CN108062598A - New situation load potential prediction method under multi-scenario - Google Patents
New situation load potential prediction method under multi-scenario Download PDFInfo
- Publication number
- CN108062598A CN108062598A CN201711308516.2A CN201711308516A CN108062598A CN 108062598 A CN108062598 A CN 108062598A CN 201711308516 A CN201711308516 A CN 201711308516A CN 108062598 A CN108062598 A CN 108062598A
- Authority
- CN
- China
- Prior art keywords
- electric energy
- terminal
- model
- scene
- method under
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000013528 artificial neural network Methods 0.000 claims abstract description 13
- 238000006467 substitution reaction Methods 0.000 claims abstract description 13
- 238000011161 development Methods 0.000 claims description 35
- 238000005516 engineering process Methods 0.000 claims description 12
- 238000005265 energy consumption Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 230000014509 gene expression Effects 0.000 claims description 6
- 230000001419 dependent effect Effects 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 4
- 238000000611 regression analysis Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 abstract 1
- 230000005611 electricity Effects 0.000 description 9
- 230000001965 increasing effect Effects 0.000 description 6
- 230000007774 longterm Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012417 linear regression Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000009916 joint effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 239000000126 substance Substances 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 provides a new situation load potential prediction method under multiple scenarios, which comprises the following steps: (1) setting a calculation scene; (2) calculating the total amount of electric energy substitution; (3) and predicting and correcting the electric energy substitution amount. A new situation load potential prediction method under multiple scenarios is designed, multiple electric energy substitution scenarios are designed, an intelligent correction prediction model combining multivariate nonlinear regression with a wavelet neural network is nested in an IPAT model, parameter settings in each scenario are determined through an unhook theory model of electric energy substitution, medium-long term prediction is conducted on terminal electric energy substitution situations under different scenarios, and prediction analysis is conducted on electric energy substitution processes and potentials through combination of prediction results. The method has the beneficial effect of accurate prediction result, and provides theoretical guidance for electric energy to replace actual work.
Description
Technical field
The present invention relates to long in load Potential Prediction technical field more particularly to population, economy, technology, one kind of policy
New situation load Potential Prediction method under phase Scenario.
Background technology
With the development of China human mortality and economic level, energy consumption is growing day by day, electricity needs and a fossil energy
The contradiction of shortage also becomes increasingly conspicuous.Due to electric energy have the characteristics that cleaning, safely, conveniently, efficient and advantage, China carries out
" using electricity instead of coal, replacing oil by electricity, electricity come from a distant place " substitutes work for the electric energy of core content.Statistics display, electric energy account for terminal energy
Source consumption proportion often improves 1 percentage point, and Energy Intensity just declines 3.7 percentage points.Therefore it should put forth effort to improve electric energy in terminal
Proportion in energy-consuming reduces to the greatest extent the burning and exhausting of terminal fossil energy to greatest extent, is discharged with pollution remission object to environment
Caused by pressure.The variation tendency for grasping electric energy and terminal energy sources consumption is conducive to analyze electric energy energy consumption condition, for guidance electricity
Work can be substituted, data support and policy guide are provided.The principal element for influencing China's power consumption has the level of economic development, electricity
Valency, population growth, technological progress, adjustment of energy policy etc..Research direction is mostly Energy Demand Forecast and potentiality point at present
Analysis, the Potentials research substituted for electric energy is less, and electric energy replacement related work has been opened comprehensively in recent years, it is therefore desirable to
The theoretical research certain to this progress provides theoretical guiding to carry out real work.
The content of the invention
The invention solves more than technical problems, provide a kind of new situation load Potential Prediction method under Scenario, energy
It is enough that the intelligence based on wavelet neural network is corrected into prediction model nesting in the analysis model, and pass through dechromed shavings model and determine
A variety of model parameters under Scenario realize effective prediction to terminal electric energy replacement amount under different scenes.
In order to solve the above technical problems, the technical solution adopted by the present invention is：A kind of new situation load under Scenario is dived
Force prediction method includes the following steps：
(1) setup algorithm scene；
(2) calculate electric energy and substitute total amount；
(3) electric energy replacement amount forecast value revision.
