CN109214449A - A kind of electric grid investment needing forecasting method - Google Patents
A kind of electric grid investment needing forecasting method Download PDFInfo
- Publication number
- CN109214449A CN109214449A CN201810985402.XA CN201810985402A CN109214449A CN 109214449 A CN109214449 A CN 109214449A CN 201810985402 A CN201810985402 A CN 201810985402A CN 109214449 A CN109214449 A CN 109214449A
- Authority
- CN
- China
- Prior art keywords
- electric grid
- grid investment
- prediction
- grey
- parameter
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention belongs to electric grid investment requirement forecasting technical field more particularly to a kind of electric grid investment needing forecasting methods, comprising: the influencing factor system of electric grid investment prediction is constructed by Delphi method；The grey relational grade of each influence factor and electric grid investment is calculated, sequence filters out input of the major influence factors of electric grid investment prediction as prediction model；The parameter of support vector machines is optimized using differential evolution improved grey wolf optimization algorithm, electric grid investment demand is predicted after establishing prediction model；Proof analysis is demonstrated has very strong generalization ability and robustness to the model that support vector machines optimizes based on the improved grey wolf algorithm of differential evolution in terms of electric grid investment prediction, it can reach good prediction effect, predict that the research in field provides new thinking for electric grid investment.
Description
Technical field
The invention belongs to electric grid investment requirement forecasting technical field more particularly to a kind of electric grid investment needing forecasting methods.
Background technique
Currently, power grid plays an increasingly important role in socio-economic development, it carries optimization energy resources
The substantial responsibility for configuring and promoting social development is the important subject of implementation of energy strategy.Expanding economy promotes electric grid investment
Demand continues to increase, accurately and effectively electric grid investment requirement forecasting, can not only help pooling of capital, reasonable arrangement power grid construction
The investment of fund, and fund cost can be reduced, economic risk is reduced, to electric grid investment planning construction process is pushed, is played
Vital effect.In recent years, domestic and foreign scholars have carried out investment demand prediction with a variety of prediction models in every field
Research, and achieve certain research achievement.However, up to the present, scholars predict for the investment demand of power grid enterprises
The acquired related research result of research is less, has been fruitful mostly using time series models, gray model, error correction mould
The models such as type are predicted that used prediction technique is relatively traditional.
Compared with classical Predicting Technique, artificial intelligence Predicting Technique presents powerful superior in terms of prediction accuracy
Property, realize good prediction effect.Neural network and support vector machines are two kinds of typical cases and widely applied artificial intelligence is pre-
Survey technology, but in contrast, the support vector machine method to grow up in Statistical Learning Theory has more solid mathematics
Theoretical basis can efficiently solve the High dimensional data model Construct question under the conditions of finite sample, and have stronger extensive
Ability has become most popular one of the research direction in machine learning field at present.In order to further increase the estimated performance of SVM,
Researchers optimize the parameter of SVM using many algorithms, as drosophila algorithm, particle swarm algorithm, genetic algorithm, whale are calculated
A variety of optimization algorithms such as method.Above-mentioned algorithm has certain help for the optimization of support vector machines parameter, but there is also bright
Aobvious deficiency, their search efficiencies are low, and convergence rate is slow, and are easily trapped into local optimum.
Summary of the invention
In order to more accurately predict electric grid investment situation, the invention proposes a kind of electric grid investment needing forecasting method, packets
It includes:
Step 1: the influencing factor system of electric grid investment prediction is constructed by Delphi method；
Step 2: calculating the grey relational grade of each influence factor and electric grid investment, sequence filters out electric grid investment prediction
Input of the major influence factors as prediction model；
Step 3: the parameter of support vector machines being optimized using differential evolution improved grey wolf optimization algorithm, is established pre-
Electric grid investment demand is predicted after surveying model.
