corrected by setting a neural network model, so that the accuracy of photovoltaic power prediction can be improved.
Drawings
The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.
Fig. 1 is a schematic flow chart of a photovoltaic power prediction method according to an embodiment of the disclosure;
FIG. 2 is a schematic effect diagram of two-dimensional spatial data of undeleted abnormal data provided by an embodiment of the present invention;
FIG. 3 is a schematic effect diagram of two-dimensional spatial data for deleting abnormal data according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a photovoltaic power prediction apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below.
It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.
It will be appreciated that the data (including but not limited to the data itself, the acquisition or use of the data) involved in the present technical solution should comply with the corresponding legal regulations and the requirements of the relevant regulations.
Fig. 1 is a schematic flow chart of a photovoltaic power prediction method provided by an embodiment of the present disclosure, where the embodiment of the present disclosure is applicable to a case of predicting photovoltaic power, the method may be performed by a photovoltaic power prediction apparatus, and the apparatus may be implemented in a form of software and/or hardware, and optionally, may be implemented by an electronic device, where the electronic device may be a mobile terminal, a PC side, a server, or the like. As shown in fig. 1, the method includes:
s110, acquiring first historical actual photovoltaic power, first historical irradiation data, first historical temperature data, first historical cloud cover data and first historical humidity data.
In this embodiment, the first historical actual photovoltaic power, the first historical irradiation data, the first historical temperature data, the first historical cloud cover data, and the first historical humidity data may all be obtained by a sensor having a data collection function or by a tool having another data collection function. The first historical actual photovoltaic power, the first historical irradiation data, the first historical temperature data, the first historical cloud amount data and the first historical humidity data are a group of environmental data, and a corresponding relation exists among the group of environmental data.
S120, obtaining second historical actual photovoltaic power and second historical irradiation data according to the first historical actual photovoltaic power and the first historical irradiation data.
In this embodiment, the data management module may convert the first historical actual photovoltaic power and the first historical irradiation data into two-dimensional spatial data, and remove the abnormal data in the two-dimensional space. After the abnormal data is removed, the reserved first historical actual photovoltaic power is used as a second historical actual photovoltaic power; the first historical irradiation data is retained as second historical irradiation data.
Optionally, obtaining the second historical actual photovoltaic power and the second historical irradiation data according to the first historical actual photovoltaic power and the first historical irradiation data includes: converting the first historical actual photovoltaic power and the first historical irradiation data into two-dimensional space data; removing abnormal data from the two-dimensional space data to obtain normal two-dimensional space data; and converting the normal two-dimensional space data into one-dimensional second historical actual photovoltaic power and one-dimensional second historical irradiation data.
In this embodiment, two features of the first historical actual photovoltaic power and the first historical irradiation data may be converted into two-dimensional spatial data by setting a two-dimensional conversion function, where a two-dimensional spatial data conversion formula is as follows:
s＝con[p′,R′]
Wherein p 'is the first historical actual photovoltaic power, R' is the first historical irradiation data, s is the two-dimensional space data, con [ ] represents the set transfer function, the single-dimensional p 'and R' data can be constructed as the two-dimensional space data s with the horizontal axis of R 'and the vertical axis of p', as shown in fig. 2 or 3.
In this embodiment, abnormal data may be removed from the two-dimensional space data, so as to obtain normal two-dimensional space data. Specifically, based on the two-dimensional spatial data s, clustering grouping is performed on all sample points by using a clustering algorithm (Density-Based Spatial Clustering ofApplications withNoise, DBSCAN). Specifically, by calculating each sample s i Determining a minimum sample number MinPoints of points within the radius range of the point setting R, and determining a sample point s i Whether or not they belong to a cluster, sample points s not belonging to any cluster i Belonging to abnormal data and markedDelete all +.>The normal two-dimensional space data formed is recorded as +.>The method meets the following conditions:
wherein Q represents a cluster formed by a DBSCAN algorithm.