Setup algorithm scene primary condition is population growth rate α, GDP per capita average growth rate per annum β, skill in the step (1)
Art progress degree γ, support on policy dynamics δ；According to IPAT models and dechromed shavings model specification difference computation scenarios, feelings are calculated
Scape basis of design is as follows：
Technological progress degree γ and support on policy dynamics δ substitutes the primary outer factor of total amount variation as electric energy is influenced,
The relation of process is substituted with electric energy according to it, with reference to dechromed shavings model, can be set using above-mentioned two influence factor as scene
The major control variable put obtains the basic foundation that following electric energy substitutes potentiality scenario analysis：
①(1+β)/(1+γ)×(1+δ)>1, show that technological progress degree γ and Government supports dynamics δ replaces electric energy at this time
The propulsion dynamics in generation is smaller, it is impossible to realize and break off relations with economic development；
(2. 1+ β)/(1+ γ) × (1+ δ)=1, show technological progress degree γ at this time be electric energy is promoted to substitute it is main because
Element realizes the unhook with economic development；
③(1+β)/(1+γ)×(1+δ)<1, show at this time except technological progress degree γ substitutes electric energy the influence of development,
Government supports dynamics δ also plays facilitation to electric energy replacement, realizes the absolute unhook with economic development；
Set standard year TBIf terminal maintains standard year horizontal with energy general layout, terminal energy sources proportion and base shared by electric energy
Quasi- year is identical, and t power consumptions are defined as electric energy replacement amount D compared to benchmark power consumption incrementssE, t, the electric energy replacement
Measure DE, tProcess is substituted for quantifying the electric energy, i.e.,
In formula：DE, tFor electric energy replacement amount；YE, tFor the actual power consumption of t；YtFor t terminal energy consumptions
Total amount；On the basis of terminal energy sources proportion shared by year electric energy.
Electric energy replacement total amount expression formula is in the step (2)：
Ct=C0×[(1+α)×(1+β)×(1-γ)×(1+δ)]t ②
In formula：CtTotal amount, C are substituted for t electric energy0On the basis of year electric energy substitute total amount.
Electric energy replacement amount forecast value revision comprises the following steps in the step (3)：
I, binary nonlinear returns growth trend modeling：
Using nonlinear regression model (NLRM) to electric energy replacement amount De,tIt is fitted, obtains De,′tIf time T is x1, GDP is
X2 obtains binary nonlinear regression model：
De,t=ax1 2+bx2 2+cx1+dx2+e ③
In formula：A, b, c, d, e are model parameter；
X1 is time T；
X2 is GDP values then；
II, the intelligence amendment based on wavelet neural network：
If t-1 terminal power consumptions Ye,t-1D' is obtained with fittinge,tThe sum of be t fitting consumption ^Ye t,
That is Ye,t-1+D'e,t=^Ye t ④
T-1 terminal power consumptions Ye,t-1With actual consumption amount Ye,tDifference be residual error ee,t,
That is Ye,t-1-Ye,t=ee,t ⑤
In formula：ee,tFor residual sequence, Ye,tFor t actual power consumptions, D'e,tFor power consumption match value；
Using wavelet neural network to residual error ee,tSelf study is carried out, obtains output residual sequence e'e,t, set training network
Input layer number is 6, and intermediate node in hidden layer is 16, and input layer number is 1, using raw residual sequence data as the phase
Output is hoped to carry out repetition training network, until training error reaches required precision；
By the prediction result D' of binary nonlinear regression analysise,tWith based on the intelligent modified residual error ^ of wavelet neural network
ee tIt is combined, realizes the prediction to electric energy replacement amount, obtain predicted value ^De,t：
^De,t=D'e,t+^e e t。 ⑥
The IPAT model expressions are：
I=P × A × T is 7.
In formula：I is environment；P is population；A is wealth；T is technology；The IPAT models are to reflect environment I by people
The variation relation that mouth P, wealth A and 3 factors of technology T influence.
The dechromed shavings model expression is：
Unhook degree=electric energy replacement amount growth rate/GDP per capita annual growth is 8.
Quantitative change rate is substituted using GDP per capita annual gradient and electric energy to represent between economic growth and terminal electric energy replacement
Degree of dependence：
When unhook degree>When 1, illustrate that electric energy replacement amount growth rate is more than the rate of economic development, electric energy, which substitutes, promotes speed
Degree is fast, and economic growth depends on electric energy substitution level, in the developing stage not broken off relations；
When unhook degree≤1, electric energy replacement amount growth rate is less than economic growth rate or is protected with the rate of economic development
It holds unanimously, economic growth not fully depends on or be less dependent on electric energy substitution level, and economic growth substitutes process with electric energy
In the stage of unhook.