The influencing factor system of the electric grid investment prediction includes: economic development, electricity needs, power grid scale and power grid effect
Beneficial four dimensions, each dimension include four factors, respectively successively are as follows: GDP, the industrial structure, population, urbanization rate, the whole society
Electricity consumption, electricity consumption growth rate, electricity sales amount, power grid maximum load, 220kV and the above transmission line length, 110kV and following
Transmission line length, 220kV and the above transformer equipment capacity, 110kV and following transformer equipment capacity, power grid gross profit, unit
Power grid asset supply load, unit power grid asset electricity sales amount, unit power grid asset power selling income.
The step 2 comprises determining that reference sequences in analytical sequence and compares sequence, carries out dimensionless to Variables Sequence
Change, calculate correlation coefficient and the degree of association, sequence will be compared and sorted according to grey relational grade size, grey relational grade is bigger, shows
The comparison sequence is more consistent with the situation that reference sequences change.
The step 3 includes:
Step 301: setting relevant parameter, initialization population；
Step 302: calculating the fitness value of grey wolf individual, and it is ranked up, before determining that fitness value is optimal
The position of three grey wolf individuals；
Step 303: calculating other grey wolf individuals in population and update wolf pack position at a distance from front three grey wolf body position
And grey wolf optimization algorithm relevant parameter；
Step 304: being made a variation with differential evolution algorithm, crossover operation, generate new progeny population；
Step 305: carrying out selection operation, update wolf pack position；
Step 306: judging whether to reach maximum number of iterations, if reaching, export current optimal solution, otherwise, jump to
Step 302 continues parameter optimization；
Step 307: the parameter value after optimization being assigned to support vector machines, establishes prediction model.
The parameter is regularization parameter c and Radial basis kernel function parameter g.
Beneficial effects of the present invention:
On the basis of analyzing electric grid investment influence factor, electric grid investment prediction index system is constructed, and transport
It uses gray relative analysis method to screen the input of electric grid investment major driving factor as prediction model, while proposing one kind and being based on
The novel power grid investment demand prediction model for the algorithm that the improved grey wolf algorithm of differential evolution optimizes support vector machines, and pass through
Proof analysis, it was demonstrated that the model that support vector machines optimizes is predicted in electric grid investment based on differential evolution improved grey wolf algorithm
Aspect has very strong generalization ability and robustness, can reach good prediction effect for electric grid investment prediction, throws for power grid
The research in money prediction field provides new thinking.
Detailed description of the invention
Fig. 1 is electric grid investment predicted impact Factor system of the invention.
Fig. 2 is the prediction result invested using DE-GWO-SVM model prediction China Power Grids of the invention.
Specific embodiment
With reference to the accompanying drawing, it elaborates to embodiment.
1, electric grid investment predicted impact Factor system constructs
The electric grid investment prediction of China is influenced by factors, in order to realize to the accurate pre- of Chinese electric grid investment
It surveys, the present invention tentatively has chosen the Correlative Influence Factors of electric grid investment prediction on the basis of consulting lot of documents, and passes through moral
Er Feifa carries out mostly wheel anonymities to the opinion of expert and consults and feed back, the final influence for determining China Power Grids investment forecasting
Factor system.It is pre- that the present invention from economic development, electricity needs, power grid scale and grid benefit four dimensions constructs electric grid investment
Influencing factor system is surveyed, each dimension includes four factors, is related to 16 influence factors altogether, respectively GDP, the industrial structure (the
Three industry accountings), population, urbanization rate, Analyzing Total Electricity Consumption, electricity consumption growth rate, electricity sales amount, power grid maximum load,
220kV and the above transmission line length, 110kV and following transmission line length, 220kV and the above transformer equipment capacity, 110kV
And following transformer equipment capacity, power grid gross profit, unit power grid asset supply load, unit power grid asset electricity sales amount, unit electricity
Net assets power selling income.Electric grid investment predicted impact Factor system is as shown in Figure 1:
2, the major influence factors screening based on grey correlation analysis
The present invention screens electric grid investment predicted impact factor with grey correlation analysis, by calculating above-mentioned 16
The grey relational grade of influence factor and electric grid investment, sequence filter out the major influence factors of electric grid investment prediction, and will screening
Input of the factor out as prediction model.
