CN115622029A - Power transmission line icing load prediction method and device, storage medium and equipment - Google Patents
Power transmission line icing load prediction method and device, storage medium and equipment Download PDFInfo
- Publication number
- CN115622029A CN115622029A CN202211181005.XA CN202211181005A CN115622029A CN 115622029 A CN115622029 A CN 115622029A CN 202211181005 A CN202211181005 A CN 202211181005A CN 115622029 A CN115622029 A CN 115622029A
- Authority
- CN
- China
- Prior art keywords
- frequency
- training set
- data
- low
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000005540 biological transmission Effects 0.000 title claims abstract description 38
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 35
- 238000012549 training Methods 0.000 claims description 163
- 238000004590 computer program Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 239000011248 coating agent Substances 0.000 claims description 6
- 238000000576 coating method Methods 0.000 claims description 6
- 125000004122 cyclic group Chemical group 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 8
- 230000015572 biosynthetic process Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 208000011580 syndromic disease Diseases 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a method, a device, a storage medium and equipment for predicting icing load of a power transmission line, wherein the method comprises the following steps: acquiring a real-time data set, and performing VMD decomposition on the real-time data set to obtain a high-frequency real-time data set, a medium-frequency real-time data set and a low-frequency real-time data set; inputting the high-frequency real-time data set, the intermediate-frequency real-time data set and the low-frequency real-time data set into a pre-trained high-frequency prediction module, a pre-trained intermediate-frequency prediction model and a pre-trained low-frequency prediction model respectively to obtain a high-frequency prediction value, an intermediate-frequency prediction value and a low-frequency prediction value; and acquiring corresponding icing load prediction data according to the high-frequency prediction value, the medium-frequency prediction value and the low-frequency prediction value. According to the method and the device, the accuracy of the prediction of the icing load of the power transmission line can be improved.
Description
Technical Field
The application relates to the technical field of icing prediction, in particular to a method, a device, a storage medium and equipment for predicting icing load of a power transmission line.
Background
An existing method of icing prediction, comprising: 1. the mechanism model, studied from the kinetic and thermodynamic principles of ice coating formation. 2. And the statistical model is used for predicting through counting the development rule of ice coating.
In the above method, since the principle of ice coating formation is too complicated, the mechanism model parameters are difficult to obtain, and in addition, the ice coating formation has strong regional and climate differences. The mechanism model cannot adapt to the power transmission line with large climate and regional difference in practical application, an accurate prediction result cannot be obtained, and the application range is limited to a certain extent.
Because the icing influence factors are more, and meteorological data in the icing process are complex and changeable, the traditional statistical model is difficult to capture the development rule of the icing load.
Disclosure of Invention
The application aims to overcome the defects in the prior art, and provides a method, a device, a storage medium and equipment for predicting the icing load of a power transmission line, which can improve the accuracy of the icing load prediction of the power transmission line.
An embodiment of the present application provides a method for predicting an icing load of a power transmission line, including:
acquiring a real-time data set, and performing VMD decomposition on the real-time data set to obtain a high-frequency real-time data set, a medium-frequency real-time data set and a low-frequency real-time data set;
inputting the high-frequency real-time data set, the intermediate-frequency real-time data set and the low-frequency real-time data set into a pre-trained high-frequency prediction module, a pre-trained intermediate-frequency prediction model and a pre-trained low-frequency prediction model respectively to obtain a high-frequency prediction value, an intermediate-frequency prediction value and a low-frequency prediction value;
and acquiring corresponding icing load prediction data according to the high-frequency prediction value, the medium-frequency prediction value and the low-frequency prediction value.
Compared with the prior art, the method and the device have the advantages that the VMD decomposition algorithm is used for decomposing the real-time data set to obtain the high-frequency real-time data set, the medium-frequency real-time data set and the low-frequency real-time data set, then the high-frequency real-time data set, the medium-frequency real-time data set and the low-frequency real-time data set are input into the pre-trained high-frequency prediction module, the pre-trained medium-frequency prediction model and the pre-trained low-frequency prediction model to obtain the high-frequency prediction value, the medium-frequency prediction value and the low-frequency prediction value, so that corresponding icing load prediction data are obtained, the icing load of the power transmission line is predicted, the mutual influence of data of different scales can be reduced, and the accuracy of the icing load prediction of the power transmission line is improved.
