CN113642677B - Regional power grid load prediction method and device - Google Patents
Regional power grid load prediction method and device Download PDFInfo
- Publication number
- CN113642677B CN113642677B CN202111184364.6A CN202111184364A CN113642677B CN 113642677 B CN113642677 B CN 113642677B CN 202111184364 A CN202111184364 A CN 202111184364A CN 113642677 B CN113642677 B CN 113642677B
- Authority
- CN
- China
- Prior art keywords
- data
- cloud
- meteorological
- layer
- load
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Tourism & Hospitality (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a regional power grid load prediction method and a device, belongs to the technical field of electric power, and solves the problem that the accuracy of load prediction is influenced by losing data information contained in non-structured meteorological factors through modeling of structured meteorological data. The method comprises the following steps: determining meteorological data influencing loads in each meteorological partition in a regional power grid, wherein the meteorological data comprise air pressure, temperature, precipitation, relative humidity, wind speed, wind direction, date type and cloud picture data, and shooting by an all-sky imager to obtain the cloud picture data; preprocessing meteorological data; establishing a cloud image classification and discrimination model of a Gabor filter-convolution neural network, and performing prediction classification processing on preprocessed cloud image data by using the discrimination model; fusing the classified cloud picture data with other meteorological data to form a meteorological data set; establishing a load prediction model; and predicting the load of each meteorological partition by using the load prediction model. The accuracy and precision of load prediction are improved.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to a regional power grid load prediction method and device.
Background
The power load prediction is the basis of planning and arranging a power generation plan of the power grid, and the high-precision load prediction plays an important role in improving the safe, stable and economic operation of the power grid. The short-term power load is easily influenced by various numerical and non-numerical factors such as meteorological conditions, holiday types and the like, the load change presents certain randomness and nonlinearity, the load prediction accuracy is influenced, and the prediction accuracy is to be further improved.
At present, the prediction methods for the power load are mainly divided into two types: a conventional prediction method and an intelligent prediction method. The traditional prediction method mainly comprises methods such as time sequence, regression model and trend extrapolation; the intelligent prediction method mainly comprises a neural network, a support vector machine and the like. The traditional prediction method has the advantages of simpler model and fixed model parameters, and is difficult to explain sudden load. The intelligent prediction method represented by the neural network can realize linear and nonlinear complex mapping and is widely applied at present. For the influence factors of short-term load, the common method considers the weather factors, such as temperature, humidity and the like, and the main data type is structured data.
Most current load prediction methods focus on establishing causal relationship between structured meteorological influence factors and loads, but modeling is performed only through structured meteorological data, data information contained in unstructured meteorological factors is lost, and the constructed model cannot reflect the explanation of unstructured data on load variables.
Disclosure of Invention
In view of the foregoing analysis, embodiments of the present invention are directed to providing a method and an apparatus for predicting a load of a regional power grid, so as to solve the problem that modeling through structured meteorological data loses data information contained in unstructured meteorological factors, thereby affecting accuracy of load prediction.
In one aspect, an embodiment of the present invention provides a regional power grid load prediction method, including: determining meteorological data influencing loads in each meteorological partition in the regional power grid, wherein the meteorological data comprise air pressure, temperature, precipitation, relative humidity, wind speed, wind direction, date type and cloud map data, and the cloud map data are obtained by shooting through an all-sky imager; preprocessing the meteorological data; establishing a cloud image classification and discrimination model of a Gabor filter-convolution neural network, and performing prediction classification processing on preprocessed cloud image data by using the discrimination model; fusing the classified cloud picture data with other meteorological data to form a meteorological data set; establishing a load prediction model of a BP neural network, wherein the meteorological data set is used as the input of the BP neural network, and the load of a meteorological partition corresponding to the meteorological data is used as the output; and predicting the load of each meteorological partition by using the load prediction model.
The beneficial effects of the above technical scheme are as follows: the cloud picture image is shot and obtained through an all-sky imager, and all-sky visible light red, green and blue three-band image data are shot and obtained at regular time through a shooting lens and a digital imaging system; preprocessing meteorological data; and establishing a cloud image classification and discrimination model of the Gabor filter-convolution neural network, and classifying the preprocessed cloud image data (namely, the unstructured data) by using the discrimination model so as to convert the cloud image data into the structured data. Fusing the classified cloud map data (i.e., structured data) with other meteorological data (i.e., structured data) to form a meteorological data set; the load of each meteorological partition is predicted by using the load prediction model, with the meteorological data set as an input and the loads of the meteorological partitions corresponding to the meteorological data as an output.
Based on the further improvement of the method, the preprocessing of the meteorological data comprises the following steps: processing abnormal meteorological data by a moving average method; normalizing the weather data using a max-min method to convert the weather data into data in a range of [0,1], wherein tuesday to thursday in a date type is converted into a numerical value of 0.2, monday to friday is converted into a numerical value of 0.4, and saturday to sunday is converted into a numerical value of 0.6, and a statutory holiday is converted into a numerical value of 0.8 to 1; and carrying out gray processing on the collected color cloud picture data to generate cloud picture data of red-green-blue three bands.
Based on a further improvement of the above method, the classified cloud picture data comprises a raindrop cloud, a rain cloud, a convolution cloud and a non-raining cloud, and are represented by 1, 2, 3 and 4, respectively, wherein the classified cloud picture data are preprocessed to obtain structured data in the range of [0,1 ].
Based on the further improvement of the method, the step of performing prediction classification processing on the preprocessed cloud image data by using the discriminant model comprises the following steps: performing feature extraction and feature fusion on the preprocessed cloud image data through a Gabor filter to obtain a Gabor feature coding image; and performing key feature mapping based on a convolutional neural network to classify the preprocessed cloud image data.
Performing feature extraction and feature fusion on the preprocessed cloud image data through a Gabor filter to obtain a Gabor feature coded image further comprises:
the two-dimensional Gabor function is defined by the following formula:
performing convolution calculation on the cloud image to obtain the following convolution results:
taking the amplitude of the convolved image as the following Gabor characteristics of the cloud image:
wherein (A), (B), (C), (B), (C), (B), (C), (B), (C)x,y) For the given position coordinates it is possible to provide,
is the center frequency of the Gabor filter,
for the phase angles of filters in different directions, the Gabor filter bank selects 8 different directions
And 5 different scales
，k max =π/2；
As a result of the convolution, a convolution operator,z=(x,y)，real(O μ v,(z) ) andimag(O μ v,(z) Respectively the real and imaginary parts of the convolution result;
fusing the Gabor features of 8 directions and 5 scales to obtain a Gabor feature encoded image.