The invention has the advantages and positive effects that：A kind of new situation load Potential Prediction method under Scenario, if
It has counted a variety of electric energy and has substituted scene, the intelligence of Multiple Non Linear Regression combination wavelet neural network is corrected prediction model is nested in
In IPAT models, the dechromed shavings model substituted by electric energy determines the parameter setting in each scene, to the end under different scenes
Electric energy alternative case is held to carry out medium- and long-term forecasting, and combines prediction result and process and potentiality progress forecast analysis is substituted to electric energy.
The present invention has prediction result accurately advantageous effect, and substituting real work development for electric energy provides theoretical guiding.
Description of the drawings
Fig. 1 is joined substantially in setup algorithm scene in the new situation load Potential Prediction embodiment of the method under a kind of Scenario
Number sets table；
Fig. 2 is that electric energy replacement amount is pre- under each scene in the new situation load Potential Prediction embodiment of the method under a kind of Scenario
Mapping；
Fig. 3 is in the year two thousand twenty, the year two thousand thirty, 2040 in the new situation load Potential Prediction embodiment of the method under a kind of Scenario
Year and the electric energy replacement amount Potentials figure of the year two thousand fifty；
Fig. 4 is terminal electric energy before and after intelligently being corrected in the new situation load Potential Prediction embodiment of the method under a kind of Scenario
Replacement amount fitting result compares figure.
Specific embodiment
It elaborates below in conjunction with the accompanying drawings to specific embodiments of the present invention.
As shown in Figs 1-4, a kind of new situation load Potential Prediction method under Scenario, includes the following steps：
1) setup algorithm scene
(1) scene covers content
This Forecasting Methodology is calculated under the scene of setting, first setup algorithm scene, determines that scene primary condition is
Demographic parameter, economic parameters, technical merit, support on policy dynamics.
(2) scene basis of design
More comprehensively forecast analysis is carried out in order to substitute potentiality to medium-term and long-term electric energy, according to IPAT models and dechromed shavings model
Set different replacement scenes.Scene basis of design is as follows：
Technological progress degree and support on policy as the primary outer factor for influencing electric energy and substituting total amount and changing, according to its with
Electric energy substitutes the relation of process, with reference to dechromed shavings model, can be set using above-mentioned two influence factor as scene main
Variable is controlled, obtains the basic foundation that following electric energy substitutes potentiality scenario analysis：
①(1+β)/(1+γ)×(1+δ)>1, show that the rate of economic development is more than electric energy and substitutes process, electric energy, which substitutes, to be implemented
Very high to economic development dependency degree, the degree of technological progress at this time and the propulsion dynamics that Government supports substitute electric energy are smaller, it is impossible to
It realizes and breaks off relations with economic development.
(2. 1+ β)/(1+ γ) × (1+ δ)=1 shows that the rate of economic development and electric energy replacement process are basically identical, electric energy
The popularization and application of replacement has been not entirely dependent on economic development, and technological progress at this time is the principal element that electric energy is promoted to substitute, real
Now with the unhook of economic development.
③(1+β)/(1+γ)×(1+δ)<1, show that electric energy substitutes speed and is more than the rate of economic development, electric energy, which substitutes, to be promoted
Economic development is needed not rely upon, at this time except technological progress substitutes electric energy the influence of development, electric energy substitutes helping for relevant policies
Holding force degree also plays facilitation to electric energy replacement, is truly realized the absolute unhook with economic development.
Wherein：α represents population growth rate；
β represents GDP per capita average growth rate per annum；
γ represents that terminal power consumption intensity increases ratio, GC group connector energy electrifing degree, i.e. technological progress degree；
δ represents that electric energy replacement amount accounts for the proportion change rate of terminal power consumption, i.e. electric energy terminal alternative structure change rate.By
It is to influence the variation of terminal energy sources alternative structure to be acted in the industrial structure optimization adjustment of Government-Leading and clean energy resource consumption guidance
Principal element, and terminal clean energy resource is primarily referred to as electric energy, therefore δ can be considered the support dynamics that government substitutes electric energy.
(3) computing object is determined
Analysis for a long time during potentiality carry out is substituted to electric energy to first have to determine analysis object, will analyze object quantization means, and
Build relevant rudimentary model.Power demand cannot be applied alone to weigh since electric energy substitutes potentiality, define electric energy replacement first
Amount substitutes process for quantifying electric energy.
Quantum chemical method is realized in order to substitute potentiality to electric energy, defines the visitor that electric energy replacement amount substitutes potentiality as analysis electric energy
See foundation.Set standard year TBIf terminal maintains standard year horizontal with energy general layout, terminal energy sources proportion and benchmark shared by electric energy
Year is identical, and t power consumptions are defined as electric energy replacement amount compared to benchmark power consumption incrementss：
In formula：De,tFor electric energy replacement amount；
Ye,tFor the actual power consumption of t；
YtFor t terminal energy consumption total amounts；
On the basis of terminal energy sources proportion shared by year electric energy.
(4) IPAT models
One famous formula with population (P), affluence degree (A) and technical merit (T) Evaluation Environment pressure of the model, table
It is up to formula
I=P × A × T
The foundation of IPAT models is to study the influence of Population on Environment variation, and reflection environment is by population, wealth and skill
The variation relation that 3 factors of art influence.Electric energy substitutes the comprehensive function for being similarly subjected to population, economic growth and technical merit, people
Mouth increases, economic level is improved can promote replacement of the electric energy to terminal energy sources with correlation technique development.Wherein electric energy substitutes
Technological progress can be embodied in the consumption intensity of electric energy and electric energy accounts for the proportion of final energy consumption.Electric energy substitutes correlation technique day
Become ripe, electric energy consumption intensity accounts for final energy consumption proportion to electric energy corresponding can also increase.
(5) dechromed shavings model
Dechromed shavings model, quantitative change rate is substituted using GDP per capita change rate and electric energy here come represent economic growth with
Degree of dependence between terminal electric energy replacement：Unhook degree=electric energy replacement amount growth rate/Growth rate of per capita GDP.
When unhook degree>When 1, illustrate that electric energy replacement amount growth rate is more than the rate of economic development, electric energy, which substitutes, promotes speed
Degree is fast, and economic growth depends on electric energy substitution level, in the developing stage not broken off relations.
When unhook degree≤1, electric energy replacement amount growth rate is less than economic growth rate or is protected with the rate of economic development
It holds unanimously, economic growth not fully depends on or be less dependent on electric energy substitution level, and economic growth substitutes process with electric energy
In the stage of unhook.
2) calculate electric energy and substitute total amount
Developing algorithm model calculates electric energy and substitutes total amount, and t substitutes total quantity algorithm on the electric energy of standard year can be with table
Up to for：
Ct=C0×[(1+α)×(1+β)×(1-γ)×(1+δ)]t
C in formulatAnd C0Respectively t and standard year electric energy substitute total amount.
3) electric energy replacement amount forecast value revision
Intelligent algorithm is combined with regression model, make prediction model can dynamic self study, when predicting electric energy replacement amount,
Intelligent amendment carries out nonlinear regression model (NLRM) prediction result using wavelet neural network.
Since electric energy replacement amount situation of change is not simple linear regression, but non-linear growth feature is showed,
Growth trend is increased joint effect with GDP by time passage and restricted.Therefore first using binary nonlinear regression curve to electric energy
Replacement amount carries out prediction modeling.
(1) binary nonlinear returns growth trend modeling：
Using nonlinear regression model (NLRM) to electric energy replacement amount De,tIt is fitted, obtains De,′t.If time T is x1, GDP is
X2 obtains binary nonlinear regression model：De,t=ax1 2+bx2 2+cx1+dx2+e
In formula：A, b, c, d, e are model parameter；
X1 is time T；
X2 is GDP values then.
(2) the intelligence amendment based on wavelet neural network
If t-1 terminal power consumptions Ye,t-1D' is obtained with fittinge,tThe sum of t fitting consumption ^Ye t,
And the difference of actual consumption amount is residual error ee,t：
In formula：ee,tFor residual sequence, Ye,tFor t actual power consumptions, D'e,tFor power consumption match value.
Using wavelet neural network to residual error ee,tSelf study is carried out, obtains output residual sequence e'e,t, set training network
Input layer number is 6, and intermediate node in hidden layer is 16, and input layer number is 1.Using raw residual sequence data as the phase
Output is hoped to carry out repetition training network, until training error reaches required precision.
By the prediction result D' of binary nonlinear regression analysise,tWith based on the intelligent modified residual error ^e of wavelet neural networket
It is combined, realizes the prediction to electric energy replacement amount, obtain predicted value ^De,t：
^De,t=D'e,t+^eet
Accuracy is illustrated so that China's terminal power consumption historical data is fitted comparison for sample as an example below, if
Year on the basis of 2000 fixed.
1) setup algorithm scene
(1) scene is set
More comprehensively forecast analysis is carried out in order to substitute potentiality to medium-term and long-term electric energy, according to IPAT models and dechromed shavings model
3 kinds of different replacement scenes are set, scene A keeps existing electric energy to substitute process, do not take any Advancing Measures；Scene B is in original
There is addition technical substitution index in electric energy replacement process.Domestic correlation technique will be greatly developed under the scene, will be quoted extensively external
Related electric technology, and by its large scale investment into terminal applies.Scene C strengthens government on the basis of technological progress is increased
To the support dynamics that terminal electric energy substitutes, policy support is provided in terminal applies for electric energy substitute technology.
(2) parameter setting
1. demographic parameter：
With reference to《Countries population's Study of developing strategy is reported》With《Population and social development report 2014》Wait Correlative plans
Prediction and judge, analyze the situation of change of China's Future population growth rate, it is contemplated that 2016-the year two thousand twenty population growth rate is
3.5 ‰, 2021-2025 annual rate of population increase are 2.4 ‰, and 2026-the year two thousand thirty population growth rate is 2.1 ‰, 2031-2035
Annual rate of population increase is 1.3 ‰, and 2036-the year two thousand forty population growth rate is for 1.3 ‰, 2041-2045 annual rate of population increase
3.1 ‰, 2046-the year two thousand fifty population growth rate is 3.1 ‰, according to more than data setting demographic parameter.
2. economic parameters：
Using actual GDP in 2014 as judging benchmark, it is contemplated that the economic growth rate of 2016-the year two thousand twenty China is 6%,
2021-2025 years are 5.4%, and 2026-the year two thousand thirty is 4.1%, and 2031-2035 years are 3.8%, and 2036-the year two thousand forty is
3.75%, 2041-2045 years are 3.5%, and 2046-the year two thousand fifty is 3.4%.
3. technical merit：
It sets electric energy in scene A and substitutes correlation technique and stagnate and develop, terminal electrical energy demands maintain present level, terminal electric energy
Consumption intensity remains unchanged, and electric energy substitutes process due to the promotion of no technological progress, and the state that do not break off relations is in economic development.
Scene B is using above-mentioned background as technical foundation, if electric energy substitute technology and economic cooperative development, terminal electrical energy demands
Improving and be significantly increased with electric energy substitute technology, terminal electric energy consumption intensity increase, and growth level and each stage are economical
Development level is consistent, and it is approximately 1 that electric energy is made, which to substitute with economic development unhook degree, at this timeEach stage electric energy replaces in scene C
It is consistent for correlation technique level with scene B.
4. support on policy dynamics：
It sets government in scene A and scene B and related work offer support on policy and correlation interference, electric energy is not provided to electric energy
Terminal alternative structure maintains stable development.Due to no government intervention, electric energy, which is substituted, to fail to realize unhook or completely de- with economy
Hook, unhook degree are not more than 1.Based on scene C substitutes related work planning objective by China to electric energy, increase government to electricity
The support dynamics of work can be substituted, electric energy terminal is made to substitute ability enhancing, alternative structure changes, and electric energy replacement amount is significantly increased.
According to dechromed shavings to population growth rate α, GDP per capita average growth rate per annum β, technology under scene A, scene B and scene C
Progress degree γ and support on policy dynamics δ parameter settings, prediction terminal energy structure development and change are as shown in Figure 1.
2) prediction result
As shown in Fig. 2, terminal electric energy replacement amount can be presented greatly before under scene A, scene B and scene C, to the year two thousand thirty
Width growth trend.Electric energy replacement amount increasing degree under wherein scene A is less than scene B and scene C, this is because scene A does not have
Technological progress substitutes electric energy with relevant policies the propulsion of work.Scene C substitutes related work due to increasing government to electric energy
It helps, therefore the electric energy replacement amount rate of rise under the scene is more than scene B.Between 2030-the year two thousand forty, electric energy replacement amount will
Tend to be steady growth, until after 2045, due to substituting field close to saturation, electric energy replacement amount also gradually tends to be steady, no
It is present with and increases substantially.
For electric energy alternative case compared with scene A, the electric energy replacement process of scene B and scene C is apparent under scene B and scene C
It is especially notable to the progradation of electric energy replacement work after scene C increases support on policy more than scene A, far above only by technology
Progress promotes the scene B that electric energy substitutes.As shown in figure 3, respectively reach electricity under 2020,2030,2040 and the year two thousand fifty, scene B
4.8 trillion kWh of energy replacement amount, 17.1 trillion kWh, 43.9 trillion kWh and 65,000,000,000,000 kWh, compared to the electricity under scene A
Energy replacement amount increases replacement 8.13%, 13.96%, 18.43% and 22.05% respectively.
As shown in figure 4, by the revised prediction model of intelligence to the fitting result of electric energy replacement amount closer to actual value,
More accurately prediction result can be obtained based on the modified prediction model of intelligence.
The embodiment of the present invention is described in detail above, but the content is only presently preferred embodiments of the present invention,
It should not be construed as limiting the practical range of the present invention.All all the changes and improvements made according to the scope of the invention etc., should all
It still belongs within this patent covering scope.
Claims (6)
1. a kind of new situation load Potential Prediction method under Scenario, it is characterised in that：Include the following steps：
(1) setup algorithm scene；
(2) calculate electric energy and substitute total amount；
(3) electric energy replacement amount forecast value revision.
2. the new situation load Potential Prediction method under a kind of Scenario according to claim 1, it is characterised in that：It is described
In step (1) setup algorithm scene primary condition for population growth rate α, GDP per capita average growth rate per annum β, technological progress degree γ,
Support on policy dynamics δ；According to IPAT models and dechromed shavings model specification difference computation scenarios, computation scenarios basis of design is such as
Under：
Technological progress degree γ and support on policy dynamics δ substitutes the primary outer factor of total amount variation, foundation as electric energy is influenced
It substitutes the relation of process with electric energy, with reference to dechromed shavings model, can set above-mentioned two influence factor as scene
Major control variable obtains the basic foundation that following electric energy substitutes potentiality scenario analysis：
①(1+β)/(1+γ)×(1+δ)>1, show what technological progress degree γ at this time and Government supports dynamics δ substituted electric energy
Propulsion dynamics is smaller, it is impossible to realize and break off relations with economic development；
(2. 1+ β)/(1+ γ) × (1+ δ)=1 shows that technological progress degree γ is the principal element that electric energy is promoted to substitute at this time,
Realize the unhook with economic development；
③(1+β)/(1+γ)×(1+δ)<1, show at this time except technological progress degree γ substitutes electric energy the influence of development, government
Support dynamics δ also plays facilitation to electric energy replacement, realizes the absolute unhook with economic development；
Set standard year TBIf terminal maintains standard year horizontal with energy general layout, terminal energy sources proportion shared by electric energy and standard year phase
Together, t power consumptions are defined as electric energy replacement amount D compared to benchmark power consumption incrementssE, t, the electric energy replacement amount DE, tWith
Process is substituted to quantify the electric energy, i.e.,
In formula：DE, tFor electric energy replacement amount；YE, tFor the actual power consumption of t；YtFor t terminal energy consumption total amounts；On the basis of terminal energy sources proportion shared by year electric energy.
3. the new situation load Potential Prediction method under a kind of Scenario according to claim 2, it is characterised in that：It is described
Electric energy replacement total amount expression formula is in step (2)：
Ct=C0×[(1+α)×(1+β)×(1-γ)×(1+δ)]t ②
In formula：CtTotal amount, C are substituted for t electric energy0On the basis of year electric energy substitute total amount.
4. the new situation load Potential Prediction method under a kind of Scenario according to claim 3, it is characterised in that：It is described
Electric energy replacement amount forecast value revision comprises the following steps in step (3)：
I, binary nonlinear returns growth trend modeling：
Using nonlinear regression model (NLRM) to electric energy replacement amount De,tIt is fitted, obtains De,′tIf time T is x1, GDP x2 are obtained
To binary nonlinear regression model：
De,t=ax1 2+bx2 2+cx1+dx2+e ③
In formula：A, b, c, d, e are model parameter；
X1 is time T；
X2 is GDP values then；
II, the intelligence amendment based on wavelet neural network：
If t-1 terminal power consumptions Ye,t-1D' is obtained with fittinge,tThe sum of be t fitting consumption ^Yet,
That is Ye,t-1+D'e,t=^Yet ④
T-1 terminal power consumptions Ye,t-1With actual consumption amount Ye,tDifference be residual error ee,t,
That is Ye,t-1-Ye,t=ee,t ⑤
In formula：ee,tFor residual sequence, Ye,tFor t actual power consumptions, D'e,tFor power consumption match value；
Using wavelet neural network to residual error ee,tSelf study is carried out, obtains output residual sequence e'e,t, setting training network input
Node layer number is 6, and intermediate node in hidden layer is 16, and input layer number is 1, and raw residual sequence data is defeated as it is expected
Out repetition training network, until training error reaches required precision；
By the prediction result D' of binary nonlinear regression analysise,tWith based on the intelligent modified residual error ^e of wavelet neural networketXiang Jie
It closes, realizes the prediction to electric energy replacement amount, obtain predicted value ^De,t：
^De,t=D'e,t+^eet。 ⑥。
5. the new situation load Potential Prediction method under a kind of Scenario according to claim 4, it is characterised in that：It is described
IPAT model expressions are：
I=P × A × T is 7.
In formula：I is environment；P is population；A is wealth；T is technology；The IPAT models be in order to reflect environment I by population P,
The variation relation that T3 factor of wealth A and technology influences.
6. the new situation load Potential Prediction method under a kind of Scenario according to claim 5, it is characterised in that：It is described
Dechromed shavings model expression is：
Unhook degree=electric energy replacement amount growth rate/GDP per capita annual growth is 8.
Quantitative change rate is substituted using GDP per capita annual gradient and electric energy come represent economic growth and terminal electric energy substitute between according to
Rely degree：
When unhook degree>When 1, illustrating that electric energy replacement amount growth rate is more than the rate of economic development, electric energy replacement fltting speed is fast,
Economic growth depends on electric energy substitution level, in the developing stage not broken off relations；
When unhook degree≤1, electric energy replacement amount growth rate is less than economic growth rate or keeps one with the rate of economic development
It causes, economic growth not fully depends on or be less dependent on electric energy substitution level, and economic growth substitutes process with electric energy and is in
The unhook stage.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711308516.2A CN108062598A (en) | 2017-12-11 | 2017-12-11 | New situation load potential prediction method under multi-scenario |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711308516.2A CN108062598A (en) | 2017-12-11 | 2017-12-11 | New situation load potential prediction method under multi-scenario |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108062598A true CN108062598A (en) | 2018-05-22 |
Family
ID=62136415
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711308516.2A Pending CN108062598A (en) | 2017-12-11 | 2017-12-11 | New situation load potential prediction method under multi-scenario |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108062598A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764584A (en) * | 2018-06-05 | 2018-11-06 | 国网浙江省电力有限公司 | A kind of enterprise electrical energy replacement potential evaluation method |
| CN108959190A (en) * | 2018-06-12 | 2018-12-07 | 国网福建省电力有限公司 | A kind of electric energy substitution theoretical inspiration calculation method based on heat equivalent method |
| CN111080481A (en) * | 2019-12-14 | 2020-04-28 | 广西电网有限责任公司电力科学研究院 | Electric energy substitution potential gray analysis method based on Markov chain correction |
| CN111507551A (en) * | 2019-01-31 | 2020-08-07 | 国网能源研究院有限公司 | Electric energy substitution environment protection policy target measuring and calculating method considering air quality improvement |
| CN111832785A (en) * | 2019-04-23 | 2020-10-27 | 国网浙江省电力有限公司电力科学研究院 | Method and system for predicting electric energy substitution potential |
| CN112036026A (en) * | 2020-08-27 | 2020-12-04 | 天津天大求实电力新技术股份有限公司 | Building thermal load prediction method based on heat storage system |
| CN112785022A (en) * | 2019-11-01 | 2021-05-11 | 华北电力大学 | Method and system for excavating electric energy substitution potential |
| CN114372691A (en) * | 2021-12-29 | 2022-04-19 | 国网天津市电力公司 | Electric energy substitution potential estimation method based on holographic perception |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824128A (en) * | 2014-02-24 | 2014-05-28 | 华南理工大学 | Method for scale prediction of regional distributed type comprehensive energy-supply system |
| CN106327028A (en) * | 2016-11-09 | 2017-01-11 | 国网能源研究院 | Terminal energy consumption prediction method and device |
| CN107292508A (en) * | 2017-06-16 | 2017-10-24 | 北京中电普华信息技术有限公司 | A kind of electric energy substitutes the analyzing and predicting method and system of potentiality |
-
2017
- 2017-12-11 CN CN201711308516.2A patent/CN108062598A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824128A (en) * | 2014-02-24 | 2014-05-28 | 华南理工大学 | Method for scale prediction of regional distributed type comprehensive energy-supply system |
| CN106327028A (en) * | 2016-11-09 | 2017-01-11 | 国网能源研究院 | Terminal energy consumption prediction method and device |
| CN107292508A (en) * | 2017-06-16 | 2017-10-24 | 北京中电普华信息技术有限公司 | A kind of electric energy substitutes the analyzing and predicting method and system of potentiality |
Non-Patent Citations (1)
| Title |
|---|
| 孙毅 等: "多情景下的电能替代潜力分析", 《电网技术》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764584B (en) * | 2018-06-05 | 2021-04-09 | 国网浙江省电力有限公司 | Enterprise electric energy substitution potential evaluation method |
| CN108764584A (en) * | 2018-06-05 | 2018-11-06 | 国网浙江省电力有限公司 | A kind of enterprise electrical energy replacement potential evaluation method |