Further, the high frequency prediction module, the medium frequency prediction model and the low frequency prediction model are obtained by training through the following steps:
acquiring a data training set; the data training set comprises an off-line training set and an on-line training set;
performing VMD decomposition on the data training set to obtain a high-frequency training set, a medium-frequency training set and a low-frequency training set;
and training three initial convolutional neural networks according to the high-frequency training set, the medium-frequency training set and the low-frequency training set to obtain the high-frequency prediction module, the medium-frequency prediction model and the low-frequency prediction model.
And performing VMD decomposition on the data training set, and inputting the data training set into three initial convolutional neural networks for training respectively to obtain three independent prediction models, namely the high-frequency prediction module, the medium-frequency prediction model and the low-frequency prediction model.
Further, the step of obtaining a training set of data includes:
carrying out normalization processing on the sample data through the following formula to obtain normalized data:
wherein, a g For normalizing data, a is sample data, a max ,a min The maximum value and the minimum value of the sample data are respectively;
and generating the data training set according to the normalized data.
Through the normalization operation, the phenomenon that the numerical values observed by different characteristic variables are greatly different to cause 'large numbers eating small numbers' can be avoided.
Further, the step of performing VMD decomposition on the data training set to obtain a high frequency training set, a medium frequency training set, and a low frequency training set includes:
constructing a variation model according to the data sequence of the data training set:
wherein min is the minimum value; u. u k The k data is the evidence mode component; w is a k The center frequency of the evidence mode component of the kth data is taken as the center frequency of the evidence mode component of the kth data; d t Is the time derivative of the function; delta (t) is a unit impulse function; j is an imaginary unit; pi is the circumference ratio; e is a natural logarithm, and represents convolution operation; s.t. represents a constraint;
converting the variation model into an unconstrained variation model:
wherein L is the iteration number of the unconstrained variant model; alpha is a penalty factor; λ is the Lagrangian multiplier;
initialization u k 、w k Lambda and the iteration times of the unconstrained variant model, wherein the initial value of the iteration times of the unconstrained variant model is 0;
updating u by adopting a multiplier alternative algorithm according to a preset cyclic process k 、w k And lambda to obtain a high-frequency intrinsic mode component, an intermediate-frequency intrinsic mode component and a low-frequency intrinsic mode component of each data sequence of the data training set;
and obtaining the high-frequency training set, the intermediate-frequency training set and the low-frequency training set according to the high-frequency intrinsic-syndrome modal component, the intermediate-frequency intrinsic-syndrome modal component and the low-frequency intrinsic-syndrome modal component.
An embodiment of the present application further provides a power transmission line icing load prediction device, including:
the real-time data decomposition module is used for acquiring a real-time data set and performing VMD decomposition on the real-time data set to obtain a high-frequency real-time data set, a medium-frequency real-time data set and a low-frequency real-time data set;
the prediction data acquisition module is used for respectively inputting the high-frequency real-time data set, the intermediate-frequency real-time data set and the low-frequency real-time data set into the high-frequency prediction module, the intermediate-frequency prediction model and the low-frequency prediction model to obtain a high-frequency prediction value, an intermediate-frequency prediction value and a low-frequency prediction value;
and the icing load prediction module is used for obtaining corresponding icing load prediction data according to the high-frequency prediction value, the medium-frequency prediction value and the low-frequency prediction value.
Compared with the prior art, the method and the device have the advantages that the VMD decomposition algorithm is used for decomposing the real-time data set to obtain the high-frequency real-time data set, the medium-frequency real-time data set and the low-frequency real-time data set, then the high-frequency real-time data set, the medium-frequency real-time data set and the low-frequency real-time data set are input into the pre-trained high-frequency prediction module, the pre-trained medium-frequency prediction model and the pre-trained low-frequency prediction model to obtain the high-frequency prediction value, the medium-frequency prediction value and the low-frequency prediction value, so that corresponding icing load prediction data are obtained, the icing load of the power transmission line is predicted, the mutual influence of data of different scales can be reduced, and the accuracy of the icing load prediction of the power transmission line is improved.