Based on the further improvement of the method, the structure of the convolutional neural network comprises: the device comprises an input layer, a convolution layer, a pooling layer, a full-link layer and an output layer, wherein the input layer receives a Gabor feature coding image; the convolutional layer, configured to perform a convolution operation by the following formula and use a Relu activation function for the convolutional layer:
wherein the content of the first and second substances,
which represents the calculation of the convolution,Frepresents the input of the convolutional layer(s),wis a parameter of the convolution filter;H f 、W f respectively the height and width of the convolution filter,Cis the number of channels;Pin order to fill in the dimension for the edges,H、Wheight and width of the input data;H conv 、W conv the height and width of a feature map formed after convolution calculation is carried out on the image;Sis the step size of the filter movement; the Relu activation function is as follows:
Based on the further improvement of the method, the BP neural network comprises: the device comprises an input layer, a middle hidden layer and an output layer, wherein input vectors of the input layer are as follows:
wherein the content of the first and second substances,when in usenWhen the number of the carbon atoms is not less than 6,x 1the load at the same time on the previous day;x 2is the temperature;x 3is the relative humidity;x 4the rainfall is shown;x 5is a date type;x 6is of cloud picture type; the output vector of the intermediate hidden layer is:
wherein the output vector is a predicted load corresponding to a meteorological partition, and the output vector of the output layer is:
the vector of expected outputs is:
based on the further improvement of the method, the algorithm steps of the BP neural network comprise:
initializing a network, selecting a random number in a (-1, 1) interval to assign values to each connection weight of the network, and setting an error and the maximum iteration number of the network;
training a network model:
the output of the intermediate hidden layer is:
wherein the content of the first and second substances,j=1,2,…,m，
the output of the output layer is:
wherein the content of the first and second substances,k=1,2,…,l，
function(s)f 1、f 2All transfer functions ofSigmoidFunction:
calculating error functions for each layer based on the desired output and the actual output:
for the input layer, the error function is:
error calculation and adjustment of network weights using error back-propagation:
the error signal is derived as:
by continuously adjusting the weights, the error is continuously reduced:
calculating a global error:
according to whether the global error reaches the accuracy of initial setting or whether the training times reach the maximum iteration times of the initial setting, and the algorithm is ended; otherwise, the error function of each layer, the network weight adjustment and the global error calculation are continued, wherein,w ij the connection weights between the input layer and hidden layer neurons,v jk is the connection weight between the neurons of the output layer,d i to output the desired output of the neuron, the hidden layer stimulus function isf 1The excitation function of the output layer isf 1，eIs an error function.
On the other hand, an embodiment of the present invention provides a regional power grid load prediction apparatus, including: the system comprises a meteorological data determining module, a cloud image acquiring module and a load monitoring module, wherein the meteorological data determining module is used for determining meteorological data of influencing loads in each meteorological partition in the regional power grid, the meteorological data comprise air pressure, temperature, precipitation, relative humidity, wind speed, wind direction, date type and cloud image data, and the cloud image data are acquired through shooting of an all-sky imager; the preprocessing module is used for preprocessing the meteorological data; the cloud image classification and discrimination model is used for establishing a cloud image classification and discrimination model of a Gabor filter-convolution neural network and performing prediction classification processing on the preprocessed cloud image data by using the discrimination model; the fusion module is used for fusing the classified cloud picture data with other meteorological data to form a meteorological data set; the load prediction model is used for establishing a load prediction model of a BP (back propagation) neural network, wherein the meteorological data set is used as the input of the BP neural network, and the load of a meteorological partition corresponding to the meteorological data is used as the output; and predicting the load of each meteorological partition by using the load prediction model.
In a further refinement of the apparatus described above, the preprocessing module is configured to: processing abnormal meteorological data by a moving average method; normalizing the weather data using a max-min method to convert the weather data into data in a range of [0,1], wherein tuesday to thursday in a date type is converted into a numerical value of 0.2, monday to friday is converted into a numerical value of 0.4, and saturday to sunday is converted into a numerical value of 0.6, and a statutory holiday is converted into a numerical value of 0.8 to 1; and carrying out gray processing on the collected color cloud picture data to generate cloud picture data of red-green-blue three bands.
Compared with the prior art, the invention can realize at least one of the following beneficial effects:
1. the cloud picture image is shot and obtained through an all-sky imager, and all-sky visible light red, green and blue three-band image data are shot and obtained at regular time through a shooting lens and a digital imaging system; preprocessing meteorological data; and establishing a cloud image classification and discrimination model of the Gabor filter-convolution neural network, and classifying the preprocessed cloud image data (namely, the unstructured data) by using the discrimination model so as to convert the cloud image data into the structured data. Fusing the classified cloud map data (i.e., structured data) with other meteorological data (i.e., structured data) to form a meteorological data set; the load of each meteorological partition is predicted by using the load prediction model, with the meteorological data set as an input and the loads of the meteorological partitions corresponding to the meteorological data as an output.
2. The structured meteorological data and the unstructured meteorological data are fused, a complex mapping relation between a composite data system and the load is constructed, the influence of the unstructured meteorological data on the load is fully mined, and the short-term load prediction accuracy of the regional power grid is improved.
3. The feature dimension is effectively reduced by using the sum of binary codes in each direction on the premise of not reducing image texture feature information so as to carry out multi-scale analysis. And taking the processed feature fusion coding result as the input of the convolutional neural network to construct a deep convolutional neural network model. In the invention, the technical schemes can be combined with each other to realize more preferable combination schemes. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
Fig. 1 is a flowchart of a regional power grid load prediction method according to an embodiment of the present invention.
FIG. 2 is a convolutional neural network structure according to an embodiment of the present invention.
Fig. 3 is a BP neural network structure according to an embodiment of the present invention.
Fig. 4 is a flowchart of a regional power grid load prediction method fusing multi-source heterogeneous meteorological data according to an embodiment of the invention.
Fig. 5 is a block diagram of a regional power grid load prediction apparatus according to an embodiment of the present invention.
FIG. 6 is a schematic diagram of convolution operations performed on convolutional layers of a convolutional neural network.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
The invention discloses a regional power grid load prediction method. As shown in fig. 1, the regional power grid load prediction method includes: step S102, determining meteorological data influencing loads in each meteorological partition in a regional power grid, wherein the meteorological data comprise air pressure, temperature, precipitation, relative humidity, wind speed, wind direction, date type and cloud picture data, and the cloud picture data are obtained through shooting by an all-sky imager; step S104, preprocessing meteorological data; step S106, establishing a cloud image classification and discrimination model of the Gabor filter-convolution neural network, and performing prediction classification processing on preprocessed cloud image data by using the discrimination model; step S108, fusing the classified cloud picture data with other meteorological data to form a meteorological data set; step S110, establishing a BP neural network to obtain a load prediction model, wherein a meteorological data set is used as the input of the BP neural network, and the load of a meteorological partition corresponding to the meteorological data is used as the output; and a step S112 of predicting the load of each meteorological partition by using the load prediction model.