Steps are as follows for the specific calculating of grey relational grade:
(1) analytical sequence is determined
If reference sequences:
X0=(x0(1),x0(2),…,x0(n)) (1)
Compare sequence:
(2) nondimensionalization is carried out to Variables Sequence
K=1,2 ..., n, i=0,1,2 ..., m
(3) calculate correlation coefficient
yj(k) and y0(k) shown in incidence coefficient such as formula (15):
ρ ∈ (0,1), k=1,2 ..., n, j=1,2 ..., m
(4) calculating correlation
XjWith X0Grey relational grade such as formula (16) shown in:
K=1,2 ..., n, j=1,2 ..., m
(5) relational degree taxis
Sequence will be compared to sort according to grey relational grade size, grey relational grade is bigger, shows the comparison sequence and reference
The situation of sequence variation is more consistent.
3, prediction model
3.1SVM (support vector machines)
Support vector machines is that the foundation that Vapnik et al. is proposed ties up theoretical and Structural risk minization in Statistical Learning Theory VC
A kind of small sample machine learning method on the basis of change, when estimating regression function with algorithm of support vector machine, basic thought is
By the way that in a Nonlinear Mapping, the data of the input space are mapped in a high-dimensional feature space, then in this height
Make linear regression in dimension space.
Given n training sample set is combined into: { (xi,yi) | i=1,2 ..., n }, wherein xi∈RdIt is defeated that training sample is tieed up for d
Enter, yi∈ R is training sample output.Using Nonlinear MappingInput sample from original
Space RdIt is mapped to high-dimensional feature space Rk, (k > d) constructs optimum linearity regression function in high-dimensional feature space:
In formula: ω is high-dimensional feature space weight vector, ω ∈ Rk；B is offset constant, b ∈ R.
Using structuring least risk principle, ω, b are found, i.e.,
In formula: ω2The complexity of Controlling model, c are regularization parameter, RempFor control errors function, RempMiddle selection is not
Same loss function, can construct various forms of support vector machines.Loss letter of the support vector machines of standard in optimization aim
Number is the first order of error.
According to institutional risk minimization principle, formula (2) can be converted are as follows:
In formula: ε is insensitive coefficient, ξi, ξi *For relaxation factor.
With Lagrange function solving optimization problem, it may be assumed that
In formula, αi,βi,It is Lagrange multiplier, and αi>0,βi>0,
According to Karush-Kuhn-Tucker optimal conditions:
DefinitionIt is the symmetric function kernel function of Mercer condition.Then optimization problem can be write
At:
Nonlinear Prediction Models are obtained as a result:
Radial basis kernel function is selected to be defined as follows as the kernel function of SVM herein:
In formula: σ is the width parameter of Radial basis kernel function.
3.2GWO (grey wolf optimization algorithm)
GWO optimization algorithm is the novel meta-heuristic optimization algorithm proposed by Mirjalili et al. in 2014, it is one
The novel Swarm Intelligent Algorithm of kind, function admirable of the algorithm in terms of finding optimal solution have the characteristics that simple and efficient.
Grey wolf optimization algorithm simulates the Social Grading system and group's hunting behavior of grey wolf family.Grey wolf in nature
Population is successively divided into from high to low by social status, tetra- grades of α, β, δ, ω.When constructing the hierarchy model of grey wolf,
Defining the current optimal solution in wolf pack is α wolf, and suboptimal solution is β wolf, and the excellent solution of third is δ wolf, remaining solution is ω wolf.In GWO algorithm
In, behavior of chasing is executed by α, β, δ wolf, ω wolf follows former three to carry out prey tracking and encircles and suppresses, and is finally completed predation task.
