CN117613905B - Power demand mid-term prediction method and system based on multidimensional component decomposition - Google Patents
Power demand mid-term prediction method and system based on multidimensional component decomposition Download PDFInfo
- Publication number
- CN117613905B CN117613905B CN202410095288.9A CN202410095288A CN117613905B CN 117613905 B CN117613905 B CN 117613905B CN 202410095288 A CN202410095288 A CN 202410095288A CN 117613905 B CN117613905 B CN 117613905B
- Authority
- CN
- China
- Prior art keywords
- power demand
- component
- demand data
- period
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000000354 decomposition reaction Methods 0.000 title claims abstract description 27
- 230000001932 seasonal effect Effects 0.000 claims abstract description 75
- 239000013598 vector Substances 0.000 claims description 79
- 230000008859 change Effects 0.000 claims description 37
- 238000012935 Averaging Methods 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Probability & Statistics with Applications (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power demand medium-term prediction method and system based on multidimensional component decomposition, wherein the method comprises the following steps: decomposing the power demand data to obtain a growing trend component, a seasonal variation component and a random fluctuation component; predicting an electric power demand growth trend component based on a VaR model, and predicting an electric power demand seasonal variation component and an electric power demand random fluctuation component; calculating a predicted value of the power demand according to the predicted result; by adding white noise, statistical extreme points and other operations, the power demand is decomposed into an increasing trend component, a seasonal variation component and a random fluctuation component, the influence of seasonal factors and random factors on the power demand mid-term prediction can be fully considered, the prediction result is more accurate, and compared with a traditional method, the mid-term prediction result predicted based on historical power demand time sequence data can fully reflect the variation trend of different property components of power demand data in a future period, so that the method has higher accuracy.
Description
Technical Field
The invention belongs to the technical field of power demand prediction, and particularly relates to a power demand mid-term prediction method and system based on multidimensional component decomposition.
Background
The power demand prediction refers to predicting the power demand of a region, an industry or an enterprise in a future period of time, and the power demand mid-term prediction refers to predicting the power demand in the future period of months or even 1 year.
At present, a great deal of research on a power demand mid-term prediction method is carried out, and most of the research is to adopt a Var model, an ARIMA model, regression analysis and the like to predict the power demand in a future period of time based on historical power demand data. The above prediction method is relatively mature, but ignores the influence of different property components in the power demand data. Generally, the power demand is subject to periodic variation by positive seasonal factors, and even has certain random characteristics. In the prior art, the scheme often ignores the point, and further influences the accuracy of the mid-term prediction of the power demand.
Disclosure of Invention
The invention provides a power demand mid-term prediction method and system based on multidimensional component decomposition, which are used for solving the technical problem that the periodic change generated by positive seasonal factors and certain random characteristics influence the accuracy of power demand mid-term prediction.
In a first aspect, the present invention provides a method for mid-term prediction of power demand based on multidimensional component decomposition, comprising:
adding the acquired power demand time series data Obtaining first target power demand data/>, by using sub-white noiseWherein/>For the first power demand data vector,/>For the second power demand data vector,/>To add the first white noise,/>To add the second white noise,/>For/>Individual power demand data vectors,/>To add the/>White noise;
For the first target power demand data />First target power demand data vector,/>In terms of time period/>Averaging the preset period to obtain second target power demand data/>, after period averaging;
Performing differential processing on the second target power demand data to obtain a standard change rate corresponding to the second target power demand dataAnd obtain the standard change rate/>Curve and axis/>Number of intersecting extremum points/>;
Judging the number of the extreme pointsWhether the first preset threshold value or the second preset threshold value is equal to the first preset threshold value or not;
If the number of extreme points Equal to a first preset threshold or a second preset threshold, the number of time periods/>Is the number of seasonal change cycles of the power demand data, and the second target power demand data/>For/>First target Power demand data vector/>An increasing trend amount of change in (2);
Acquiring the increasing trend variation of each first target power demand data vector, and measuring the average value of each increasing trend variation to obtain the first target power demand data An increasing amount trend component of (2);
According to the first First target Power demand data vector/>Respectively calculating the first target power demand data/>A seasonal variation component and a random fluctuation component;
And respectively predicting a growing trend component, a seasonal variation component and a random fluctuation component in a future period of time, and calculating a final power demand predicted value according to a predicted result.
In a second aspect, the present invention provides a mid-demand prediction system for electric power based on multidimensional component decomposition, comprising:
an adding module configured to add the acquired power demand time series data Obtaining first target power demand data/>, by using sub-white noiseWherein/>For the first power demand data vector,/>For the second power demand data vector,/>To add the first white noise,/>In order to add the second white noise,For/>Individual power demand data vectors,/>To add the/>White noise;
a first processing module configured to process the first target power demand data />First target Power demand data vector/>,/>In terms of time period/>Averaging the preset period to obtain second target power demand data/>, after period averaging;
A second processing module configured to process the second target power demand dataPerforming differential processing to obtain a standard change rate/>, which corresponds to the second target power demand dataAnd obtain the standard change rate/>Curve and axis/>Number of intersecting extremum points/>;
A judging module configured to judge the number of extreme pointsWhether the first preset threshold value or the second preset threshold value is equal to the first preset threshold value or not;
A determining module configured to, if the number of extreme points Equal to a first preset threshold or a second preset threshold, the number of time periods/>Is the number of seasonal change cycles of the power demand data, and the second target power demand data/>For/>First target Power demand data vector/>An increasing trend amount of change in (2);
The acquisition module is configured to acquire the increasing trend variation of each first target power demand data vector, and average the increasing trend variation to acquire the first target power demand data An increasing amount trend component of (2);
A calculation module configured to according to the first First target Power demand data vector/>Respectively calculating the first target power demand data/>A seasonal variation component and a random fluctuation component;
And the prediction module is configured to predict a growth trend component, a seasonal variation component and a random fluctuation component in a future period of time respectively, and calculate a final power demand predicted value according to a predicted result.
In a third aspect, there is provided an electronic device, comprising: the system comprises at least one processor and a memory communicatively connected with the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the mid-power demand prediction method based on multi-dimensional component decomposition of any one of the embodiments of the present invention.
In a fourth aspect, the present invention also provides a computer readable storage medium having stored thereon a computer program, which when executed by a processor, causes the processor to perform the steps of the mid-power demand prediction method based on multi-dimensional component decomposition of any of the embodiments of the present invention.
According to the power demand mid-term prediction method and system based on multidimensional component decomposition, the power demand is decomposed into the growing trend component, the seasonal variation component and the random fluctuation component by adding white noise, counting the number of extreme points, filtering and other operations, the influence of the seasonal factor and the random factor on the power demand mid-term prediction can be fully considered, so that the prediction result is more accurate, and compared with the traditional method, the mid-term prediction result predicted based on historical power demand time sequence data can fully reflect the change trend of different property components of the power demand data in a future period, so that the method has more accuracy.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for predicting a mid-term power demand based on multi-dimensional component decomposition according to an embodiment of the present invention;
FIG. 2 is a block diagram of a system for predicting a mid-term power demand based on multidimensional component decomposition according to an embodiment of the present invention;
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flowchart of a method for predicting a mid-term power demand based on multidimensional component decomposition according to the present application is shown.
As shown in fig. 1, the method for predicting the mid-term of power demand based on multi-dimensional component decomposition specifically includes the following steps:
step S101, adding the acquired power demand time series data Obtaining first target power demand data/>, by using sub-white noise.
In the course of this step the process is carried out,For the first power demand data vector,/>For the second power demand data vector,/>To add the first white noise,/>To add the second white noise,/>For/>Individual power demand data vectors,/>To add the/>White noise.
Step S102, for the first target power demand data/>First target Power demand data vector/>,/>In terms of time period/>Averaging the preset period to obtain second target power demand data/>, after period averaging。
In this step, the first target power demand data/>First target power demand data vector,/>In terms of time period/>The expression for averaging processing for the preset period is:
,
In the method, in the process of the invention, For/>Electric power demand data after adding white noise for the second time/>The value of the individual time periods is set,For/>Electric power demand data after adding white noise for the second time/>Value of individual period,/>Is the firstElectric power demand data after adding white noise for the second time/>Value of individual period,/>For/>Electric power demand data after adding white noise for the second time/>Value of individual period,/>For/>Electric power demand data after adding white noise for the second time/>Value of individual period,/>For/>Electric power demand data after adding white noise for the second time/>Value of individual period,/>For/>Electric power demand data after adding white noise for the second time/>A value of each period.
Step S103, performing differential processing on the second target power demand data to obtain a standard change rate corresponding to the second target power demand dataAnd obtain the standard change rate/>Curve and axis of (2)Number of intersecting extremum points/>。
In this step, the standard change rate is calculatedThe expression of (2) is:
,
In the method, in the process of the invention, For/>Power demand data after adding white noise for the second time is per >Period after period averageNumerical value of/>For/>Power demand data after adding white noise for the second time is per >Period after period averaging of each period/>Is a numerical value of (2).
Step S104, judging the number of the extreme pointsWhether equal to the first preset threshold or the second preset threshold.
In practical application, if the number of extreme pointsNot equal to the first preset threshold or the second preset threshold, the time period number/>Iterating through the values of (1) and carrying out the iteration on the first target power demand data/>/>First target Power demand data vector/>,/>In the number of time periods after iteration/>And carrying out averaging treatment on the preset period to obtain second target power demand data after period averaging.
It should be noted that the first preset threshold is set to 0, and the second preset threshold is set to 12.
Step S105, if the number of extreme pointsEqual to a first preset threshold or a second preset threshold, the number of time periods/>Is the number of seasonal change cycles of the power demand data, and the second target power demand dataFor/>First target Power demand data vector/>Is a variable amount of the increasing trend of (a).
Step S106, obtaining the increasing trend variation of each first target power demand data vector, and obtaining the average value of each increasing trend variation to obtain the first target power demand dataIs a component of the growth trend of (a).
In this step, it is assumed that the first target power demand dataThe growth trend component of (a) isThen calculateThe expression of (2) is: In which, in the process, Is the firstFirst target power demand data vectorK is the total number of first target power demand data vectors.
Step S107, according to the firstFirst target Power demand data vector/>Respectively calculating the first target power demand data/>A seasonal variation component and a random fluctuation component of (a).
In this step, according to the first stepFirst target Power demand data vector/>Calculation of the amount of change in the growing trend of (1) >First target Power demand data vector/>Residual component/>The residual component/>Inputting to IIR low-pass filter to obtain the/>First target Power demand data vector/>Seasonal variation of (2); wherein,。
Acquiring seasonal variation of each first target power demand data vector, and measuring an average value of each seasonal variation to obtain first target power demand dataSeasonal variation component of (2); suppose the first target power demand data/>Seasonal variation component of/>Then calculate/>The expression of (2) is: /(I)。
According to the firstFirst target Power demand data vector/>Calculation of the increasing trend variable and seasonal variable of (1) >First target Power demand data vector/>Random fluctuation variation of (a); calculating random fluctuation variable quantity/>The expression of (2) is: /(I)。
Acquiring random fluctuation variable quantities of all first target power demand data vectors, and measuring average values of all random fluctuation variable quantities to obtain the first target power demand dataIs included in the random fluctuation component of the (c). Assume first target power demand dataThe random fluctuation variation component of (1) is/>Then calculate/>The expression of (2) is: /(I)。
Step S108, predicting the growth trend component, the seasonal variation component and the random fluctuation component in a future period of time respectively, and calculating a final power demand predicted value according to the predicted result.
In this step, the predicted value of the trend component is obtained by predicting the trend component in a future period of time based on a preset VaR (Vector autoregression, vector autoregressive) modelWherein a predicted value/>, of the growing trend component is calculatedThe expression of (2) is:
,
In the method, in the process of the invention, To-be-estimated parameter of 1 st autoregressive term,/>In the first/>, for increasing trend componentValue of individual period,/>To-be-estimated parameter of 2 nd autoregressive term,/>In the first/>, for increasing trend componentValue of individual period,/>Is the firstParameters to be estimated of the autoregressive term,/>For increasing the value of the trend component in the t-p time period,/>For the value of the random disturbance term in the t-th period,/>Is the number of time periods of the history data,/>Is the number of predicted time periods;
Calculating the proportion of the seasonal variation component in the power demand data of each period of one year to the increasing trend component, and predicting the seasonal variation component of a future period according to the proportion of the seasonal variation component in the power demand data of each period of one year to the increasing trend component to obtain the seasonal variation component predicted value Wherein the seasonal variation component predictive value/>, is calculatedThe expression of (2) is:
,
,
,
In the method, in the process of the invention, For the proportion of seasonal variation component to the increasing trend component in the power demand data for each period of one year,/>In the historical power demand data, the/>Years/>Ratio of seasonal variation component to increasing trend component,/>For years contained in historical power demand data,/>In the historical power demand data, the/>Years/>Seasonal variation component of/>In the historical power demand data, the/>Years/>Is a component of the increasing trend of (2);
Predicting random fluctuation components according to an arithmetic average method to obtain random fluctuation component predicted values Calculating the predicted value/>, of the random fluctuation componentThe expression of (2) is:
,
In the method, in the process of the invention, For the value of the random fluctuation component in the period t-j,/>The period number is an arithmetic average;
Predicting the value of the growth trend component Predicted value of seasonal variation component/>Said random fluctuation component predictive value/>And summing to obtain a final power demand predicted value.
In summary, the method of the application decomposes the power demand data, predicts the decomposed growth trend component, seasonal variation component and random fluctuation component, calculates the power demand predicted value according to the predicted result, decomposes the power demand into the growth trend component, seasonal variation component and random fluctuation component by adding white noise, counting the number of extreme points, filtering processing and other operations in the process, fully considers the influence of seasonal factors and random factors on the power demand mid-term prediction, makes the predicted result more accurate, and compared with the traditional method, the mid-term predicted result predicted based on the historical power demand time sequence data can fully reflect the variation trend of different property components of the power demand data in a future period, thereby having more accuracy.
Referring to fig. 2, a block diagram of a power demand mid-term prediction system based on multidimensional component decomposition according to the present application is shown.
As shown in fig. 2, the mid-demand power prediction system 200 includes an adding module 210, a first processing module 220, a second processing module 230, a judging module 240, a determining module 250, an obtaining module 260, a calculating module 270, and a predicting module 280.
Wherein the adding module 210 is configured to add the acquired power demand time series dataObtaining first target power demand data/>, by using sub-white noiseWherein/>For the first power demand data vector,/>For the second power demand data vector,/>To add the first white noise,/>To add the second white noise,/>For/>Individual power demand data vectors,/>To add the/>White noise; a first processing module 220 configured to perform a process on the first target power demand data/>/>First target power demand data vector,/>In terms of time period/>Averaging the preset period to obtain second target power demand data/>, after period averaging; A second processing module 230 configured to perform a process on the second target power demand data/>Performing differential processing to obtain a standard change rate/>, which corresponds to the second target power demand dataAnd obtain the standard change rate/>Curve and axis/>Number of intersecting extremum points/>; A judging module 240 configured to judge the number/>Whether the first preset threshold value or the second preset threshold value is equal to the first preset threshold value or not; a determining module 250 configured to, if the number of extreme points/>Equal to a first preset threshold or a second preset threshold, the number of time periods/>Is the number of seasonal change cycles of the power demand data, and the second target power demand data/>For/>First target Power demand data vector/>An increasing trend amount of change in (2); an obtaining module 260 configured to obtain the growth trend variation of each first target power demand data vector, and average the growth trend variation to obtain the first target power demand data/>An increasing amount trend component of (2); a calculation module 270 configured to, according to the/>First target Power demand data vector/>Respectively calculating the first target power demand data/>A seasonal variation component and a random fluctuation component; the prediction module 280 is configured to predict the component of the growing trend, the component of the seasonal variation and the component of the random fluctuation respectively in a future period of time, and calculate a final predicted value of the power demand according to the predicted result.
It should be understood that the modules depicted in fig. 2 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations and features described above for the method and the corresponding technical effects are equally applicable to the modules in fig. 2, and are not described here again.
In other embodiments, embodiments of the present invention further provide a computer readable storage medium having stored thereon a computer program, the program instructions, when executed by a processor, cause the processor to perform the mid-power demand prediction method based on multidimensional component decomposition in any of the method embodiments described above;
As one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions configured to:
adding the acquired power demand time series data Obtaining first target power demand data/>, by using sub-white noiseWherein/>For the first power demand data vector,/>For the second power demand data vector,/>To add the first white noise,/>To add the second white noise,/>For/>Individual power demand data vectors,/>To add the/>White noise;
For the first target power demand data />First target power demand data vector,/>In terms of time period/>Averaging the preset period to obtain second target power demand data/>, after period averaging;
Performing differential processing on the second target power demand data to obtain a standard change rate corresponding to the second target power demand dataAnd obtain the standard change rate/>Curve and axis/>Number of intersecting extremum points/>;
Judging the number of the extreme pointsWhether the first preset threshold value or the second preset threshold value is equal to the first preset threshold value or not;
If the number of extreme points Equal to a first preset threshold or a second preset threshold, the number of time periods/>Is the number of seasonal change cycles of the power demand data, and the second target power demand data/>For/>First target Power demand data vector/>An increasing trend amount of change in (2);
Acquiring the increasing trend variation of each first target power demand data vector, and measuring the average value of each increasing trend variation to obtain the first target power demand data An increasing amount trend component of (2);
According to the first First target Power demand data vector/>Respectively calculating the first target power demand data/>A seasonal variation component and a random fluctuation component;
And respectively predicting a growing trend component, a seasonal variation component and a random fluctuation component in a future period of time, and calculating a final power demand predicted value according to a predicted result.
The computer readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for a function; the storage data area may store data created from the use of the mid-demand prediction system based on multidimensional component decomposition, and the like. In addition, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer readable storage medium optionally includes memory remotely located with respect to the processor, the remote memory being connectable to the mid-demand prediction system for power based on multi-dimensional component decomposition via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 3, where the device includes: a processor 310 and a memory 320. The electronic device may further include: an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 may be connected by a bus or other means, for example in fig. 3. Memory 320 is the computer-readable storage medium described above. The processor 310 executes various functional applications of the server and data processing by running non-volatile software programs, instructions and modules stored in the memory 320, i.e., implements the mid-power demand prediction method based on multi-dimensional component decomposition of the above-described method embodiments. The input device 330 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the mid-demand power prediction system based on multi-dimensional component decomposition. The output device 340 may include a display device such as a display screen.
The electronic equipment can execute the method provided by the embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment may be found in the methods provided in the embodiments of the present invention.
As an embodiment, the electronic device is applied to a power demand mid-term prediction system based on multidimensional component decomposition, and is used for a client, and includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to:
adding the acquired power demand time series data Obtaining first target power demand data/>, by using sub-white noiseWherein/>For the first power demand data vector,/>For the second power demand data vector,/>To add the first white noise,/>To add the second white noise,/>For/>Individual power demand data vectors,/>To add the/>White noise;
For the first target power demand data />First target power demand data vector,/>In terms of time period/>Averaging the preset period to obtain second target power demand data/>, after period averaging;
Performing differential processing on the second target power demand data to obtain a standard change rate corresponding to the second target power demand dataAnd obtain the standard change rate/>Curve and axis/>Number of intersecting extremum points/>;
Judging the number of the extreme pointsWhether the first preset threshold value or the second preset threshold value is equal to the first preset threshold value or not;
If the number of extreme points Equal to a first preset threshold or a second preset threshold, the number of time periods/>Is the number of seasonal change cycles of the power demand data, and the second target power demand data/>For/>First target Power demand data vector/>An increasing trend amount of change in (2);
Acquiring the increasing trend variation of each first target power demand data vector, and measuring the average value of each increasing trend variation to obtain the first target power demand data An increasing amount trend component of (2);
According to the first First target Power demand data vector/>Respectively calculating the first target power demand data/>A seasonal variation component and a random fluctuation component;
And respectively predicting a growing trend component, a seasonal variation component and a random fluctuation component in a future period of time, and calculating a final power demand predicted value according to a predicted result.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product, which may be stored in a computer-readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the various embodiments or methods of some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A mid-term prediction method of power demand based on multidimensional component decomposition, comprising:
adding the acquired power demand time series data Sub-white noise to obtain first target power demand dataWherein/>For the first power demand data vector,/>For the second power demand data vector,/>To add the first white noise,/>To add the second white noise,/>For/>Individual power demand data vectors,/>To add the/>White noise;
For the first target power demand data />First target power demand data vector,/>In terms of time period/>Averaging the preset period to obtain second target power demand data/>, after period averaging;
Performing differential processing on the second target power demand data to obtain a standard change rate corresponding to the second target power demand dataAnd obtain the standard change rate/>Curve and axis/>Number of intersecting extremum points/>;
Judging the number of the extreme pointsWhether the first preset threshold value or the second preset threshold value is equal to the first preset threshold value or not;
If the number of extreme points Equal to a first preset threshold or a second preset threshold, the number of time periods/>Is the number of seasonal change cycles of the power demand data, and the second target power demand data/>For/>First target Power demand data vector/>An increasing trend amount of change in (2);
Acquiring the increasing trend variation of each first target power demand data vector, and measuring the average value of each increasing trend variation to obtain the first target power demand data An increasing amount trend component of (2);
According to the first First target Power demand data vector/>Respectively calculating the first target power demand data/>A seasonal variation component and a random fluctuation component;
Predicting the trend component, the seasonal variation component and the random fluctuation component in a future period of time respectively, and calculating a final power demand predicted value according to a predicted result, wherein the predicting the trend component, the seasonal variation component and the random fluctuation component in the future period of time respectively, and calculating the final power demand predicted value according to the predicted result comprises:
Predicting the growth trend component in a future period of time based on a preset VaR model to obtain a prediction value of the growth trend component Wherein a predicted value/>, of the growing trend component is calculatedThe expression of (2) is:
,
In the method, in the process of the invention, To-be-estimated parameter of 1 st autoregressive term,/>In the first/>, for increasing trend componentValue of individual period,/>To-be-estimated parameter of 2 nd autoregressive term,/>In the first/>, for increasing trend componentValue of individual period,/>For/>Parameters to be estimated of the autoregressive term,/>For increasing the value of the trend component in the t-p time period,/>For the value of the random disturbance term in the t-th period,/>Is the number of time periods of the history data,/>Is the number of predicted time periods;
Calculating the proportion of the seasonal variation component in the power demand data of each period of one year to the increasing trend component, and predicting the seasonal variation component of a future period according to the proportion of the seasonal variation component in the power demand data of each period of one year to the increasing trend component to obtain the seasonal variation component predicted value Wherein the seasonal variation component predictive value/>, is calculatedThe expression of (2) is:
,
,
,
In the method, in the process of the invention, The seasonal variation component in the power demand data for each period of a year is a proportion of the increasing trend component,In the historical power demand data, the proportion of seasonal variation component of the annual period to the growth trend component is/areFor years contained in historical power demand data,/>In historical power demand data, seasonal variation components of the annual time period,An increasing trend component of the annual time period in the historical power demand data;
Predicting random fluctuation components according to an arithmetic average method to obtain random fluctuation component predicted values Calculating the predicted value/>, of the random fluctuation componentThe expression of (2) is:
,
In the method, in the process of the invention, For the value of the random fluctuation component in the period t-j,/>The period number is an arithmetic average;
Predicting the value of the growth trend component Predicted value of seasonal variation component/>Said random fluctuation component predictive value/>And summing to obtain a final power demand predicted value.