Compared with the prior art, in the regional power grid load prediction method provided by the embodiment, the cloud image is shot and acquired by the all-sky imager, and the red, green and blue three-band image data of all-sky visible light is shot and acquired at regular time by the shooting lens and the digital imaging system; preprocessing meteorological data; and establishing a Gabor filter-convolution neural network cloud image classification and discrimination model, and classifying the preprocessed cloud image data by using the discrimination model so as to convert the classified cloud image data into structured data. Fusing the classified cloud map data (i.e., structured data) with other meteorological data (i.e., structured data) to form a meteorological data set; the load of each meteorological partition is predicted by using the load prediction model, with the meteorological data set as an input and the loads of the meteorological partitions corresponding to the meteorological data as an output.
Hereinafter, referring to fig. 1, step S102, step S104, step S106, step S108, step S110, and step S112 in the regional power grid load prediction method according to the embodiment of the present invention will be described in detail.
The regional power grid load prediction method comprises the following steps: step S102, determining meteorological data influencing loads in each meteorological partition in a regional power grid, wherein the meteorological data comprise air pressure, temperature, precipitation, relative humidity, wind speed, wind direction, date type, cloud picture data and the like, and the cloud picture data are obtained through shooting by an all-sky imager. Specifically, the meteorological data includes structured meteorological data and unstructured meteorological data. Structured weather data includes air pressure, temperature, precipitation, relative humidity, wind speed, wind direction, and date type (holiday and weekday), among others. The unstructured image data includes cloud image data or radar tiles.
And step S104, preprocessing the meteorological data. Preprocessing meteorological data includes: processing abnormal meteorological data by a moving average method; normalizing the weather data using a max-min method to convert the weather data into data in a range of [0,1], wherein tuesday to thursday in the date type are converted into a numerical value of 0.2, monday to friday are converted into a numerical value of 0.4, and saturday to sunday are converted into a numerical value of 0.6, and statutory holidays are converted into a numerical value of 0.8 to 1; and carrying out gray processing on the collected color cloud picture data to generate cloud picture data of red-green-blue three bands.
And S106, establishing a Gabor filter-convolution neural network cloud image classification and discrimination model, and performing prediction classification processing on the preprocessed cloud image data by using the discrimination model. The method for performing prediction classification processing on the preprocessed cloud image data by using the discriminant model comprises the following steps: the method for performing prediction classification processing on the preprocessed cloud image data by using the discriminant model comprises the following steps: performing feature extraction and feature fusion on the preprocessed cloud image data through a Gabor filter to obtain a Gabor feature coding image; and performing key feature mapping based on the convolutional neural network to classify the preprocessed cloud image data. The classified cloud image data includes a raindrop cloud, a rain cloud, a rolling cloud, a non-rainfall cloud, and the like, and the classified cloud image data is represented by 1, 2, 3, and 4, respectively. The classified cloud map data is preprocessed to obtain structured data in the range of [0,1 ].
Specifically, the feature extraction and feature fusion of the preprocessed cloud image data through the Gabor filter to obtain the Gabor feature coded image further includes:
the two-dimensional Gabor function is defined by the following formula:
performing convolution calculation on the cloud image to obtain the following convolution results:
the convolved image amplitudes were taken as the following Gabor features of the cloud:
wherein (A), (B), (C), (B), (C), (B), (C), (B), (C)x,y) For the given position coordinates it is possible to provide,
is the center frequency of the Gabor filter,
for the phase angles of filters in different directions, the Gabor filter bank selects 8 different directions
And 5 different scales
，k max =π/2；
As a result of the convolution, a convolution operator,z=(x,y)，real(O μ v,(z) ) andimag(O μ v,(z) Respectively, the real and imaginary parts of the convolution result.
(1) Gabor filter feature extraction
1) Feature extraction
Based on the further improvement of the method, the step of performing feature extraction of cloud image textures on the preprocessed cloud image data through a Gabor filter further comprises the following steps: the two-dimensional Gabor function is defined by the following formula:
wherein (A), (B), (C), (B), (C), (B), (C), (B), (C)x,y) For the given position coordinates it is possible to provide,
is the center frequency of the Gabor filter,
for the phase angles of filters in different directions, the Gabor filter bank selects 8 different directions
And 5 different scales
，k max =π/2。
Suppose the cloud image isI（x,y) The filter bank with 8 directions and 5 scales formed by the Gabor filter is recorded asG μ v,(x,y) Then, thenI（x,y) And Gabor functionG μ v,Is convoluted into
In the formula:O μ v,(z) As a result of the convolution, a convolution operator,z=(x,y)。
the amplitude information reflects the energy spectrum of the cloud image, and the amplitude response of the convolution image is taken as the output characteristic
In the formula (I), the compound is shown in the specification,C μ v,(z) Is the amplitude characteristic of the cloud picture,real(O μ v,(z) ) andimag(O μ v,(z) Respectively as the real part and the imaginary part of the convolution result, and each cloud image is converted into feature images with 5 scales and 8 directions through Gabor feature extraction, so as to realize cloud image feature level data enhancement.
2) Feature fusion
Firstly, fusing Gabor characteristics in 8 directions of the same scale, and calculating an average value of characteristic amplitude values by adopting a mode:
using avgvFor threshold value, performing binary transformation on each Gabor characteristic amplitude value, and assigning a weight value of 2 to each bit binary code s (x)pObtaining a decimal code value rv (z) epsilon [0, 255) representing the fused feature]
Secondly, 5 scales of Gabor features are fused:
(2) convolutional neural network
Based on the further improvement of the method, the Gabor characteristic diagram obtained by the coding is subjected to cloud image type judgment by using a convolutional neural network, and the structure of the convolutional neural network comprises the following steps: an input layer, a convolutional layer, an activation function, a pooling layer, a full-link layer, and an output layer, wherein,
1) input layer
Input layer of convolutional neural network is Gabor characteristic coding image
。
2) Convolutional layer (refer to fig. 6)
The formula of the convolution operation is:
wherein the content of the first and second substances,
which represents the calculation of the convolution,Frepresents the input of the convolutional layer(s),wis a parameter of the convolution filter;H f 、W f respectively the height and width of the convolution filter,Cis the number of channels;Pin order to fill in the dimension for the edges,H、Wheight and width of the input data;H conv 、W conv the height and width of a feature map formed after convolution calculation is carried out on the image;Sis the step size of the filter movement; the Relu activation function is used for the convolutional layer operation activation function,
3) pooling layer
The pooling layer is not a network layer in a strict sense, because the pooling layer has no parameters to be learned, and only hyper-parameters such as pooling type, kernel size, step size and the like need to be set. The pooling operation is actually a down-sampling, which plays a role in feature dimension reduction and also has a role in reducing overfitting in a certain sense. The fully connected layer can map the feature map to a sample mark space, which is equivalent to the function of a classifier.