It should be noted that, if the minimum sample number MinPoints of the points in the set R radius range of the sample point meets the set sample number requirement, the sample point belongs to the corresponding cluster, and if the minimum sample number MinPoints of the points in the set R radius range of the sample point does not meet the set sample number requirement, the sample point does not belong to the corresponding cluster. If a sample point does not belong to any cluster, the sample point belongs to outlier data. And deleting the abnormal data from the two-dimensional space data to obtain normal two-dimensional space data. As shown in fig. 2, fig. 2 is a schematic effect diagram of two-dimensional spatial data of undeleted abnormal data provided in an embodiment of the present invention. Fig. 3 is a schematic effect diagram of two-dimensional spatial data for deleting abnormal data according to an embodiment of the present invention. The abscissa of fig. 2 is the first historical irradiation data, and the ordinate of fig. 2 is the first historical actual photovoltaic power. The abscissa of fig. 3 is the second historical irradiation data, and the ordinate of fig. 3 is the second historical actual photovoltaic power.
According to the embodiment, the accuracy of determining the initial historical photovoltaic predicted power can be improved by converting the first historical actual photovoltaic power and the first historical irradiation data into two-dimensional space data and removing abnormal data under the two-dimensional space data.
And S130, respectively retaining second historical temperature data, second historical cloud amount data and second historical humidity data corresponding to the second historical actual photovoltaic power.
In this embodiment, second historical temperature data corresponding to the second historical actual photovoltaic power may be retained; the second historical cloud amount data corresponding to the second historical actual photovoltaic power is reserved; and retaining second historical humidity data corresponding to the second historical actual photovoltaic power.
In this embodiment, second historical temperature data corresponding to the second historical irradiation data may also be retained; second historical cloud cover data corresponding to the second historical irradiation data are reserved; second historical humidity data corresponding to the second historical irradiance data is retained.
In this embodiment, the retained second historical actual photovoltaic power, second historical irradiance data, second historical temperature data, second historical cloud cover data, and second historical humidity data may all be considered one-dimensional data. According to the embodiment, the first historical actual photovoltaic power and the first historical irradiation data are converted into two-dimensional space data, abnormal data are removed under the two-dimensional space data, and normal data are reserved, so that the accuracy of the target photovoltaic predicted power can be improved.
And S140, determining initial historical photovoltaic predicted power according to the second historical irradiation data and the second historical temperature data.
The initial historical photovoltaic predicted power may be photovoltaic power generated using a mathematical physical model. In this embodiment, the second historical irradiation data and the second historical temperature data may be input into a mathematical physical model that outputs the initial historical photovoltaic predicted power.
And S150, training a set neural network model according to the second historical irradiation data, the second historical temperature data, the second historical cloud cover data, the second historical humidity data, the initial historical photovoltaic predicted power and the second historical actual photovoltaic power to obtain a trained set neural network model.
The set neural network model may be a neural network model formed by any deep learning algorithm.
Optionally, training the set neural network model according to the second historical irradiation data, the second historical temperature data, the second historical cloud cover data, the second historical humidity data, the initial historical photovoltaic predicted power and the second historical actual photovoltaic power to obtain a trained set neural network model, including: the second historical irradiation data, the second historical temperature data, the second historical cloud cover data, the second historical humidity data and the initial historical photovoltaic predicted power are used as training data; inputting training data into a set neural network model to obtain training photovoltaic predicted power; determining an error according to the training photovoltaic predicted power and the second historical actual photovoltaic power; and setting a neural network model according to the error training.
Specifically, the training mode of the set neural network model is as follows: inputting the second historical irradiation data, the second historical temperature data, the second historical cloud amount data, the second historical humidity data and the initial historical photovoltaic predicted power into a set neural network model to obtain training photovoltaic predicted power; obtaining an error between the training photovoltaic predicted power and the second historical actual photovoltaic power based on the loss function; and updating the weight vector and the threshold vector according to the error to train the set neural network model, and stopping training the set neural network model if the error or the iteration number meets the training stopping condition to obtain the trained set neural network model. The loss function may be any type of loss function, such as a mean square error, among others. The training stop condition may be that the error is less than or equal to a set error value, the number of iterations is greater than or equal to a set number of iterations, etc. In this embodiment, a random gradient descent method may be used to optimally set parameters in the neural network model.
S160, radiation prediction data and temperature prediction data are obtained.