Further, the method also comprises the following steps:
the training set acquisition module is used for acquiring a data training set; the data training set comprises an off-line training set and an on-line training set;
the training set decomposition module is used for performing VMD decomposition on the data training set to obtain a high-frequency training set, a medium-frequency training set and a low-frequency training set;
and the training module is used for training three initial convolutional neural networks according to the high-frequency training set, the medium-frequency training set and the low-frequency training set to obtain the high-frequency prediction module, the medium-frequency prediction model and the low-frequency prediction model.
And performing VMD decomposition on the data training set, and inputting the data training set into three initial convolutional neural networks for training respectively to obtain three independent prediction models, namely the high-frequency prediction module, the medium-frequency prediction model and the low-frequency prediction model.
Further, the training set acquisition module comprises:
carrying out normalization processing on the sample data through the following formula to obtain normalized data:
wherein, a g For normalizing data, a is sample data, a max ,a min The maximum value and the minimum value of the sample data are respectively;
and generating the data training set according to the normalized data.
Through the normalization operation, the phenomenon that the numerical values observed by different characteristic variables are greatly different to cause 'large numbers eating small numbers' can be avoided.
Further, the training set decomposition module comprises:
constructing a variation model according to the data sequence of the data training set:
wherein min is the minimum value; u. of k The k-th data is the evidence modal component; w is a k Center frequency of the evidence mode component for the k data；d t Is a time derivative of the function; delta (t) is a unit impulse function; j is an imaginary unit; pi is the circumference ratio; e is a natural logarithm, and represents convolution operation; s.t. represents a constraint;
and (3) converting the variation model into an unconstrained variation model:
wherein L is the iteration number of the unconstrained variant model; alpha is a penalty factor; λ is lagrange multiplier;
initialization u k 、w k Lambda and the iteration times of the unconstrained variable model, wherein the initial value of the iteration times of the unconstrained variable model is 0;
according to a preset cyclic process, updating u by adopting a multiplier alternative algorithm k 、w k And lambda to obtain a high-frequency intrinsic mode component, an intermediate-frequency intrinsic mode component and a low-frequency intrinsic mode component of each data sequence of the data training set;
and obtaining the high-frequency training set, the medium-frequency training set and the low-frequency training set according to the high-frequency intrinsic mode component, the medium-frequency intrinsic mode component and the low-frequency intrinsic mode component.
An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, which when executed by a processor, implements the steps of the method for predicting icing load of a power transmission line as described above.
An embodiment of the present application further provides a computer device, which includes a storage, a processor, and a computer program stored in the storage and executable by the processor, and when the processor executes the computer program, the steps of the method for predicting icing load of a power transmission line as described above are implemented.
In order that the application may be more clearly understood, specific embodiments thereof will be described below with reference to the accompanying drawings.
Drawings
Fig. 1 is a flowchart of a method for predicting an icing load of a power transmission line according to an embodiment of the present application.
Fig. 2 is a flow chart of a prediction model training of the method for predicting the icing load of the power transmission line according to an embodiment of the present application.
Fig. 3 is a schematic block connection diagram of a power transmission line icing load prediction device according to an embodiment of the present application.
Fig. 4 is a program diagram of a computer-readable storage medium according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
It should be understood that the embodiments described are only some embodiments of the present application, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the embodiments in the present application.
When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. In the description of the present application, it is to be understood that the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not necessarily used to describe a particular order or sequence, nor are they to be construed as indicating or implying relative importance. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as the case may be. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The word "if as used herein may be interpreted as" at 8230; \8230when "or" when 8230; \8230when "or" in response to a determination ".
Further, in the description of the present application, "a plurality" means two or more unless otherwise specified. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
Please refer to fig. 1, which is a flowchart illustrating a method for predicting an icing load of a power transmission line according to an embodiment of the present application, including:
s1: and acquiring a real-time data set, and performing VMD decomposition on the real-time data set to obtain a high-frequency real-time data set, a medium-frequency real-time data set and a low-frequency real-time data set.