4) Full connection layer
All neurons between the two layers have weighted connections, and the fully connected layer is usually at the tail of the convolutional neural network.
5) Output layer
The classified cloud data are denoted by 1, 2, 3 and 4.
And S108, fusing the classified cloud picture data with other meteorological data to form a meteorological data set.
Step S110, establishing a load prediction model of the BP neural network, wherein a meteorological data set is used as the input of the BP neural network, and the actual load of a meteorological partition corresponding to the meteorological data is used as the output to train the load prediction model. The BP neural network comprises: an input layer, an intermediate hidden layer, and an output layer.
The input vectors for the input layer are:
wherein when
When the temperature of the water is higher than the set temperature,x 1the load at the same time on the previous day;x 2is the temperature;x 3is the relative humidity;x 4the rainfall is shown;x 5is a date type;x 6of the cloud picture type.
The output vector of the intermediate hidden layer is:
the output vector of the output layer is: and actual load of the meteorological partition corresponding to the moment to be predicted.
And the output vector is the load of the meteorological partition corresponding to the moment to be predicted, which is obtained by calculating by using a load prediction model.
The vector of expected outputs is:
by adjusting the weight of the BP neural network, the output vector of the output layer continuously approaches the expected output vector, and the training of the BP neural network is completed. Predicting the load at a certain future moment, performing structured processing on the cloud image data at the moment, fusing factors such as unstructured meteorology and load as the input of a BP neural network, wherein the output vector of the network is the predicted value of the load at the moment.
The algorithm steps of the BP neural network comprise: initializing a network, selecting a random number in a (-1, 1) interval to assign values to each connection weight of the network, and setting an error and the maximum iteration number of the network;
training network model
The output of the intermediate hidden layer is:
wherein the content of the first and second substances,j=1,2,…,m，
the output of the output layer is:
wherein the content of the first and second substances,k=1,2,…,l，
function(s)f 1、f 2All transfer functions ofSigmoidFunction:
calculating error functions for each layer based on the desired output and the actual output:
for the input layer, the error function is:
error calculation and adjustment of network weights using error back-propagation:
the error signal is derived as:
by continuously adjusting the weights, the error is continuously reduced:
calculating a global error:
according to whether the global error reaches the accuracy of initial setting or whether the training times reach the maximum iteration times of the initial setting, and the algorithm is ended; otherwise, the error function of each layer, the network weight adjustment and the global error calculation are continuously calculated. Wherein the content of the first and second substances,w ij the connection weights between the input layer and hidden layer neurons,v jk is the connection weight between the neurons of the output layer,d i to output the desired output of the neuron, the hidden layer stimulus function isf 1The excitation function of the output layer isf 1，eIs an error function.
In step S112, the trained load prediction model is used to predict the load of each meteorological partition. And (5) repeating the step (S102), the step (S104), the step (S106), the step (S108) and the step (S110), establishing a BP neural network which is a prediction model, and setting the output vector of the BP neural network as the load corresponding to each meteorological partition at the moment to be predicted.
The invention discloses a regional power grid load prediction device. Hereinafter, the regional power grid load prediction apparatus will be described in detail with reference to fig. 5. The regional power grid load prediction device comprises: meteorological data determination module 502, preprocessing module 504, cloud classification discriminant model 506, fusion module 508, and load prediction model 510.
The meteorological data determining module 502 is configured to determine meteorological data of an influence load in each meteorological partition in a regional power grid, where the meteorological data includes air pressure, temperature, precipitation, relative humidity, wind speed, wind direction, date type, and cloud map data, and the cloud map data is obtained by shooting with an all-sky imager.
The preprocessing module 504 is used for preprocessing meteorological data. The pre-processing module 504 is configured to: processing abnormal meteorological data by a moving average method; normalizing the weather data using a max-min method to convert the weather data into data in a range of [0,1], wherein tuesday to thursday in the date type are converted into a numerical value of 0.2, monday to friday are converted into a numerical value of 0.4, and saturday to sunday are converted into a numerical value of 0.6, and statutory holidays are converted into a numerical value of 0.8 to 1; and carrying out gray processing on the collected color cloud picture data to generate cloud picture data of red-green-blue three bands.
The cloud image classification and discrimination model 506 is used for establishing a cloud image classification and discrimination model of the Gabor filter-convolutional neural network, and predicting and classifying the preprocessed cloud image data by using the discrimination model. The fusion module 508 is configured to fuse the classified cloud image data with other meteorological data to form a meteorological data set. A load prediction model 510, configured to establish a BP neural network to obtain a load prediction model, where a meteorological data set is used as an input of the BP neural network, and a load of a meteorological partition corresponding to the meteorological data is used as an output; and predicting the load of each meteorological partition by using the load prediction model.
Hereinafter, the regional power grid load prediction method will be described in detail by way of specific examples with reference to fig. 2 to 4.
With the continuous development of weather related technologies, the weather big data provides rich weather data information, including air pressure, air temperature, precipitation, relative humidity, wind speed, wind direction, satellite cloud pictures, radar jigsaw puzzle, and the like. The structured data and the unstructured meteorological data are fused, a complex mapping relation between a composite data system and the load is constructed, the influence of the unstructured meteorological data on the load is fully mined, and the short-term load prediction accuracy of the regional power grid is improved.
The invention provides a regional power grid short-term load prediction method fusing multi-source heterogeneous meteorological data. The method mainly comprises the following steps: a. the method comprises the steps of building load influence factors, b, preparing data, c, preprocessing the data, d, building a prediction model, and e, evaluating the effectiveness of the model. The specific contents are as follows:
a. and constructing load influence factors. Mainly comprises structured data: load, temperature, relative humidity, rainfall, type of date (holiday, working day) of t-1, t-2, t-3 (t is 15 minutes to 1 hour, e.g. 15 minutes one time, 96 points of the whole day). Unstructured data: cloud pictures (cloud of rain, cloud of convolution).