The irradiation prediction data may be understood as irradiance prediction data of a place where the photovoltaic module is located at a future time (next time) obtained based on the third party prediction data. The third-party prediction data may be prediction data obtained from weather forecast, and the temperature prediction data may be understood as environmental temperature prediction data of a place where the photovoltaic module is located at a future time obtained based on the third-party prediction data.
S170, determining initial photovoltaic predicted power according to irradiation predicted data and temperature predicted data.
The initial photovoltaic predicted power may be photovoltaic generated power obtained by using a mathematical physical model. In this embodiment, the irradiance prediction data and the temperature prediction data may be input into a mathematical physical model that outputs the initial photovoltaic predicted power. The mathematical physical model may be a photovoltaic power physical model. The irradiation prediction data and the temperature prediction data can be environmental factors affecting the target photovoltaic predicted power. The method for determining the initial photovoltaic predicted power is the same as the method for determining the initial historical photovoltaic predicted power, and the initial photovoltaic predicted power and the initial historical photovoltaic predicted power can be obtained through a mathematical physical model.
Optionally, determining the initial photovoltaic predicted power according to the irradiation prediction data and the temperature prediction data includes: obtaining photovoltaic standard power, irradiation standard data, temperature standard data and temperature coefficients; determining irradiation influence factors according to irradiation prediction data and irradiation standard data; determining a temperature influence factor according to the temperature standard data, the temperature coefficient and the temperature prediction data; and determining initial photovoltaic predicted power according to the photovoltaic standard power, the irradiation influence factor and the temperature influence factor.
In this embodiment, the irradiation prediction data and the irradiation standard data are divided to obtain an irradiation influence factor, the result obtained by subtracting the temperature prediction data from the temperature standard data is multiplied by a temperature coefficient, and the multiplied result is added with 1 to obtain the temperature influence factor. And multiplying the photovoltaic standard power, the irradiation influence factor and the temperature influence factor in sequence to obtain the initial photovoltaic predicted power. Wherein the temperature coefficient is a photovoltaic power temperature coefficient.
Illustratively, the initial photovoltaic predicted power or mathematical physical model formula is as follows:
wherein, the physical quantity containing the subscript STC is the operation parameter under the standard test condition; p (P) STC Is the photovoltaic standard power under standard test conditions, G STC Can take 1000W/m as irradiation standard data under standard test condition 2 ；T STC The temperature standard data can be 25 ℃; g is irradiation prediction data; k is a temperature coefficient; and t is the surface working temperature of the photovoltaic module battery pack, namely temperature prediction data.
In this embodiment, P in the mathematical physical model may be fitted by least squares STC Parameters and k parameters.
S180, inputting the initial photovoltaic predicted power into the trained set neural network model for error correction, and obtaining the target photovoltaic predicted power.
The initial photovoltaic predicted power may be understood as a photovoltaic power having a prediction error compared to an actual photovoltaic predicted power, and the target photovoltaic predicted power may be a photovoltaic predicted power obtained by correcting the initial photovoltaic predicted power.
Optionally, inputting the initial photovoltaic predicted power into the trained set neural network model for error correction to obtain the target photovoltaic predicted power, including: acquiring cloud cover prediction data, humidity prediction data and temperature prediction data; and inputting the irradiation prediction data, the cloud amount prediction data, the humidity prediction data, the temperature prediction data and the initial photovoltaic prediction power into a trained set neural network model for error correction to obtain the target photovoltaic prediction power.
In this embodiment, environmental factors affecting the target photovoltaic predicted power, such as cloud amount predicted data, humidity predicted data and temperature predicted data, of the place where the photovoltaic module is located at a future time may be obtained based on the third party predicted data, the irradiation predicted data, the cloud amount predicted data, the humidity predicted data, the temperature predicted data and the initial photovoltaic predicted power are input into the trained set neural network model, and error correction is performed on the initial photovoltaic predicted power through the set neural network model to obtain the target photovoltaic predicted power.
