CN114638396A - Photovoltaic power prediction method and system based on neural network instantiation - Google Patents
Photovoltaic power prediction method and system based on neural network instantiation Download PDFInfo
- Publication number
- CN114638396A CN114638396A CN202210042396.0A CN202210042396A CN114638396A CN 114638396 A CN114638396 A CN 114638396A CN 202210042396 A CN202210042396 A CN 202210042396A CN 114638396 A CN114638396 A CN 114638396A
- Authority
- CN
- China
- Prior art keywords
- irradiance
- neural network
- wind speed
- power station
- photovoltaic power
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 36
- 210000002569 neuron Anatomy 0.000 claims abstract description 11
- 230000005284 excitation Effects 0.000 claims description 28
- 238000012360 testing method Methods 0.000 claims description 19
- 238000010248 power generation Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 15
- 238000010606 normalization Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 abstract description 6
- 230000007547 defect Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 26
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 230000001186 cumulative effect Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- YCKRFDGAMUMZLT-UHFFFAOYSA-N Fluorine atom Chemical compound [F] YCKRFDGAMUMZLT-UHFFFAOYSA-N 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 229910052731 fluorine Inorganic materials 0.000 description 1
- 239000011737 fluorine Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Biophysics (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention provides a photovoltaic power prediction method and a system based on neural network instantiation, which comprises the following steps: acquiring the temperature, irradiance and wind speed of a photovoltaic power station to be detected; normalizing the temperature, the irradiance and the wind speed to obtain normalized data; inputting the normalized data into a pre-trained prediction model to obtain the power of the photovoltaic power station to be tested; the pre-trained prediction model is obtained by training a constructed neural network based on the normalized historical temperature, irradiance, wind speed and corresponding power of the photovoltaic power station; the neural network is constructed based on the electrical topology of the power station. The invention adopts a neural network neuron materialized modeling method, overcomes the defect that mechanism modeling is difficult to adapt to changeable field environment, and improves the accuracy.
Description
Technical Field
The invention relates to the field of new energy power generation, in particular to a photovoltaic power prediction method and system based on neural network instantiation.
Background
The large-scale development of renewable energy sources is one of important ways for realizing the optimization and adjustment of energy source structures. Under the strong support and promotion, the photovoltaic power generation has been rapidly increased for many years continuously, the cumulative installed power of the photovoltaic power generation reaches 25343 ten thousand kilowatts, the cumulative installed power of the photovoltaic power generation is increased by 24.1 percent on the same scale, and the cumulative installed power of the photovoltaic power generation accounts for 11.52 percent of the total installed capacity.
However, the output of the photovoltaic power station is greatly influenced by the environment, such as dust deposition on the surface of an array, trees, buildings, cloud layers and the like, and the environmental factors are often random, so that the photovoltaic output has strong randomness and volatility, the output of the photovoltaic power station is difficult to predict and control, and the photovoltaic power station is covered with the misconception of 'garbage electricity'. Therefore, a high-precision photovoltaic power station output prediction method must be deeply researched, photovoltaic power station power prediction is supported, and a basis is provided for new energy scheduling. The number of the photovoltaic power station generating units is large, and the photovoltaic power station generating units are difficult to accurately predict through a mechanism modeling prediction method; the neural network prediction takes an object as a black box, trains the neural network by using historical data, identifies the object and lacks of specific physical significance support. At present, scholars at home and abroad make a great deal of research work on photovoltaic power station prediction models, the research results can be divided into mechanism modeling and intelligent algorithm modeling, the mechanism modeling is difficult to adapt to changeable field environments, the intelligent algorithm modeling lacks physical significance support, and the precision needs to be improved.
Disclosure of Invention
In order to solve the problems of inaccurate mechanism modeling prediction and difficult adaptation to changeable field environments, the invention provides a photovoltaic power prediction method based on neural network instantiation, which comprises the following steps:
acquiring the temperature, irradiance and wind speed of a photovoltaic power station to be detected;
normalizing the temperature, the irradiance and the wind speed to obtain normalized data;
inputting the normalized data into a pre-trained prediction model to obtain the power of the photovoltaic power station to be tested;
the pre-trained prediction model is obtained by training a constructed neural network based on the normalized historical temperature, irradiance, wind speed and corresponding power of the photovoltaic power station;
the neural network is constructed based on the electrical topology of the power station.