Short term loading is sensitive to temperature, relative humidity, rainfall, date type. The temperature has direct influence on short-term electricity load, the temperature rises in summer, the air conditioning load increases, the temperature falls in winter, and the heating load increases. The relative humidity and the rainfall affect the comfort of the human body, and further affect the power load. The date type data is introduced into the model in consideration of the large difference between the working day load and the holiday load data (acquired from the power grid dispatching system), so that the load levels under different date types can be effectively distinguished. The cloud layer shields the sun in a short time period, changes the radiation quantity of the sun on the ground, directly influences the comfort of a human body, agriculture and partial industrial electricity, is particularly obvious in summer and winter, and can cause the load to change in a short time. In addition, precipitation can be generated in a short time by part of cloud pictures, the load of the regional power grid can change rapidly in a short time, and the influence of the rapidly changing cloud on the load can be reflected to a certain extent by the introduction of cloud picture data.
And (4) preparing data. Considering that the difference of temperature, humidity, rainfall and the like exists between different areas in the same area power grid, if the load of the whole area power grid and the average temperature, humidity and rainfall of the whole area are modeled, because the granularity of meteorological factor data adopted by the model is large, the model cannot well explain the complex causal change relationship between meteorological factors (influencing factors) and loads (prediction indexes), and the prediction precision is greatly influenced. Therefore, according to the meteorological data area division (generally consistent with the administrative area division), the full network load is decomposed into the subarea power network load which is consistent with the meteorological subareas, and the spatial consistency of the meteorological factors in the meteorological subareas and the subarea power network load data is ensured. For example, a regional power grid has N meteorological partitions, which split the grid load into N loads, one for each partition. Since the data period of the short-term load of the regional power grid is generally 15 minutes (alternatively, 30 minutes, 1 hour, and the like), the meteorological data acquisition period is set to be 15 minutes (alternatively, 30 minutes, 1 hour, and the like) synchronously, and the consistency of the meteorological data and the load data in time is ensured. Therefore, the load data and the meteorological data are kept synchronous on a space-time scale, and a basic data set for regional power grid load prediction is established.
The cloud image data processing method will be explained below. And similarly, according to the meteorological region division, dividing the region covered by the regional power grid into equal-proportion sizes, and capturing the cloud pictures in each partition every 15 minutes (optionally, 30 minutes, 1 hour and the like) based on the dynamically-changed meteorological cloud pictures to ensure the consistency of the cloud picture data and the meteorological data on the time acquisition dimension and the spatial region dimension. The cloud picture is shot by an all-sky imager, and a shooting lens and a digital imaging system are utilized to regularly shoot and obtain all-sky visible light red, green and blue three-band images, and a shooting range consistent with an area range is set, so that the coverage range of the cloud picture is ensured to be consistent with the area range.
And (4) preprocessing data. Factors affecting the short-term load of the regional power grid and data of missing or abnormal load easily interfere with model training, and further affect the accuracy of load prediction. In addition, the different index dimensions of different influencing factors need to be subjected to non-dimensionalization treatment before being input into the model for analysis and prediction. The data preprocessing mainly comprises true abnormal data processing and data normalization processing.
And (5) processing abnormal data. In the process of collecting, transmitting and storing the mass historical data of load prediction, due to equipment or human factors, abnormal data values such as data with large deviation or default data can be generated, the abnormal data can influence the result of data analysis, and the error of a prediction model is increased. The technical scheme adopts a moving average method to process index data and setxIn order to observe the data, it is,tthe time data exception is really processed as follows:
c2 data normalization processing
Numerical data processing: for this type of data, the data was normalized using the max-min method, and the calculation is disclosed as follows:
wherein x is the original numerical data.
Date type digitization processing: tuesday to Thursday are mapped to 0.2, Monday and Friday are both mapped to 0.4, Saturday and Sunday are mapped to 0.6, and minor-major hypothesis is mapped to 0.8-1 as the case may be.
Cloud graph data processing
Graying treatment: the cloud picture preprocessing is mainly used for graying the image. Carrying out gray processing on the collected color image to reduce the complexity of pixel point color, adopting YUV gray processing, and disclosing as follows:
load prediction model construction
The prediction model is a key link of load prediction, and the quality of the model design determines the precision of the load prediction. In consideration of the advantage of the neural network prediction model for linear and nonlinear influence factors, the technical scheme provides a series two-stage hybrid neural network prediction model. The technical scheme designs a proper network structure and a proper model depth by fully considering the data input by the model and the data scale.
The first stage is as follows: and designing a cloud image classification model discrimination model of the Gabor filter-convolution neural network, and performing prediction classification processing on the cloud image subjected to data preprocessing.
And a second stage: and splicing the cloud image classification data obtained in the first stage with other structured data to form a new data set, taking the set data as the input of a BP neural network, taking the regional power grid load as the output of a model, carrying out network training, and finally predicting the regional power grid load.
Constructing a model:
the first stage is as follows: cloud image classification and discrimination model of Gabor filter-convolution neural network
The technical scheme mainly focuses on the shielding condition of light rays in a short time and the probability of rainfall which may be generated, and divides the cloud picture into four types of clear clouds, rainy clouds, ponding clouds and other clouds.
Raining layer cloud: belongs to a low cloud group, is dark gray, does not strike thunder or flash, is spread all day long, and completely shields the light of the sun and the moon.
Rain and cloud accumulation: belonging to the low cloud family, can bring various degrees of rainfall, and sometimes even can generate tornadoes and strong outward whirlwind airflow.
Volume cloud: the sky is mainly the rolling cloud, and is accompanied by the common development and change of the rolling cloud and the rolling cloud, which indicates the coming of the rainstorm weather.
Non-raining clouds: not belonging to the category of clear, rainy layer cloud, accumulated rain cloud and rolling accumulated cloud.
The method adopts a Gabor filter technology to extract the features of the cloud picture texture, and then performs key feature mapping based on a Convolutional Neural Network (CNN) to realize the classification and the discrimination of the cloud picture.
The Gabor filter is an effective tool for extracting spatial local texture features, and is essentially a short-time fourier transform with a window function being a gaussian function. In the space domain, the two-dimensional Gabor filter is a sinusoidal plane wave modulated by Gaussian envelope, and can perform local and directional frequency analysis on two-dimensional information, so that extraction of texture information is realized. The two-dimensional Gabor function is defined by the following formula:
wherein (A), (B), (C), (B), (C), (B), (C), (B), (C)x,y) For the given position coordinates it is possible to provide,
is the center frequency of the Gabor filter,
for the phase angles of filters in different directions, the Gabor filter bank selects 8 different directions
And 5 different scales
，k max =π/2。
Suppose the cloud image isI（x,y) The filter bank with 8 directions and 5 scales formed by the Gabor filter is recorded as
G μ v ,(x,y) Then, thenI（x,y) And Gabor functionG μ v,Is convoluted into
In the formula:O μ v,(z) As a result of the convolution, a convolution operator,z=(x,y)。
the amplitude information reflects the energy spectrum of the cloud image, and the amplitude response of the convolution image is taken as the output characteristic
In the formula (I), the compound is shown in the specification,C μ v,(z) Is the amplitude characteristic of the cloud picture,real(O μ v,(z) ) andimag(O μ v,(z) Respectively as the real part and the imaginary part of the convolution result, and each cloud image is converted into feature images with 5 scales and 8 directions through Gabor feature extraction, so as to realize cloud image feature level data enhancement.