Optionally, the irradiation prediction data, the cloud cover prediction data, the humidity prediction data, the temperature prediction data and the initial photovoltaic prediction power are input into a trained set neural network model to perform error correction, so as to obtain a target photovoltaic prediction power, which comprises the following steps: inputting irradiation prediction data, cloud amount prediction data, humidity prediction data, temperature prediction data and initial photovoltaic prediction power into a hidden layer to obtain hidden output data; and inputting the hidden output data into an output layer to obtain the target photovoltaic predicted power.
The neural network model is set to comprise a hidden layer and an output layer. The hidden layer and the output layer each include a corresponding activation function and weight vector.
The set neural network model formula can be expressed as:
x＝[P,r,t,c,h]
u＝f 1 (w 1 x+b 1 )
O＝f 2 (w 2 u+b 2 )
wherein P, r, t, c and h represent initial photovoltaic predicted power, irradiation predicted data, temperature predicted data, cloud cover predicted data, and humidity predicted data, respectively, f 1 And f 2 Activating functions of the hidden layer and the output layer respectively; x is an input vector for setting a neural network model, w 1 And w 2 The weight vectors of the hidden layer and the output layer, respectively. b 1 、b 2 Threshold vectors for the hidden layer and the output layer, respectively. u represents the output vector of the hidden layer, i.e. the hidden output data, and O represents the target photovoltaic predicted power.
According to the technical scheme, first historical actual photovoltaic power, first historical irradiation data, first historical temperature data, first historical cloud cover data and first historical humidity data are obtained; obtaining second historical actual photovoltaic power and second historical irradiation data according to the first historical actual photovoltaic power and the first historical irradiation data; respectively retaining second historical temperature data, second historical cloud amount data and second historical humidity data corresponding to the second historical actual photovoltaic power; determining an initial historical photovoltaic predicted power from the second historical irradiance data and the second historical temperature data; training a set neural network model according to the second historical irradiation data, the second historical temperature data, the second historical cloud amount data, the second historical humidity data, the initial historical photovoltaic predicted power and the second historical actual photovoltaic power to obtain a trained set neural network model; acquiring irradiation prediction data and temperature prediction data; determining an initial photovoltaic predicted power from the irradiance prediction data and the temperature prediction data; and inputting the initial photovoltaic predicted power into the trained set neural network model to correct errors, so as to obtain the target photovoltaic predicted power. According to the embodiment of the disclosure, the data management module is used for removing abnormal data, so that the accuracy of determining the initial historical photovoltaic predicted power can be improved; and the initial photovoltaic predicted power is corrected by setting a neural network model, so that the accuracy of photovoltaic power prediction can be improved.
It should be noted that the technical scheme provided by the invention can be divided into a data management module and a prediction module. The technical scheme provided by the invention is a photovoltaic power prediction integrated model formed by a data management module and a prediction module. The data management module can be used for converting photovoltaic power data and irradiation data into two-dimensional space data and carrying out data management on the two-dimensional space data so as to remove abnormal data. It should be noted that, in the actual application stage and/or the training stage of the model, the data management module may be used to manage the data first, and then the prediction module may be executed. The prediction module may be a data-driven based prediction module that may include a mathematical physical model and a set neural network model. The output of the mathematical physical model is the initial photovoltaic predicted power, and the output of the neural network model is set as the target photovoltaic predicted power.
Compared with the prior art, the technical scheme provided by the embodiment only adopts a plurality of complicated large models, and the abnormal data processing is only carried out aiming at one dimension of the photovoltaic power data. This can lead to difficult model training and abnormal data can lead to difficult model learning rules for photovoltaic power effectively, resulting in poor accuracy of photovoltaic power prediction models. Aiming at the problems of poor prediction precision, complex model and the like in a data-driven photovoltaic power prediction model, the invention provides the photovoltaic power prediction integrated model with a data management function according to the characteristics of photovoltaic power randomness, strong weather correlation and the like, so that the prediction precision of target photovoltaic prediction power can be improved, the weight of the model is improved, and the safe and stable operation of a power system is ensured.
The invention establishes a photovoltaic power prediction integrated model with a data management function, namely a photovoltaic power prediction method by adopting a multidimensional data management module and a data-driven prediction module, can effectively improve the quality of data, so that the data-driven prediction model efficiently learns the mapping relation between the photovoltaic power and the environmental factors, improves the accuracy of the photovoltaic power prediction, reduces the operation cost and ensures the safe and stable operation of a power system.