S2: and respectively inputting the high-frequency real-time data set, the medium-frequency real-time data set and the low-frequency real-time data set into a pre-trained high-frequency prediction module, a pre-trained medium-frequency prediction model and a pre-trained low-frequency prediction model to obtain a high-frequency prediction value, a medium-frequency prediction value and a low-frequency prediction value.
S3: and acquiring corresponding icing load prediction data according to the high-frequency prediction value, the medium-frequency prediction value and the low-frequency prediction value.
Compared with the prior art, the method and the device have the advantages that the VMD decomposition algorithm is used for decomposing the real-time data set to obtain the high-frequency real-time data set, the medium-frequency real-time data set and the low-frequency real-time data set, then the high-frequency real-time data set, the medium-frequency real-time data set and the low-frequency real-time data set are input into the pre-trained high-frequency prediction module, the pre-trained medium-frequency prediction model and the pre-trained low-frequency prediction model to obtain the high-frequency prediction value, the medium-frequency prediction value and the low-frequency prediction value, and therefore the corresponding icing load prediction data are obtained, so that the icing load of the power transmission line can be predicted, the mutual influence of data of different scales can be reduced, and the accuracy of the icing load prediction of the power transmission line is improved.
The real-time data set comprises real-time information of icing load and microclimate information, and the low-frequency prediction model, the medium-frequency prediction model and the high-frequency prediction module are respectively F L ,F S ,F H The high frequency real-time data set, the medium frequency real-time data set and the low frequency real-time data set are respectively
Inputting the high-frequency real-time data set, the intermediate-frequency real-time data set and the low-frequency real-time data set into a pre-trained high-frequency prediction module, a pre-trained intermediate-frequency prediction model and a pre-trained low-frequency prediction model respectively to obtain a high-frequency prediction value, an intermediate-frequency prediction value and a low-frequency prediction value as follows:
wherein,
and respectively representing the high-frequency predicted value, the medium-frequency predicted value and the low-frequency predicted value. And the corresponding icing load prediction data is
Wherein,
data are predicted for icing load.
In one possible embodiment, the high frequency prediction module, the medium frequency prediction model and the low frequency prediction model are obtained by training the following steps:
s201: acquiring a data training set; the data training set comprises an off-line training set and an on-line training set;
the off-line training set and the on-line training set respectively comprise data of icing load and microclimate information.
The acquiring a training set of data comprises: and dividing data of an off-line training set and data of an on-line training set, wherein the data of the on-line training set must be P data which are continuous at n moments and before. Thus the data for offline training is [ y ] 1 ...y n-p ],[X 1 ...X n-p ](ii) a The online scroll resolved data is [ y ] n-p+1 ...y n ],[X n-p+1 ...X n ]. Wherein y corresponds to a unary time series and X corresponds to a multivariate time series.
S202: performing VMD decomposition on the data training set to obtain a high-frequency training set, a medium-frequency training set and a low-frequency training set;
s203: and training three initial convolutional neural networks according to the high-frequency training set, the medium-frequency training set and the low-frequency training set to obtain the high-frequency prediction module, the medium-frequency prediction model and the low-frequency prediction model.
Referring to fig. 2, in the embodiment, the low frequency prediction model F is obtained by performing VMD decomposition on a data training set and then inputting the data training set into three initial convolutional neural networks for training respectively L The intermediate frequency prediction model F S And said high frequency prediction module F H 。
In one possible embodiment, the step of acquiring a training set of data includes:
firstly, acquiring ice coating data of a line in a period of time past at the current moment and microclimate data of an area to which the line belongs, wherein the sampling time is preferably more than one month, and the sampling time interval is 30 minutes. Icing data is expressed as Y = [ Y ] 1 ...y n ]And weather information
q is the dimension of meteorological information, and the selected characteristic dimensions comprise temperature, humidity, sunlight, wind speed, wind direction angle and pressure intensity, so that q =6.
Carrying out normalization processing on the sample data through the following formula to obtain normalized data:
wherein, a g For normalizing data, a is sample data, a max ,a min The maximum value and the minimum value of the sample data are respectively;
and generating the data training set according to the normalized data.
In this embodiment, through the normalization operation, the phenomenon that the numerical values observed by different characteristic variables are greatly different, which causes the phenomenon that the number is counted up to the decimal number, can be avoided.