The main hunting process of wolf pack are as follows: be on the track of the game, surround prey and attack prey.Grey wolf gradually surrounds prey
Behavior may be expressed as:
D=| CXp(t)-X(t)| (9)
X (t+1)=Xp(t)-A×D (10)
Wherein, D indicates the spacing of grey wolf and prey, and t indicates current iteration number, XpIndicate the position vector of prey, X table
Show the position vector of grey wolf, A and C are parameter vectors, and A=2ar1- a, C=2r2, wherein r1And r2Be between [0,1] with
Machine vector, a is in an iterative process from 2 linear decreases to 0.
For the hunting behavior for simulating grey wolf, it is assumed that α wolf, β wolf, δ wolf have a better understanding to the position of prey, grey wolf group
The position of this three be can use to judge the orientation where prey.Grey wolf group according to the location information of α wolf, β wolf, δ wolf come
Update process such as formula (11)-formula (17) of self-position
Dα=| C1·Xα(t)-X(t)| (11)
Dβ=| C2·Xβ(t)-X(t)| (12)
Dδ=| C3·Xδ(t)-X(t)| (13)
X1=Xα(t)-A1×Dα (14)
X2=Xβ(t)-A2×Dβ (15)
X3=Xδ(t)-A3×Dδ (16)
The searching process of GWO algorithm is exactly first to carry out assessment positioning to the position of prey by α wolf, β wolf, δ wolf, then population
Remaining interior individual randomly updates position as reference around prey.Grey wolf group is according to the position of α wolf, β wolf, δ wolf
Information is as shown in Figure 2 come the process for updating self-position:
3.3DE (differential evolution)
Differential evolution algorithm is a kind of heuristic random searching algorithm based on population difference, which is by R.Storn
Chebyshev multinomial is solved with K.Price and is proposed.Differential evolution algorithm mainly includes variation, intersection and selection three
Kind operation.
It is defined in D dimension search space, there are the population that scale is N, XiIt (g) is i-th of g generation individual, if:
In formula,For the lower bound of population at individual,For the upper bound of population at individual, tmaxFor maximum number of iterations.
(1) initialization population
N number of initial population individual is generated at random in entire search space, as shown in formula (19):
In formula, rand (0,1) is that equally distributed random number is obeyed on [0,1],Respectively jth dimension the upper bound and
Lower bound.
(2) mutation operation
Variation individual is generated by formula (20):
Vi(t+1)=xr1(t)+F[xr2(t)-xr3(t)] (20)
In formula, F is zoom factor, and value range is [0,1], r1, r2, and r3 is to be not mutually equal in section [1, N] and and i
Not equal random integers.
(3) crossover operation
Crossover operation can increase the diversity of population, the jth of i-th of individual be tieed up, the method for realizing crossover operation
As shown in formula (21):
In formula, CR is crossover probability, jrandIndicate a random dimension.
(4) selection operation
It selects to enter follow-on individual using greedy algorithm in differential evolution algorithm, that is, selects preferably individual work
For new individual, to ensure the Evolutionary direction of population.As shown in formula (22):
3.4DE-GWO-SVM
When being predicted using the SVM algorithm of Radial basis kernel function, it is thus necessary to determine that regularization parameter c and Radial basis kernel function
The value of the value of parameter g, the two parameters directly affects the precision of regression forecasting.Parameter of the selection GWO algorithm to SVM herein
It optimizes, but since that when handling optimization problem, there are late convergences is slow, easily falls into local optimum etc. asks for GWO algorithm
Therefore topic introduces differential evolution algorithm herein on the basis of grey wolf algorithm and makes improvements, to reinforce global search energy
Power, and then improve the accuracy of SVM algorithm prediction.Specific step is as follows by DE-GWO-SVM:
Step 301: setting relevant parameter, initialization population.
Step 302: calculating the fitness value of grey wolf individual, and it is ranked up, before determining that fitness value is optimal
The position of three grey wolf individuals, is respectively labeled as Xα, XβAnd Xδ。
Step 303: calculating other grey wolves individual and X in populationα, XβAnd XδDistance, update wolf pack position and GWO
Algorithm relevant parameter.
Step 304: being made a variation, crossover operation, generate new progeny population.