Fig. 4 is a schematic structural diagram of a photovoltaic power prediction apparatus according to an embodiment of the present disclosure. The device comprises: a historical data acquisition module 410, a data remediation module 420, a retention module 430, an initial historical photovoltaic predicted power determination module 440, a training module 450, a predicted data acquisition module 460, an initial photovoltaic predicted power determination module 470, and a target photovoltaic predicted power acquisition module 480.
A historical data acquisition module 410, configured to acquire a first historical actual photovoltaic power, a first historical irradiation data, a first historical temperature data, a first historical cloud cover data, and a first historical humidity data;
the data management module 420 obtains a second historical actual photovoltaic power and second historical irradiation data according to the first historical actual photovoltaic power and the first historical irradiation data;
A retaining module 430, configured to retain second historical temperature data, second historical cloud cover data, and second historical humidity data corresponding to the second historical actual photovoltaic power, respectively;
an initial historical photovoltaic predicted power determination module 440 for determining an initial historical photovoltaic predicted power based on the second historical irradiance data and the second historical temperature data;
the training module 450 is configured to train a set neural network model according to the second historical irradiation data, the second historical temperature data, the second historical cloud cover data, the second historical humidity data, the initial historical photovoltaic predicted power and the second historical actual photovoltaic power, and obtain a trained set neural network model;
a predicted data acquisition module 460 for acquiring irradiation predicted data and temperature predicted data;
an initial photovoltaic predicted power determination module 470 for determining an initial photovoltaic predicted power from the irradiance prediction data and the temperature prediction data;
and the target photovoltaic predicted power obtaining module 480 is configured to input the initial photovoltaic predicted power into the trained set neural network model for error correction, so as to obtain the target photovoltaic predicted power.
According to the technical scheme, a historical data acquisition module is used for acquiring first historical actual photovoltaic power, first historical irradiation data, first historical temperature data, first historical cloud amount data and first historical humidity data; obtaining second historical actual photovoltaic power and second historical irradiation data according to the first historical actual photovoltaic power and the first historical irradiation data through a data management module; respectively reserving second historical temperature data, second historical cloud amount data and second historical humidity data corresponding to the second historical actual photovoltaic power through a reservation module; determining initial historical photovoltaic predicted power according to the second historical irradiation data and the second historical temperature data by an initial historical photovoltaic predicted power determination module; training a set neural network model through a training module according to the second historical irradiation data, the second historical temperature data, the second historical cloud cover data, the second historical humidity data, the initial historical photovoltaic predicted power and the second historical actual photovoltaic power to obtain a trained set neural network model; acquiring irradiation prediction data and temperature prediction data through a prediction data acquisition module; determining an initial photovoltaic predicted power according to the irradiation predicted data and the temperature predicted data by an initial photovoltaic predicted power determining module; and inputting the initial photovoltaic predicted power into the trained set neural network model through a target photovoltaic predicted power obtaining module to carry out error correction, so as to obtain the target photovoltaic predicted power. According to the embodiment of the disclosure, the data management module is used for removing abnormal data, so that the accuracy of determining the initial historical photovoltaic predicted power can be improved; and the initial photovoltaic predicted power is corrected by setting a neural network model, so that the accuracy of photovoltaic power prediction can be improved.
Optionally, the initial photovoltaic predicted power determination module is specifically configured to: obtaining photovoltaic standard power, irradiation standard data, temperature standard data and temperature coefficients; determining an irradiation influence factor according to the irradiation prediction data and the irradiation standard data; determining a temperature influence factor according to the temperature standard data, the temperature coefficient and the temperature prediction data; and determining initial photovoltaic predicted power according to the photovoltaic standard power, the irradiation influence factor and the temperature influence factor.
Optionally, wherein the formula of the initial photovoltaic predicted power is expressed as:
wherein P is the initial photovoltaic predicted power, and the physical quantity containing the subscript STC is the operation parameter under the standard test condition; p (P) STC Is the photovoltaic standard power under standard test conditions, G STC Irradiation standard data under standard test conditions; t (T) STC Is temperature standard data; g is the irradiation prediction data; k is the temperature coefficient; t is temperature prediction data.