In a possible embodiment, the step of performing VMD decomposition on the data training set to obtain a high frequency training set, a medium frequency training set, and a low frequency training set includes:
constructing a variation model according to the data sequence of the data training set:
wherein min is the minimum value; u. of k The k-th data is the evidence modal component; w is a k The central frequency of the kth data intrinsic mode component; d t Is the time derivative of the function; delta (t) is a unit impulse function; j is an imaginary unit; pi is the circumference ratio; e is a natural logarithm, and represents convolution operation; s.t. represents a constraint;
converting the variation model into an unconstrained variation model:
wherein L is the iteration number of the unconstrained variant model; alpha is a penalty factor; λ is the Lagrangian multiplier;
initialization u k 、w k Lambda and the iteration times of the unconstrained variable model, wherein the initial value of the iteration times of the unconstrained variable model is 0;
according to a preset cyclic process, updating u by adopting a multiplier alternative algorithm k 、w k And lambda to obtain high-frequency and medium-frequency and low-frequency intrinsic mode components of each data sequence of the data training set, including:
updating u by adopting multiplier alternation algorithm k 、w k The process for λ and λ is as follows:
updating u k ：
In the formula: w is the frequency; w is a k Represents the center frequency of the kth component;
are respectively f (t), u i (t), a Fourier transform of λ (t);
represents the Fourier change after the kth component iteration L +1
Updating w k ：
In the formula:
represents the center frequency of the L +1 st iteration of the kth component;
represents the Fourier change after the k component iteration L +1
Updating lambda:
in the formula:
a Fourier transform that is the L +1 th iteration of λ;
is f (t) Fourier transform;
the sum after fourier transform after L +1 iterations is performed for all components.
According to the preset precision epsilon, if the preset precision epsilon is met:
stop updating u k 、w k And λ, otherwise, continue updating u k 、w k And λ.
Obtaining the high-frequency training set, the intermediate-frequency training set and the low-frequency training set according to the high-frequency intrinsic mode component, the intermediate-frequency intrinsic mode component and the low-frequency intrinsic mode component, including:
performing VMD decomposition to obtain signal matrix of different components of icing load
Expressing the value of the ith IMF component of the icing load at the nth-p moment, and performing VMD decomposition on each characteristic to obtain a signal matrix of different components of the matrix meteorological factors:
U i the ith component representing the microclimate information,
the sequence of values at the (n-p) th time instant of the ith IMF component expressed as the qth feature. Input label is
The expression form of the high-frequency training set, the medium-frequency training set and the low-frequency training set is as follows:
referring to fig. 3, an embodiment of the present application further provides a device for predicting an icing load of a power transmission line, including:
the real-time data decomposition module 1 is used for acquiring a real-time data set and performing VMD decomposition on the real-time data set to obtain a high-frequency real-time data set, a medium-frequency real-time data set and a low-frequency real-time data set;
the prediction data acquisition module 2 is configured to input the high-frequency real-time data set, the intermediate-frequency real-time data set, and the low-frequency real-time data set into the high-frequency prediction module, the intermediate-frequency prediction model, and the low-frequency prediction model respectively to obtain a high-frequency prediction value, an intermediate-frequency prediction value, and a low-frequency prediction value;
and the icing load prediction module 3 is used for obtaining corresponding icing load prediction data according to the high-frequency prediction value, the medium-frequency prediction value and the low-frequency prediction value.
Compared with the prior art, the method and the device have the advantages that the VMD decomposition algorithm is used for decomposing the real-time data set to obtain the high-frequency real-time data set, the medium-frequency real-time data set and the low-frequency real-time data set, then the high-frequency real-time data set, the medium-frequency real-time data set and the low-frequency real-time data set are input into the pre-trained high-frequency prediction module, the pre-trained medium-frequency prediction model and the pre-trained low-frequency prediction model to obtain the high-frequency prediction value, the medium-frequency prediction value and the low-frequency prediction value, so that corresponding icing load prediction data are obtained, the icing load of the power transmission line is predicted, the mutual influence of data of different scales can be reduced, and the accuracy of the icing load prediction of the power transmission line is improved.