Preferably, the neural network comprises: an input layer, a hidden layer and an output layer;
the input layer is used for inputting the temperature, irradiance and wind speed of the photovoltaic power station after normalization processing into the pre-trained neural network and transmitting the temperature, irradiance and wind speed to the hidden layer;
the hidden layer is used for calculating the input of the hidden layer according to the combination of the temperature, the irradiance and the wind speed of the photovoltaic power station transmitted by the input layer, the connection weight of the hidden layer and the threshold value of the hidden layer, calculating the output of the hidden layer according to the combination of the input of the hidden layer and the excitation function of the hidden layer, and transmitting the output of the hidden layer to the output layer;
the output layer is used for calculating to obtain output layer input based on hidden layer output, the connection weight of the output layer and the threshold value of the output layer, calculating to obtain power corresponding to the temperature, irradiance and wind speed of the photovoltaic power station by combining the output layer input with the excitation function of the output layer, and outputting the power;
preferably, the training of the prediction model comprises:
constructing a sample set by the normalized historical temperature, irradiance, wind speed and corresponding power of the photovoltaic power station;
dividing the sample set into a training set and a testing set according to a set proportion;
taking the normalized historical temperature, irradiance and wind speed of the photovoltaic power station in the training set as the input of a neural network, and taking the power in the training set as the output of the neural network to train the neural network to obtain an initial prediction model;
testing the initial predictive model by the test set,
based on the historical temperature, irradiance and wind speed of the normalized photovoltaic power station in the test set as the input of the initial prediction model, outputting predicted power by the initial prediction model;
calculating an error between the predicted power and the power in the test set and transmitting the error back to an output layer and a hidden layer of a neural network;
adjusting the connection weight and the threshold value in the hidden layer and the output layer based on the error until reaching a set error range;
and taking the initial prediction model when the error reaches a set error range as a trained prediction model.
Preferably, the normalized data is calculated as follows:
in the formula, xiRaw historical data such as temperature T, irradiance C, wind speed D, and output power P; x is the number ofminIs the minimum value of the original historical data; x is the number ofmaxIs the maximum value of the original historical data; x'iIs a normalized calendarHistory data; i is the ith data.
Preferably, the excitation function of the hidden layer is as follows:
f(1)(X)＝A*S*B*η*X；
in the formula (f)(1)Is the excitation function of the hidden layer; a is the conversion efficiency multiplication of the photovoltaic module; s is the area of the photovoltaic module corresponding to the power generation unit; b, the inversion efficiency of the photovoltaic inverter; eta is the boosting efficiency; x is the last layer neuron output.
Preferably, the excitation function of the output layer is as follows:
f(2)(X)＝E*X；
in the formula (f)(2)Is the excitation function of the output layer; e is the efficiency of the power station grid-connected main transformer; x is the last layer neuron output.
The invention also provides a photovoltaic power prediction system based on the instantiation of the neural network, which comprises:
the data acquisition module is used for acquiring the temperature, irradiance and wind speed of the photovoltaic power station to be detected;
the data processing module is used for carrying out normalization processing on the temperature, the irradiance and the wind speed to obtain normalized data;
the training module is used for inputting the normalized data into a pre-trained prediction model to obtain the power of the photovoltaic power station to be tested;
the pre-trained prediction model is obtained by training a constructed neural network based on the normalized historical temperature, irradiance, wind speed and corresponding power of the photovoltaic power station;
the neural network is constructed based on the electrical topology of the power station.
Preferably, the training of the prediction model comprises:
constructing a sample set by the normalized historical temperature, irradiance, wind speed and corresponding power of the photovoltaic power station;
dividing the sample set into a training set and a testing set according to a set proportion;
taking the normalized historical temperature, irradiance and wind speed of the photovoltaic power station in the training set as the input of a neural network, and taking the power in the training set as the output of the neural network to train the neural network to obtain an initial prediction model;
based on the historical temperature, irradiance and wind speed of the normalized photovoltaic power station in the test set as the input of the initial prediction model, outputting predicted power by the initial prediction model;
calculating an error between the predicted power and the power in the test set and passing the error back to an output layer of a neural network;
adjusting the connection weight and the threshold value in the hidden layer and the output layer based on the error until reaching a set error range;
and taking the initial prediction model when the error reaches a set error range as a trained prediction model.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a photovoltaic power prediction method and a system based on neural network instantiation, which comprises the following steps: acquiring the temperature, irradiance and wind speed of a photovoltaic power station to be detected; normalizing the temperature, the irradiance and the wind speed to obtain normalized data; inputting the normalized data into a pre-trained prediction model to obtain the power of the photovoltaic power station to be tested; the pre-trained prediction model is obtained by training a constructed neural network based on the normalized historical temperature, irradiance, wind speed and corresponding power of the photovoltaic power station; the neural network is constructed based on the electrical topology of the power station. The neural network adopted by the invention is constructed based on the electric appliance topological structure of the power station, so that the problem that mechanism modeling is difficult to adapt to changeable field environment is solved, and the accuracy is improved.