Optionally, the target photovoltaic predicted power obtaining module is specifically configured to: acquiring cloud cover prediction data, humidity prediction data and temperature prediction data; and inputting the irradiation prediction data, the cloud amount prediction data, the humidity prediction data, the temperature prediction data and the initial photovoltaic prediction power into a set neural network model to obtain target photovoltaic prediction power.
Optionally, the set neural network model includes a hidden layer and an output layer; optionally, the target photovoltaic predicted power obtaining module is further configured to: inputting the irradiation prediction data, the cloud amount prediction data, the humidity prediction data, the temperature prediction data and the initial photovoltaic prediction power into a hidden layer to obtain hidden output data; and inputting the hidden output data into an output layer to obtain the target photovoltaic predicted power.
Optionally, the formula for setting the neural network model is expressed as:
x＝[P,r,t,c,h]，
u＝f 1 (w 1 x+b 1 )，
O＝f 2 (w 2 u+b 2 )，
wherein P, r, t, c and h represent the initial photovoltaic predicted power, the irradiance predicted data, the temperature predicted data, the cloud cover predicted data, and the humidity predicted data, respectively, f 1 And f 2 Activating functions of the hidden layer and the output layer respectively; x is the input vector of the set neural network model, w 1 And w 2 And the weight vectors of the hidden layer and the output layer are respectively. b 1 、b 2 Threshold vectors for the hidden layer and the output layer, respectively. u represents the output vector of the hidden layer, and O represents the target photovoltaic predicted power.
Optionally, the data management module is specifically configured to: converting the first historical actual photovoltaic power and the first historical irradiation data into two-dimensional space data; removing abnormal data from the two-dimensional space data to obtain normal two-dimensional space data; and converting the normal two-dimensional space data into one-dimensional second historical actual photovoltaic power and one-dimensional second historical irradiation data.
The photovoltaic power prediction device provided by the embodiment of the disclosure can execute the photovoltaic power prediction method provided by any embodiment of the disclosure, and has the corresponding functional modules and beneficial effects of the execution method.
It should be noted that each unit and module included in the above apparatus are only divided according to the functional logic, but not limited to the above division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for convenience of distinguishing from each other, and are not used to limit the protection scope of the embodiments of the present disclosure.
Fig. 5 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as photovoltaic power prediction methods.
In some embodiments, the photovoltaic power prediction method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the photovoltaic power prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the photovoltaic power prediction method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems on chip (socs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (12)
1. A method of photovoltaic power prediction, comprising:
acquiring first historical actual photovoltaic power, first historical irradiation data, first historical temperature data, first historical cloud cover data and first historical humidity data;
obtaining second historical actual photovoltaic power and second historical irradiation data according to the first historical actual photovoltaic power and the first historical irradiation data;
respectively retaining second historical temperature data, second historical cloud amount data and second historical humidity data corresponding to the second historical actual photovoltaic power;
Determining an initial historical photovoltaic predicted power from the second historical irradiance data and the second historical temperature data;
training a set neural network model according to the second historical irradiation data, the second historical temperature data, the second historical cloud amount data, the second historical humidity data, the initial historical photovoltaic predicted power and the second historical actual photovoltaic power to obtain a trained set neural network model;
acquiring irradiation prediction data and temperature prediction data; determining an initial photovoltaic predicted power from the irradiance prediction data and the temperature prediction data;
and inputting the initial photovoltaic predicted power into the trained set neural network model to correct errors, so as to obtain the target photovoltaic predicted power.
2. The method of claim 1, wherein determining an initial photovoltaic predicted power from the irradiance prediction data and the temperature prediction data comprises:
obtaining photovoltaic standard power, irradiation standard data, temperature standard data and temperature coefficients;
determining an irradiation influence factor according to the irradiation prediction data and the irradiation standard data;
determining a temperature influence factor according to the temperature standard data, the temperature coefficient and the temperature prediction data;
And determining initial photovoltaic predicted power according to the photovoltaic standard power, the irradiation influence factor and the temperature influence factor.
3. The method of claim 2, wherein the equation for the initial photovoltaic predicted power is expressed as:
wherein P is the initial photovoltaic predicted power, and the physical quantity containing the subscript STC is the operation parameter under the standard test condition; p (P) STC Is the photovoltaic standard power under standard test conditions, G STC Irradiation standard data under standard test conditions; t (T) STC Is temperature standard data; g is the irradiation prediction data; k is the temperature coefficient; t is temperature prediction data.
4. The method of claim 1, wherein inputting the initial photovoltaic predicted power into the trained set neural network model for error correction to obtain a target photovoltaic predicted power comprises:
acquiring cloud cover prediction data, humidity prediction data and temperature prediction data;
and inputting the irradiation prediction data, the cloud amount prediction data, the humidity prediction data, the temperature prediction data and the initial photovoltaic prediction power into the trained set neural network model for error correction to obtain target photovoltaic prediction power.
5. The method of claim 4, wherein the set neural network model comprises a hidden layer and an output layer; inputting the irradiation prediction data, the cloud amount prediction data, the humidity prediction data, the temperature prediction data and the initial photovoltaic prediction power into the trained set neural network model for error correction to obtain target photovoltaic prediction power, wherein the method comprises the following steps of:
inputting the irradiation prediction data, the cloud amount prediction data, the humidity prediction data, the temperature prediction data and the initial photovoltaic prediction power into a hidden layer to obtain hidden output data;
and inputting the hidden output data into an output layer to obtain the target photovoltaic predicted power.
6. The method of claim 5, wherein the formulation of the set neural network model is expressed as:
x＝[P,r,t,c,h]，
u＝f 1 (w 1 x+b 1 )，
O＝f 2 (w 2 u+b 2 )，
wherein P, r, t, c and h represent the initial photovoltaic predicted power, the irradiance predicted data, the temperature predicted data, the cloud cover predicted data, and the humidity predicted data, respectively, f 1 And f 2 Activating functions of the hidden layer and the output layer respectively; x is the input vector of the set neural network model, w 1 And w 2 And the weight vectors of the hidden layer and the output layer are respectively. b 1 、b 2 Threshold vectors for the hidden layer and the output layer, respectively. u represents the output vector of the hidden layer, and O represents the target photovoltaic predicted power.
7. The method of claim 1, wherein obtaining second historical actual photovoltaic power and second historical irradiance data from the first historical actual photovoltaic power and first historical irradiance data, further comprises:
converting the first historical actual photovoltaic power and the first historical irradiation data into two-dimensional space data;
removing abnormal data from the two-dimensional space data to obtain normal two-dimensional space data;
and converting the normal two-dimensional space data into one-dimensional second historical actual photovoltaic power and one-dimensional second historical irradiation data.
8. The method of claim 1, wherein training a set neural network model from the second historical irradiance data, the second historical temperature data, the second historical cloud cover data, the second historical humidity data, the initial historical photovoltaic predicted power, and the second historical actual photovoltaic power, obtaining a trained set neural network model, comprises:
Taking the second historical irradiation data, the second historical temperature data, the second historical cloud cover data, the second historical humidity data and the initial historical photovoltaic predicted power as training data;
inputting the training data into the set neural network model to obtain training photovoltaic predicted power;
determining an error from the training photovoltaic predicted power and the second historical actual photovoltaic power;
and training the set neural network model according to the error.
9. A photovoltaic power generation apparatus, comprising:
the historical data acquisition module is used for acquiring first historical actual photovoltaic power, first historical irradiation data, first historical temperature data, first historical cloud cover data and first historical humidity data;
the data management module is used for obtaining second historical actual photovoltaic power and second historical irradiation data according to the first historical actual photovoltaic power and the first historical irradiation data;
the reservation module is used for respectively reserving second historical temperature data, second historical cloud amount data and second historical humidity data corresponding to the second historical actual photovoltaic power;
the initial historical photovoltaic predicted power determining module is used for determining initial historical photovoltaic predicted power according to the second historical irradiation data and the second historical temperature data;
The training module is used for training a set neural network model according to the second historical irradiation data, the second historical temperature data, the second historical cloud cover data, the second historical humidity data, the initial historical photovoltaic predicted power and the second historical actual photovoltaic power to obtain a trained set neural network model;
the predicted data acquisition module is used for acquiring irradiation predicted data and temperature predicted data;
the initial photovoltaic predicted power determining module is used for determining initial photovoltaic predicted power according to the irradiation predicted data and the temperature predicted data;
and the target photovoltaic predicted power obtaining module is used for inputting the initial photovoltaic predicted power into the trained set neural network model for error correction to obtain the target photovoltaic predicted power.