Step 305: carrying out selection operation, update wolf pack position.
Step 306: judging whether to reach maximum number of iterations, if reaching, export current optimal solution (c, g), otherwise, jump
It goes to step 302 and continues parameter optimization.
Step 307: the parameter value after optimization being assigned to SVM, establishes prediction model.
4, pre- flow gauge
It is more that the accuracy of electric grid investment prediction will receive economic development, electricity needs, power grid scale and grid benefit etc.
The influence of aspect factor.In order to realize the Accurate Prediction to electric grid investment, herein in analysis electric grid investment predicted impact factor
On the basis of, propose DE-GWO-SVM electric grid investment prediction model.The prediction steps of the model are as follows:
(1) data acquire
Collecting sample data, including history electric grid investment, GDP, the industrial structure, population, urbanization rate, whole society's electricity consumption
Amount, electricity consumption growth rate, electricity sales amount, power grid maximum load, 220kV and the above transmission line length, 110kV and following transmission of electricity
Line length, 220kV and the above transformer equipment capacity, 110kV and following transformer equipment capacity, power grid gross profit, unit power grid
The data such as assets supply load, unit power grid asset electricity sales amount, unit power grid asset power selling income, and dimensionless is carried out to data
Change processing.
(2) influence factor is screened
The grey relational grade for calculating above-mentioned 16 influence factors and electric grid investment, is screened according to the sequence of grey relational grade
The major influence factors of electric grid investment prediction out, and using the factor filtered out as the input of prediction model.
(3) the electric grid investment prediction based on DE-GWO-SVM model
Using the major influence factors of the electric grid investment filtered out prediction as mode input, with DE-GWO-SVM model pair
Electric grid investment is predicted.
According to the electric grid investment predicted impact Factor system constructed above, we have collected -2016 years Chinese nineteen nineties
GDP, the industrial structure (tertiary industry accounting), population, urbanization rate, Analyzing Total Electricity Consumption, electricity consumption growth rate, electricity sales amount,
Power grid maximum load, 220kV and the above transmission line length, 110kV and following transmission line length, 220kV and the above power transformation
Place capacity, 110kV and following transformer equipment capacity, power grid gross profit, unit power grid asset supply load, unit power grid asset
The electric grid investments influence factor data such as electricity sales amount, unit power grid asset power selling income.(data source in China Statistical Yearbook and
China Power yearbook).
In order to determine the input of prediction model, we screen electric grid investment influence factor using grey relational grade index,
Realize Feature Dimension Reduction.Each influence factor and the grey relational grade calculated result of electric grid investment are as follows:
1 grey relational grade calculated result of table
According to table 1, we choose five factors of the grey relational grade greater than 0.85 as the defeated of electric grid investment prediction model
Enter, respectively GDP, Analyzing Total Electricity Consumption, power grid electricity sales amount, 220kV and the above transmission line length and 220kV or more become
Electric equipment capacity.Model output is electric grid investment.
In order to improve forecasting accuracy and reliability, before the projection, we are first according to formula (1) to above-mentioned original number
According to progress nondimensionalization processing.
Treated, and data are as shown in table 2:
2 data prediction result of table
In the present invention, we are using the data of Chinese 1990-2009 as training sample set, with the number of 2010-2016
According to as test sample collection, electric grid investment is predicted with DE-GWO-SVM model.Model major parameter is set such as 3 institute of table
Show:
The setting of 3 model parameter of table
Prediction result with DE-GWO-SVM model prediction China Power Grids as shown in Fig. 2, invest, prediction effect is good, in advance
It is higher to survey precision.
This embodiment is merely preferred embodiments of the present invention, but scope of protection of the present invention is not limited thereto,
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by anyone skilled in the art,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with scope of protection of the claims
Subject to.
Claims (5)
1. a kind of electric grid investment needing forecasting method characterized by comprising
Step 1: the influencing factor system of electric grid investment prediction is constructed by Delphi method；
Step 2: calculating the grey relational grade of each influence factor and electric grid investment, sequence filters out the main of electric grid investment prediction
Input of the influence factor as prediction model；
Step 3: the parameter of support vector machines being optimized using differential evolution improved grey wolf optimization algorithm, establishes prediction mould
Electric grid investment demand is predicted after type.
2. method according to claim 1, which is characterized in that the influencing factor system of electric grid investment prediction include: through
Help development, electricity needs, power grid scale and grid benefit four dimensions, and each dimension includes four factors, respectively successively are as follows:
GDP, the industrial structure, population, urbanization rate, Analyzing Total Electricity Consumption, electricity consumption growth rate, electricity sales amount, power grid maximum load,
220kV and the above transmission line length, 110kV and following transmission line length, 220kV and the above transformer equipment capacity, 110kV
And following transformer equipment capacity, power grid gross profit, unit power grid asset supply load, unit power grid asset electricity sales amount, unit electricity
Net assets power selling income.
3. method according to claim 1 or claim 2, which is characterized in that the step 2 comprises determining that the reference in analytical sequence
Sequence and compare sequence, nondimensionalization, calculate correlation coefficient and the degree of association are carried out to Variables Sequence, sequence will be compared according to grey
The sequence of degree of association size, grey relational grade is bigger, and the situation for showing that the comparison sequence and reference sequences change is more consistent.
4. method according to claim 1 or claim 2, which is characterized in that the step 3 includes:
Step 301: setting relevant parameter, initialization population；
Step 302: calculating the fitness value of grey wolf individual, and it is ranked up, to determine the optimal front three of fitness value
The position of grey wolf individual；
Step 303: calculate population in other grey wolf individuals with front three grey wolf body position at a distance from, update wolf pack position and
Grey wolf optimization algorithm relevant parameter；
Step 304: being made a variation with differential evolution algorithm, crossover operation, generate new progeny population；
Step 305: carrying out selection operation, update wolf pack position；
Step 306: judging whether to reach maximum number of iterations, if reaching, export current optimal solution, otherwise, go to step
302 continue parameter optimization；
Step 307: the parameter value after optimization being assigned to support vector machines, establishes prediction model.
5. method according to claim 1 or claim 2, which is characterized in that the parameter is regularization parameter c and Radial basis kernel function
Parameter g.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810985402.XA CN109214449A (en) | 2018-08-28 | 2018-08-28 | A kind of electric grid investment needing forecasting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810985402.XA CN109214449A (en) | 2018-08-28 | 2018-08-28 | A kind of electric grid investment needing forecasting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109214449A true CN109214449A (en) | 2019-01-15 |
Family
ID=64986009
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810985402.XA Pending CN109214449A (en) | 2018-08-28 | 2018-08-28 | A kind of electric grid investment needing forecasting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109214449A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147933A (en) * | 2019-04-17 | 2019-08-20 | 华中科技大学 | A kind of Numerical control cutting blanking Job-Shop scheduled production method based on improvement grey wolf algorithm |
| CN110231833A (en) * | 2019-06-14 | 2019-09-13 | 渤海大学 | A kind of oil field inspection fixed-point data acquisition system and method based on multiple no-manned plane |
| CN110322050A (en) * | 2019-06-04 | 2019-10-11 | 西安邮电大学 | A kind of wind energy resources compensation data method |
| CN110351241A (en) * | 2019-05-31 | 2019-10-18 | 浙江工业大学 | A kind of industrial network DDoS intruding detection system classification method based on GWA optimization |
| CN110378526A (en) * | 2019-07-15 | 2019-10-25 | 安徽理工大学 | The mobile method for predicting of bus station based on GW and SVR, system and storage medium |
| CN111667098A (en) * | 2020-05-14 | 2020-09-15 | 湖北工业大学 | Wind power station output power prediction method based on multi-model combination optimization |
| CN111695718A (en) * | 2020-04-16 | 2020-09-22 | 国网江苏省电力有限公司经济技术研究院 | Power grid development aid decision-making method considering investment demand and planning target |
| CN112861418A (en) * | 2020-12-25 | 2021-05-28 | 三峡大学 | Short-term icing thickness prediction method for stay cable based on GA-WOA-GRNN network |
| CN113269638A (en) * | 2021-04-28 | 2021-08-17 | 阜阳市星启链数据科技有限公司 | Financial risk analysis system based on block chain |
| CN113627639A (en) * | 2020-05-07 | 2021-11-09 | 中国石油化工股份有限公司 | Well testing productivity prediction method and system for carbonate fracture-cave reservoir |
| CN113822583A (en) * | 2021-09-24 | 2021-12-21 | 广东电网有限责任公司 | Power distribution network investment demand prediction method and device, terminal equipment and medium |
| CN116227234A (en) * | 2023-05-05 | 2023-06-06 | 四川传媒学院 | Novel prediction method for life of sports equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150154504A1 (en) * | 2012-12-17 | 2015-06-04 | Arizona Board Of Regents On Behalf Of Arizona State University | Support vector machine enhanced models for short-term wind farm generation forecasting |
| CN107358307A (en) * | 2017-05-03 | 2017-11-17 | 国网浙江省电力公司 | A kind of power grid enterprises investment budgey method under multi-constraint condition based on electricity sales amount prediction |
| CN107578028A (en) * | 2017-09-20 | 2018-01-12 | 广东工业大学 | A kind of face identification method, device, equipment and computer-readable recording medium |
-
2018
- 2018-08-28 CN CN201810985402.XA patent/CN109214449A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150154504A1 (en) * | 2012-12-17 | 2015-06-04 | Arizona Board Of Regents On Behalf Of Arizona State University | Support vector machine enhanced models for short-term wind farm generation forecasting |
| CN107358307A (en) * | 2017-05-03 | 2017-11-17 | 国网浙江省电力公司 | A kind of power grid enterprises investment budgey method under multi-constraint condition based on electricity sales amount prediction |
| CN107578028A (en) * | 2017-09-20 | 2018-01-12 | 广东工业大学 | A kind of face identification method, device, equipment and computer-readable recording medium |
Non-Patent Citations (1)
| Title |
|---|
| SHUYU DAI等: "Forecasting of Power Grid Investment in China Based on Support Vector Machine Optimized by Differential Evolution Algorithm and GreyWolf Optimization Algorithm", 《APPLIED SCIENCES》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147933A (en) * | 2019-04-17 | 2019-08-20 | 华中科技大学 | A kind of Numerical control cutting blanking Job-Shop scheduled production method based on improvement grey wolf algorithm |
| CN110147933B (en) * | 2019-04-17 | 2021-08-03 | 华中科技大学 | Numerical control cutting blanking workshop scheduling and scheduling method based on improved wolf algorithm |
| CN110351241B (en) * | 2019-05-31 | 2021-08-03 | 浙江工业大学 | GWA (global warming environment) optimization-based industrial network DDoS (distributed denial of service) intrusion detection system classification method |
| CN110351241A (en) * | 2019-05-31 | 2019-10-18 | 浙江工业大学 | A kind of industrial network DDoS intruding detection system classification method based on GWA optimization |
| CN110322050A (en) * | 2019-06-04 | 2019-10-11 | 西安邮电大学 | A kind of wind energy resources compensation data method |
| CN110322050B (en) * | 2019-06-04 | 2023-04-07 | 西安邮电大学 | Wind energy resource data compensation method |
| CN110231833A (en) * | 2019-06-14 | 2019-09-13 | 渤海大学 | A kind of oil field inspection fixed-point data acquisition system and method based on multiple no-manned plane |
| CN110231833B (en) * | 2019-06-14 | 2022-01-28 | 渤海大学 | Oil field inspection fixed point data acquisition system and method based on multiple unmanned aerial vehicles |
| CN110378526A (en) * | 2019-07-15 | 2019-10-25 | 安徽理工大学 | The mobile method for predicting of bus station based on GW and SVR, system and storage medium |