In one possible embodiment, the method further comprises:
the training set acquisition module is used for acquiring a data training set; the data training set comprises an off-line training set and an on-line training set;
the training set decomposition module is used for performing VMD decomposition on the data training set to obtain a high-frequency training set, a medium-frequency training set and a low-frequency training set;
and the training module is used for training three initial convolutional neural networks according to the high-frequency training set, the medium-frequency training set and the low-frequency training set to obtain the high-frequency prediction module, the medium-frequency prediction model and the low-frequency prediction model.
VMD decomposition is carried out on a data training set, and then the three initial convolutional neural networks are respectively input for training, so that three independent prediction models, namely the high-frequency prediction module, the medium-frequency prediction model and the low-frequency prediction model, are obtained.
In one possible embodiment, the training set obtaining module includes:
carrying out normalization processing on the sample data through the following formula to obtain normalized data:
wherein, a g For normalizing data, a is sample data, a max ,a min The maximum value and the minimum value of the sample data are respectively;
and generating the data training set according to the normalized data.
Through the normalization operation, the phenomenon that the numerical values observed by different characteristic variables are greatly different to cause 'large numbers eating small numbers' can be avoided.
In one possible embodiment, the training set decomposition module includes:
constructing a variation model according to the data sequence of the data training set:
wherein min is the minimum value; u. of k The k-th data is the evidence modal component; w is a k The central frequency of the kth data intrinsic mode component; d is a radical of t Is a time derivative of the function; delta (t) is a unit impulse function; j is an imaginary unit; pi is the circumference ratio; e is a natural logarithm, and represents convolution operation; s.t. represents a constraint;
converting the variation model into an unconstrained variation model:
wherein L is the iteration number of the unconstrained variant model; alpha is a penalty factor; λ is lagrange multiplier;
initialization u k 、w k Lambda and the iteration times of the unconstrained variant model, wherein the initial value of the iteration times of the unconstrained variant model is 0;
according to a preset cyclic process, updating u by adopting a multiplier alternative algorithm k 、w k And lambda to obtain a high-frequency intrinsic mode component, an intermediate-frequency intrinsic mode component and a low-frequency intrinsic mode component of each data sequence of the data training set;
and obtaining the high-frequency training set, the medium-frequency training set and the low-frequency training set according to the high-frequency intrinsic mode component, the medium-frequency intrinsic mode component and the low-frequency intrinsic mode component.
An embodiment of the present application further provides a computer-readable storage medium 800, the computer-readable storage medium 800 stores a computer program, and the computer program when executed by a processor implements the steps of the method for predicting icing load of a power transmission line as described above.
Referring to fig. 4, an embodiment of the present application further provides a computer device, which includes a storage, a processor, and a computer program stored in the storage and executable by the processor, where the processor implements the steps of the method for predicting icing load of a power transmission line as described above when executing the computer program.
The above-described device embodiments are merely illustrative, and the components described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
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 so forth) 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 block or blocks and/or flowchart 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.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method for predicting icing load of a power transmission line is characterized by comprising the following steps:
acquiring a real-time data set, and performing VMD decomposition on the real-time data set to obtain a high-frequency real-time data set, a medium-frequency real-time data set and a low-frequency real-time data set;
inputting the high-frequency real-time data set, the intermediate-frequency real-time data set and the low-frequency real-time data set into a pre-trained high-frequency prediction module, a pre-trained intermediate-frequency prediction model and a pre-trained low-frequency prediction model respectively to obtain a high-frequency prediction value, an intermediate-frequency prediction value and a low-frequency prediction value;
and acquiring corresponding icing load prediction data according to the high-frequency prediction value, the medium-frequency prediction value and the low-frequency prediction value.
2. The method for predicting the icing load of the power transmission line according to claim 1, wherein the high-frequency prediction module, the medium-frequency prediction model and the low-frequency prediction model are obtained by training through the following steps:
acquiring a data training set; the data training set comprises an off-line training set and an on-line training set;
performing VMD decomposition on the data training set to obtain a high-frequency training set, a medium-frequency training set and a low-frequency training set;
and training three initial convolutional neural networks according to the high-frequency training set, the medium-frequency training set and the low-frequency training set to obtain the high-frequency prediction module, the medium-frequency prediction model and the low-frequency prediction model.
