CN114638405A - Energy demand prediction method and device and computer equipment - Google Patents
Energy demand prediction method and device and computer equipment Download PDFInfo
- Publication number
- CN114638405A CN114638405A CN202210186735.2A CN202210186735A CN114638405A CN 114638405 A CN114638405 A CN 114638405A CN 202210186735 A CN202210186735 A CN 202210186735A CN 114638405 A CN114638405 A CN 114638405A
- Authority
- CN
- China
- Prior art keywords
- matrix
- independent variable
- energy demand
- principal components
- prediction
- 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 41
- 238000012417 linear regression Methods 0.000 claims abstract description 8
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims description 165
- 230000001419 dependent effect Effects 0.000 claims description 55
- 238000012545 processing Methods 0.000 claims description 21
- 238000011161 development Methods 0.000 claims description 20
- 239000013598 vector Substances 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 17
- 238000012216 screening Methods 0.000 claims description 12
- 230000001186 cumulative effect Effects 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- SHGAZHPCJJPHSC-YCNIQYBTSA-N all-trans-retinoic acid Chemical compound OC(=O)\C=C(/C)\C=C\C=C(/C)\C=C\C1=C(C)CCCC1(C)C SHGAZHPCJJPHSC-YCNIQYBTSA-N 0.000 claims description 3
- 238000012886 linear function Methods 0.000 claims description 3
- 230000014759 maintenance of location Effects 0.000 claims description 3
- 238000013459 approach Methods 0.000 claims description 2
- 230000008859 change Effects 0.000 abstract description 5
- 238000000513 principal component analysis Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 12
- 238000005265 energy consumption Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 229910052799 carbon Inorganic materials 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012847 principal component analysis method Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 238000000265 homogenisation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an energy demand prediction method, an energy demand prediction device and computer equipment. The invention provides an energy demand prediction model based on principal component analysis and multiple linear regression analysis, and compared with a method for predicting future energy demand according to historical energy demand change narrative, the model provided by the invention is more in line with energy demand prediction influenced by actual policies and economy.
Description
Technical Field
The invention belongs to the technical field of power markets, and particularly relates to an energy demand prediction method, an energy demand prediction device and computer equipment.
Background
With the development of resource industry, the new energy ratio in energy consumption is continuously improved, and the energy demand is changed from single to diversified. Accurate and effective energy demand prediction can better study and judge the energy demand structure and the energy demand level of each stage, and the use and the development of energy are effectively managed. At present, an accurate and effective energy demand prediction method is lacked, so that the existing energy development route cannot be adjusted and distributed in a targeted manner. The problems of multiple influencing factors, complex model and the like exist in energy demand prediction.
In the related technology, the energy prediction method mainly comprises energy demand prediction based on a BP neural network model, an autoregressive moving average model (ARIMA) and a grey prediction model, the basic principle is mainly to speculate the future energy demand through the historical trend, but the energy demand is influenced by a plurality of factors, wherein the economic growth is one of the important factors influencing the growth and change of the energy consumption in China; in addition, the industrial structure is also an important factor influencing the energy demand of China, and the second industry is the main power for the energy consumption increase of China; the population quantity and structure can directly influence the total energy consumption, the urbanization process has a great influence on the energy consumption, and the urbanization rate and the energy consumption have positive correlation. Therefore, not only the historical development trend of energy consumption itself but also the coupling relationship between factors such as economic growth, industrial structure transformation and social development and the energy demand need to be considered when predicting the future energy demand.
The existing energy demand prediction method based on the ARIMA model requires that given time sequence data are stable, otherwise, the energy demand change rule cannot be captured. In addition, the autoregressive model describes the relationship between a current value and a historical value, namely, the autoregressive model is a prediction model based on a time angle and cannot reflect the relationship of influence factors of economy, policy and the like on energy demand in China. In addition, the gray prediction model uses a generated data sequence instead of an original data sequence, so that the gray prediction model is more suitable for medium and short term prediction and exponential growth prediction, is not suitable for predicting energy demand with a large time span under a double-carbon target, and the existing energy demand prediction cannot consider future environmental policies, economic development plans and the like.
Disclosure of Invention
In view of the above, the present invention provides an energy demand prediction method, an energy demand prediction apparatus, and a computer device to solve the problem that the existing energy demand prediction in the prior art cannot be applied to predicting an energy demand with a large time span under a dual-carbon target.
In order to achieve the purpose, the invention adopts the following technical scheme: an energy demand forecasting method comprising:
acquiring original independent variable data, establishing an original independent variable matrix according to the original independent variable data, and carrying out standardization processing to obtain a standardized matrix; wherein the raw independent variable data comprises a plurality of categories of indexes related to economic development of the power industry, and the indexes comprise industry added value, yield and price index;
obtaining a correlation coefficient matrix according to the standardized matrix, obtaining a characteristic value of the correlation coefficient matrix, calculating a corresponding characteristic vector according to the characteristic value, and constructing an independent variable matrix according to the characteristic vector;
determining contribution degrees of the synthesized principal components according to the characteristic values, screening the independent variable matrix according to the contribution degrees, determining the principal components in a preset number, and constructing a prediction matrix according to the principal components in the preset number;
acquiring dependent variable data, and establishing a dependent variable matrix according to the dependent variable data; wherein the dependent variable data comprises energy demand historical data;
and constructing an energy demand prediction model according to the prediction matrix and the dependent variable matrix, wherein the energy demand prediction model is used for calculating future energy demand.
Further, the establishing an original independent variable matrix according to the original independent variable data and performing standardization processing to obtain a standardized matrix includes:
suppose the actual result of the jth index of a certain industry in the historical period n is Xj＝[x1j,x2j,…,xnj]TThen the original independent variable matrix of the macro economy of the industry in the historical period n is:
normalizing the original independent variable matrix to obtain the normalized data x of the ith row and the jth columnij；
Wherein,
means representing the average of the jth index for that industry over a historical period, i.e.
var(xij) Indicating the standard deviation of the class j index, i.e.
(j＝1,2,…,k)。
Further, obtaining an eigenvalue of the correlation coefficient matrix, and calculating a corresponding eigenvector according to the eigenvalue, including:
the correlation coefficient matrix is:
calculating to obtain the eigenvalue lambda of the correlation coefficient matrix according to the correlation coefficient matrix1，λ2，…,λk；
Calculating a characteristic vector corresponding to the characteristic value according to the characteristic value in the following mode;
ATRA＝diag(λ1,λ2,…,λk)
wherein, XTIs an inverted matrix of the original argument matrix X, A ═ aij)k×kRepresenting orthonormal eigenvectors corresponding to eigenvalues, aijRepresenting the ith column and jth row elements in the feature vector a.
Further, the constructing an independent variable matrix according to the feature vector includes:
calculating an independent variable matrix according to the original independent variable matrix and the characteristic vector in the following way;
Y＝ATX
further, the determining a contribution degree of the synthesized principal component according to the eigenvalue, screening the independent variable matrix according to the contribution degree, determining a preset number of each principal component, and constructing a prediction matrix according to the preset number of each principal component includes:
characteristic value lambda1，λ2，…,λkRepresenting the contribution rate of the synthesized principal components, arranging the eigenvectors of the principal components in descending order, and defining the cumulative contribution rate of the principal components as the cumulative contribution rate of the principal components if the cumulative value of the first p eigenvalues approaches 1, wherein p < k, representing that the information retention rate of the p principal components on the original index set is high
And carrying out value taking according to a preset range to screen each main component, wherein the obtained k economic operation index synthesized main components are as follows:
further, for each synthesized principal component, covariance calculation is performed to obtain:
principal component yjIs equal to its corresponding eigenvalue lambdaiThe covariance between any two different principal components is 0, i.e. there is no correlation between the respective principal components.
Further, the energy demand prediction model is a multiple linear regression analysis model, including:
Z＝β0+β1Y′1+β2Y′2+…+βkY′k (8)
wherein, it is assumed that the explained variable Z and a plurality of explained variables Y ', Y'2,…Y′kHave a linear relation between them, are multi-element linear functions of interpretation variables, beta0，β1，…，βkThe prediction matrix is formed by processing a regression coefficient, an explanatory variable Z, namely a source demand, and an explanatory variable Y, namely an economic development plan, an environmental policy target, an industrial structure and other factors.
Further, the preset range is 85% to 95%.
The embodiment of the application provides an energy demand prediction device, includes:
the acquisition module is used for acquiring original independent variable data, establishing an original independent variable matrix according to the original independent variable data and carrying out standardization processing to obtain a standardized matrix; wherein the raw independent variable data comprises a plurality of categories of indexes related to economic development of the power industry, and the indexes comprise industry added value, yield and price index;
the construction module is used for obtaining a correlation coefficient matrix according to the standardized matrix, obtaining an eigenvalue of the correlation coefficient matrix, calculating a corresponding eigenvector according to the eigenvalue, and constructing an independent variable matrix according to the eigenvector;
the determining module is used for determining the contribution degree of the synthesized principal components according to the characteristic values, screening the independent variable matrix according to the contribution degree, determining the principal components in a preset number, and constructing a prediction matrix according to the principal components in the preset number;
the establishment module is used for acquiring dependent variable data and establishing a dependent variable matrix according to the dependent variable data; wherein the dependent variable data comprises energy demand historical data;
and the construction module is used for constructing an energy demand prediction model according to the prediction matrix and the dependent variable matrix.
An embodiment of the present application provides a computer device, including: a memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of any of the energy demand prediction methods described above.
An embodiment of the present application further provides a computer storage medium, which stores a computer program, and when the computer program is executed by a processor, the processor executes the steps of any one of the energy demand prediction methods.
By adopting the technical scheme, the invention can achieve the following beneficial effects:
the invention provides an energy demand prediction method, an energy demand prediction device and computer equipment, which are used for predicting in consideration of economic growth influencing energy demand and also in consideration of the problem of 'pseudo regression' possibly caused in a multiple linear regression model due to strong correlation of relevant indexes of economic development, such as yield value, price index and the like. In contrast, the method adopts a principal component analysis method to process the independent variable matrix, so that the factors in the obtained new independent variable matrix are not related to each other, and the problem of 'pseudo regression' caused by overlarge autocorrelation of the variables in the multiple regression model prediction is avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram illustrating the steps of the energy demand prediction method according to the present invention;
FIG. 2 is a schematic flow chart illustrating a method for predicting energy demand according to the present invention;
FIG. 3 is a schematic structural diagram of an energy demand prediction apparatus according to the present invention;
fig. 4 is a schematic diagram of a hardware structure of an embodiment of the energy demand prediction method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
A specific energy demand prediction method, apparatus, and computer device provided in the embodiments of the present application are described below with reference to the accompanying drawings.
As shown in fig. 1, the energy demand prediction method provided in the embodiment of the present application includes:
s101, acquiring original independent variable data, establishing an original independent variable matrix according to the original independent variable data, and performing standardization processing to obtain a standardized matrix; wherein the raw independent variable data comprises a plurality of categories of indexes related to economic development of the power industry, and the indexes comprise industry added value, yield and price index;
as shown in fig. 2, the raw independent variable data required to be acquired by the present invention includes indexes related to national development of the industry or region, such as industry increment value, yield, price index, and dependent variable data includes energy demand history data. It is to be understood that the original independent variable data may also include data of other dimensions, and the dependent variable data may also include data of other dimensions, which is not limited herein.
After the original independent variable data are obtained, an original independent variable matrix X is established, which specifically comprises the following steps:
suppose that the actual result of the j-th type related index in a certain industry in the historical period n is Xj＝[x1j,x2j,…,xnj]TThe raw argument matrix of the macro-economy of the industry over the history period n can be expressed as:
then, the original independent variable matrix is standardized to obtain the data x after the ith row and the jth column are standardizedij(ii) a The following were used:
it should be noted that, because there are differences in the properties, dimensions, orders of magnitude, etc. of each index, it is necessary to perform normalization processing on the indexes, and the normalization processing on the original independent variable matrix in the present application may specifically adopt methods such as a Z-score method and standard deviation processing.
In the formula,
representing the average of the jth index for that industry over a historical period, i.e.
var(xij) Indicating the standard deviation of the class j index, i.e.
(j＝1,2,…,k)。
S102, obtaining a correlation coefficient matrix according to the standardized matrix, obtaining an eigenvalue of the correlation coefficient matrix, calculating a corresponding eigenvector according to the eigenvalue, and constructing an independent variable matrix according to the eigenvector;
specifically, each macroscopic economic index j after the standardization treatment has a homogenization treatment condition. Aiming at each macroscopic economic index in the time span n, a correlation coefficient matrix can be obtained:
and then based on said correlationCalculating a coefficient matrix to obtain an eigenvalue lambda of the correlation coefficient matrix1，λ2，…,λk. Characteristic value lambda1，λ2，…,λkWith corresponding feature vectors, the calculation is as follows:
ATRA＝diag(λ1,λ2,…,λk) (5)
wherein, XTIs an inverted matrix of the original argument matrix X, A ═ aij)k×kRepresenting orthonormal eigenvectors corresponding to eigenvalues, aijRepresenting the ith column and jth row elements in the feature vector a.
S103, determining contribution degrees of the synthesized principal components according to the characteristic values, screening the independent variable matrix according to the contribution degrees, determining the principal components in a preset number, and constructing a prediction matrix according to the principal components in the preset number;
different from the original independent variable matrix X, aiming at each result in the industry historical period n, an independent variable matrix is constructed: y is ATAnd (4) X. To obtain
Then, screening the independent variable matrix Y to obtain a matrix Y' for predicting dependent variables, wherein the specific process is as follows:
characteristic value lambda1，λ2，…,λkExpressing the contribution rate of the synthesized principal components, arranging the feature vectors of the principal components in descending order, assuming that the cumulative value of the first p (p < k) feature values is very close to 1, indicating that the information retention degree of the p principal components on the original index set is very high, and defining the cumulative contribution degree as the principal component
The value can be selected according to the actual situation (generally between 85% and 95%), thereby screening each main component. The obtained k-term economic operation index synthesis main components are as follows:
independent variable Y matrixes obtained by a principal component analysis method are not related to each other, so that the problem of pseudo regression is avoided;
from the analysis on the mathematical principle, the following conclusion can be obtained after the covariance calculation is carried out on each synthesized principal component:
main component y'jIs equal to its corresponding eigenvalue lambdaiThe covariance between any two different principal components is 0 (i.e., uncorrelated).
S104, acquiring dependent variable data, and establishing a dependent variable matrix according to the dependent variable data; wherein the dependent variable data comprises energy demand historical data;
dependent variable data includes energy demand history data.
And S105, constructing an energy demand prediction model according to the prediction matrix and the dependent variable matrix, wherein the energy demand prediction model is used for calculating future energy demand.
And (3) establishing a multiple linear regression analysis model by using the independent variable matrix Y and the dependent variable matrix Z, namely the historical value of the energy demand, and obtaining an energy-economy prediction model by using the dependent variable matrix formed by the obtained prediction matrix and the obtained dependent variable data.
Multiple linear regression models are commonly used to study the relationship of a dependent variable to a number of independent variables, and are represented by the following equation:
Z＝β0+β1Y′1+β2Y′2+…+βkY′k (9)
wherein, it is assumed that the explained variable Z and a plurality of explained variables Y ', Y'2,…Y′kHave a linear relationship between them and are multivariate linear functions of interpretation variables, beta0，β1，…，βkThe model is a regression coefficient, and the interpretation variable Z is an independent variable matrix formed by processing factors such as energy demand, economic development planning, environmental policy targets, industrial structures and the like.
According to the method and the device, the future independent variable matrix X can be set, the corresponding prediction matrix Y' is calculated, and the future energy demand matrix Z is calculated based on the established multiple linear regression model.
As shown in fig. 3, the present application provides an energy demand prediction apparatus including:
an obtaining module 201, configured to obtain original independent variable data, establish an original independent variable matrix according to the original independent variable data, and perform standardization processing to obtain a standardized matrix; wherein the raw independent variable data comprises a plurality of categories of indexes related to economic development of the power industry, wherein the indexes comprise industry added value, yield and price index;
a constructing module 202, configured to obtain a correlation coefficient matrix according to the normalized matrix, obtain an eigenvalue of the correlation coefficient matrix, calculate a corresponding eigenvector according to the eigenvalue, and construct an independent variable matrix according to the eigenvector;
the determining module 203 is configured to determine a contribution degree of a synthesized principal component according to the eigenvalue, screen the independent variable matrix according to the contribution degree, determine a preset number of each principal component, and construct a prediction matrix according to the preset number of each principal component;
the establishing module 204 is configured to obtain dependent variable data and establish a dependent variable matrix according to the dependent variable data; wherein the dependent variable data comprises energy demand historical data;
and the constructing module 205 is used for constructing an energy demand prediction model according to the prediction matrix and the dependent variable matrix.
The energy demand prediction device provided by the application has the working principle that the acquisition module 201 acquires original independent variable data, establishes an original independent variable matrix according to the original independent variable data and carries out standardization processing to obtain a standardized matrix; wherein the raw independent variable data comprises a plurality of categories of indexes related to economic development of the power industry, and the indexes comprise industry added value, yield and price index; the constructing module 202 obtains a correlation coefficient matrix and an eigenvalue of the correlation coefficient matrix according to the standardized matrix, calculates a corresponding eigenvector according to the eigenvalue, and constructs an independent variable matrix according to the eigenvector; the determining module 203 determines the contribution degree of the synthesized principal component according to the eigenvalue, screens the independent variable matrix according to the contribution degree, determines the principal components in a preset number, and constructs a prediction matrix according to the principal components in the preset number; the establishing module 204 acquires dependent variable data and establishes a dependent variable matrix according to the dependent variable data; wherein the dependent variable data comprises energy demand historical data; the construction module 205 constructs an energy demand prediction model according to the prediction matrix and the dependent variable matrix.
The present application provides a computer device comprising: memory, which may include volatile memory on a computer-readable medium, Random Access Memory (RAM), and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), and a network interface. The computer device stores an operating system, and the memory is an example of a computer-readable medium. The computer program, when executed by the processor, causes the processor to perform the energy demand prediction method, the structure shown in fig. 4 is a block diagram of only a part of the structure relating to the present application, and does not constitute a limitation of the computer apparatus to which the present application is applied, and a specific computer apparatus may include more or less components than those shown in the drawings, or combine some components, or have a different arrangement of components.
In one embodiment, the energy demand prediction method provided by the present application may be implemented in the form of a computer program, which is executable on a computer device as shown in fig. 4.
In some embodiments, the computer program, when executed by the processor, causes the processor to perform the steps of: acquiring original independent variable data, establishing an original independent variable matrix according to the original independent variable data, and carrying out standardization processing to obtain a standardized matrix; wherein the raw independent variable data comprises a plurality of categories of indexes related to economic development of the power industry, and the indexes comprise industry added value, yield and price index; obtaining a correlation coefficient matrix according to the standardized matrix, obtaining a characteristic value of the correlation coefficient matrix, calculating a corresponding characteristic vector according to the characteristic value, and constructing an independent variable matrix according to the characteristic vector; determining contribution degrees of the synthesized principal components according to the characteristic values, screening the independent variable matrix according to the contribution degrees, determining the principal components in a preset number, and constructing a prediction matrix according to the principal components in the preset number; acquiring dependent variable data, and establishing a dependent variable matrix according to the dependent variable data; wherein the dependent variable data comprises energy demand historical data; and constructing an energy demand prediction model according to the prediction matrix and the dependent variable matrix, wherein the energy demand prediction model is used for calculating future energy demand.
The present application also provides a computer storage medium, examples of which 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 cassette 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.
In some embodiments, the present invention further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the computer program obtains original independent variable data, establishes an original independent variable matrix according to the original independent variable data, and performs normalization processing to obtain a normalized matrix; wherein the raw independent variable data comprises a plurality of categories of indexes related to economic development of the power industry, and the indexes comprise industry added value, yield and price index; obtaining a correlation coefficient matrix according to the standardized matrix, obtaining a characteristic value of the correlation coefficient matrix, calculating a corresponding characteristic vector according to the characteristic value, and constructing an independent variable matrix according to the characteristic vector; determining contribution degrees of the synthesized principal components according to the characteristic values, screening the independent variable matrix according to the contribution degrees, determining the principal components in a preset number, and constructing a prediction matrix according to the principal components in the preset number; acquiring dependent variable data, and establishing a dependent variable matrix according to the dependent variable data; wherein the dependent variable data comprises energy demand historical data; and constructing an energy demand prediction model according to the prediction matrix and the dependent variable matrix, wherein the energy demand prediction model is used for calculating future energy demand.
In summary, the present invention provides an energy demand prediction method, an energy demand prediction apparatus, and a computer device, which include obtaining original independent variable data, establishing an original independent variable matrix, normalizing the original independent variable matrix, obtaining a correlation coefficient matrix of the original independent variable matrix, obtaining eigenvalues of the correlation coefficient matrix and eigenvectors corresponding to the eigenvalues, constructing an independent variable matrix according to the eigenvectors, screening the independent variable matrix to obtain a prediction matrix for predicting dependent variables, and obtaining an energy demand prediction model by combining the prediction matrix and the dependent variable matrix. The invention provides an energy demand prediction model based on principal component analysis and multiple linear regression analysis, and compared with a method for predicting future energy demand according to historical energy demand change narrative, the model provided by the invention is more in line with energy demand prediction influenced by actual policies and economy.
It is to be understood that the embodiments of the method provided above correspond to the embodiments of the apparatus described above, and the corresponding specific contents may be referred to each other, which is not described herein again.
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, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. An energy demand prediction method, comprising:
acquiring original independent variable data, establishing an original independent variable matrix according to the original independent variable data, and performing standardization processing to obtain a standardized matrix; wherein the raw independent variable data comprises a plurality of categories of indexes related to economic development of the power industry, and the indexes comprise industry added value, yield and price index;
obtaining a correlation coefficient matrix according to the standardized matrix, obtaining a characteristic value of the correlation coefficient matrix, calculating a corresponding characteristic vector according to the characteristic value, and constructing an independent variable matrix according to the characteristic vector;
determining contribution degrees of the synthesized principal components according to the characteristic values, screening the independent variable matrix according to the contribution degrees, determining the principal components in a preset number, and constructing a prediction matrix according to the principal components in the preset number;
acquiring dependent variable data, and establishing a dependent variable matrix according to the dependent variable data; wherein the dependent variable data comprises energy demand historical data;
and constructing an energy demand prediction model according to the prediction matrix and the dependent variable matrix, wherein the energy demand prediction model is used for calculating future energy demand.
2. The method of claim 1, wherein the establishing an original independent variable matrix from the original independent variable data and performing normalization processing to obtain a normalized matrix comprises:
suppose the actual result of the jth index of a certain industry in the historical period n is Xj＝[x1j,x2j,…,xnj]TThen the original independent variable matrix of the macro economy of the industry in the historical period n is:
normalizing the original independent variable matrix to obtain the normalized data x of the ith row and the jth columnij；
Wherein,
representing the average of the jth index for that industry over a historical period, i.e.
var(xij) Indicating the standard deviation of the class j index, i.e.
3. The method according to claim 1 or 2, wherein obtaining eigenvalues of the correlation coefficient matrix, and calculating corresponding eigenvectors from the eigenvalues comprises:
the correlation coefficient matrix is:
calculating to obtain an eigenvalue lambda of the correlation coefficient matrix according to the correlation coefficient matrix1，λ2，…,λk；
Calculating a characteristic vector corresponding to the characteristic value according to the characteristic value in the following mode;
ATRA＝diag(λ1,λ2,…,λk)
wherein XTIs an inverted matrix of the original argument matrix X, A ═ aij)k×kRepresents the orthonormal eigenvector corresponding to the eigenvalue, aijRepresenting the ith column and jth row elements in the feature vector a.
4. The method of claim 1, wherein constructing an argument matrix from the feature vectors comprises:
calculating an independent variable matrix according to the original independent variable matrix and the characteristic vector in the following way;
Y＝ATX
5. the method according to claim 1, wherein the determining a contribution degree of the synthesized principal component according to the eigenvalue, screening the independent variable matrix according to the contribution degree, determining a preset number of principal components, and constructing a prediction matrix according to the preset number of principal components comprises:
characteristic value lambda1，λ2，…,λkRepresenting the contribution rate of the synthesized principal components, arranging the eigenvectors of the principal components in descending order, and defining the cumulative contribution rate of the principal components as the cumulative contribution rate of the principal components if the cumulative value of the first p eigenvalues approaches 1, wherein p < k, representing that the information retention rate of the p principal components on the original index set is high
And carrying out value taking according to a preset range to screen each main component, wherein the obtained k economic operation index synthesized main components are as follows:
y′1＝a11X1+a12X2+…+a1kXk
y′2＝a21X1+a22X2+…+a2kXk
…
y′p＝ap1X1+ap2X2+…+apkXk
and forming a prediction matrix Y' by the principal components synthesized by the k economic operation indexes.
6. The method of claim 5, wherein the covariance calculation is performed for each of the synthesized principal components to obtain:
principal component yjIs equal to its corresponding eigenvalue lambdaiThe covariance between any two different principal components is 0, i.e. there is no correlation between the respective principal components.
7. The method of claim 6,
the energy demand prediction model is a multiple linear regression analysis model and comprises the following steps:
Z＝β0+β1Y1′+β2Y′2+…+βkY′k
wherein, it is assumed that the explained variable Z and a plurality of explained variables Y ', Y'2,…Y′kHave a linear relationship between them and are multivariate linear functions of interpretation variables, beta0，β1，…，βkThe prediction matrix is formed by processing a regression coefficient, an explanatory variable Z, namely a source demand, and an explanatory variable Y, namely an economic development plan, an environmental policy target, an industrial structure and other factors.
8. The method of claim 5,
the predetermined range is 85% to 95%.
9. An energy demand prediction apparatus comprising:
the acquisition module is used for acquiring original independent variable data, establishing an original independent variable matrix according to the original independent variable data and carrying out standardization processing to obtain a standardized matrix; wherein the raw independent variable data comprises a plurality of categories of indexes related to economic development of the power industry, wherein the indexes comprise industry added value, yield and price index;
the construction module is used for obtaining a correlation coefficient matrix according to the standardized matrix, obtaining an eigenvalue of the correlation coefficient matrix, calculating a corresponding eigenvector according to the eigenvalue, and constructing an independent variable matrix according to the eigenvector;
the determining module is used for determining the contribution degree of the synthesized principal components according to the characteristic values, screening the independent variable matrix according to the contribution degree, determining the principal components in a preset number, and constructing a prediction matrix according to the principal components in the preset number;
the establishment module is used for acquiring dependent variable data and establishing a dependent variable matrix according to the dependent variable data; wherein the dependent variable data comprises energy demand historical data;
and the construction module is used for constructing an energy demand prediction model according to the prediction matrix and the dependent variable matrix.
10. A computer device, comprising: a memory storing a computer program which, when executed by the processor, causes the processor to carry out the energy demand prediction method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210186735.2A CN114638405A (en) | 2022-02-28 | 2022-02-28 | Energy demand prediction method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210186735.2A CN114638405A (en) | 2022-02-28 | 2022-02-28 | Energy demand prediction method and device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114638405A true CN114638405A (en) | 2022-06-17 |
Family
ID=81947302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210186735.2A Pending CN114638405A (en) | 2022-02-28 | 2022-02-28 | Energy demand prediction method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114638405A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116049341A (en) * | 2023-03-08 | 2023-05-02 | 北京七兆科技有限公司 | Hydrologic data standardization method, device, equipment and storage medium |
-
2022
- 2022-02-28 CN CN202210186735.2A patent/CN114638405A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116049341A (en) * | 2023-03-08 | 2023-05-02 | 北京七兆科技有限公司 | Hydrologic data standardization method, device, equipment and storage medium |
| CN116049341B (en) * | 2023-03-08 | 2023-08-15 | 北京七兆科技有限公司 | Hydrologic data standardization method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sharma et al. | Survey of stock market prediction using machine learning approach | |
| Lucarelli et al. | A deep reinforcement learning approach for automated cryptocurrency trading | |
| Groll et al. | LASSO-type penalization in the framework of generalized additive models for location, scale and shape | |
| CN106485348A (en) | A kind of Forecasting Methodology of transaction data and device | |
| Khan et al. | A study of forecasting stocks price by using deep Reinforcement Learning | |
| Jadid Abdulkadir et al. | Unscented kalman filter for noisy multivariate financial time-series data | |
| Ruta | Automated trading with machine learning on big data | |
| US7480535B2 (en) | Method for the computer-supported generation of prognoses for operative systems and a system for the generation of prognoses for operative systems | |
| Ruxue et al. | Load forecasting based on weighted grey relational degree and improved ABC-SVM | |
| Jesus et al. | A model of anytime algorithm performance for bi-objective optimization | |
| CN114638405A (en) | Energy demand prediction method and device and computer equipment | |
| Wendong et al. | A multi-factor analysis model of quantitative investment based on GA and SVM | |
| CN112686470A (en) | Power grid saturation load prediction method and device and terminal equipment | |
| Fang et al. | An attention-based deep learning model for multi-horizon time series forecasting by considering periodic characteristic | |
| Sharifi et al. | Application of net cash flow at risk in project portfolio selection | |
| Tak | A novel ARMA type possibilistic fuzzy forecasting functions based on grey-wolf optimizer (ARMA-PFFs) | |
| Filipiak et al. | Dynamic portfolio optimization in ultra-high frequency environment | |
| CN114168635A (en) | Trading strategy mining method, system, equipment and storage medium for securities portfolio investment | |
| KAMLEY et al. | Multiple regression: A data mining approach for predicting the stock market trends based on open, close and high price of the month | |
| Wang et al. | LightGBM-BES-BiLSTM Carbon Price Prediction Based on Environmental Impact Factors | |
| Zhou et al. | Research on low-carbon flexible job shop scheduling problem based on improved Grey Wolf Algorithm | |
| Supriyanto | Comparison of Grid Search and Evolutionary Parameter Optimization with Neural Networks on JCI Stock Price Movements during the Covid 19 | |
| Li | Study on Early Warning on the Financial Risk of Project Venture Capital through a Neural Network Model | |
| CN117933677B (en) | Regional frequency modulation-based associated data prediction method and device for hydropower plant | |
| Hazboun | Decision Support System Terms of SME’s Credit Lending Based on Machine Learning Approach |
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 |