| CN111695718A (en) * | 2020-04-16 | 2020-09-22 | 国网江苏省电力有限公司经济技术研究院 | Power grid development aid decision-making method considering investment demand and planning target |
| CN113627639A (en) * | 2020-05-07 | 2021-11-09 | 中国石油化工股份有限公司 | Well testing productivity prediction method and system for carbonate fracture-cave reservoir |
| CN111667098A (en) * | 2020-05-14 | 2020-09-15 | 湖北工业大学 | Wind power station output power prediction method based on multi-model combination optimization |
| CN111667098B (en) * | 2020-05-14 | 2023-04-18 | 湖北工业大学 | Wind power station output power prediction method based on multi-model combination optimization |
| CN112861418A (en) * | 2020-12-25 | 2021-05-28 | 三峡大学 | Short-term icing thickness prediction method for stay cable based on GA-WOA-GRNN network |
| CN113269638A (en) * | 2021-04-28 | 2021-08-17 | 阜阳市星启链数据科技有限公司 | Financial risk analysis system based on block chain |
| CN113822583A (en) * | 2021-09-24 | 2021-12-21 | 广东电网有限责任公司 | Power distribution network investment demand prediction method and device, terminal equipment and medium |
| CN116227234A (en) * | 2023-05-05 | 2023-06-06 | 四川传媒学院 | Novel prediction method for life of sports equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214449A (en) | A kind of electric grid investment needing forecasting method | |
| Abualigah et al. | Salp swarm algorithm: a comprehensive survey | |
| Wu et al. | An intuitionistic fuzzy multi-criteria framework for large-scale rooftop PV project portfolio selection: Case study in Zhejiang, China | |
| Wang et al. | An improved grey model optimized by multi-objective ant lion optimization algorithm for annual electricity consumption forecasting | |
| CN108491969A (en) | Spatial Load Forecasting model building method based on big data | |
| Assareh et al. | Application of PSO (particle swarm optimization) and GA (genetic algorithm) techniques on demand estimation of oil in Iran | |
| Zhou et al. | Multiobjective evolutionary algorithms: A survey of the state of the art | |
| CN108846526A (en) | A kind of CO2 emissions prediction technique | |
| Feng et al. | Reinforcement learning based dynamic model selection for short-term load forecasting | |
| CN112700045B (en) | Intelligent site selection system based on land reserve implementation monitoring model | |
| CN106022614A (en) | Data mining method of neural network based on nearest neighbor clustering | |
| Wei et al. | Forecasting the daily natural gas consumption with an accurate white-box model | |
| CN108898259A (en) | Adaptive Evolutionary planning Methods of electric load forecasting and system based on multi-factor comprehensive | |
| Liang et al. | Large-scale portfolio optimization using multiobjective dynamic mutli-swarm particle swarm optimizer | |
| CN107909221A (en) | Power-system short-term load forecasting method based on combination neural net | |
| Alzaeemi et al. | Examining the forecasting movement of palm oil price using RBFNN-2SATRA metaheuristic algorithms for logic mining | |
| CN111428766B (en) | Power consumption mode classification method for high-dimensional mass measurement data | |
| CN111008790A (en) | Hydropower station group power generation electric scheduling rule extraction method | |
| Fan et al. | Multi-objective LSTM ensemble model for household short-term load forecasting | |
| Yang et al. | The stochastic decision making framework for long-term multi-objective energy-water supply-ecology operation in parallel reservoirs system under uncertainties | |
| CN116187835A (en) | Data-driven-based method and system for estimating theoretical line loss interval of transformer area | |
| Cao et al. | PSO-Stacking improved ensemble model for campus building energy consumption forecasting based on priority feature selection | |
| Vasanthkumar et al. | Improving energy consumption prediction for residential buildings using Modified Wild Horse Optimization with Deep Learning model | |
| CN109919374A (en) | Prediction of Stock Price method based on APSO-BP neural network | |
| Laith et al. | Salp swarm algorithm: a comprehensive survey |
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 |