| CN108959190A (en) * | 2018-06-12 | 2018-12-07 | 国网福建省电力有限公司 | A kind of electric energy substitution theoretical inspiration calculation method based on heat equivalent method |
| CN108959190B (en) * | 2018-06-12 | 2022-04-01 | 国网福建省电力有限公司 | Electric energy substitution theory potential calculation method based on heat equivalent method |
| CN111507551A (en) * | 2019-01-31 | 2020-08-07 | 国网能源研究院有限公司 | Electric energy substitution environment protection policy target measuring and calculating method considering air quality improvement |
| CN111507551B (en) * | 2019-01-31 | 2022-05-03 | 国网能源研究院有限公司 | Electric energy substitution target measuring and calculating method considering air quality improvement |
| CN111832785A (en) * | 2019-04-23 | 2020-10-27 | 国网浙江省电力有限公司电力科学研究院 | Method and system for predicting electric energy substitution potential |
| CN112785022A (en) * | 2019-11-01 | 2021-05-11 | 华北电力大学 | Method and system for excavating electric energy substitution potential |
| CN112785022B (en) * | 2019-11-01 | 2024-06-07 | 华北电力大学 | Method and system for excavating electric energy substitution potential |
| CN111080481A (en) * | 2019-12-14 | 2020-04-28 | 广西电网有限责任公司电力科学研究院 | Electric energy substitution potential gray analysis method based on Markov chain correction |
| CN112036026A (en) * | 2020-08-27 | 2020-12-04 | 天津天大求实电力新技术股份有限公司 | Building thermal load prediction method based on heat storage system |
| CN112036026B (en) * | 2020-08-27 | 2023-09-22 | 天津天大求实电力新技术股份有限公司 | Building heat load prediction method based on heat storage system |
| CN114372691A (en) * | 2021-12-29 | 2022-04-19 | 国网天津市电力公司 | Electric energy substitution potential estimation method based on holographic perception |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108062598A (en) | New situation load potential prediction method under multi-scenario | |
| Wang et al. | Forecasting energy demand in China and India: Using single-linear, hybrid-linear, and non-linear time series forecast techniques | |
| Ma et al. | Forecasting iron ore import and consumption of China using grey model optimized by particle swarm optimization algorithm | |
| Wang et al. | An improved grey multivariable model for predicting industrial energy consumption in China | |
| Pao et al. | Forecasting of CO2 emissions, energy consumption and economic growth in China using an improved grey model | |
| Behrang et al. | Forecasting future oil demand in Iran using GSA (Gravitational Search Algorithm) | |
| CN108416691B (en) | Energy substitution environment-friendly potential calculation method | |
| CN108009667A (en) | A kind of energy demand total amount and structure prediction system | |
| CN107918368B (en) | The dynamic prediction method and equipment of iron and steel enterprise's coal gas yield and consumption | |
| Xiong et al. | Forecast of natural gas consumption in the Asia-Pacific region using a fractional-order incomplete gamma grey model | |
| CN106355285B (en) | Power load prediction method based on parameter correction | |
| Wang et al. | Inherent spatiotemporal uncertainty of renewable power in China | |
| CN110309949A (en) | A kind of region electric energy substitution Potential Prediction method and system | |
| CN104021432A (en) | Power load medium and long term prediction method based on improved grey prediction model | |
| CN111415068A (en) | Power distribution decision modeling method based on relevance of transformation measures and loss load index | |
| CN112308270A (en) | Long-term electricity load prediction method and device and computer implementation system | |
| CN104834975A (en) | Power network load factor prediction method based on intelligent algorithm optimization combination | |
| KR20200022255A (en) | Method and apparatus for optimizing energy storage device based on energy generation and bidding | |
| Bhotto et al. | Short-term demand prediction using an ensemble of linearly-constrained estimators | |
| CN112560330B (en) | Simulation data generation method and system for electricity utilization behavior prediction | |
| Voswinkel et al. | Flow-based market coupling: What drives welfare in Europe's electricity market design? | |
| CN101860025A (en) | Predictor-corrector technology-based power loss calculation method of grid in future operation mode | |
| CN108108837A (en) | A kind of area new energy power supply structure optimization Forecasting Methodology and system | |
| CN116722605B (en) | Power distribution network scheduling optimization method based on Internet of things | |
| CN112508231A (en) | Medium-and-long-term power load prediction method and system based on system dynamics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180522 |
|
| RJ01 | Rejection of invention patent application after publication |