2) Feature fusion
Firstly, fusing Gabor characteristics in 8 directions of the same scale, and calculating an average value of characteristic amplitude values by adopting a mode:
using avgvFor threshold value, performing binary transformation on each Gabor characteristic amplitude value, and assigning a weight value of 2 to each bit binary code s (x)pObtaining a decimal code value rv (z) epsilon [0, 255) representing the fused feature]
Secondly, 5 scales of Gabor features are fused:
the method effectively reduces the feature dimension on the premise of not reducing the image texture feature information so as to carry out multi-scale analysis. And taking the processed feature fusion coding result as the input of the convolutional neural network to construct a deep convolutional neural network model.
The convolutional neural network is a deep neural network, and can better distinguish and process images. The convolutional neural network has two important characteristics of local connection and weight sharing, the parameter quantity of the model is greatly reduced compared with the fully-connected neural network, and the problems of gradient disappearance or explosion and overfitting of the deep neural network can be effectively solved. As shown in fig. 2, the convolutional neural network structure is composed of an input layer, a convolutional layer, an activation function, a pooling layer, a full-link layer, and an output layer.
The convolutional neural network convolutional layer mainly utilizes a convolutional filter to carry out convolutional operation, each feature in the picture is firstly locally sensed, and then comprehensive operation is carried out on the local feature at a higher level, so that global information is extracted, and key features of the picture are obtained.
The formula of the convolution layer's calculation principle convolution operation is as follows:
wherein the content of the first and second substances,
which represents the calculation of the convolution,Frepresents the input of the convolutional layer(s),wis a parameter of the convolution filter;H f 、W f respectively the height and width of the convolution filter,Cis the number of channels;Pin order to fill in the dimension for the edges,H、Wheight and width of the input data;H conv 、W conv the height and width of a feature map formed after convolution calculation is carried out on the image;Sis the step size of the filter movement.
The pooling layer mainly divides the feature plane after convolution into a plurality of sub-blocks, and extracts features on each sub-block to construct a new feature plane, so that the pooling layer can remarkably reduce the size of the feature plane, greatly reduce the complex calculation amount and simultaneously avoid excessive information loss. The common pooling mode is the most important characteristic method and the average characteristic method, and the technical specification scheme adopts the maximum characteristic method to carry out pooling operation.
Relu activation functions are used for convolutional layer operation activation functions, and the role of Relu is to enhance the nonlinearity of the network for better generalization capability. For every negative value in the image, the Relu function returns a value of 0, and for every positive value, returns a value of 1, as shown by the equation:
and a second stage: BP neural network model based on multi-source heterogeneous meteorological data fusion
The method comprises the steps of carrying out sample splicing on preprocessed structured meteorological data, first-stage processed unstructured meteorological data, load and date type data and the like to form the input of a BP neural network, constructing a BP neural network model based on multi-source heterogeneous meteorological data fusion, and predicting the short-term load of a regional power grid based on the trained model.
The BP neural network belongs to a multilayer feedforward neural network, has strong nonlinear mapping capability, and is mainly used for scenes such as function fitting, model identification and classification, time sequence prediction and the like. The BP neural network is composed of an input layer, a middle hidden layer and an output layer, and the topological structure of the BP neural network is shown in figure 3.
A typical BP neural network is a three-layer network model. The input vector formed by the structured image data, the load data, the date type data after data preprocessing and the non-structured image cloud picture data after first-stage processing is set as
Wherein when
When the temperature of the water is higher than the set temperature,x 1the load at the same time on the previous day;x 2is the temperature;x 3is relative toHumidity;x 4the rainfall is shown;x 5is a date type;x 6of the cloud picture type.
The output vector of the hidden layer is
The output layer outputs a vector of
The vector of the desired output is
The method adopts a back propagation algorithm to carry out optimization, the basic principle of the algorithm is that a signal of an error is used between an actual output value and an expected output value, the error signal is back propagated from an output layer by layer, the weight is continuously adjusted in a re-propagation process, the error is continuously reduced, and finally the weight is continuously corrected, so that the result of the neural network is closer to the expected output.
The BP neural network algorithm comprises the following steps:
the method comprises the following steps: the network is initialized. And selecting random numbers in the (-1, 1) interval to assign values to each connection weight of the network, and setting the error and the maximum iteration number of the network.
Step two: training network model
(1) Output of hidden layer
Wherein the content of the first and second substances,j=1,2,…,m，
(2) output of the output layer
Wherein the content of the first and second substances,k=1,2,…,l，
function(s)f 1、f 2All transfer functions ofSigmoidFunction(s)
f(x) Continuously and derivable, derivatives of
Step three: calculating error functions of the layers for the desired output to the actual output
For the input layer, the error function is
Step four: error calculation and network weight adjustment by using the idea of error back propagation
Further deriving an error signal of
Continuously adjusting the weight to reduce the error, and adjusting the weight to make the error in the gradient descending direction proportional, which is expressed by the following formula
Step five: calculating global error
Wherein the content of the first and second substances,w ij the connection weights between the input layer and hidden layer neurons,v jk is the connection weight between the neurons of the output layer,d i to output the desired output of the neuron, the hidden layer stimulus function isf 1The excitation function of the output layer isf 1，eIs an error function.
Step six: and finishing the process according to the judgment basis. Judging whether the global error reaches the accuracy of initial setting or judging whether the training times reaches the maximum iteration times of the initial setting, and if so, finishing the algorithm; if not, the operation needs to be continued in the third step.
The technical scheme provides a regional power grid short-term load prediction method integrating multi-source heterogeneous meteorological data, and the flow is shown in the figure. FIG. 4 is a flow of a regional power grid short-term load prediction method fusing multi-source heterogeneous meteorological data.
e. Evaluation of model validity
To evaluate the prediction accuracy of the present solution, the average absolute percentage error (c) is used hereiny MAPE ) And root mean square error: (y RMSE ) And evaluating the performance of the prediction model by using the two error evaluation indexes. The smaller the calculated values of the above, the more accurate the load prediction result.
nIs the total number of the prediction results;y real (i)、y fore (i) Is as followsiThe actual value and the predicted value of the load at each time.
Compared with the prior art, the invention can realize at least one of the following beneficial effects:
1. the cloud picture image is shot and obtained through an all-sky imager, and all-sky visible light red, green and blue three-band image data are shot and obtained at regular time through a shooting lens and a digital imaging system; preprocessing meteorological data; and establishing a cloud image classification and discrimination model of the Gabor filter-convolution neural network, and classifying the preprocessed cloud image data (namely, the unstructured data) by using the discrimination model so as to convert the cloud image data into the structured data. Fusing the classified cloud map data (i.e., structured data) with other meteorological data (i.e., structured data) to form a meteorological data set; the load of each meteorological partition is predicted by using the load prediction model, with the meteorological data set as an input and the loads of the meteorological partitions corresponding to the meteorological data as an output.
2. The structured meteorological data and the unstructured meteorological data are fused, a complex mapping relation between a composite data system and the load is constructed, the influence of the unstructured meteorological data on the load is fully mined, and the short-term load prediction accuracy of the regional power grid is improved.
3. The feature dimension is effectively reduced by using the sum of binary codes in each direction on the premise of not reducing image texture feature information so as to carry out multi-scale analysis. And taking the processed feature fusion coding result as the input of the convolutional neural network to construct a deep convolutional neural network model.
Those skilled in the art will appreciate that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program, which is stored in a computer readable storage medium, to instruct related hardware. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (8)
1. A regional power grid load prediction method is characterized by comprising the following steps:
determining meteorological data influencing loads in each meteorological partition in the regional power grid, wherein the meteorological data comprise air pressure, temperature, precipitation, relative humidity, wind speed, wind direction, date type and cloud map data, and the cloud map data are obtained by shooting through an all-sky imager;
preprocessing the meteorological data;
establishing a Gabor filter-convolutional neural network cloud image classification discrimination model, and performing prediction classification processing on preprocessed cloud image data by using the discrimination model, wherein the classified cloud image data comprises a rainy layer cloud, a rain cloud, a convolutional cloud and a non-raining cloud, and the classified cloud image data is represented by 1, 2, 3 and 4 respectively, and is preprocessed to obtain structural data in a range of [0,1], wherein the step of performing feature extraction and feature fusion on the preprocessed cloud image data through a Gabor filter to obtain a Gabor feature coding image further comprises the steps of:
the two-dimensional Gabor function is defined by the following formula:
performing convolution calculation on the cloud image to obtain the following convolution results:
taking the amplitude of the convolved image as the following Gabor characteristics of the cloud image:
wherein (A), (B), (C), (B), (C), (B), (C), (B), (C)x,y) For the given position coordinates it is possible to provide,
is the center frequency of the Gabor filter,
for the phase angles of filters in different directions, the Gabor filter bank selects 8 different directions
And 5 different scales
，k max =π/2；O μ v,(z) As a result of the convolution, a convolution operator,z=(x,y)，real(O μ v,(z) ) andimag(O μ v,(z) Respectively the real and imaginary parts of the convolution result; fusing the Gabor features of 8 directions and 5 scales to obtain a Gabor feature coded image;
fusing the classified cloud picture data with other meteorological data to form a meteorological data set;
establishing a load prediction model of a BP neural network, wherein the meteorological data set is used as the input of the BP neural network, and the load of a meteorological partition corresponding to the meteorological data is used as the output; and
and predicting the load of each meteorological partition by using the load prediction model.
2. The regional power grid load prediction method of claim 1, wherein preprocessing the meteorological data comprises:
processing abnormal meteorological data by a moving average method;
normalizing the weather data using a max-min method to convert the weather data into data in a range of [0,1], wherein tuesday to thursday in a date type is converted into a numerical value of 0.2, monday to friday is converted into a numerical value of 0.4, and saturday to sunday is converted into a numerical value of 0.6, and a statutory holiday is converted into a numerical value of 0.8 to 1; and
and carrying out gray processing on the collected color cloud image data to generate cloud image data of red-green-blue three bands.
3. The regional power grid load prediction method according to claim 1, wherein the performing prediction classification processing on the preprocessed cloud image data by using the discriminant model further comprises: performing key feature mapping based on a convolutional neural network to classify the preprocessed cloud data.
4. The regional power grid load prediction method of claim 1, wherein the structure of the convolutional neural network comprises: an input layer, a convolutional layer, a pooling layer, a full-link layer, and an output layer, wherein,
the input layer receives a Gabor feature coded image;
the convolutional layer, configured to perform a convolution operation by the following formula and use a Relu activation function for the convolutional layer:
wherein the content of the first and second substances,
which represents the calculation of the convolution,Frepresents the input of the convolutional layer(s),wis a parameter of the convolution filter;H f 、W f respectively the height and width of the convolution filter,Cis the number of channels;Pin order to fill in the dimension for the edges,H、Wheight and width of the input data;H conv 、 W conv the height and width of a feature map formed after convolution calculation is carried out on the image;Sis the step size of the filter movement; the Relu activation function is as follows:
the pooling layer is used for performing feature dimension reduction and reducing overfitting;
the full connection layer is used for mapping the characteristic diagram to a sample mark space so as to classify the cloud diagram data; and
and the output layer is used for outputting the classified cloud picture data.
5. The regional power grid load prediction method of claim 3, wherein the BP neural network comprises: an input layer, an intermediate hidden layer and an output layer,
the input vectors of the input layer are:
wherein whennWhen the number of the carbon atoms is not less than 6,x 1the load at the same time on the previous day;x 2is the temperature;x 3is the relative humidity;x 4the rainfall is shown;x 5is a date type;x 6is of cloud picture type;
the output vector of the intermediate hidden layer is:
wherein the output vector is a predicted load of the corresponding weather partition;
the output vector of the output layer is:
the vector of expected outputs is:
6. the regional power grid load prediction method of claim 5, wherein the algorithm step of the BP neural network comprises:
initializing a network, selecting a random number in a (-1, 1) interval to assign values to each connection weight of the network, and setting an error and the maximum iteration number of the network;
training a network model:
the output of the intermediate hidden layer is:
wherein the content of the first and second substances,j=1,2,…,m，
the output of the output layer is:
wherein the content of the first and second substances,k=1,2,…,l，
function(s)f 1、f 2All transfer functions ofSigmoidFunction:
calculating error functions for each layer based on the desired output and the actual output:
for the input layer, the error function is:
error calculation and adjustment of network weights using error back-propagation:
the error signal is derived as:
the error is continuously reduced by continuously adjusting the weights as follows:
calculating a global error:
according to whether the global error reaches the accuracy of initial setting or whether the training times reach the maximum iteration times of the initial setting, and the algorithm is ended; otherwise, the error function of each layer, the network weight adjustment and the global error calculation are continued, wherein,w ij the connection weights between the input layer and hidden layer neurons,v jk is the connection weight between the neurons of the output layer,d i to output the desired output of the neuron, the hidden layer is stimulatedFunction is asf 1The excitation function of the output layer isf 2，eIs an error function.