3. The method for predicting icing load of power transmission lines according to claim 2, wherein the step of obtaining a training set of data comprises:
carrying out normalization processing on the sample data through the following formula to obtain normalized data:
wherein, a g For normalizing data, a is sample data, a max ,a min The maximum value and the minimum value of the sample data are respectively;
and generating the data training set according to the normalized data.
4. The method for predicting the icing load of the power transmission line according to claim 3, wherein the step of performing VMD decomposition on the data training set to obtain a high-frequency training set, a medium-frequency training set and a low-frequency training set comprises the following steps:
constructing a variation model according to the data sequence of the data training set:
wherein min is the minimum value; u. of k The k-th data is the evidence modal component; w is a k The central frequency of the kth data intrinsic mode component; d t Is a time derivative of the function; delta (t) is a unit impulse function; j is an imaginary unit; pi is the circumference ratio; e is a natural logarithm, and represents convolution operation; s.t. represents a constraint;
converting the variation model into an unconstrained variation model:
wherein L is the iteration number of the unconstrained variant model; alpha is a penalty factor; λ is lagrange multiplier;
initialization u k 、w k λ and unconstrained variantThe initial value of the iteration times of the unconstrained variable model is 0;
updating u by adopting a multiplier alternative algorithm according to a preset cyclic process k 、w k And lambda to obtain a high-frequency intrinsic mode component, an intermediate-frequency intrinsic mode component and a low-frequency intrinsic mode component of each data sequence of the data training set;
and obtaining the high-frequency training set, the medium-frequency training set and the low-frequency training set according to the high-frequency intrinsic mode component, the medium-frequency intrinsic mode component and the low-frequency intrinsic mode component.
5. A power transmission line icing load prediction device is characterized by comprising:
the real-time data decomposition module is used for acquiring a real-time data set and performing VMD decomposition on the real-time data set to obtain a high-frequency real-time data set, a medium-frequency real-time data set and a low-frequency real-time data set;
the prediction data acquisition module is used for respectively inputting the high-frequency real-time data set, the intermediate-frequency real-time data set and the low-frequency real-time data set into the high-frequency prediction module, the intermediate-frequency prediction model and the low-frequency prediction model to obtain a high-frequency prediction value, an intermediate-frequency prediction value and a low-frequency prediction value;
and the icing load prediction module is used for obtaining corresponding icing load prediction data according to the high-frequency prediction value, the medium-frequency prediction value and the low-frequency prediction value.
6. The apparatus for predicting ice coating load on transmission line according to claim 5, further comprising:
the training set acquisition module is used for acquiring a data training set; the data training set comprises an off-line training set and an on-line training set;
the training set decomposition module is used for performing VMD decomposition on the data training set to obtain a high-frequency training set, a medium-frequency training set and a low-frequency training set;
and the training module is used for training three initial convolutional neural networks according to the high-frequency training set, the medium-frequency training set and the low-frequency training set to obtain the high-frequency prediction module, the medium-frequency prediction model and the low-frequency prediction model.
7. The device for predicting icing load of power transmission line according to claim 6, wherein the training set obtaining module comprises:
carrying out normalization processing on the sample data through the following formula to obtain normalized data:
wherein, a g To normalize the data, a is the sample data, a max ,a min The maximum value and the minimum value of the sample data are respectively;
and generating the data training set according to the normalized data.
8. The device for predicting icing load of power transmission line according to claim 7, wherein the training set decomposition module comprises:
constructing a variation model according to the data sequence of the data training set:
wherein min is the minimum value; u. of k The k-th data is the evidence modal component; w is a k The central frequency of the kth data intrinsic mode component; d t Is a time derivative of the function; delta (t) is a unit impulse function; j is an imaginary unit; pi is the circumference ratio; e is a natural logarithm, and represents convolution operation; s.t. represents a constraint;
converting the variation model into an unconstrained variation model:
wherein L is the iteration number of the unconstrained variant model; alpha is a penalty factor; λ is lagrange multiplier;
initialization u k 、w k Lambda and the iteration times of the unconstrained variable model, wherein the initial value of the iteration times of the unconstrained variable model is 0;
updating u by adopting a multiplier alternative algorithm according to a preset cyclic process k 、w k And lambda to obtain a high-frequency intrinsic mode component, an intermediate-frequency intrinsic mode component and a low-frequency intrinsic mode component of each data sequence of the data training set;
and obtaining the high-frequency training set, the medium-frequency training set and the low-frequency training set according to the high-frequency intrinsic mode component, the medium-frequency intrinsic mode component and the low-frequency intrinsic mode component.
9. A computer-readable storage medium storing a computer program, characterized in that: the computer program when executed by a processor implements the steps of the method of predicting icing load of a power transmission line according to any one of claims 1 to 4.
10. A computer device, characterized by: comprising a memory, a processor and a computer program stored in said memory and executable by said processor, said processor when executing said computer program implementing the steps of the method for predicting icing load of an electric transmission line according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211181005.XA CN115622029A (en) | 2022-09-27 | 2022-09-27 | Power transmission line icing load prediction method and device, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211181005.XA CN115622029A (en) | 2022-09-27 | 2022-09-27 | Power transmission line icing load prediction method and device, storage medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115622029A true CN115622029A (en) | 2023-01-17 |
Family
ID=84860485
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211181005.XA Pending CN115622029A (en) | 2022-09-27 | 2022-09-27 | Power transmission line icing load prediction method and device, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115622029A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117196123A (en) * | 2023-11-06 | 2023-12-08 | 深圳市粤能电气有限公司 | Data control method, device and equipment for digital production of power distribution equipment |
-
2022
- 2022-09-27 CN CN202211181005.XA patent/CN115622029A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117196123A (en) * | 2023-11-06 | 2023-12-08 | 深圳市粤能电气有限公司 | Data control method, device and equipment for digital production of power distribution equipment |
| CN117196123B (en) * | 2023-11-06 | 2024-03-19 | 深圳市粤能电气有限公司 | Data control method, device and equipment for digital production of power distribution equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112766549A (en) | Air pollutant concentration forecasting method and device and storage medium | |
| CN113283588B (en) | Near-shore single-point wave height forecasting method based on deep learning | |
| CN112288193A (en) | Ocean station surface salinity prediction method based on GRU deep learning of attention mechanism | |
| CN117117819A (en) | Photovoltaic power generation short-term power prediction method, system, equipment and medium | |
| CN113822418A (en) | Wind power plant power prediction method, system, device and storage medium | |
| CN115186923A (en) | Photovoltaic power generation power prediction method and device and electronic equipment | |
| CN112508299A (en) | Power load prediction method and device, terminal equipment and storage medium | |
| CN116581756B (en) | Wind power prediction method, model training method, device, equipment and medium | |
| CN115622029A (en) | Power transmission line icing load prediction method and device, storage medium and equipment | |
| CN112906757A (en) | Model training method, optical power prediction method, device, equipment and storage medium | |
| CN115018022B (en) | Quality control method, device, equipment and medium for gridding environment monitoring data | |
| CN116451594A (en) | Training method and device of icing prediction model, prediction method and device and electronic equipment | |
| CN114498619A (en) | Wind power prediction method and device | |
| CN114330934A (en) | Model parameter self-adaptive GRU new energy short-term power generation power prediction method | |
| CN115577752A (en) | Ultra-short-term photovoltaic power prediction method and system | |
| CN116663746A (en) | Power load prediction method and device, computer equipment and storage medium | |
| CN115689055A (en) | Short-term solar irradiance prediction method and device | |
| CN114444821A (en) | Integrated learning load prediction method, system and medium for power internet of things | |
| CN116885711A (en) | Wind power prediction method, device, equipment and readable storage medium | |
| CN116960975A (en) | Photovoltaic power generation amount prediction method and device | |
| CN117154680A (en) | Wind power prediction method based on non-stationary transducer model | |
| CN115130743B (en) | Wind turbine generator set regulation rate prediction method and system based on variation inference | |
| CN112734073A (en) | Photovoltaic power generation short-term prediction method based on long and short-term memory network | |
| CN114118611A (en) | Wind power prediction method and system based on prediction algorithm pool | |
| CN110457863B (en) | Parameter estimation method for wind driven generator pitch subsystem based on ellipsoid contraction filtering |
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 |