10. The apparatus of claim 9, wherein the initial photovoltaic predicted power determination module is specifically configured to:
obtaining photovoltaic standard power, irradiation standard data, temperature standard data and temperature coefficients;
determining an irradiation influence factor according to the irradiation prediction data and the irradiation standard data;
determining a temperature influence factor according to the temperature standard data, the temperature coefficient and the temperature prediction data;
And determining initial photovoltaic predicted power according to the photovoltaic standard power, the irradiation influence factor and the temperature influence factor.
11. An electronic device, the electronic device comprising:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the photovoltaic power prediction method of any of claims 1-8.
12. A storage medium containing computer executable instructions for performing the photovoltaic power prediction method of any of claims 1-8 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311081650.9A CN117117849A (en) | 2023-08-25 | 2023-08-25 | Photovoltaic power prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311081650.9A CN117117849A (en) | 2023-08-25 | 2023-08-25 | Photovoltaic power prediction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117117849A true CN117117849A (en) | 2023-11-24 |
Family
ID=88812354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311081650.9A Pending CN117117849A (en) | 2023-08-25 | 2023-08-25 | Photovoltaic power prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117117849A (en) |
-
2023
- 2023-08-25 CN CN202311081650.9A patent/CN117117849A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105790261B (en) | Random harmonic power flow calculation method | |
| CN111682530A (en) | Method, device, equipment and medium for determining out-of-limit probability of voltage of power distribution network | |
| CN116931438B (en) | Method, device, equipment and medium for determining parameters of speed regulator of water turbine | |
| CN117744916A (en) | Method and device for predicting energy storage capacity, computer equipment and readable storage medium | |
| CN117332898A (en) | New energy small time scale power time sequence rolling prediction method based on machine learning | |
| CN117057258A (en) | Black-start overvoltage prediction method and system based on weight distribution correlation coefficient | |
| CN116151446A (en) | Ultra-short-term wind power prediction method and device based on CEEMD and CNN-LSTM models | |
| CN117117849A (en) | Photovoltaic power prediction method, device, equipment and storage medium | |
| CN116577843A (en) | Wind power prediction method for distributed sodar | |
| CN116125279A (en) | Method, device, equipment and storage medium for determining battery health state | |
| CN116050250A (en) | Power grid digital twin model modeling method and device based on hybrid driving model | |
| CN113408808B (en) | Training method, data generation device, electronic equipment and storage medium | |
| CN114817985A (en) | Privacy protection method, device, equipment and storage medium for electricity consumption data | |
| CN117131315B (en) | Out-of-tolerance electric energy meter determining method and medium based on solving multi-element quadratic function extremum | |
| CN117236234B (en) | Iterative step number prediction method and device in semiconductor device simulation | |
| CN117236233B (en) | Semiconductor device initial value evaluation method, device, electronic equipment and storage medium | |
| CN114626636A (en) | Power grid load prediction method and device, modeling method, computer equipment and medium | |
| CN116913407A (en) | Transformer fault identification method, device, equipment and medium | |
| CN116049252A (en) | Data processing method, device, electronic equipment and storage medium | |
| CN115983486A (en) | Wind power output prediction method and device, electronic equipment and storage medium | |
| CN115860249A (en) | Distributed photovoltaic power generation power prediction method, device, equipment and medium | |
| CN118033461A (en) | Method and device for evaluating battery health state and electronic equipment | |
| CN118014018A (en) | Building energy consumption prediction method, device, equipment and storage medium | |
| CN116484719A (en) | Method, device, equipment and storage medium for determining internal temperature rise value | |
| CN117833208A (en) | Power distribution network state deduction method and device, electronic equipment and storage medium |
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 |