7. A regional power grid load prediction apparatus, comprising:
the system comprises a meteorological data determining module, a cloud image acquiring module and a load monitoring module, wherein the meteorological data determining module is used for determining meteorological data of influencing loads in each meteorological partition in the regional power grid, the meteorological data comprise air pressure, temperature, precipitation, relative humidity, wind speed, wind direction, date type and cloud image data, and the cloud image data are acquired through shooting of an all-sky imager;
the preprocessing module is used for preprocessing the meteorological data;
a cloud image classification and discrimination model, configured to establish a cloud image classification and discrimination model of a Gabor filter-convolutional neural network, and perform prediction classification processing on preprocessed cloud image data by using the discrimination model, where the classified cloud image data includes a rainy layer cloud, a rain cloud, a rolling cloud, and a non-raining cloud, and are represented by 1, 2, 3, and 4, respectively, where the classified cloud image data is preprocessed to obtain structured data in a [0,1] range, and where performing feature extraction and feature fusion on the preprocessed cloud image data through a Gabor filter to obtain a Gabor feature coded image further includes:
the two-dimensional Gabor function is defined by the following formula:
performing convolution calculation on the cloud image to obtain the following convolution results:
taking the amplitude of the convolved image as the following Gabor characteristics of the cloud image:
wherein (A), (B), (C), (B), (C), (B), (C), (B), (C)x,y) For the given position coordinates it is possible to provide,
is the center frequency of the Gabor filter,
for the phase angles of filters in different directions, the Gabor filter bank selects 8 different directions
And 5 different scales
，k max =π/2；O μ v,(z) As a result of the convolution, a convolution operator,z=(x,y)，real(O μ v,(z) ) andimag(O μ v,(z) Respectively the real and imaginary parts of the convolution result; fusing the Gabor features of 8 directions and 5 scales to obtain a Gabor feature coded image;
the fusion module is used for fusing the classified cloud picture data with other meteorological data to form a meteorological data set; and
the load prediction model is used for establishing a load prediction model of a BP (back propagation) neural network, wherein the meteorological data set is used as the input of the BP neural network, and the load of a meteorological partition corresponding to the meteorological data is used as the output; and predicting the load of each meteorological partition by using the load prediction model.
8. The regional power grid load prediction device of claim 7, wherein the preprocessing module is configured to:
processing abnormal meteorological data by a moving average method;
normalizing the weather data using a max-min method to convert the weather data into data in a range of [0,1], wherein tuesday to thursday in a date type is converted into a numerical value of 0.2, monday to friday is converted into a numerical value of 0.4, and saturday to sunday is converted into a numerical value of 0.6, and a statutory holiday is converted into a numerical value of 0.8 to 1; and
and carrying out gray processing on the collected color cloud image data to generate cloud image data of red-green-blue three bands.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111184364.6A CN113642677B (en) | 2021-10-12 | 2021-10-12 | Regional power grid load prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111184364.6A CN113642677B (en) | 2021-10-12 | 2021-10-12 | Regional power grid load prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113642677A CN113642677A (en) | 2021-11-12 |
| CN113642677B true CN113642677B (en) | 2022-02-22 |
Family
ID=78426496
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111184364.6A Active CN113642677B (en) | 2021-10-12 | 2021-10-12 | Regional power grid load prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642677B (en) |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678406A (en) * | 2015-12-31 | 2016-06-15 | 国网湖北省电力公司 | Short-term load prediction method based on cloud model |
| US20200111174A1 (en) * | 2018-10-04 | 2020-04-09 | Yishen Wang | Probabilistic Load Forecasting via Point Forecast Feature Integration |
| CN113256022B (en) * | 2021-06-16 | 2023-02-24 | 广东电网有限责任公司 | Method and system for predicting electric load of transformer area |
-
2021
- 2021-10-12 CN CN202111184364.6A patent/CN113642677B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113642677A (en) | 2021-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113609889B (en) | High-resolution remote sensing image vegetation extraction method based on sensitive characteristic focusing perception | |
| CN115223063B (en) | Deep learning-based unmanned aerial vehicle remote sensing wheat new variety lodging area extraction method and system | |
| CN113391607A (en) | Hydropower station gate control method and system based on deep learning | |
| CN112712033B (en) | Automatic division method for catchment areas of municipal drainage pipe network | |
| CN115861619A (en) | Airborne LiDAR (light detection and ranging) urban point cloud semantic segmentation method and system of recursive residual double-attention kernel point convolution network | |
| CN115272848B (en) | Intelligent change detection method for buildings in multi-cloud and multi-fog farmland protection area | |
| CN112950780A (en) | Intelligent network map generation method and system based on remote sensing image | |
| Sardar et al. | Convolution neural network-based agriculture drought prediction using satellite images | |
| CN111640087A (en) | Image change detection method based on SAR (synthetic aperture radar) deep full convolution neural network | |
| CN215813842U (en) | Hydropower station gate control system based on deep learning | |
| CN115019163A (en) | City factor identification method based on multi-source big data | |
| CN112861802B (en) | Full-automatic crop classification method based on space-time deep learning fusion technology | |
| Yan et al. | Estimation of urban-scale photovoltaic potential: A deep learning-based approach for constructing three-dimensional building models from optical remote sensing imagery | |
| Filippi et al. | Self-organizing map-based applications in remote sensing | |
| CN113642677B (en) | Regional power grid load prediction method and device | |
| CN113591608A (en) | High-resolution remote sensing image impervious surface extraction method based on deep learning | |
| CN117237660A (en) | Point cloud data processing and segmentation method based on deep learning feature aggregation | |
| CN110533118B (en) | Remote sensing image sparse representation classification method based on multi-core learning | |
| CN112446256A (en) | Vegetation type identification method based on deep ISA data fusion | |
| Amakhchan et al. | Automatic filtering of LiDAR building point cloud using multilayer perceptron Neuron Network | |
| CN116343058A (en) | Global collaborative fusion-based multispectral and panchromatic satellite image earth surface classification method | |
| CN113642676B (en) | Regional power grid load prediction method and device based on heterogeneous meteorological data fusion | |
| Jing et al. | Time series land cover classification based on semi-supervised convolutional long short-term memory neural networks | |
| Rathnayake et al. | Performance of neural networks in forecasting short range occurrence of rainfall | |
| Maheswari et al. | Fused LISS IV Image Classification using Deep Convolution Neural Networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |