CN108022014A - A kind of Load Prediction In Power Systems method and system - Google Patents
A kind of Load Prediction In Power Systems method and system Download PDFInfo
- Publication number
- CN108022014A CN108022014A CN201711269680.7A CN201711269680A CN108022014A CN 108022014 A CN108022014 A CN 108022014A CN 201711269680 A CN201711269680 A CN 201711269680A CN 108022014 A CN108022014 A CN 108022014A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- data
- prediction
- load
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000010183 spectrum analysis Methods 0.000 claims abstract description 11
- 238000012706 support-vector machine Methods 0.000 claims abstract description 9
- 238000005457 optimization Methods 0.000 claims description 11
- 210000000349 chromosome Anatomy 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 3
- 230000001373 regressive effect Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000009825 accumulation Methods 0.000 claims description 2
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000013459 approach Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 2
- 240000002853 Nelumbo nucifera Species 0.000 description 2
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000004043 dyeing Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
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
-
- 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
-
- 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
-
- 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)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (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 kind of Load Prediction In Power Systems method and system, including：Obtain electric system historical load data；The historical load data got is pre-processed；Trend is carried out to pretreated data to handle, obtain trend term using gray theory；Carry out spectrum analysis and determine Decomposition order, the data after going trend processing are decomposed using variation mode decomposition；The support vector cassification summation that data after decomposition are optimized using improved NSGA II is reconstructed；Trend term is added to obtain final prediction result according to the result after reconstruct；The predicted value of each load component is overlapped, determines actual prediction result.Beneficial effect of the present invention：Load Prediction In Power Systems method and system provided by the present invention, the support vector machine method optimized based on gray theory-variation mode decomposition and NSGA II, can successfully managing load prediction, to fluctuate big accuracy not high, the shortcomings that being easily trapped into local optimum.
Description
Technical field
The present invention relates to technical field of power systems, more particularly to a kind of Load Prediction In Power Systems method and system.
Background technology
Load forecast is the important content of Power System Planning and operation of power networks, premise and basis.In country energetically
Energy conservation and environmental protection is advocated to save under the situation of existing energy-output ratio, the accuracy of load forecast is related to whole power grid enterprise
Economy, Effec-tive Function and the entirely safe operation of power generation power grid of industry, i.e., essence of the current situation for load forecast
Degree proposes the requirement of higher standard.
Currently used short-term load forecasting conventional method has pre- as the classics of representative using time series method, regression analysis
Survey method, using expert system approach, neutral net, fuzzy logic method as representative artificial intelligence approach.Since electric load changes
Process is a highly complex non-linear process, and conventional method is difficult to set up effective mathematical model, causes prediction result smart
Degree is not high.
Gray forecast approach error when predicting the electric load of fluctuation change greatly is larger in existing electric system prediction,
It is poor to discrete data precision of prediction.
The theoretical foundation of artificial intelligence maturation, there is an application in practical power systems, however they also have it is respective
Defect, forecast result are unsatisfactory.
The content of the invention
The purpose of the present invention is exactly to solve the above-mentioned problems, it is proposed that a kind of Load Prediction In Power Systems method and is
The support vector machine method that system, this method and system are optimized based on gray theory-variation mode decomposition and NSGA-II, Neng Gouyou
It is not high that effect fluctuates load prediction big accuracy, the shortcomings that being easily trapped into local optimum.
To achieve these goals, the present invention adopts the following technical scheme that：
The invention discloses a kind of Load Prediction In Power Systems method, comprise the following steps：
(1) electric system historical load data is obtained；
(2) historical load data got is pre-processed；
(3) trend is carried out to pretreated data to handle, obtain trend term using gray theory；
(4) carry out spectrum analysis and determine Decomposition order, the data after going trend processing are carried out using variation mode decomposition
Decompose；
(5) the support vector cassification summation that the data after decomposition are optimized using improved NSGA- II is reconstructed；
(6) trend term is added to obtain final prediction result according to the result after reconstruct；
(7) predicted value of each load component is overlapped, determines actual prediction result.
Further, the historical load data to getting pre-processes, and is specially：
Data are carried out to change and remove outlier processing at equal intervals, the data containing marginal value is changed at equal intervals, and dispose
Edge data.
Further, it is described using gray theory pretreated data are carried out with trend processing to be specially：
To pretreated data accumulation or inverse accumulated generating ash model, the differential equation is determined with time series data
Parameter, progressively makes ash quantity albefaction, and then makes prediction to to-be.
Further, according to the definition type of gray system theory, parameter a and u are solved；
Parameter a and u according to trying to achieve obtain prediction model and are：
Reduced by regressive, it is as follows to obtain final prediction result：
Wherein, x(1)For x(0)One-accumulate generation new sequence；A and u is parameter, u items in order to control；x(0)(1) it is
Beginning data；x(0)(t) it is data of time when being t, x(1)(t) it is x(0)(t) the new sequence of one-accumulate generation；For t
Data when+1,For one-accumulate generationNew sequence.
Further, the data after going trend processing are decomposed specially using variation mode decomposition：
Using variation mode decomposition data, input signal is decomposed into the k finite bandwidths with centre frequency, is referred to as
Mode uk, make the sum of the bandwidth estimation of each mode minimum.
Further, decomposition model is specially：
In formula, δ (t) is impulse function；To seek partial derivative to t；F is original signal, ukFor the mode of k-th of limited-bandwidth
Component；ωkFor the centre frequency of the modal components of k-th of limited-bandwidth；uk(t) it is k-th limited-bandwidth of time when being t
Modal components.
Further, the support vector cassification that the data after decomposition are optimized using improved NSGA- II is summed and carried out
Reconstruct, is specially：
According to supporting vector machine model, introduce Lagrange multiplier algorithm and obtain optimization object function：
Introduce Nonlinear MappingRn→ H, a new data set is mapped as by sample：
Then the above problem is converted into：
Wherein, αiFor Lagrange multiplier.
Further, pretreatment operation is carried out using method for normalizing, support vector machines parameter is optimized, specifically
For：
In formula：x'ijFor the normalized value of i-th of input quantity jth dimension, x'ij∈[0,1]；Tieed up for i-th of input quantity jth
Original value；xjminMinimum value in being tieed up for all input quantity jth；xjmaxMaximum in being tieed up for all input quantity jth；
Set population scale Ppop, iterative algebra Ggen, using floating-point encoding, chromosome is encoded, wherein dyeing
The 1st multiplication factor C of body, the 2nd is Radial basis kernel function parameter γ, and the 3rd is Emse, the 4th is 1-R, and the 5th is Rrank,
The layering of i.e. every chromosome, the smaller then fitness of numerical value is bigger, and the 6th is Ddis, for level it is identical when judge degree of rarefication according to
According to；
Random generation initial population, with EmseIt is object function with R, carries out quick non-dominated ranking and selection, intersect, become
It is different；
When iterations reaches maximum iteration, optimized parameter C and γ are obtained.
The invention also discloses a kind of Load Prediction In Power Systems system, including：
Data acquisition module, for obtaining electric system historical load data；
Pretreatment module, carries out data at equal intervals to change and remove the processing of outlier；
Trend processing module is gone, carrying out trend to initial data using gray theory is handled；
Training optimization module, carries out spectrum analysis and determines Decomposition order, decomposed input data with variation mode decomposition, and
The support vector cassification that the data of processing are optimized using improved NSGA- II is summed and is reconstructed；
Prediction module, adds trend term to obtain prediction result according to the result after reconstruct；
As a result determining module, for the predicted value of each load component to be overlapped, determines actual prediction result.
Further, further include：
Processing module, for after the electric system historical load data is obtained, being born to the electric system history
Lotus data are normalized.
The beneficial effects of the invention are as follows：
Load Prediction In Power Systems method and system provided by the present invention, are System History load data by obtaining point
Trend is carried out to historical load data to handle, and determine Decomposition order using spectrum analysis using gray theory, then through variation
Mode decomposition decomposes input data, carries out classification summation reconstruct using improved NSGA- II support vector machines optimized afterwards,
Finally result is added trend term and is superimposed and obtains prediction result, Load Prediction In Power Systems system provided by the present invention, is based on
Gray theory-variation mode decomposition and the support vector machine method of NSGA-II optimizations, it is big can to successfully manage load prediction fluctuation
Accuracy is not high, the shortcomings that being easily trapped into local optimum.
Brief description of the drawings
Fig. 1 is a kind of flow chart of embodiment of Load Prediction In Power Systems method provided by the present invention；
Fig. 2 is the prediction model schematic diagram of the embodiment of the present invention；
Fig. 3 is the schematic diagram that SVM handles data；
Fig. 4 is the amplitude change curve of sampled data and utilizes Grey Theory Forecast curve map；
Fig. 5 is the sampled data amplitude change curve after trend；
Fig. 6 removes the spectrum analysis figure after trend for sampled data；
Fig. 7 is each mode and spectrum analysis figure after sampled data progress variation mode decomposition；
Fig. 8 (a)-Fig. 8 (c) is respectively the prediction result of each modal components of sampled data；
Fig. 9 finally predicts for method GM-VMD-SVM involved by this patent and other two methods EMD-SVM and GM-SVM
Comparative result result figure；
Figure 10 is the structure diagram of Load Prediction In Power Systems device provided in an embodiment of the present invention.
Embodiment：
The present invention will be further described with example below in conjunction with the accompanying drawings：
A kind of flow chart of embodiment of power system load method provided by the present invention was as shown in Figure 1, should
Method includes：
Step S101：Obtain electric system historical load data；
Electric system historical load data can be the historical data gathered by data acquisition and monitoring device.Obtaining
To after historical load data, it can further include and pretreatment is normalized to the electric system historical load data.
Step S102：Data are pre-processed；
Data are carried out to change and remove outlier processing at equal intervals, makes to obtain data containing marginal value and changes at equal intervals, and dispose
Edge data, to improve precision of prediction.
Step S103：Trend is carried out using gray theory to data to handle.
The definition type of gray system theory is
x(0)(t)+az(1)(t)=u t=2,3 ..., N；
z(1)(t)=0.5x(1)(t-1)+0.5x(1)(t)；
Wherein x(1)For x(0)One-accumulate generation new sequence；A and u is parameter, wherein u items in order to control, above-mentioned two formula
It can obtain：
Bring a, u for trying to achieve into following equation：
Can obtain prediction model is
Reduced by regressive, it is as follows to obtain final prediction result：
x(1)For x(0)One-accumulate generation new sequence；A and u is parameter, u items in order to control；x(0)(1) it is starting number
According to；x(0)(t) it is data of time when being t, x(1)(t) it is x(0)(t) the new sequence of one-accumulate generation；For t+1 when
Data,For one-accumulate generationNew sequence.
Step S104：Carry out spectrum analysis and determine Decomposition order, decomposed input data with variation mode decomposition, and will place
The data of reason are reconstructed using the support vector cassification summation of improved NSGA- II optimizations.
Using variation mode decomposition data, input signal is decomposed into the k finite bandwidths with centre frequency, is referred to as
Mode uk, make the sum of the bandwidth estimation of each mode minimum, its decomposition model is as follows：
In formula：{uk}:={ u1,…,ukIt is each modal components；{ωk}:={ ω1,ω2,…,ωkIt is each modal components
Centre frequency；δ (t) is impulse function；To seek partial derivative to t；F is original signal.
To try to achieve the optimal solution of above-mentioned restricted problem, Lagrange multiplier operator λ (t) is introduced, by restrictive variational problem
It is converted into non-binding variational problem：
The saddle point that optimal solution can ask for above-mentioned Lagrangian by alternating direction Multiplier Algorithm obtains.
Summed and reconstructed using the support vector cassification of improved NSGA- II optimizations, supporting vector machine model is：
In formula：ω is hyperplane method vector；C is penalty factor；N is sample size；ξ is relaxation factor, is represented linearly not
Permission mistake point rate in the case of can dividing；yiFor sample output quantity, and yi∈{-1,+1}；xiFor sample input quantity；B is threshold value.
Introduce Lagrange multiplier algorithm and obtain optimization object function：
α in formulaiFor Lagrange multiplier.
Introduce Nonlinear MappingRn→ H, a new data set is mapped as by sample
Then the above problem is converted into：
The precision of prediction of SVM regression models is generally characterized with performance by mean square error Emse and coefficient R, its formula
It is as follows：
Pretreatment operation is carried out using method for normalizing, it is as follows to support vector machines parameter optimization, formula：
In formula：x'ijFor the normalized value of i-th of input quantity jth dimension, x'ij∈[0,1]；For i-th of input quantityjDimension
Original value；xjminMinimum value in being tieed up for all input quantity jth；xjmaxMaximum in being tieed up for all input quantity jth.
Set population scale Ppop, iterative algebra Ggen, using floating-point encoding, chromosome is encoded, wherein dyeing
The 1st multiplication factor C of body, the 2nd is Radial basis kernel function parameter γ, and the 3rd is Emse, the 4th is 1-R, and the 5th is Rrank,
The layering of i.e. every chromosome, the smaller then fitness of numerical value is bigger, and the 6th is Ddis, for level it is identical when judge degree of rarefication according to
According to.
Random generation initial population, with EmseIt is object function with R, carries out quick non-dominated ranking and selection, intersect, become
It is different.
When iterations reaches maximum iteration, optimized parameter C and γ are obtained.
Step S105 adds trend term to obtain prediction result according to the result after reconstruct.Trend term in step S103 by carrying ash
The trend to data obtained by color theoretical fitting is simulated, i.e. match value in Fig. 4.
The predicted value of each load component is overlapped by step S106, determines actual prediction result.
Fig. 4 to Fig. 8 is the process being predicted in an embodiment to the demand history data of acquisition.First to Fig. 4 original numbers
Trend is gone to obtain data shown in Fig. 5 according to using gray model, and it is 6 to obtain basic frequency, i.e. Fig. 6.Then variation mode point is utilized
Solution is decomposed Fig. 6 data, Decomposition order 6, obtains each mode as shown in Figure 7 and its spectrum analysis.Recycle and improve
II Support Vector Machines Optimizeds of NSGA- carry out classification summation reconstruct, and afterwards plus trend term obtains each mode shown in Fig. 8 (a)-Fig. 8 (c)
Prediction result.The load prediction curve in Fig. 9 shown in GM-VMD-SVM, Fig. 9 are obtained after finally each mode prediction result is superimposed
Middle two other curve is respectively the load prediction results of other two methods EMD-SVM and GM-SVM.It can be obtained by comparing
Know that this patent method therefor prediction effect is preferable.
Present invention also offers a kind of Load Prediction In Power Systems device, as shown in Figure 10, including：
Data acquisition module, for obtaining electric system historical load data；
Pretreatment module, carries out data at equal intervals to change and remove the processing of outlier；
Trend processing module is gone, carrying out trend to initial data using gray theory is handled；
Training optimization module, carries out spectrum analysis and determines Decomposition order, decomposed input data with variation mode decomposition, and
The support vector cassification that the data of processing are optimized using improved NSGA- II is summed and is reconstructed；
Processing module, for after the electric system historical load data is obtained, being born to the electric system history
Lotus data are normalized；
Prediction module, adds trend term to obtain prediction result according to the result after reconstruct；
As a result determining module, for the predicted value of each load component to be overlapped, determines actual prediction result.
This patent utilizes a kind of support vector machine method optimized through gray theory-variation mode decomposition and NSGA-II, energy
It is enough preferably to tackle the non-linear and non-stationary of electric load signal, i.e., in the larger signal of processing fluctuation, variation mould
State is decomposed can be with good processing；And tackle marginal value i.e. redundancy when, Grey Model can preferably utilize datum
According to being predicted；NSGA-II has more preferable ability of searching optimum, it is possible to increase precision of prediction.
Although above-mentioned be described the embodiment of the present invention with reference to attached drawing, model not is protected to the present invention
The limitation enclosed, those skilled in the art should understand that, on the basis of technical scheme, those skilled in the art are not
Need to make the creative labor the various modifications that can be made or deformation still within protection scope of the present invention.
Claims (10)
- A kind of 1. Load Prediction In Power Systems method, it is characterised in that comprise the following steps：(1) electric system historical load data is obtained；(2) historical load data got is pre-processed；(3) trend is carried out to pretreated data to handle, obtain trend term using gray theory；(4) carry out spectrum analysis and determine Decomposition order, the data after going trend processing are decomposed using variation mode decomposition；(5) the support vector cassification summation that the data after decomposition are optimized using improved NSGA- II is reconstructed；(6) trend term is added to obtain final prediction result according to the result after reconstruct；(7) predicted value of each load component is overlapped, determines actual prediction result.
- 2. a kind of Load Prediction In Power Systems method as claimed in claim 1, it is characterised in that described to be gone through to what is got History load data is pre-processed, and is specially：Data are carried out to change and remove outlier processing at equal intervals, the data containing marginal value is changed at equal intervals, and dispose edge Data.
- 3. a kind of Load Prediction In Power Systems method as claimed in claim 1, it is characterised in that described utilizes gray theory Pretreated data are carried out with trend processing is specially：To pretreated data accumulation or inverse accumulated generating ash model, the ginseng of the differential equation is determined with time series data Amount, progressively makes ash quantity albefaction, and then make prediction to to-be.
- A kind of 4. Load Prediction In Power Systems method as claimed in claim 3, it is characterised in thatAccording to the definition type of gray system theory, parameter is solvedaWithu；According to the parameter tried to achieveaWithuObtaining prediction model is：<mrow> <msup> <mover> <mi>x</mi> <mo>^</mo> </mover> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> </msup> <mrow> <mo>(</mo> <mi>t</mi> <mo>+</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>=</mo> <mrow> <mo>(</mo> <msup> <mi>x</mi> <mrow> <mo>(</mo> <mn>0</mn> <mo>)</mo> </mrow> </msup> <mo>(</mo> <mn>1</mn> <mo>)</mo> <mo>-</mo> <mfrac> <mi>u</mi> <mi>a</mi> </mfrac> <mo>)</mo> </mrow> <msup> <mi>e</mi> <mrow> <mo>-</mo> <mi>a</mi> <mi>t</mi> </mrow> </msup> <mo>+</mo> <mfrac> <mi>u</mi> <mi>a</mi> </mfrac> <mo>;</mo> </mrow>Reduced by regressive, it is as follows to obtain final prediction result：<mrow> <msup> <mover> <mi>x</mi> <mo>^</mo> </mover> <mrow> <mo>(</mo> <mn>0</mn> <mo>)</mo> </mrow> </msup> <mrow> <mo>(</mo> <mi>t</mi> <mo>+</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>=</mo> <msup> <mover> <mi>x</mi> <mo>^</mo> </mover> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> </msup> <mrow> <mo>(</mo> <mi>t</mi> <mo>+</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>-</mo> <msup> <mi>x</mi> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> </msup> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>;</mo> </mrow>Wherein,x (1)Forx (0)One-accumulate generation new sequence；aWithuIt is parameter,uItem in order to control；x(0)(1) it is starting number According to；x(0)(t) it is data of time when being t, x(1)(t) it is x(0)(t) the new sequence of one-accumulate generation；For t+1 when Data,For one-accumulate generationNew sequence.
- 5. a kind of Load Prediction In Power Systems method as claimed in claim 1, it is characterised in that utilize variation mode decomposition pair The data gone after trend processing are decomposed specially：Using variation mode decomposition data, input signal is decomposed into the k finite bandwidths with centre frequency, is referred to as mode uk, make the sum of the bandwidth estimation of each mode minimum.
- 6. a kind of Load Prediction In Power Systems method as claimed in claim 5, it is characterised in that decomposition model is specially：<mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <mi>min</mi> <mo>{</mo> <mo>&Sigma;</mo> <mo>|</mo> <mo>|</mo> <msub> <mo>&part;</mo> <mi>t</mi> </msub> <mo>+</mo> <mfrac> <mi>j</mi> <mrow> <mi>&pi;</mi> <mi>t</mi> </mrow> </mfrac> <msub> <mi>u</mi> <mi>k</mi> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <msup> <mi>e</mi> <mrow> <mo>-</mo> <msub> <mi>j&omega;</mi> <mi>k</mi> </msub> <mi>t</mi> </mrow> </msup> <mo>|</mo> <msubsup> <mo>|</mo> <mn>2</mn> <mn>2</mn> </msubsup> <mo>}</mo> </mrow> </mtd> </mtr> <mtr> <mtd> <mtable> <mtr> <mtd> <mrow> <mi>s</mi> <mo>.</mo> <mi>t</mi> <mo>.</mo> </mrow> </mtd> <mtd> <mrow> <munder> <mo>&Sigma;</mo> <mi>k</mi> </munder> <msub> <mi>u</mi> <mi>k</mi> </msub> <mo>=</mo> <mi>f</mi> </mrow> </mtd> </mtr> </mtable> </mtd> </mtr> </mtable> </mfenced>In formula, δ (t) is impulse function；To seek partial derivative to t；F is original signal, ukFor the modal components of k-th of limited-bandwidth； ωkFor the centre frequency of the modal components of k-th of limited-bandwidth；uk(t) be k-th limited-bandwidth of time when being t mode point Amount.
- 7. a kind of Load Prediction In Power Systems method as claimed in claim 1, it is characterised in that utilize the data after decomposition The support vector cassification summation that improved NSGA- II optimizes is reconstructed, and is specially：According to supporting vector machine model, introduce Lagrange multiplier algorithm and obtain optimization object function：<mrow> <mi>max</mi> <mi> </mi> <mi>L</mi> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>&alpha;</mi> <mi>i</mi> </msub> <mo>-</mo> <mfrac> <mn>1</mn> <mn>2</mn> </mfrac> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mi>j</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>&alpha;</mi> <mi>i</mi> </msub> <msub> <mi>&alpha;</mi> <mi>j</mi> </msub> <msub> <mi>y</mi> <mi>i</mi> </msub> <msub> <mi>y</mi> <mi>j</mi> </msub> <msubsup> <mi>x</mi> <mi>i</mi> <mi>T</mi> </msubsup> <msub> <mi>x</mi> <mi>j</mi> </msub> <mo>;</mo> </mrow><mrow> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>&alpha;</mi> <mi>i</mi> </msub> <msub> <mi>y</mi> <mi>i</mi> </msub> <mo>=</mo> <mn>0</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mn>0</mn> <mo>&le;</mo> <msub> <mi>&alpha;</mi> <mi>i</mi> </msub> <mo>&le;</mo> <mi>C</mi> </mrow> </mtd> </mtr> </mtable> </mfenced> <mo>,</mo> <mi>i</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mn>...</mn> <mo>,</mo> <mi>n</mi> <mo>;</mo> </mrow>Introduce Nonlinear MappingSample is mapped as a new data set：Then the above problem is converted into：Wherein, αiFor Lagrange multiplier.
- 8. a kind of Load Prediction In Power Systems method as claimed in claim 7, it is characterised in that carried out using method for normalizing Pretreatment operation, optimizes support vector machines parameter, is specially：<mrow> <msubsup> <mi>x</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> <mo>&prime;</mo> </msubsup> <mo>=</mo> <mfrac> <mrow> <msub> <mi>x</mi> <mi>j</mi> </msub> <mo>-</mo> <msub> <mi>x</mi> <mrow> <mi>j</mi> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> </msub> </mrow> <mrow> <msub> <mi>x</mi> <mrow> <mi>j</mi> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>-</mo> <msub> <mi>x</mi> <mrow> <mi>j</mi> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> </msub> </mrow> </mfrac> <mo>;</mo> </mrow>In formula：x'ijFor the normalized value of i-th of input quantity jth dimension, x'ij∈[0,1]；Tieed up for i-th of input quantity jth original Value；xjminMinimum value in being tieed up for all input quantity jth；xjmaxMaximum in being tieed up for all input quantity jth；Set population scale Ppop, iterative algebra Ggen, using floating-point encoding, chromosome is encoded, wherein chromosome the 1st Position multiplication factor C, the 2nd is Radial basis kernel function parameter γ, and the 3rd is Emse, the 4th is 1-R, and the 5th is Rrank, i.e., it is every The layering of bar chromosome, the smaller then fitness of numerical value is bigger, and the 6th is Ddis, it is the foundation that degree of rarefication is judged when level is identical；Random generation initial population, with EmseIt is object function with R, carries out quick non-dominated ranking and selection, intersects, variation；When iterations reaches maximum iteration, optimized parameter C and γ are obtained.
- A kind of 9. Load Prediction In Power Systems system, it is characterised in that including：Data acquisition module, for obtaining electric system historical load data；Pretreatment module, carries out data at equal intervals to change and remove the processing of outlier；Trend processing module is gone, carrying out trend to initial data using gray theory is handled；Training optimization module, carries out spectrum analysis and determines Decomposition order, decomposed input data with variation mode decomposition, and will place The data of reason are reconstructed using the support vector cassification summation of improved NSGA- II optimizations；Prediction module, adds trend term to obtain prediction result according to the result after reconstruct；As a result determining module, for the predicted value of each load component to be overlapped, determines actual prediction result.
- 10. a kind of Load Prediction In Power Systems system as claimed in claim 9, it is characterised in that further include：Processing module, for after the electric system historical load data is obtained, to the electric system historical load number According to being normalized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711269680.7A CN108022014B (en) | 2017-12-05 | 2017-12-05 | Power system load prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711269680.7A CN108022014B (en) | 2017-12-05 | 2017-12-05 | Power system load prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108022014A true CN108022014A (en) | 2018-05-11 |
| CN108022014B CN108022014B (en) | 2021-06-01 |
Family
ID=62078389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711269680.7A Active CN108022014B (en) | 2017-12-05 | 2017-12-05 | Power system load prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108022014B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960486A (en) * | 2018-06-12 | 2018-12-07 | 郑州航空工业管理学院 | Interactive set evolvement method based on grey support vector regression prediction adaptive value |
| CN109376921A (en) * | 2018-10-15 | 2019-02-22 | 河南理工大学 | Based on hereditary artificial fish school optimization RBF neural short-term load forecasting method |
| CN109449974A (en) * | 2018-11-16 | 2019-03-08 | 大连理工大学 | A kind of integrated energy system Optimization Scheduling based on change Mode Decomposition and sample entropy theory |
| CN109816164A (en) * | 2019-01-16 | 2019-05-28 | 国网信通亿力科技有限责任公司 | A kind of Methods of electric load forecasting |
| CN111178575A (en) * | 2019-11-12 | 2020-05-19 | 国网山西省电力公司晋中供电公司 | Grey model power load prediction method |
| CN113406525A (en) * | 2021-06-15 | 2021-09-17 | 安庆师范大学 | Lithium battery pack residual life prediction method based on optimized variational modal decomposition |
| CN114707710A (en) * | 2022-03-22 | 2022-07-05 | 湖南大学 | Method for evaluating day-by-day net load standby demand of power system and computer device |
| CN116227087A (en) * | 2023-03-29 | 2023-06-06 | 南京理工大学 | Method for predicting tensile characteristics of welded joint of thin-wall part based on finite element method |
| CN117878927A (en) * | 2024-03-11 | 2024-04-12 | 国网黑龙江省电力有限公司绥化供电公司 | Power system load trend analysis method based on time sequence analysis |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400203A (en) * | 2013-07-19 | 2013-11-20 | 西安交通大学 | Electric vehicle charging station load prediction method based on support vector machine |
| CN103544544A (en) * | 2013-10-29 | 2014-01-29 | 广东工业大学 | Energy consumption forecasting method and device |
| CN103729501A (en) * | 2013-12-18 | 2014-04-16 | 国网山西省电力公司晋中供电公司 | Short-term power load predicting method based on grey theory |
| CN104376368A (en) * | 2014-08-19 | 2015-02-25 | 上海交通大学 | Wind power generation short-term load forecasting method and device based on frequency domain decomposition |
| DE102014010117A1 (en) * | 2014-07-08 | 2016-01-14 | Evohaus Gmbh | Forecasting and control system for the electricity purchase of households |
| CN107392364A (en) * | 2017-07-12 | 2017-11-24 | 河海大学 | The short-term load forecasting method of variation mode decomposition and depth belief network |
-
2017
- 2017-12-05 CN CN201711269680.7A patent/CN108022014B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400203A (en) * | 2013-07-19 | 2013-11-20 | 西安交通大学 | Electric vehicle charging station load prediction method based on support vector machine |
| CN103544544A (en) * | 2013-10-29 | 2014-01-29 | 广东工业大学 | Energy consumption forecasting method and device |
| CN103729501A (en) * | 2013-12-18 | 2014-04-16 | 国网山西省电力公司晋中供电公司 | Short-term power load predicting method based on grey theory |
| DE102014010117A1 (en) * | 2014-07-08 | 2016-01-14 | Evohaus Gmbh | Forecasting and control system for the electricity purchase of households |
| CN104376368A (en) * | 2014-08-19 | 2015-02-25 | 上海交通大学 | Wind power generation short-term load forecasting method and device based on frequency domain decomposition |
| CN107392364A (en) * | 2017-07-12 | 2017-11-24 | 河海大学 | The short-term load forecasting method of variation mode decomposition and depth belief network |
Non-Patent Citations (1)
| Title |
|---|
| 路雪艳、赵超凡、吴晓峰、韩晓霞: "基于改进的NSGA_Ⅱ多目标优化方法研究", 《计算机应用研究》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960486B (en) * | 2018-06-12 | 2021-10-29 | 郑州航空工业管理学院 | Interactive set evolution method for predicting adaptive value based on gray support vector regression |
| CN108960486A (en) * | 2018-06-12 | 2018-12-07 | 郑州航空工业管理学院 | Interactive set evolvement method based on grey support vector regression prediction adaptive value |
| CN109376921A (en) * | 2018-10-15 | 2019-02-22 | 河南理工大学 | Based on hereditary artificial fish school optimization RBF neural short-term load forecasting method |
| CN109449974A (en) * | 2018-11-16 | 2019-03-08 | 大连理工大学 | A kind of integrated energy system Optimization Scheduling based on change Mode Decomposition and sample entropy theory |
| CN109449974B (en) * | 2018-11-16 | 2021-06-08 | 大连理工大学 | Comprehensive energy system optimization scheduling method based on variable mode decomposition and sample entropy theory |
| CN109816164A (en) * | 2019-01-16 | 2019-05-28 | 国网信通亿力科技有限责任公司 | A kind of Methods of electric load forecasting |
| CN111178575A (en) * | 2019-11-12 | 2020-05-19 | 国网山西省电力公司晋中供电公司 | Grey model power load prediction method |
| CN113406525A (en) * | 2021-06-15 | 2021-09-17 | 安庆师范大学 | Lithium battery pack residual life prediction method based on optimized variational modal decomposition |
| CN113406525B (en) * | 2021-06-15 | 2023-06-02 | 金陵科技学院 | Lithium battery pack residual life prediction method based on optimization variation modal decomposition |
| CN114707710A (en) * | 2022-03-22 | 2022-07-05 | 湖南大学 | Method for evaluating day-by-day net load standby demand of power system and computer device |
| CN114707710B (en) * | 2022-03-22 | 2024-05-28 | 湖南大学 | Method for evaluating daily payload standby requirement of power system and computer device |
| CN116227087A (en) * | 2023-03-29 | 2023-06-06 | 南京理工大学 | Method for predicting tensile characteristics of welded joint of thin-wall part based on finite element method |
| CN117878927A (en) * | 2024-03-11 | 2024-04-12 | 国网黑龙江省电力有限公司绥化供电公司 | Power system load trend analysis method based on time sequence analysis |
| CN117878927B (en) * | 2024-03-11 | 2024-05-28 | 国网黑龙江省电力有限公司绥化供电公司 | Power system load trend analysis method based on time sequence analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108022014B (en) | 2021-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108022014A (en) | A kind of Load Prediction In Power Systems method and system | |
| Li et al. | Short-term load-forecasting method based on wavelet decomposition with second-order gray neural network model combined with ADF test | |
| Wu et al. | A novel hybrid system based on multi-objective optimization for wind speed forecasting | |
| Li et al. | Smart wind speed forecasting approach using various boosting algorithms, big multi-step forecasting strategy | |
| CN108256697A (en) | A kind of Forecasting Methodology for power-system short-term load | |
| CN107886161A (en) | A kind of global sensitivity analysis method for improving Complex Information System efficiency | |
| CN107292453A (en) | A kind of short-term wind power prediction method based on integrated empirical mode decomposition Yu depth belief network | |
| CN111832825B (en) | Wind power prediction method and system integrating long-term memory network and extreme learning machine | |
| Wang et al. | A hesitant fuzzy wind speed forecasting system with novel defuzzification method and multi-objective optimization algorithm | |
| CN103235893B (en) | A kind of user-commodity clicking rate adaptive prediction device and Forecasting Methodology | |
| CN101782743A (en) | Neural network modeling method and system | |
| CN108537337A (en) | Lithium ion battery SOC prediction techniques based on optimization depth belief network | |
| Han et al. | Network traffic prediction using variational mode decomposition and multi-reservoirs echo state network | |
| Datong et al. | Online adaptive status prediction strategy for data-driven fault prognostics of complex systems | |
| CN107958309A (en) | A kind of high dam multi-point deformetion condition combines forecasting procedure | |
| Chinnathambi et al. | Deep neural networks (DNN) for day-ahead electricity price markets | |
| CN103605909A (en) | Water quality predication method based on grey theory and support vector machine | |
| Cheng et al. | Forecasting monthly runoff time series by single-layer feedforward artificial neural network and grey wolf optimizer | |
| CN108647807A (en) | The prediction technique of river discharge | |
| CN116861201A (en) | Power supply system based on artificial intelligence | |
| CN116702831A (en) | Hybrid short-term wind power prediction method considering massive loss of data | |
| Wu et al. | Explainable temporal dependence in multi-step wind power forecast via decomposition based chain echo state networks | |
| CN111563631A (en) | Wind power generation power prediction method and device based on variational modal decomposition | |
| CN115080795A (en) | Multi-charging-station cooperative load prediction method and device | |
| CN106779135A (en) | A kind of hybrid power ship bearing power Forecasting Methodology |
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 |