Drawings
FIG. 1 is a schematic flow chart of a photovoltaic power prediction method based on neural network instantiation provided by the present invention;
FIG. 2 is a photovoltaic power plant topology schematic of the present invention;
FIG. 3 is a block diagram of a neural network of the present invention;
FIG. 4 is a flow chart of the predictive modeling of the present invention;
fig. 5 is an electrical topology structural diagram of the photovoltaic power plant of the present invention.
Detailed Description
For a better understanding of the present invention, reference is made to the following description taken in conjunction with the accompanying drawings and examples. The invention provides a photovoltaic power prediction method based on neural network instantiation.
Example 1:
the invention provides a photovoltaic power prediction method based on neural network instantiation, which is shown in figure 1: the method comprises the following steps:
step 1: acquiring the temperature, irradiance and wind speed of a photovoltaic power station to be detected;
step 2: normalizing the temperature, the irradiance and the wind speed to obtain normalized data;
and step 3: inputting the normalized data into a pre-trained prediction model to obtain the power of the photovoltaic power station to be tested;
the pre-trained prediction model is obtained by training a constructed neural network based on the normalized historical temperature, irradiance, wind speed and corresponding power of the photovoltaic power station;
the neural network is constructed based on the electrical topology of the power station.
Before step 1, the method further comprises the following steps:
the neural network includes: an input layer, a hidden layer and an output layer;
the input layer is used for inputting the temperature, irradiance and wind speed of the photovoltaic power station after normalization processing into the pre-trained neural network and transmitting the temperature, irradiance and wind speed to the hidden layer;
the hidden layer is used for calculating the input of the hidden layer according to the combination of the temperature, the irradiance and the wind speed of the photovoltaic power station transmitted by the input layer, the connection weight of the hidden layer and the threshold value of the hidden layer, calculating the output of the hidden layer according to the combination of the input of the hidden layer and the excitation function of the hidden layer, and transmitting the output of the hidden layer to the output layer;
the excitation function of the hidden layer is shown as follows:
f(1)(X)＝A*S*B*η*X；
in the formula (f)(1)Is the excitation function of the hidden layer; a is the conversion efficiency multiplication of the photovoltaic module; s is the area of the photovoltaic module corresponding to the power generation unit; b, the inversion efficiency of the photovoltaic inverter; eta is the boosting efficiency; x is the last layer neuron output.
The output layer is used for calculating to obtain output layer input based on hidden layer output, the connection weight of the output layer and the threshold value of the output layer, calculating to obtain power corresponding to the temperature, irradiance and wind speed of the photovoltaic power station by combining the output layer input with the excitation function of the output layer, and outputting the power;
the excitation function of the output layer is shown as follows:
f(2)(X)＝E*X；
in the formula (f)(2)Is the excitation function of the output layer; e is the efficiency of the power station grid-connected main transformer; x is the last layer neuron output.
The network input and output relationship is as follows:
1) input layer
The input is T, C, D
The output is O1 (1)＝T、O2 (1)＝C、O3 (1)＝D (4)
2) Hidden layer
Input is as
The output is Oj (2)＝f(1)(Ij (1))j＝1,2,…,m (6)
3) Output layer
Input is as
Output layer P ═ f(2)(I(2)) (8)
In the formula of omegajiRepresenting the connection weight, theta, of the hidden layerjThreshold, ω, representing the hidden layerjRepresents the connection weight of the output layer, and θ represents the threshold of the output layer.
The photovoltaic power plant includes a plurality of power generation units.