2. A mid-demand prediction method based on multi-dimensional component decomposition according to claim 1, wherein said method is based on said first stepFirst target Power demand data vector/>Respectively calculating the first target power demand data/>The seasonal variation component and the random fluctuation component of (a) include:
According to the first First target Power demand data vector/>Calculation of the amount of change in the growing trend of (1) >First target Power demand data vector/>Residual component/>The residual component/>Inputting to IIR low-pass filter to obtain the/>First target Power demand data vector/>Seasonal variation of (2);
Acquiring seasonal variation amounts of the first target power demand data vectors, and measuring average values of the seasonal variation amounts to obtain the first target power demand data Seasonal variation component of (2);
According to the first First target Power demand data vector/>Calculation of the increasing trend variable and seasonal variable of (a)First target Power demand data vector/>Random fluctuation variation of (a);
Acquiring random fluctuation variable quantities of all first target power demand data vectors, and measuring average values of all random fluctuation variable quantities to obtain the first target power demand data Is included in the random fluctuation component of the (c).
3. The mid-demand prediction method based on multi-dimensional component decomposition according to claim 1, wherein said first target power demand data is/>First target power demand data vector,/>In terms of time period/>The expression for averaging processing for the preset period is:
,
In the method, in the process of the invention, For/>Electric power demand data after adding white noise for the second time/>Value of individual period,/>For/>Electric power demand data after adding white noise for the second time/>Value of individual period,/>For/>Electric power demand data after adding white noise for the second time/>Value of individual period,/>For/>Electric power demand data after adding white noise for the second time/>Value of individual period,/>For/>Electric power demand data after adding white noise for the second time/>Value of individual period,/>For/>Electric power demand data after adding white noise for the second time/>Value of individual period,/>For/>Electric power demand data after adding white noise for the second time/>A value of each period.
4. The mid-demand prediction method for electric power based on multi-dimensional component decomposition according to claim 1, wherein said standard rate of change is calculatedThe expression of (2) is:
,
In the method, in the process of the invention, For/>Power demand data after adding white noise for the second time is per >Period after period averaging of each period/>Numerical value of/>For/>Power demand data after adding white noise for the second time is per >Period after period averaging of each period/>Is a numerical value of (2).
5. The method for predicting mid-demand power based on multidimensional component decomposition according to claim 1, wherein the number of time periods isThe value of (2) is/>;
Judging the number of the extreme pointsAfter whether the first preset threshold value or the second preset threshold value is equal, the method further comprises:
If the number of extreme points Not equal to the first preset threshold value or the second preset threshold value, the number of the time periods/>Iterating through the values of the first target power demand data/>/>First target power demand data vector,/>In the number of time periods after iteration/>And carrying out averaging treatment on the preset period to obtain second target power demand data after period averaging.
6. A mid-demand prediction system for power based on multi-dimensional component decomposition, comprising:
an adding module configured to add the acquired power demand time series data Obtaining first target power demand data/>, by using sub-white noiseWherein/>For the first power demand data vector,/>For the second power demand data vector,/>To add the first white noise,/>To add the second white noise,/>For/>Individual power demand data vectors,/>To add the/>White noise;
a first processing module configured to process the first target power demand data />First target Power demand data vector/>,/>In terms of time period/>Averaging the preset period to obtain second target power demand data/>, after period averaging;
A second processing module configured to process the second target power demand dataPerforming differential processing to obtain a standard change rate/>, which corresponds to the second target power demand dataAnd obtain the standard change rate/>Curve and axis/>Number of intersecting extremum points/>;
A judging module configured to judge the number of extreme pointsWhether the first preset threshold value or the second preset threshold value is equal to the first preset threshold value or not;
A determining module configured to, if the number of extreme points Equal to a first preset threshold or a second preset threshold, the number of time periods/>Is the number of seasonal change cycles of the power demand data, and the second target power demand dataFor/>First target Power demand data vector/>An increasing trend amount of change in (2);
The acquisition module is configured to acquire the increasing trend variation of each first target power demand data vector, and average the increasing trend variation to acquire the first target power demand data An increasing amount trend component of (2);
A calculation module configured to according to the first First target Power demand data vector/>Respectively calculating the first target power demand data/>A seasonal variation component and a random fluctuation component;
The prediction module is configured to predict a growing trend component, a seasonal variation component and a random fluctuation component in a future period of time respectively, and calculate a final power demand predicted value according to a prediction result, wherein the predicting the growing trend component, the seasonal variation component and the random fluctuation component in the future period of time respectively, and calculating the final power demand predicted value according to the prediction result comprises:
Predicting the growth trend component in a future period of time based on a preset VaR model to obtain a prediction value of the growth trend component Wherein a predicted value/>, of the growing trend component is calculatedThe expression of (2) is:
,
In the method, in the process of the invention, To-be-estimated parameter of 1 st autoregressive term,/>In the first/>, for increasing trend componentValue of individual period,/>To-be-estimated parameter of 2 nd autoregressive term,/>In the first/>, for increasing trend componentValue of individual period,/>For/>Parameters to be estimated of the autoregressive term,/>For increasing the value of the trend component in the t-p time period,/>For the value of the random disturbance term in the t-th period,/>Is the number of time periods of the history data,/>Is the number of predicted time periods;
Calculating the proportion of the seasonal variation component in the power demand data of each period of one year to the increasing trend component, and predicting the seasonal variation component of a future period according to the proportion of the seasonal variation component in the power demand data of each period of one year to the increasing trend component to obtain the seasonal variation component predicted value Wherein the seasonal variation component predictive value/>, is calculatedThe expression of (2) is:
,
,
,
In the method, in the process of the invention, The seasonal variation component in the power demand data for each period of a year is a proportion of the increasing trend component,In the historical power demand data, the proportion of seasonal variation component of the annual period to the growth trend component is/areFor years contained in historical power demand data,/>In historical power demand data, seasonal variation components of the annual time period,An increasing trend component of the annual time period in the historical power demand data;
Predicting random fluctuation components according to an arithmetic average method to obtain random fluctuation component predicted values Calculating the predicted value/>, of the random fluctuation componentThe expression of (2) is:
,
In the method, in the process of the invention, For the value of the random fluctuation component in the period t-j,/>The period number is an arithmetic average;
Predicting the value of the growth trend component Predicted value of seasonal variation component/>Said random fluctuation component predictive value/>And summing to obtain a final power demand predicted value.
7. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 5.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method of any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410095288.9A CN117613905B (en) | 2024-01-24 | 2024-01-24 | Power demand mid-term prediction method and system based on multidimensional component decomposition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410095288.9A CN117613905B (en) | 2024-01-24 | 2024-01-24 | Power demand mid-term prediction method and system based on multidimensional component decomposition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117613905A CN117613905A (en) | 2024-02-27 |
CN117613905B true CN117613905B (en) | 2024-05-14 |
Family
ID=89946623
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410095288.9A Active CN117613905B (en) | 2024-01-24 | 2024-01-24 | Power demand mid-term prediction method and system based on multidimensional component decomposition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117613905B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118171899B (en) * | 2024-05-16 | 2024-08-13 | 中电装备山东电子有限公司 | Power demand response business analysis method based on private transformer terminal user |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105184674A (en) * | 2015-09-07 | 2015-12-23 | 杭州凯达电力建设有限公司 | Electric energy metering error prediction method and device |
CN106295798A (en) * | 2016-08-29 | 2017-01-04 | 江苏省电力试验研究院有限公司 | Empirical mode decomposition and Elman neural network ensemble wind-powered electricity generation Forecasting Methodology |
CN113298308A (en) * | 2021-05-31 | 2021-08-24 | 石家庄科林电气股份有限公司 | Parameter self-adaptive power consumption prediction method and system |
CN113962491A (en) * | 2021-12-01 | 2022-01-21 | 国网河北省电力有限公司雄安新区供电公司 | Short-term combined prediction method and device for cooling, heating and power loads based on seasonal decomposition |
WO2022111841A1 (en) * | 2020-11-27 | 2022-06-02 | Hitachi Energy Switzerland Ag | Load forecasting for electrical equipment using machine learning |
CN114676896A (en) * | 2022-03-16 | 2022-06-28 | 佰聆数据股份有限公司 | Electric power operation monitoring method and system based on time decomposition improved algorithm |
CN116995668A (en) * | 2023-08-16 | 2023-11-03 | 国家电网公司东北分部 | Middle-long term power load prediction method and system based on improved seasonal ARIMA model |
CN117318050A (en) * | 2023-11-28 | 2023-12-29 | 国网湖北省电力有限公司 | Virtual power plant load data prediction method integrating 5G short sharing |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210224677A1 (en) * | 2020-01-21 | 2021-07-22 | International Business Machines Corporation | Forecasting model generation for time series data with change point and seasonality |
-
2024
- 2024-01-24 CN CN202410095288.9A patent/CN117613905B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105184674A (en) * | 2015-09-07 | 2015-12-23 | 杭州凯达电力建设有限公司 | Electric energy metering error prediction method and device |
CN106295798A (en) * | 2016-08-29 | 2017-01-04 | 江苏省电力试验研究院有限公司 | Empirical mode decomposition and Elman neural network ensemble wind-powered electricity generation Forecasting Methodology |
WO2022111841A1 (en) * | 2020-11-27 | 2022-06-02 | Hitachi Energy Switzerland Ag | Load forecasting for electrical equipment using machine learning |
CN113298308A (en) * | 2021-05-31 | 2021-08-24 | 石家庄科林电气股份有限公司 | Parameter self-adaptive power consumption prediction method and system |
CN113962491A (en) * | 2021-12-01 | 2022-01-21 | 国网河北省电力有限公司雄安新区供电公司 | Short-term combined prediction method and device for cooling, heating and power loads based on seasonal decomposition |
CN114676896A (en) * | 2022-03-16 | 2022-06-28 | 佰聆数据股份有限公司 | Electric power operation monitoring method and system based on time decomposition improved algorithm |
CN116995668A (en) * | 2023-08-16 | 2023-11-03 | 国家电网公司东北分部 | Middle-long term power load prediction method and system based on improved seasonal ARIMA model |
CN117318050A (en) * | 2023-11-28 | 2023-12-29 | 国网湖北省电力有限公司 | Virtual power plant load data prediction method integrating 5G short sharing |
Non-Patent Citations (2)
Title |
---|
Monthly electricity consumption forecast of the park based on hybrid forecasting method;Bin Peng et al.;《 2021 China International Conference on Electricity Distribution (CICED)》;20211008;第789-793页 * |
计及季节与趋势因素的综合能源系统负荷预测;张铁岩等;《沈阳工业大学学报》;20200930;第42卷(第5期);第481-487页 * |
Also Published As
Publication number | Publication date |
---|---|
CN117613905A (en) | 2024-02-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11888316B2 (en) | Method and system of predicting electric system load based on wavelet noise reduction and EMD-ARIMA | |
CN117613905B (en) | Power demand mid-term prediction method and system based on multidimensional component decomposition | |
CN111382906A (en) | Power load prediction method, system, equipment and computer readable storage medium | |
CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
CN112508299A (en) | Power load prediction method and device, terminal equipment and storage medium | |
CN111598303A (en) | Summer short-term load prediction method based on meteorological component decomposition | |
CN115616333A (en) | Power distribution network line loss prediction method and system | |
CN117934247B (en) | Carbon emission factor prediction method and device based on time sequence decomposition, electronic equipment and storage medium | |
CN115271219A (en) | Short-term load prediction method and prediction system based on causal relationship analysis | |
CN111709585A (en) | Air conditioner load prediction method and device and storage medium | |
CN112700050B (en) | Method and system for predicting ultra-short-term 1 st point power of photovoltaic power station | |
CN111950752A (en) | Photovoltaic power station generating capacity prediction method, device and system and storage medium thereof | |
CN116544931B (en) | Power load distribution prediction method based on integrated fragment transformation and time convolution network | |
CN116436098B (en) | Multi-equipment intermodal control method and system for power equipment | |
CN110826196B (en) | Industrial equipment operation data processing method and device | |
CN109376957B (en) | Method for predicting load of thermal power plant | |
CN117035155A (en) | Water quality prediction method | |
CN111080037A (en) | Short-term power load prediction method and device based on deep neural network | |
CN110969238A (en) | Method and device for calibrating electricity consumption data | |
CN115169747A (en) | Method and device for predicting non-stationary time sequence of power load and related equipment | |
CN115545490A (en) | Power station engineering cost analysis method and device based on small sample machine learning | |
CN115759455A (en) | Load probability density prediction method based on time sequence Gaussian mixture density network | |
CN115528684A (en) | Ultra-short-term load prediction method and device and electronic equipment | |
CN114117349A (en) | Power system random variable probability analysis method, system, equipment and storage medium | |
CN114091878A (en) | Energy power industry chain risk early warning method and system based on spot market model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |