CN106557835A - Electricity demand forecasting method and system based on consumer confidence index - Google Patents
Electricity demand forecasting method and system based on consumer confidence index Download PDFInfo
- Publication number
- CN106557835A CN106557835A CN201610932288.5A CN201610932288A CN106557835A CN 106557835 A CN106557835 A CN 106557835A CN 201610932288 A CN201610932288 A CN 201610932288A CN 106557835 A CN106557835 A CN 106557835A
- Authority
- CN
- China
- Prior art keywords
- index
- leading
- leading indicators
- industry
- measured
- 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
- 230000005611 electricity Effects 0.000 title claims abstract description 113
- 238000013277 forecasting method Methods 0.000 title claims abstract description 16
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 47
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 47
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000011161 development Methods 0.000 claims abstract description 17
- 230000008859 change Effects 0.000 claims description 73
- 230000001932 seasonal effect Effects 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 15
- 230000000694 effects Effects 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 13
- 238000000354 decomposition reaction Methods 0.000 claims description 12
- 238000005498 polishing Methods 0.000 claims description 10
- 230000001419 dependent effect Effects 0.000 claims description 9
- 125000004122 cyclic group Chemical group 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000003780 insertion Methods 0.000 claims description 3
- 230000037431 insertion Effects 0.000 claims description 3
- CWYNVVGOOAEACU-UHFFFAOYSA-N Fe2+ Chemical compound [Fe+2] CWYNVVGOOAEACU-UHFFFAOYSA-N 0.000 description 13
- 239000002184 metal Substances 0.000 description 13
- 229910052751 metal Inorganic materials 0.000 description 13
- 238000003490 calendering Methods 0.000 description 12
- 238000005272 metallurgy Methods 0.000 description 12
- 239000002131 composite material Substances 0.000 description 5
- 230000003111 delayed effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 2
- 239000010953 base metal Substances 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 238000000205 computational method Methods 0.000 description 2
- 238000010411 cooking Methods 0.000 description 2
- 229910052802 copper Inorganic materials 0.000 description 2
- 239000010949 copper Substances 0.000 description 2
- 230000008034 disappearance Effects 0.000 description 2
- 239000003517 fume Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910000960 colored gold Inorganic materials 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003455 independent Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013439 planning 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of electricity demand forecasting method and system based on consumer confidence index, methods described includes：Obtain the electric power index in electricity consumption industry preset time period to be measured；The electric power index is pre-processed；On the basis of current industry power consumption, leading indicators are filtered out from electric power index；According to the goodness of fit of each index, time difference coefficient correlation and auto-correlation coefficient, the weight of agriculture products in leading indicators；Synthesis consumer confidence index in advance is determined according to the weight of index；According to synthesis consumer confidence index and the time difference coefficient correlation of current industry power consumption in advance, leading issue is determined；According to the leading issue, the current industry power consumption of leading synthesis consumer confidence index and the electricity consumption industry to be measured to the electricity consumption industry to be measured carries out regression fit；The trade power consumption amount of the electricity consumption industry to be measured is predicted according to regression fit result.Accurate Prediction trade power consumption amount of the present invention, the development plan for future electrical energy industry provide decision-making foundation.
Description
Technical field
The present invention relates to electricity demand forecasting technical field, more particularly to a kind of electricity demand forecasting side based on consumer confidence index
Method and system.
Background technology
With the continuous intensification of Chinese Urbanization and process of industrialization, electricity consumption demand drastically changes, the ripple of power consumption
Move closely related in macroeconomic change.Power consumption is the leading indicators for reflecting real economy future operation situation, is closed
The social electricity consumption of note has vital meaning for the development of planning power industry.Electricity needs it is whether accurate, no
Power grid security reliability electricity consumption can be only affected, while the production and management decision-making and economic benefit of enterprises of managing electric wire netting can be affected.
Due to the reason such as industry is numerous, trade power consumption characteristic is different, traditional electricity demand forecasting method gradually shows
Reveal the deficiency of predictive ability, it is impossible to meet the demand of existing electricity demand forecasting, it is impossible to which the supply of electric power control to electrical network is provided
Important technical support.
The content of the invention
Based on above-mentioned situation, the present invention proposes a kind of electricity demand forecasting method and system based on consumer confidence index, accurately
Prediction trade power consumption amount, the development plan for future electrical energy industry provide decision-making foundation.
To achieve these goals, the embodiment of technical solution of the present invention is：
A kind of electricity demand forecasting method based on consumer confidence index, comprises the following steps：
Obtain the electric power index in electricity consumption industry preset time period to be measured, the electric power index according to the electricity consumption to be measured
The index of the industry development association of industry determines；
The electric power index is pre-processed, the pretreatment includes normalized, seasonal adjustment and Trend Decomposition；
On the basis of the current industry power consumption of the electricity consumption industry to be measured, from carry out in pretreated electric power index sieve
Select leading indicators；
According to the goodness of fit of each index, time difference coefficient correlation and auto-correlation coefficient in the leading indicators, institute is determined
State the weight of each index in leading indicators；
Determine that according to the weight of each index in the leading indicators the leading synthesis boom of the electricity consumption industry to be measured refers to
Number；
Used with the current industry of the electricity consumption industry to be measured according to the leading synthesis consumer confidence index of the electricity consumption industry to be measured
The time difference coefficient correlation of electricity, determines the leading synthesis consumer confidence index and the electricity consumption industry to be measured of the electricity consumption industry to be measured
The leading issue of current industry power consumption；
According to the leading issue, the leading synthesis consumer confidence index and the electricity consumption row to be measured to the electricity consumption industry to be measured
The current industry power consumption of industry carries out regression fit；
The trade power consumption amount of the electricity consumption industry to be measured is predicted according to regression fit result.
A kind of electricity demand forecasting system based on consumer confidence index, including：
Index selection module, for obtaining the electric power index in electricity consumption industry preset time period to be measured, the electric power index
Determined according to the index associated with the industry development of the electricity consumption industry to be measured；
Index pretreatment module, for pre-processing to the electric power index, it is described pretreatment include normalized,
Seasonal adjustment and Trend Decomposition；
Index screening module, on the basis of the current industry power consumption of the electricity consumption industry to be measured, from carrying out from pre-
Leading indicators are filtered out in electric power index after reason；
Index weights determining module, for according to the goodness of fit of each index, time difference phase relation in the leading indicators
Number and auto-correlation coefficient, determine the weight of each index in the leading indicators；
Synthesize consumer confidence index determining module in advance, described in determining according to the weight of each index in the leading indicators
The leading synthesis consumer confidence index of electricity consumption industry to be measured；
Leading issue determining module, it is to be measured with described for the leading synthesis consumer confidence index according to the electricity consumption industry to be measured
The time difference coefficient correlation of the current industry power consumption of electricity consumption industry, determines the leading synthesis consumer confidence index of the electricity consumption industry to be measured
With the leading issue of the current industry power consumption of the electricity consumption industry to be measured；
Regression fit module, for according to the leading issue, the leading synthesis boom to the electricity consumption industry to be measured refers to
The current industry power consumption of number and the electricity consumption industry to be measured carries out regression fit；
Electricity demand forecasting module, for being carried out to the trade power consumption amount of the electricity consumption industry to be measured according to regression fit result
Prediction.
Compared with prior art, beneficial effects of the present invention are：Electricity demand forecasting method of the present invention based on consumer confidence index
And system, after obtaining the electric power index for affecting industry development, electric power index is pre-processed, then from pretreated electric power
Leading indicators are filtered out in index, according to the goodness of fit of each index, time difference coefficient correlation and auto-correlation system in leading indicators
The weight of number agriculture products, synthesizes consumer confidence index, and Accurate Prediction industry on this basis in advance according to the weight calculation of index
Power consumption, improves the reasonability for predicting the outcome, and the development plan for future electrical energy industry provides decision-making foundation.
Description of the drawings
Fig. 1 is the electricity demand forecasting method flow diagram in one embodiment based on consumer confidence index；
Fig. 2 is based on the electricity demand forecasting method flow diagram in method one shown in Fig. 1 specific example based on consumer confidence index；
Fig. 3 is the electricity demand forecasting system structure diagram in one embodiment based on consumer confidence index.
Specific embodiment
To make the objects, technical solutions and advantages of the present invention become more apparent, below in conjunction with drawings and Examples, to this
Invention is described in further detail.It should be appreciated that specific embodiment described herein is only to explain the present invention,
Protection scope of the present invention is not limited.
Electricity demand forecasting method in one embodiment based on consumer confidence index, as shown in figure 1, comprising the following steps：
Step S101：Obtain the electric power index in electricity consumption industry preset time period to be measured, the electric power index according to institute
The index for stating the industry development association of electricity consumption industry to be measured determines；
Here, obtain in the index that electric power index is associated from the industry development with the electricity consumption industry to be measured, to there is coloured gold
As a example by category is smelted and rolls processing industry, the electricity in non-ferrous metal metallurgy and calendering processing industry in January, 2013 in December, 2015 is obtained
Power index, the index associated with the industry development of non-ferrous metal metallurgy and calendering processing industry are included：Auto output, domestic refrigerator are produced
Amount, colour TV yield etc., can obtain the electric power of non-ferrous metal metallurgy and calendering processing industry according to actual needs from these indexs
Index.
Step S102：The electric power index is pre-processed, it is described pretreatment include normalized, seasonal adjustment and
Trend Decomposition；
Step S103：On the basis of the current industry power consumption of the electricity consumption industry to be measured, from carrying out pretreated electricity
Leading indicators are filtered out in power index；
Here, leading indicators are also referred to as emissary index also known as leading indicator, refer to the month economic situation and can that presages for the future
The trade cycle property change that can occur, and the market index of interest rate Long-term change trend early indication is provided for analyst.
Step S104：According to the goodness of fit of each index, time difference coefficient correlation and auto-correlation system in the leading indicators
Number, determines the weight of each index in the leading indicators；
Specifically, the weight of index refers to relative importance of the index in the overall evaluation.
Step S105：The leading conjunction of the electricity consumption industry to be measured is determined according to the weight of each index in the leading indicators
Into consumer confidence index；
Here, the prosperous change of consumer confidence index reflection industry.
Step S106：According to the leading synthesis consumer confidence index of the electricity consumption industry to be measured and working as the electricity consumption industry to be measured
The time difference coefficient correlation of front industry power consumption, determines the leading synthesis consumer confidence index and the use to be measured of the electricity consumption industry to be measured
The leading issue of the current industry power consumption of electric industry；
Specifically, what coefficient correlation was calculated is the two indices correlation of the same period, and what time difference coefficient correlation was calculated is have stagnant
Coefficient correlation between later stage or the index of antephase；
Here, the time difference coefficient correlation of asynchronous leading synthesis consumer confidence index and current industry power consumption is calculated, such as
By taking delayed or leading 4 phase as an example, then 9 time difference coefficient correlations can be calculated, a time difference coefficient correlation of the maximum that takes absolute value
Corresponding antephase is used as leading issue.
Step S107：According to the leading issue, leading synthesis consumer confidence index to the electricity consumption industry to be measured and described
The current industry power consumption of electricity consumption industry to be measured carries out regression fit；
Here, regression model is built according to leading issue, in advance synthesis consumer confidence index and current industry power consumption.
Step S108：The trade power consumption amount of the electricity consumption industry to be measured is predicted according to regression fit result.
Additionally, in a specific example, it is described according to the goodness of fit of each index, time difference phase in the leading indicators
Relation number and auto-correlation coefficient, determine that the mode of the weight of each index in the leading indicators includes：
Successively using each index in the leading indicators as dependent variable, using in the leading indicators except as dependent variable
Outer remaining each index of index returned as independent variable, obtain each in the leading indicators using stepwise regression method
The maximum goodness of fit of individual index, determines the leading indicators according to the goodness of fit that each index in the leading indicators is maximum
In each index while independent information；
Here, successively using each index as dependent variable, other have the index of theoretical first line of a couplet system therewith as independent variable
Returned, using the method for successive Regression, taken the maximum of which goodness of fitWherein i=1 ..., kjIndex in expression group
Sequence number, j=1,2,3 represent respectively in advance, consistent, lagging indicator group, kjIt is the index number of jth index group, parameter
While independent information SDi：Other indexs for having theoretical first line of a couplet system therewith refer to right to participate in as independent variable
The index of re-computation, refers herein to similar index, i.e., selected whole leading indicators.Wherein successive Regression is to adopt which
In an index as dependent variable, other indexs are stepped up independent variable number as independent variable, compare using different independents variable
When the goodness of fit, the regression equation for selecting the wherein goodness of fit maximum is used as optimum regression equation.
The time difference coefficient correlation of each index and preset reference index in the leading indicators is obtained respectively, it is each from what is obtained
The time difference coefficient correlation of maximum absolute value is obtained in individual time difference coefficient correlation, according to the time difference coefficient correlation of the maximum absolute value
Determine the time difference independent information of each index in the leading indicators；
Specifically, calculate the time difference coefficient correlation of each index and reference index Wherein xtRepresent each index in leading indicators, ytReference index is represented, t represents the epoch number of index,
For xtMean value,For ytMean value, n represents total epoch number, t=1,2,3 ... n, select the time difference phase relation of maximum
Number Rl'=max | Rl|, work as Rl'When≤0, R is takenl'=0.Judgement is leading or lagging indicator, for leading indicators are madeFor lagging indicator makees Rmi=l'Rl', wherein mi represents the index number of leading indicators or lagging indicator, as l '>
0, it is lagging indicator, l '<0, it is leading indicators, for coincidence indicator is not then processed, especially, for index i of l=0, by
In SDiIncluded its information, then takes Rl'=0.Finally obtain the time difference independent information of index：DDi=1/Rmi, work as Rmi=0
When take DDi=0.
The auto-correlation coefficient of each index in the leading indicators is obtained respectively, is obtained from each auto-correlation coefficient for obtaining
The auto-correlation coefficient of the maximum that takes absolute value, according to the auto-correlation coefficient of the maximum absolute value, using the time difference as weight, it is determined that
The prediction independent information of each index in the leading indicators；
Here, calculate the auto-correlation coefficient of each indexL=0,1,2 ..., its
Middle Rls(l+1) individual auto-correlation coefficient of s-th index is represented, maximum absolute value therein is selected：Rl's=max | Rls|, make
Weight is done with the time difference：Rsi=lRl's, here it is the prediction independent information of index：PDi=Rsi。
According to independent information while each index, time difference independent information and prediction independent information in the leading indicators,
Determine the weight of each index in the leading indicators.
Specifically, above-mentioned three kinds of independent informations are added, and are normalized, obtain each index weights：From the foregoing, compound independent information enabling legislation proposed by the present invention is according to calculating finger
Target independent information, time difference coefficient correlation, three kinds of information of auto-correlation coefficient, draw the weight of each index after normalization.
Additionally, in a specific example, determining the use to be measured according to the weight of each index in the leading indicators
The mode of the leading synthesis consumer confidence index of electric industry includes：
Obtain the symmetrical rate of change of each index in the leading indicators；
Here, symmetrical rate of change is different from the direct rate of change of time series, and it is divided by two with the variable quantity in two periods
The mean value in individual period, rather than divided by the value of initial period, so that positive change has symmetrical shape with negative change
Formula.
Index Y is set in one embodimentijT i-th index of () for jth index group, calculates Yij(t) symmetrical rate of change Cij
T the concrete formula of () is as follows：
Wherein, T is total epoch number, as composing indexes YijWhen having zero or negative value in (t), or during ratio sequence, Cij
T () is equal to YijThe first-order difference of (t)：
Cij(t)=Yij(t)-Yij(t-1), t=2,3 ..., T
The mark of each index in the leading indicators is determined according to the symmetrical rate of change of each index in the leading indicators
The standardization factor；
In one embodiment, in order to avoid the big index of amplitude of fluctuation occupies ascendancy in composite index number, to each finger
The symmetrical standardized rate of target is standardized so as to which average absolute value is equal to 1.
Normalized factors Aij, concrete formula is as follows:
According to the standard of each index in the symmetrical rate of change and the leading indicators of each index in the leading indicators
Change the factor, it is determined that according to the standardization rate of change of each index in the leading indicators；
Here, using AijCome to CijT () is standardized calculating, obtain standardizing rate of change SijT (), concrete formula is such as
Under：
According to the power of each index in the standardization rate of change and the leading indicators of each index in the leading indicators
Weight, determines the average rate of change of the leading indicators；
In one embodiment, average rate of change R of leading indicators group is calculatedjT (), concrete formula are as follows：
Wherein wijIt is the weight of each index.
The standard of index factor of the leading indicators is determined according to the average rate of change of the leading indicators；
Here, gauge index normalization factor Fj, concrete formula is as follows：
Wherein F2=1
According to the average rate of change and the standard of index factor of the leading indicators, the standardization of the leading indicators is determined
The average rate of change；
Here, normalized average rate of change VjT (), concrete formula are as follows：
Determine that according to the standardization average rate of change of the leading indicators the leading synthesis of the electricity consumption industry to be measured is prosperous
Index.
In one embodiment, synthesis consumer confidence index I in advance is calculatedj(t)
The concrete formula for calculating the initial consumer confidence index of synthesis in advance is as follows：
Ij(1)=100
Additionally, in a specific example, the pretreatment is also including missing values process.
Here, it is to need to carry out when initial data has missing values that missing values are processed.
Additionally, in a specific example, including to the mode pre-processed by the electric power index：
Using linear interpolation method, based on the national numerical value for obtaining, proportion of utilization method determines the numerical value being inserted into, according to determination
The numerical value being inserted into and the numerical value lacked in electric power index described in default value growth rate polishing；
Specifically, missing values are processed and typically adopt linear interpolation, if disappearance is more, just using identical whole nation data,
Then adoption rate method is calculatedN be total moon number of degrees, yi,k *For the monthly number of known i-th index k
Value, yi,kFor the monthly national numerical value of i-th index k, yi,tFor the monthly national numerical value of i-th index t, yi,t *Insertion is needed
Numerical value, the data uneven for national data carry out polishing using the constant method of assumed growth rate.
Effect is carried out to the electric power index after polishing missing values；
In one embodiment, method for normalizing adopts the efficiency coefficient method, computational methods to be：
Effect formula of direct index is：
Effect formula of inverse indicators is：
Effect formula of intermediate value optimal index is：
yitFor the monthly numerical value of i-th index t, yi,midAfter being sorted for i-th index value from small to large positioned at centre
Value (i.e. median, numerical value take middle two average when having even number).Each each monthly index is done into above-mentioned place
Reason.
Electric power index after to being normalized carries out seasonal adjustment, obtain each index seasonal factor sequence and
Trend cyclic sequence；
Trend point is carried out to the seasonal factor sequence of each index that obtains and trend cyclic sequence using default filter method
Solution.
In order to more fully understand said method, electricity demand forecasting of the present invention detailed below based on consumer confidence index
The application example of method.
This application example is by taking certain province's non-ferrous metal metallurgy and calendering processing industry as an example.
As shown in Fig. 2 may comprise steps of：
Step S201：Obtain certain electric power for saving non-ferrous metal metallurgy and calendering processing industry in January, 2013 in December, 2015
Index, the electric power index according to certain province non-ferrous metal metallurgy and calendering processing industry industry development associate index determination,
The electric power index of acquisition is as shown in table 1, with January, 2013 as base period.
Certain the province's non-ferrous metal metallurgy of table 1 and the electric power index of calendering processing industry
Step S202：Above-mentioned electric power index is pre-processed, the pretreatment includes missing values process, at normalization
Reason, seasonal adjustment and Trend Decomposition；
(1) missing values are processed and typically adopt linear interpolation, if disappearance is more, just using identical whole nation data, then
Adoption rate method is calculatedN be total moon number of degrees, yi,k *For the monthly numerical value of known i-th index k,
yi,kFor the monthly national numerical value of i-th index k, yi,tFor the monthly national numerical value of i-th index t, yi,t *Need what is inserted
Numerical value, the data uneven for national data carry out polishing using the constant method of assumed growth rate.
(2) method for normalizing adopts the efficiency coefficient method, computational methods to be：
Effect formula of direct index is：
Effect formula of inverse indicators is：
Effect formula of intermediate value optimal index is：
yitFor the monthly numerical value of i-th index t, yi,midAfter being sorted for i-th index value from small to large positioned at centre
Value (i.e. median, numerical value take middle two average when having even number).Each each monthly index is done into above-mentioned place
Reason.
(3) seasonal adjustment is carried out using Census X-12 methods, the seasonal factor sequence and trend for obtaining each index is followed
Ring sequence；
(4) Trend Decomposition is carried out using HP filter methods
Step S203：Using time difference Gray Correlation, with it is above-mentioned certain save working as non-ferrous metal metallurgy and calendering processing industry
On the basis of front industry power consumption, leading indicators are filtered out in pretreated electric power index is carried out, the leading indicators for filtering out
As shown in table 2；
2 index screening result of table
| Auto output | In advance |
| Marketable Housing Area Sold | It is delayed |
| The sum of investments in fixed assets used | In advance |
| M1 | Unanimously |
| Domestic refrigerator yield | Unanimously |
| Domestic cooking fume remover | In advance |
| Colour TV yield | In advance |
| Main business income | In advance |
| The average number of whole practitioners | Unanimously |
| Current assets average balance | Unanimously |
| Copper product import volume | Unanimously |
| Copper product export volume | It is delayed |
| Ten kinds of non-ferrous metal rate of production and marketing | Unanimously |
| LME base metal indexes | In advance |
Step S204：The weight of the leading indicators for filtering out is determined using compound independent information enabling legislation, i.e., according to described
The goodness of fit of each index, time difference coefficient correlation and auto-correlation coefficient in leading indicators, determine in the leading indicators each
The weight of index, as a result as shown in table 3：
3 weight calculation result of table
| Auto output | 0.175961 |
| The sum of investments in fixed assets used | 0.405183 |
| Domestic cooking fume remover yield | 0.014174 |
| Colour TV yield | 0.217294 |
| Main business income | 0.013767 |
| LME base metal indexes | 0.173621 |
Step S205：Above-mentioned certain province's non-ferrous metal metallurgy and calendering processing are determined according to the weight of the leading indicators for filtering out
The leading synthesis consumer confidence index of industry；
(1) calculate the symmetrical rate of change of each index；
Symmetrical rate of change is different from the direct rate of change of time series, and it is divided by two periods with the variable quantity in two periods
Mean value, rather than divided by the value of initial period so that positive change with negative change with symmetrical form.
If index YijT i-th index of () for jth index group, calculates Yij(t) symmetrical rate of change CijThe concrete formula of (t)
It is as follows：
Wherein, T is total epoch number, as composing indexes YijWhen having zero or negative value in (t), or during ratio sequence, Cij
T () is equal to YijThe first-order difference of (t)：
Cij(t)=Yij(t)-Yij(t-1), t=2,3 ..., T
(2) normalization factor of parameter；
In order to avoid the big index of amplitude of fluctuation occupies ascendancy in composite index number, the symmetrical standardized rate to each index
It is standardized so as to which average absolute value is equal to 1.
Normalized factors Aij, concrete formula is as follows:
(3) the standardization rate of change of parameter；
Here, using AijCome to CijT () is standardized calculating, obtain standardizing rate of change SijT (), concrete formula is such as
Under：
(4) average rate of change of parameter；
Calculate average rate of change R of leading indicators groupjT (), concrete formula are as follows：
Wherein wijIt is the weight of each index.
(5) standard of index factor of parameter；
Gauge index normalization factor Fj, concrete formula is as follows：
Wherein F2=1
(6) the standardization average rate of change of parameter；
Normalized average rate of change VjT (), concrete formula are as follows：
(7) calculate synthesis consumer confidence index in advance.
Calculate synthesis consumer confidence index I in advancej(t)
The concrete formula for calculating the initial consumer confidence index of synthesis in advance is as follows：
Ij(1)=100
The leading synthesis consumer confidence index and current industry power consumption numerical value for calculating is as shown in table 4.
Table 4 synthesizes consumer confidence index and current industry power consumption in advance
Step S206：Using time difference correlation coefficient process, the elder generation of above-mentioned certain province's non-ferrous metal metallurgy and calendering processing industry is calculated
Row synthesizes the leading issue of consumer confidence index and current industry power consumption；
Step S207：According to above-mentioned leading issue, to above-mentioned certain province's non-ferrous metal metallurgy and the leading conjunction of calendering processing industry
Regression fit is carried out into consumer confidence index and current industry power consumption；
According to table 4, can be found by calculating the different trade power consumption amounts of lag period and the coefficient correlation of leading composite index number,
When antephase number is 3, coefficient correlation is maximum, is 0.818588.Therefore leading issue is selected for 3, now, structure regression model
It is as follows：
log(Yt)=C+C1*Xt-3+ut, wherein YtFor trade power consumption amount, XtFor synthesis consumer confidence index in advance.
Step S208：According to above-mentioned regression model to above-mentioned certain province's non-ferrous metal metallurgy and the trade power consumption of calendering processing industry
Amount is predicted.
By the leading composite index number in October, 2015 is substituted in regression equation, obtain estimating average：113,
846.35, and by plus-minus twice mean square error3379.72 (whereinSequential value to estimate to obtain), obtain
The estimation interval of in January, 2016 trade power consumption amount is [110,466.63,117,226.07], and in January, 2016 actual row
Industry power consumption is 119,828.19, therefore in the range of estimation interval, therefore predict it is effective.
By the leading composite index number of 2015 11, December is substituted in regression equation, obtain estimating average：103,
010.86th, 99,040.05, estimation interval [99,631.14,106,390.58], [95,660.33,102,419.77], 2016 years
2nd, March actual power consumption is respectively 102,935.81,101,135.68, and both of which is fallen in estimation interval, therefore predicts
It is effective.
It is evidenced from the above discussion that, the present embodiment affects the electric power index of industry development by obtaining, and fluctuates for industry
Property it is big obtain reasonable index weight using the correlation and autocorrelation of index the characteristics of correlation is strong and between index, according to obtaining
The index weights for taking calculate consumer confidence index, and Accurate Prediction trade power consumption amount on this basis, improve the reasonability for predicting the outcome,
Development plan for future electrical energy industry provides decision-making foundation.
Electricity demand forecasting system in one embodiment based on consumer confidence index, such as Fig. 3 show, including：
Index selection module 301, for obtaining the electric power index in electricity consumption industry preset time period to be measured, the electric power refers to
Mark is determined according to the index associated with the industry development of the electricity consumption industry to be measured；
Index pretreatment module 302, for pre-processing to the electric power index, the pretreatment is included at normalization
Reason, seasonal adjustment and Trend Decomposition；
Index screening module 303, it is on the basis of the current industry power consumption of the electricity consumption industry to be measured, pre- from carrying out
Leading indicators are filtered out in electric power index after process；
Index weights determining module 304, for according to the goodness of fit of each index in the leading indicators, when difference correlation
Coefficient and auto-correlation coefficient, determine the weight of each index in the leading indicators；
Synthesis consumer confidence index determining module 305, determines for the weight according to each index in the leading indicators in advance
The leading synthesis consumer confidence index of the electricity consumption industry to be measured；
Leading issue determining module 306, for the leading synthesis consumer confidence index according to the electricity consumption industry to be measured with it is described
The time difference coefficient correlation of the current industry power consumption of electricity consumption industry to be measured, determines that the leading synthesis of the electricity consumption industry to be measured is prosperous
The leading issue of index and the current industry power consumption of the electricity consumption industry to be measured；
Regression fit module 307, for according to the leading issue, the leading synthesis to the electricity consumption industry to be measured is prosperous
The current industry power consumption of index and the electricity consumption industry to be measured carries out regression fit；
Electricity demand forecasting module 308, for the trade power consumption amount according to regression fit result to the electricity consumption industry to be measured
It is predicted.
As shown in figure 3, in a specific example, the index weights determining module 304 includes：
Index simultaneously independent information determining unit 3041, for successively using each index in the leading indicators as because
Variable, using in the leading indicators, in addition to the index as dependent variable, remaining each index is returned as independent variable, adopts
The maximum goodness of fit of each index in the leading indicators is obtained with stepwise regression method, according in the leading indicators each
Independent information while the maximum goodness of fit of index determines each index in the leading indicators；
Index time difference independent information determining unit 3042, for obtain in the leading indicators respectively each index with it is default
The time difference coefficient correlation of reference index, obtains the time difference phase relation of maximum absolute value from each time difference coefficient correlation for obtaining
Number, determines the time difference independent information of each index in the leading indicators according to the time difference coefficient correlation of the maximum absolute value；
Index prediction independent information determining unit 3043, for obtain respectively each index in the leading indicators from phase
Relation number, obtains the auto-correlation coefficient of maximum absolute value, from each auto-correlation coefficient for obtaining according to the maximum absolute value
Auto-correlation coefficient, using the time difference as weight, determine the prediction independent information of each index in the leading indicators；
Index weights determining unit 3044, for according to independent information while each index in the leading indicators, when
Difference independent information and prediction independent information, determine the weight of each index in the leading indicators.
As shown in figure 3, in a specific example, the leading synthesis consumer confidence index determining module 305 includes：
The symmetrical rate of change obtaining unit 3051 of index, for obtaining the symmetrical change of each index in the leading indicators
Rate；
Criterion factor specifying unit 3052, for the symmetrical rate of change according to each index in the leading indicators
Determine the normalization factor of each index in the leading indicators；
Criterion rate of change determining unit 3053, for the symmetrical change according to each index in the leading indicators
The normalization factor of each index in rate and the leading indicators, it is determined that according to the standardization of each index in the leading indicators
Rate of change；
Index average rate of change determining unit 3054, for the standardization change according to each index in the leading indicators
In rate and the leading indicators, the weight of each index, determines the average rate of change of the leading indicators；
Index index normalization factor determining unit 3055, for determining institute according to the average rate of change of the leading indicators
State the standard of index factor of leading indicators；
Criterion average rate of change determining unit 3056, for according to the average rate of change of the leading indicators and referring to
Number normalization factor, determines the standardization average rate of change of the leading indicators；
Synthesis consumer confidence index determining unit 3057, true for the standardization average rate of change according to the leading indicators in advance
The leading synthesis consumer confidence index of the fixed electricity consumption industry to be measured.
Additionally, in a specific example, the pretreatment is also including missing values process.
As shown in figure 3, in a specific example, the index pretreatment module 302 includes：
Index missing values processing unit 3021, for adopting linear interpolation method, based on the national numerical value for obtaining, proportion of utilization
Method determines the numerical value being inserted into, according to scarce in the numerical value being inserted into and electric power index described in default value growth rate polishing that determine
The numerical value of mistake；
Index normalized unit 3022, for carrying out effect to the electric power index after polishing missing values；
Index seasonal adjustment unit 3023, for obtain carry out season of each index in the electric power index after effect because
Prime sequences and trend cyclic sequence；
Index Trend Decomposition unit 3024, for the seasonal factor sequence and trend cyclic sequence of each index to obtaining
Carry out Trend Decomposition.
It is evidenced from the above discussion that, electricity demand forecasting method and system of the present invention based on consumer confidence index, Accurate Prediction industry
Power consumption, the development plan for future electrical energy industry provide decision-making foundation.
Each technical characteristic of embodiment described above arbitrarily can be combined, to make description succinct, not to above-mentioned reality
Apply all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, the scope of this specification record is all considered to be.
Embodiment described above only expresses the several embodiments of the present invention, and its description is more concrete and detailed, but and
Therefore can not be construed as limiting the scope of the patent.It should be pointed out that for one of ordinary skill in the art comes
Say, without departing from the inventive concept of the premise, some deformations and improvement can also be made, these belong to the protection of the present invention
Scope.Therefore, the protection domain of patent of the present invention should be defined by claims.
Claims (10)
1. a kind of electricity demand forecasting method based on consumer confidence index, it is characterised in that comprise the following steps：
Obtain the electric power index in electricity consumption industry preset time period to be measured, the electric power index according to the electricity consumption industry to be measured
Industry development association index determine；
The electric power index is pre-processed, the pretreatment includes normalized, seasonal adjustment and Trend Decomposition；
On the basis of the current industry power consumption of the electricity consumption industry to be measured, from carrying out filtering out in pretreated electric power index
Leading indicators；
According to the goodness of fit of each index, time difference coefficient correlation and auto-correlation coefficient in the leading indicators, the elder generation is determined
The weight of each index in row index；
The leading synthesis consumer confidence index of the electricity consumption industry to be measured is determined according to the weight of each index in the leading indicators；
According to the current industry power consumption of the leading synthesis consumer confidence index of the electricity consumption industry to be measured and the electricity consumption industry to be measured
Time difference coefficient correlation, determine that the leading synthesis consumer confidence index of the electricity consumption industry to be measured is current with the electricity consumption industry to be measured
The leading issue of trade power consumption amount；
According to the leading issue, the leading synthesis consumer confidence index and the electricity consumption industry to be measured to the electricity consumption industry to be measured
Current industry power consumption carries out regression fit；
The trade power consumption amount of the electricity consumption industry to be measured is predicted according to regression fit result.
2. the electricity demand forecasting method based on consumer confidence index according to claim 1, it is characterised in that described in the basis
The goodness of fit of each index, time difference coefficient correlation and auto-correlation coefficient in leading indicators, determine in the leading indicators each
The mode of the weight of index includes：
Successively using each index in the leading indicators as dependent variable, using in the leading indicators except the finger as dependent variable
Outer remaining each index of mark is returned as independent variable, is obtained in the leading indicators each using stepwise regression method and is referred to
The maximum goodness of fit of mark, determines according to the maximum goodness of fit of each index in the leading indicators each in the leading indicators
Independent information while individual index；
Obtain the time difference coefficient correlation of each index and preset reference index in the leading indicators respectively, from each for obtaining when
The time difference coefficient correlation of maximum absolute value is obtained in difference correlation coefficient, is determined according to the time difference coefficient correlation of the maximum absolute value
The time difference independent information of each index in the leading indicators；
The auto-correlation coefficient of each index in the leading indicators is obtained respectively, obtains exhausted from each auto-correlation coefficient for obtaining
To the auto-correlation coefficient that value is maximum, according to the auto-correlation coefficient of the maximum absolute value, using the time difference as weight, it is determined that described
The prediction independent information of each index in leading indicators；
According to independent information while each index, time difference independent information and prediction independent information in the leading indicators, it is determined that
The weight of each index in the leading indicators.
3. the electricity demand forecasting method based on consumer confidence index according to claim 1 and 2, it is characterised in that according to described
In leading indicators, the weight of each index determines that the mode of the leading synthesis consumer confidence index of the electricity consumption industry to be measured includes：
Obtain the symmetrical rate of change of each index in the leading indicators；
The standardization of each index in the leading indicators is determined according to the symmetrical rate of change of each index in the leading indicators
The factor；
According to the standardization of each index in the symmetrical rate of change and the leading indicators of each index in the leading indicators because
Son, it is determined that according to the standardization rate of change of each index in the leading indicators；
According in the leading indicators each index standardization rate of change and the leading indicators in each index weight, really
The average rate of change of the fixed leading indicators；
The standard of index factor of the leading indicators is determined according to the average rate of change of the leading indicators；
According to the average rate of change and the standard of index factor of the leading indicators, determine that the standardization of the leading indicators is average
Rate of change；
The leading synthesis consumer confidence index of the electricity consumption industry to be measured is determined according to the standardization average rate of change of the leading indicators.
4. the electricity demand forecasting method based on consumer confidence index according to claim 1, it is characterised in that the pretreatment is also
Including missing values process.
5. the electricity demand forecasting method based on consumer confidence index according to claim 4, it is characterised in that the electric power is referred to
The mode pre-processed by mark includes：
Using linear interpolation method, based on the national numerical value for obtaining, proportion of utilization method determines the numerical value being inserted into, according to treating for determining
The numerical value lacked in the numerical value and electric power index described in default value growth rate polishing of insertion；
Effect is carried out to the electric power index after polishing missing values；
Obtain the seasonal factor sequence and trend cyclic sequence of each index in the electric power index after carrying out effect；
The seasonal factor sequence of each index and trend cyclic sequence to obtaining carries out Trend Decomposition.
6. a kind of electricity demand forecasting system based on consumer confidence index, it is characterised in that include：
Index selection module, for obtaining the electric power index in electricity consumption industry preset time period to be measured, the electric power index according to
The index associated with the industry development of the electricity consumption industry to be measured is determined；
Index pretreatment module, for pre-processing to the electric power index, the pretreatment includes normalized, season
Adjustment and Trend Decomposition；
Index screening module, on the basis of the current industry power consumption of the electricity consumption industry to be measured, from after being pre-processed
Electric power index in filter out leading indicators；
Index weights determining module, for according to the goodness of fit of each index in the leading indicators, time difference coefficient correlation and
Auto-correlation coefficient, determines the weight of each index in the leading indicators；
Synthesis consumer confidence index determining module, described to be measured for being determined according to the weight of each index in the leading indicators in advance
The leading synthesis consumer confidence index of electricity consumption industry；
Leading issue determining module, for the leading synthesis consumer confidence index according to the electricity consumption industry to be measured and the electricity consumption to be measured
The time difference coefficient correlation of the current industry power consumption of industry, determines leading synthesis consumer confidence index and the institute of the electricity consumption industry to be measured
State the leading issue of the current industry power consumption of electricity consumption industry to be measured；
Regression fit module, for according to the leading issue, leading synthesis consumer confidence index to the electricity consumption industry to be measured and
The current industry power consumption of the electricity consumption industry to be measured carries out regression fit；
Electricity demand forecasting module, it is pre- for being carried out to the trade power consumption amount of the electricity consumption industry to be measured according to regression fit result
Survey.
7. the electricity demand forecasting system based on consumer confidence index according to claim 6, it is characterised in that the index weights
Determining module includes：
Index simultaneously independent information determining unit, for successively using each index in the leading indicators as dependent variable, will
In the leading indicators, in addition to the index as dependent variable, remaining each index is returned as independent variable, is adopted and is progressively returned
Method is returned to obtain the maximum goodness of fit of each index in the leading indicators, it is maximum according to each index in the leading indicators
Goodness of fit independent information while determine each index in the leading indicators；
Index time difference independent information determining unit, for obtaining each index and preset reference index in the leading indicators respectively
Time difference coefficient correlation, from each time difference coefficient correlation for obtaining obtain maximum absolute value time difference coefficient correlation, according to institute
The time difference coefficient correlation for stating maximum absolute value determines the time difference independent information of each index in the leading indicators；
Index prediction independent information determining unit, for obtaining the auto-correlation coefficient of each index in the leading indicators respectively,
The auto-correlation coefficient of maximum absolute value is obtained from each auto-correlation coefficient for obtaining, according to the auto-correlation of the maximum absolute value
Coefficient, using the time difference as weight, determines the prediction independent information of each index in the leading indicators；
Index weights determining unit, for independent information, the time difference independently believe while each index according in the leading indicators
Breath and prediction independent information, determine the weight of each index in the leading indicators.
8. the electricity demand forecasting system based on consumer confidence index according to claim 6 or 7, it is characterised in that it is described in advance
Synthesis consumer confidence index determining module includes：
The symmetrical rate of change obtaining unit of index, for obtaining the symmetrical rate of change of each index in the leading indicators；
Criterion factor specifying unit, described in being determined according to the symmetrical rate of change of each index in the leading indicators
The normalization factor of each index in leading indicators；
Criterion rate of change determining unit, for the symmetrical rate of change according to each index in the leading indicators and described
The normalization factor of each index in leading indicators, it is determined that according to the standardization rate of change of each index in the leading indicators；
Index average rate of change determining unit, for the standardization rate of change according to each index in the leading indicators and described
The weight of each index in leading indicators, determines the average rate of change of the leading indicators；
Index index normalization factor determining unit, for determining the leading finger according to the average rate of change of the leading indicators
The target standard of index factor；
Criterion average rate of change determining unit, for the average rate of change and the standard of index according to the leading indicators
The factor, determines the standardization average rate of change of the leading indicators；
Synthesize consumer confidence index determining unit in advance, for treating according to the determination of the standardization average rate of change of the leading indicators
Survey the leading synthesis consumer confidence index of electricity consumption industry.
9. the electricity demand forecasting system based on consumer confidence index according to claim 6, it is characterised in that the pretreatment is also
Including missing values process.
10. the electricity demand forecasting system based on consumer confidence index according to claim 9, it is characterised in that the index is pre-
Processing module includes：
Index missing values processing unit, for adopting linear interpolation method, based on the national numerical value for obtaining, proportion of utilization method determines to be treated
The numerical value of insertion, according to the numerical value being inserted into and the number lacked in electric power index described in default value growth rate polishing that determine
Value；
Index normalized unit, for carrying out effect to the electric power index after polishing missing values；
Index seasonal adjustment unit, for obtain carry out in the electric power index after effect the seasonal factor sequence of each index and
Trend cyclic sequence；
Index Trend Decomposition unit, the seasonal factor sequence and trend cyclic sequence for each index to obtaining carry out trend
Decompose.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610932288.5A CN106557835B (en) | 2016-10-24 | 2016-10-24 | Electricity demand forecasting method and system based on consumer confidence index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610932288.5A CN106557835B (en) | 2016-10-24 | 2016-10-24 | Electricity demand forecasting method and system based on consumer confidence index |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106557835A true CN106557835A (en) | 2017-04-05 |
| CN106557835B CN106557835B (en) | 2018-03-30 |
Family
ID=58443416
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610932288.5A Active CN106557835B (en) | 2016-10-24 | 2016-10-24 | Electricity demand forecasting method and system based on consumer confidence index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106557835B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476030A (en) * | 2020-05-08 | 2020-07-31 | 中国科学院计算机网络信息中心 | Prospective factor screening method based on deep learning |
| CN111583063A (en) * | 2020-05-11 | 2020-08-25 | 国网四川省电力公司电力科学研究院 | Business start and end time detection method based on standard template and storage medium |
| CN112116265A (en) * | 2020-09-25 | 2020-12-22 | 国网上海市电力公司 | Industry landscape index construction method driven by electric power data |
| CN112348281A (en) * | 2020-11-23 | 2021-02-09 | 国网北京市电力公司 | Power data processing method and device |
| CN112508251A (en) * | 2020-11-27 | 2021-03-16 | 国网浙江省电力有限公司杭州供电公司 | Load prediction method and device based on electric cockpit |
| CN112949897A (en) * | 2020-12-22 | 2021-06-11 | 浙江华云信息科技有限公司 | Industry electricity market prosperity index analysis method based on three-point prediction exploration method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104112163A (en) * | 2014-04-24 | 2014-10-22 | 国家电网公司 | Construction method of electric power forecasting business index |
-
2016
- 2016-10-24 CN CN201610932288.5A patent/CN106557835B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104112163A (en) * | 2014-04-24 | 2014-10-22 | 国家电网公司 | Construction method of electric power forecasting business index |
Non-Patent Citations (2)
| Title |
|---|
| 谈一鸣，孙伟卿: "基于经济分析的上海电力景气研究", 《电网与清洁能源》 * |
| 马精华: "地市电力景气指数研究", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476030A (en) * | 2020-05-08 | 2020-07-31 | 中国科学院计算机网络信息中心 | Prospective factor screening method based on deep learning |
| CN111476030B (en) * | 2020-05-08 | 2022-03-15 | 中国科学院计算机网络信息中心 | Prospective factor screening method based on deep learning |
| CN111583063A (en) * | 2020-05-11 | 2020-08-25 | 国网四川省电力公司电力科学研究院 | Business start and end time detection method based on standard template and storage medium |
| CN111583063B (en) * | 2020-05-11 | 2022-07-01 | 国网四川省电力公司电力科学研究院 | Business start and end time detection method based on standard template and storage medium |
| CN112116265A (en) * | 2020-09-25 | 2020-12-22 | 国网上海市电力公司 | Industry landscape index construction method driven by electric power data |
| CN112348281A (en) * | 2020-11-23 | 2021-02-09 | 国网北京市电力公司 | Power data processing method and device |
| CN112508251A (en) * | 2020-11-27 | 2021-03-16 | 国网浙江省电力有限公司杭州供电公司 | Load prediction method and device based on electric cockpit |
| CN112949897A (en) * | 2020-12-22 | 2021-06-11 | 浙江华云信息科技有限公司 | Industry electricity market prosperity index analysis method based on three-point prediction exploration method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106557835B (en) | 2018-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106557835B (en) | Electricity demand forecasting method and system based on consumer confidence index | |
| CN109376953B (en) | Medium-and-long-term electric quantity prediction method and system | |
| CN104657788B (en) | Key industry electricity demand forecasting method based on Industrial Cycle index | |
| CN111210170B (en) | Environment-friendly management and control monitoring and evaluation method based on 90% electricity distribution characteristic index | |
| Billio et al. | Combination schemes for turning point predictions | |
| CN110109971A (en) | A kind of low-voltage platform area user power utilization Load Characteristic Analysis method | |
| CN103793788B (en) | A kind of ordered electric management method | |
| CN104881718B (en) | Region electric power consumer confidence index construction method based on multiple dimensioned economic leading indicators | |
| CN104504619B (en) | Two kinds consider that the monthly system of temperature and economic growth factor calls power predicating method | |
| CN109492818A (en) | Based on energy development and the entitled electricity demand forecasting method of Shapley value | |
| Pessanha et al. | Forecasting long-term electricity demand in the residential sector | |
| CN110321934A (en) | A kind of method and system detecting user power utilization abnormal data | |
| Ugoh et al. | Application of ARIMAX Model on Forecasting Nigeria’s GDP | |
| CN110298765A (en) | A kind of power distribution network electric power method for detecting abnormality based on objective correlative factor | |
| CN110414776B (en) | Quick response analysis system for power utilization characteristics of different industries | |
| CN106251015A (en) | The consumer confidence index system construction of the two-way dimension of electrically-based economy and Forecasting Methodology | |
| Islam et al. | Load profile segmentation using residential energy consumption data | |
| KR101726870B1 (en) | Method for early warning in corporate finance | |
| Bordoloi et al. | Estimation of potential output in India | |
| CN107704723A (en) | A kind of notable Variable Selection based on Slope correlation | |
| Zhang et al. | Research on the improved combinatorial prediction model of steel price based on time series | |
| CN113705091A (en) | Non-uniform design flood calculation method considering change environment and scheduling influence | |
| CN110829409A (en) | Non-invasive power load identification method and device | |
| Vergnes et al. | Using stochastic modelling for long-term network planning of LV distribution grids at Dutch DNO | |
| Tsui et al. | Forecasting Singapore economic growth with mixed-frequency data |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210602 Address after: 510700 3rd, 4th and 5th floors of building J1 and 3rd floor of building J3, No.11 Kexiang Road, Science City, Luogang District, Guangzhou City, Guangdong Province Patentee after: China South Power Grid International Co.,Ltd. Address before: 510080 water Donggang 8, Dongfeng East Road, Yuexiu District, Guangzhou, Guangdong. Patentee before: China South Power Grid International Co.,Ltd. Patentee before: POWER GRID TECHNOLOGY RESEARCH CENTER. CHINA SOUTHERN POWER GRID |