An electrical topological structure of a photovoltaic power station to be modeled is investigated, and as shown in fig. 2, conversion efficiency of photovoltaic modules of each power generation unit of the power station, area of the photovoltaic modules of each power generation unit, inversion efficiency of a photovoltaic inverter, efficiency of a box-type transformer, and efficiency of a power station grid-connected main transformer are collected.
The method also comprises training a prediction model before step 1:
initializing connection weights among neurons in a neural network and thresholds of the neurons, wherein the hidden layer corresponds to the power generation units, the determinants irradiance directly acts on the power generation units, and the transmission efficiency from the power generation units to a grid-connected main transformer is close to 100%, so that the connection weights in the network are uniformly initialized to 1, and the thresholds are uniformly initialized to 0;
training a neural network, training a model by using historical data, transmitting input information in a forward direction in a direction shown in figure 3, and finally outputting output of a layer and an expected value OdComparing, reversely transmitting the error, adjusting the weight and the threshold value, repeating the operation until the output error reaches the allowable range, completing modeling, wherein the modeling process is shown in fig. 4, and the specific steps are as follows:
constructing a sample set by the normalized historical temperature, irradiance, wind speed and corresponding power of the photovoltaic power station;
dividing the sample set into a training set and a testing set according to a set proportion;
taking the normalized historical temperature, irradiance and wind speed of the photovoltaic power station in the training set as the input of a neural network, and taking the power in the training set as the output of the neural network to train the neural network to obtain an initial prediction model;
based on the historical temperature, irradiance and wind speed of the normalized photovoltaic power station in the test set as the input of the initial prediction model, outputting predicted power by the initial prediction model;
calculating an error between the predicted power and the power in the test set and transmitting the error back to an output layer and a hidden layer of a neural network;
adjusting the connection weight and the threshold value in the hidden layer and the output layer based on the error until reaching a set error range;
and taking the initial prediction model when the error reaches a set error range as a trained prediction model.
The method specifically comprises the step 1 of obtaining the temperature, irradiance and wind speed of the photovoltaic power station to be detected.
In step 2, normalizing the temperature, irradiance and wind speed to obtain normalized data, which specifically comprises:
the normalized data is calculated as follows:
in the formula, xiIs original historical data; x is a radical of a fluorine atomminIs the minimum value of the original historical data; x is the number ofmaxIs the maximum value of the original historical data; x'iThe normalized historical data is obtained; i is the ith data. The raw historical data of the present embodiment includes temperature, irradiance, wind speed, or output power.
In step 3, inputting the normalized data into a pre-trained prediction model to obtain the power of the photovoltaic power station to be tested, and the method specifically comprises the following steps:
inputting the obtained temperature, irradiance and wind speed of the photovoltaic power station through an input layer of a neural network, and transmitting the temperature, irradiance and wind speed to a hidden layer through the input layer;
calculating the temperature, irradiance and wind speed of the photovoltaic power station input to the input layer through the hidden layer by an excitation function of the hidden layer to obtain the output of the hidden layer, and transmitting the output of the hidden layer to the output layer;
and the output layer is combined with the excitation function of the output layer to calculate the power of the photovoltaic power station corresponding to the temperature, the irradiance and the wind speed of the photovoltaic power station, and the power of the photovoltaic power station is output.
Example 2:
based on the same invention concept, the invention also provides a photovoltaic power prediction system based on the instantiation of the neural network, which comprises the following components:
the data acquisition module is used for acquiring the temperature, irradiance and wind speed of the photovoltaic power station to be measured;
the data processing module is used for carrying out normalization processing on the temperature, the irradiance and the wind speed to obtain normalized data;
the training module is used for inputting the normalized data into a pre-trained prediction model to obtain the power of the photovoltaic power station to be tested;
the pre-trained prediction model is obtained by training a constructed neural network based on the normalized historical temperature, irradiance, wind speed and corresponding power of the photovoltaic power station;
a photovoltaic power prediction system based on neural network instantiation further comprising: the neural network training module is used for training the neural network based on the normalized historical temperature, irradiance and wind speed of the photovoltaic power station and the corresponding power.
The neural network includes: an input layer, a hidden layer and an output layer;
the input layer is used for inputting the temperature, irradiance and wind speed of the photovoltaic power station after normalization processing into the pre-trained neural network and transmitting the temperature, irradiance and wind speed to the hidden layer;
the hidden layer is used for calculating the input of the hidden layer according to the combination of the temperature, the irradiance and the wind speed of the photovoltaic power station transmitted by the input layer, the connection weight of the hidden layer and the threshold value of the hidden layer, calculating the output of the hidden layer according to the combination of the input of the hidden layer and the excitation function of the hidden layer, and transmitting the output of the hidden layer to the output layer; wherein the photovoltaic power station comprises a plurality of power generation units;
the excitation function of the hidden layer is shown as follows:
f(1)(X)＝A*S*B*η*X；
in the formula (f)(1)Is the excitation function of the hidden layer; a is the conversion efficiency multiplication of the photovoltaic module; s is the area of the photovoltaic module corresponding to the power generation unit; b, the inversion efficiency of the photovoltaic inverter; eta is the boosting efficiency; and X is the neuron output of the last layer.
The output layer is used for calculating to obtain output layer input based on hidden layer output, the connection weight of the output layer and the threshold value of the output layer, calculating to obtain power corresponding to the temperature, irradiance and wind speed of the photovoltaic power station by combining the output layer input with the excitation function of the output layer, and outputting the power;
the excitation function of the output layer is shown as follows:
f(2)(X)＝E*X；
in the formula (f)(2)Is the excitation function of the output layer; e is the efficiency of the power station grid-connected main transformer; x is the last layer neuron output.
The network input and output relationship is as follows:
1) input layer
The input is T, C, D
The output is O1 (1)＝T、O2 (1)＝C、O3 (1)＝D (4)
2) Hidden layer
Input is as
The output is Oj (2)＝f(1)(Ij (1))j＝1,2,…,m (6)
3) Output layer
Input is as
Output layer P ═ f(2)(I(2)) (8)
In the formula of omegajiConnection weights, θ, representing the hidden layerjThreshold, ω, representing the hidden layerjRepresents the connection weight of the output layer, and θ represents the threshold of the output layer.
The electrical topology of the target power station to be modeled is investigated, and as shown in fig. 5, the structure of the neural network is determined according to the electrical topology of the power station.
The data acquisition module is specifically used for acquiring the temperature, irradiance and wind speed of the photovoltaic power station to be detected.
The data processing module is specifically configured to:
the normalized data is calculated as follows:
in the formula, xiIs original historical data; x is the number ofminIs the minimum value of the original historical data; x is the number ofmaxIs the maximum value of the original historical data; x'iThe normalized historical data is obtained; i is the ith data. The raw historical data of the present embodiment includes temperature, irradiance, wind speed, or output power.
The training module is specifically configured to:
inputting the obtained temperature, irradiance and wind speed of the photovoltaic power station through an input layer of a neural network, and transmitting the temperature, irradiance and wind speed to a hidden layer through the input layer;
calculating the temperature, irradiance and wind speed of the photovoltaic power station input to the input layer through the hidden layer by an excitation function of the hidden layer to obtain the output of the hidden layer, and transmitting the output of the hidden layer to the output layer;
and the output layer is combined with the excitation function of the output layer to calculate power corresponding to the temperature, irradiance and wind speed of the photovoltaic power station, and the power is output.
It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The present invention is not limited to the above embodiments, and any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention are included in the scope of the claims of the present invention which are filed as the application.
Claims (8)
1. A photovoltaic power prediction method based on neural network instantiation is characterized by comprising the following steps:
acquiring the temperature, irradiance and wind speed of a photovoltaic power station to be detected;
normalizing the temperature, the irradiance and the wind speed to obtain normalized data;
inputting the normalized data into a pre-trained prediction model to obtain the power of the photovoltaic power station to be tested;
the pre-trained prediction model is obtained by training a pre-constructed neural network based on the normalized historical temperature, irradiance, wind speed and corresponding power of the photovoltaic power station;
the neural network is constructed based on the electrical topology of the power station.
2. The method of claim 1, wherein the neural network comprises: an input layer, a hidden layer and an output layer;
the input layer is used for inputting the temperature, irradiance and wind speed of the photovoltaic power station after normalization processing into the pre-trained neural network and transmitting the temperature, irradiance and wind speed to the hidden layer;
the hidden layer is used for calculating the input of the hidden layer according to the combination of the temperature, the irradiance and the wind speed of the photovoltaic power station transmitted by the input layer, the connection weight of the hidden layer and the threshold value of the hidden layer, calculating the output of the hidden layer according to the combination of the input of the hidden layer and the excitation function of the hidden layer, and transmitting the output of the hidden layer to the output layer;
the output layer is used for calculating to obtain output layer input based on hidden layer output, the connection weight of the output layer and the threshold value of the output layer, calculating to obtain power corresponding to the temperature, irradiance and wind speed of the photovoltaic power station by combining the output layer input with the excitation function of the output layer, and outputting the power;
wherein the photovoltaic power station is composed of a plurality of power generation units.
3. The method of claim 2, wherein the training of the predictive model comprises:
constructing a sample set by the normalized historical temperature, irradiance, wind speed and corresponding power of the photovoltaic power station;
dividing the sample set into a training set and a testing set according to a set proportion;
taking the normalized historical temperature, irradiance and wind speed of the photovoltaic power station in the training set as the input of a neural network, and taking the power in the training set as the output of the neural network to train the neural network to obtain an initial prediction model;
testing the initial predictive model by the test set,
based on the historical temperature, irradiance and wind speed of the normalized photovoltaic power station in the test set as the input of the initial prediction model, outputting predicted power by the initial prediction model;
calculating an error between the predicted power and the power in the test set and transmitting the error back to an output layer and a hidden layer of a neural network;
adjusting the connection weight and the threshold value in the hidden layer and the output layer based on the error until reaching a set error range;
and taking the initial prediction model when the error reaches a set error range as a trained prediction model.
4. The method of claim 1, wherein the normalized data is calculated as:
in the formula, xiRaw historical data of temperature, irradiance, wind speed, or output power; x is the number ofminIs the minimum value of the original historical data; x is the number ofmaxIs the maximum value of the original historical data; x'iThe normalized historical data is obtained; i is the ith data.
5. The method of claim 2, wherein the excitation function of the hidden layer is represented by the following equation:
f(1)(X)＝A*S*B*η*X；
in the formula, f(1)An excitation function for the hidden layer; a is the conversion efficiency multiplication of the photovoltaic module; s is the area of the photovoltaic module corresponding to the power generation unit; b, the inversion efficiency of the photovoltaic inverter; eta is the boosting efficiency; x is the last layer neuron output.
6. The method of claim 2, wherein the excitation function of the output layer is as follows:
f(2)(X)＝E*X；
in the formula (f)(2)Is the excitation function of the output layer; e is the efficiency of the power station grid-connected main transformer; x is the last layer neuron output.
7. A photovoltaic power prediction system instantiated based on a neural network, comprising:
the data acquisition module is used for acquiring the temperature, irradiance and wind speed of the photovoltaic power station to be detected;
the data processing module is used for carrying out normalization processing on the temperature, the irradiance and the wind speed to obtain normalized data;
the training module is used for inputting the normalized data into a pre-trained prediction model to obtain the power of the photovoltaic power station to be tested;
the pre-trained prediction model is obtained by training a constructed neural network based on the normalized historical temperature, irradiance, wind speed and corresponding power of the photovoltaic power station;
the neural network is constructed based on the electrical topology of the power station.
8. The system of claim 7, wherein the training of the predictive model comprises:
constructing a sample set by the normalized historical temperature, irradiance, wind speed and corresponding power of the photovoltaic power station;
dividing the sample set into a training set and a testing set according to a set proportion;
taking the normalized historical temperature, irradiance and wind speed of the photovoltaic power station in the training set as the input of a neural network, and taking the power in the training set as the output of the neural network to train the neural network to obtain an initial prediction model;
based on the historical temperature, irradiance and wind speed of the normalized photovoltaic power station in the test set as the input of the initial prediction model, outputting predicted power by the initial prediction model;
calculating an error between the predicted power and the power in the test set and passing the error back to an output layer of a neural network;
adjusting the connection weight and the threshold value in the hidden layer and the output layer based on the error until reaching a set error range;
and taking the initial prediction model when the error reaches a set error range as a trained prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210042396.0A CN114638396A (en) | 2022-01-14 | 2022-01-14 | Photovoltaic power prediction method and system based on neural network instantiation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210042396.0A CN114638396A (en) | 2022-01-14 | 2022-01-14 | Photovoltaic power prediction method and system based on neural network instantiation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114638396A true CN114638396A (en) | 2022-06-17 |
Family
ID=81945962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210042396.0A Pending CN114638396A (en) | 2022-01-14 | 2022-01-14 | Photovoltaic power prediction method and system based on neural network instantiation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114638396A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116706907A (en) * | 2023-08-09 | 2023-09-05 | 深圳航天科创泛在电气有限公司 | Photovoltaic power generation prediction method based on fuzzy reasoning and related equipment |
| CN117713580A (en) * | 2024-02-06 | 2024-03-15 | 杭州利沃得电源有限公司 | Switching method and device for modulation mode of photovoltaic inverter |
| CN118036529A (en) * | 2024-02-20 | 2024-05-14 | 山东大学 | Method and system for calculating effective irradiance and temperature for photovoltaic prediction |
-
2022
- 2022-01-14 CN CN202210042396.0A patent/CN114638396A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116706907A (en) * | 2023-08-09 | 2023-09-05 | 深圳航天科创泛在电气有限公司 | Photovoltaic power generation prediction method based on fuzzy reasoning and related equipment |
| CN116706907B (en) * | 2023-08-09 | 2024-01-23 | 深圳航天科创泛在电气有限公司 | Photovoltaic power generation prediction method based on fuzzy reasoning and related equipment |
| CN117713580A (en) * | 2024-02-06 | 2024-03-15 | 杭州利沃得电源有限公司 | Switching method and device for modulation mode of photovoltaic inverter |
| CN117713580B (en) * | 2024-02-06 | 2024-05-24 | 杭州利沃得电源有限公司 | Switching method and device for modulation mode of photovoltaic inverter |
| CN118036529A (en) * | 2024-02-20 | 2024-05-14 | 山东大学 | Method and system for calculating effective irradiance and temperature for photovoltaic prediction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Dynamic spatio-temporal correlation and hierarchical directed graph structure based ultra-short-term wind farm cluster power forecasting method | |
| CN114638396A (en) | Photovoltaic power prediction method and system based on neural network instantiation | |
| CN108306303B (en) | Voltage stability evaluation method considering load increase and new energy output randomness | |
| CN103106544B (en) | A kind of photovoltaic generation prognoses system based on T-S Fuzzy neutral net | |
| CN105426956A (en) | Ultra-short-period photovoltaic prediction method | |
| Goudarzi et al. | Intelligent analysis of wind turbine power curve models | |
| Fei et al. | A practical model for single-step power prediction of grid-connected PV plant using artificial neural network | |
| Li et al. | Short-term power generation forecasting of a photovoltaic plant based on PSO-BP and GA-BP neural networks | |
| CN111509768A (en) | Scene simulation method and system of comprehensive energy system | |
| CN106779175B (en) | Time-interval-considered nonlinear photovoltaic output prediction method | |
| Almadhor | Performance prediction of distributed PV generation systems using Artificial Neural Networks (ANN) and Mesh Networks | |
| CN113065680B (en) | Energy demand prediction method and system for energy Internet | |
| CN112116171A (en) | Novel photovoltaic power generation power prediction method based on neural network | |
| Tao et al. | On comparing six optimization algorithms for network-based wind speed forecasting | |
| CN112101626A (en) | Distributed photovoltaic power generation power prediction method and system | |
| CN115660232A (en) | Ultra-short-term prediction method, device and system for wind power | |
| CN107292434A (en) | A kind of intelligent Forecasting of wind power output | |
| Omer et al. | Adaptive boosting and bootstrapped aggregation based ensemble machine learning methods for photovoltaic systems output current prediction | |
| Paulin et al. | SOLAR PHOTOVOLTAIC OUTPUT POWER FORECASTING USING BACK PROPAGATION NEURAL NETWORK. | |
| Jiangxia et al. | A combination prediction model for wind farm output power | |
| Kumar et al. | Short-term wind power plant predicting with artificial neural network | |
| Ashraf et al. | A Hybrid Statistical Model for Ultra Short Term Wind Speed Prediction | |
| Elmejdki et al. | Prediction model of wind speed using hybrid artificial neural network based on Levenberg-Marquardt algorithm | |
| CN106548248A (en) | A kind of harmonic trend probability index Forecasting Methodology of the electrical network of power station containing large-sized photovoltaic | |
| Panapakidis et al. | Deep learning approach based on LSTM model for short-term solar generation forecasting |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |