CN108717585A - A kind of long term electric power demand forecasting method - Google Patents
A kind of long term electric power demand forecasting method Download PDFInfo
- Publication number
- CN108717585A CN108717585A CN201810453676.4A CN201810453676A CN108717585A CN 108717585 A CN108717585 A CN 108717585A CN 201810453676 A CN201810453676 A CN 201810453676A CN 108717585 A CN108717585 A CN 108717585A
- Authority
- CN
- China
- Prior art keywords
- prediction
- electricity needs
- key index
- eviews
- index
- 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
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The present invention relates to a kind of electric power demand forecasting methods at a specified future date.This method specifies different stages of development economic society, the development trend of electricity needs key index, is predicted electricity needs at a specified future date using co-integration model.Prediction technique of the present invention determines the development trend of key index by across comparison first, determining influences the key index that electricity needs increases, stationary test is carried out to key index based on Eviews, the index for being unsatisfactory for co integration test is rejected, Johansen co integration tests are then carried out, is determined and is assisted whole relationship and carry out Granger Causality Tests, finally build co-integration model, it predicts key index, is based on long-run equilibrium Relationship Prediction long term electricity needs, judge that regional industryization develops future trend.Prediction technique of the present invention is prediction area electricity needs at a specified future date, judges that regional economy and industrial future development provide new approach, has good use value.
Description
Technical field
The present invention relates to electric power demand forecasting analysis fields, are related to a kind of electric power demand forecasting method at a specified future date, more particularly to
A kind of electric power demand forecasting method at a specified future date based on Qian Nali industrialization phases theory and co-integration model.
Background technology
Electric power demand forecasting method is widely used in fields such as Electricity market analysis, Electric Power Network Planning, dispatchings of power netwoks, is power grid
One of the important content of one of important link that planning boundary determines and dispatching of power netwoks safe and stable operation.Electricity needs is pre-
Survey includes ultra-short term, short-term, mid-term, electric power demand forecasting at a specified future date, and ultra-short term and short-term forecast are in Electricity market analysis and electric power
Scheduling field is widely used, and medium-long term electric power demand forecasting is power grid medium term planning, power grid target net planning boundary condition
Important content is the element task of Electric Power Network Planning.The common method of electricity needs at a specified future date has growth curve method, this method to build on
Economic society and electricity needs development meet the rule of development of " Fast growth phase-transition stage-saturation stage "；In addition at a specified future date
Electric power demand forecasting is also frequently with space density method, gray prediction etc..Qian Nali industrialization phase theories be used to study judgement
Regional Economic social development degree, co-integration model are commonly used for the length between specific economic variable in contemporary econometrics
The research of phase balanced relation.
Electric power development is supported as the important energy source of socio-economic development, and there are one with the specific indexes of socio-economic development
Fixed relation of long standing relation.Therefore, when carrying out electric power demand forecasting at a specified future date, development trend and the influence of economic society should be fully considered
The development trend of electricity needs factor, to establish electric power at a specified future date that is relatively comprehensive, reliable, accurate and meeting socio-economic development
Needing forecasting method.A kind of electricity needs at a specified future date based on Qian Nali industrialization phases theory and co-integration model of the present invention
The research of long-run equilibrium relationship between Econometric index is applied to electric power demand forecasting field by prediction technique, by comparing not
With advanced country's economic society and electricity needs index development, research electricity needs index and other key influence factors
Long-run equilibrium relationship.
Invention content
The purpose of the present invention is to provide a kind of electric power demand forecasting method at a specified future date, this method is prediction area electric power at a specified future date
Demand provides new approach, has good value for applications.
To achieve the above object, the technical scheme is that：A kind of long term electric power demand forecasting method, including walk as follows
Suddenly：
Step S1：Typical advanced developed country economic society and electricity needs index development course table are established, according to Qian Na
In stage residing for industrialization phase theoretical judgment country variant；
Step S2：The across comparison countries and regions for determining prediction area, determine the development trend of key index；
Step S3：Determine the major influence factors and key index that the regional electricity needs of prediction increases；
Step S4：The stationary test of key index data is carried out based on Eviews, rejects the finger for being unsatisfactory for co integration test
Mark；
Step S5：Johansen co integration tests are carried out based on Eviews, is determined and is assisted whole relationship and carry out Granger cause and effect inspections
It tests；
Step S6：Co-integration model is established based on Eviews, carries out the prediction of key index, is carried out based on long-run equilibrium relationship
Electric power demand forecasting at a specified future date；
Step S7：Error correction model is established based on Eviews, corrects prediction result in S6.
In an embodiment of the present invention, the economic society and electricity needs index development course table include national territorial area,
GDP, GDP per capita, economic growth rate, the industrial structure, Urbanization Rate, population, population growth rate, Analyzing Total Electricity Consumption and speedup,
Maximum load, power structure, per capita household electricity consumption, GDP synthesis power consumption, energy-consuming growth rate, according to Qian Nali industrialization phases
Determine the developing stage residing for country variant.
In an embodiment of the present invention, in step S2, determine that the mode of the across comparison countries and regions in prediction area is：
The countries and regions development of selection is ahead of prediction area, after economic growth rate and energy-consuming growth rate have passed through rapid growth
It falls after rise and is in low speed build phase, GDP per capita is located at higher level, and energy-consuming growth rate and electricity consumption growth rate are in low
Speed increases.
In an embodiment of the present invention, in step S3, determine major influence factors that the regional electricity needs of prediction increases and
Key index is determined by the method including grey correlation, regression analysis and expert judgments.
In an embodiment of the present invention, stationary test process is in step S4：Based on Eviews choose it is corresponding influence because
The historical data of element uses ADF inspections or PP to examine and whether determines sequence for stationary sequence, and whether unstable sequence is single whole sequence
Row, meet single whole sequence is determined as several ranks singly whole sequence, and the influence factor to being unsatisfactory for single whole sequence or different rank carries out
It rejects；It refers to that can reach stable nonstationary random process by difference singly to have suffered journey, if an original series are steady, is claimed
For I (0) process；If an original time series non-stationary becomes stable by first difference, as shown in formula (1), ytFor
Non-stationary random series, Δ ytFor stationary random sequence, then ytFor I (1) process；
Δyt=yt-yt-1 (1)。
In an embodiment of the present invention, carrying out Johansen co integration test steps based on Eviews in step S5 is：To closing
Key factor determines best lag order p according to information standard method, establishes VAR (p) models, carries out Johansen co integration tests, really
Fixed whether there is assists whole relationship, if continuing adjustment related keyword index there is no if, if in the presence of obtaining assisting whole vector β；VAR(p)
Model tormulation is：
In an embodiment of the present invention, in step S5 to VAR (p) models carry out Granger Causality Tests, Granger because
Fruit is examined and is expressed as, for VAR (p) models of k variable, it is assumed that ytOptimum prediction the result is that
Y is not present in multiscalar VAR (p) modelsjtTo yitThe causal necessary conditions of Granger be
In an embodiment of the present invention, co-integration model is established based on Eviews in step S6, carries out the prediction of key index,
Different prediction techniques can be determined according to different indexs, on key index fundamentals of forecasting, utilize established co-integration model pair
The medium-term and long-term electricity needs in prediction area is predicted, and determines the regional future developing trend of prediction.
In an embodiment of the present invention, error correction model is established based on Eviews in step S7, that is, contains and assists whole constraint
VAR models, prediction result is modified；VEC model tormulations are
ecmt-1=β ' yt-1 (6)。
Compared to the prior art, the invention has the advantages that：Prediction technique of the present invention arranges advanced prosperity first
The economic society and electricity needs development indicators situation of countries and regions judge residing rank according to Qian Nali industrialization phase theories
Section.And compared according to These parameters, research influences the key index of electricity needs development, and stationary test is carried out to These parameters
And co integration test, determine the long-run equilibrium relationship between electricity needs and index of correlation.It is right on the fundamentals of forecasting of influence index
Regional electricity needs is predicted, judges industrial development future trend.Prediction technique of the present invention be electricity needs long-range forecasting and
Development course judgement provides new approach, has good use value.
Description of the drawings
Fig. 1 is the method for the present invention flow chart.
Specific implementation mode
Below in conjunction with the accompanying drawings, technical scheme of the present invention is specifically described.
As shown in Figure 1, a kind of of the present invention is needed based on the electric power at a specified future date of Qian Nali industrialization phases theory and co-integration model
Prediction technique is sought, is included the following steps：
Step S1：Typical advanced developed country economic society and electricity needs index development course table are established, according to Qian Na
In stage residing for industrialization phase theoretical judgment country variant；
The typical developed country's linked development index of table 1
Step S2：The across comparison countries and regions for determining prediction area, determine the development trend of key index；
Step S3：It determines the major influence factors and key index that the regional electricity needs of prediction increases, grey form and aspect can be passed through
The methods of Guan Xing, regression analysis and expert judgments determine；
Step S4：The stationary test of key index data is carried out based on Eviews, rejects the finger for being unsatisfactory for co integration test
Mark；Whether the historical data for choosing corresponding influence factor uses ADF inspections or PP to examine determining sequence for stationary sequence, unstable
Whether sequence is single whole sequence, and meet single whole sequence is determined as several ranks singly whole sequence, to being unsatisfactory for single whole sequence or not same order
Several influence factors are rejected；
ADF inspection result of the table 2 to time sequence of interval
Step S5：Carry out Johansen co integration tests based on Eviews, to key factor according to information standard method (including most
Maximum-likelihood method, AIC information criterions, SC criterion etc.) determine best lag order p, VAR (p) models are established, Johansen associations are carried out
Whole inspection, it is determined whether there is the whole relationship of association (maximum inspection by attributes, Maximum characteristic root, which are examined, to be determined), continue to adjust if there is no if
Whole related keyword index, if in the presence of obtaining assisting whole vector β.VAR (p) model tormulations are：
Granger Causality Tests are carried out to VAR (p) models, Granger Causality Tests are expressed as, for k variable
VAR (p) models, it is assumed that ytOptimum prediction the result is that
Y is not present in multiscalar VAR (p) modelsjtTo yitThe causal necessary conditions of Granger be
3 VAR lag order selection criterions of table judge result
4 co integration test of table (inspection of characteristic root mark) result
5 co integration test of table (Maximum characteristic root inspection) result
Table 6 assists whole vectorial coefficient estimated result
| Predicted value | Variable 1 | Variable 2 | …… | Variable N |
| x | x | x | …… | x |
8 Granger Causality Tests result of table (dependent variable is independent variable)
Step S6：Co-integration model is established based on Eviews, the key index prediction for influencing electricity needs is then carried out, is based on
Long-run equilibrium relationship carries out electric power demand forecasting at a specified future date；Prediction to key index can determine different pre- according to different indexs
Survey method, such as economic indicator can be used gray prediction, Monte Carlo forecast, industrial structure prediction can be used Fouruer functions,
Gaussian Function Fittings, on key index fundamentals of forecasting, using established co-integration model to the medium-term and long-term of prediction area
Electricity needs is predicted, and determines the regional future developing trend of prediction.
Step S7：Error correction model is established based on Eviews, corrects prediction result in S6.Establish error correction model
(VEC models) contains the VAR models for assisting whole constraint, is modified to prediction result.VEC model tormulations are
ecmt-1=β ' yt-1 (6)。
Example：It is 2035 regional to A based on the areas A 1990-2015 history economic society data and electricity needs data
Electricity needs is predicted.A kind of electric power demand forecasting method at a specified future date based on Qian Nali industrialization phases theory and co-integration model
Include the following steps：
Step S1：Typical advanced developed country economic society and electricity needs index development course table are established, according to Qian Na
In stage residing for industrialization phase theoretical judgment country variant；
The typical developed country's linked development index of table 9
Step S2：From the point of view of developed countries and regions index, GDP per capita is in higher level, and tertiary industry accounting is higher than
Secondary industry accounting, the level of urbanization resident and business substantially in 75% or more, electric energy consumption structure account for it is relatively high, it is electric per capita
Power consumption reaches certain level.Economic speedup and the speedup of electricity power consumption are in relatively low growth interval, and development is in
Under saturation state, but country variant or area are due to differences, economic society and electric power such as economic structure is different, energy-consuming consciousness
Demand parameter has a certain difference between country variant or area.
Step S3：Choose regional GDP GDP, value of secondary industry accounting S2, population POP, unit output value power consumption
The long-run equilibrium relationship between each variable and electricity needs Q is analyzed and studied to explanatory variables of the EF as electricity needs Q, chooses
1990-2015 economic societies and electricity needs historical data.
10 A regional economy social development indices situations of table
11 areas A electricity needs development indicators situation of table
Step S4：The stationary test that key index data are carried out based on Eviews, is examined using ADF, from inspection result
It is the whole sequence of single order list that variable is chosen in judgement, meets co integration test condition.
ADF inspection result of the table 12 to time sequence of interval
Step S5：There are 5 criterion to select second-order lag first, therefore, determines that second order is lag order herein.It is based on
The inspection of Johansen feature traces shows at least there are 3 whole passes of association with Maximum characteristic root inspection after Eviews establishes VAR models
System.And the whole vector of association is (1.0, -0.903, -11.092, -0.086,0.110).Granger Causality Tests display area production
Total value, population are the Granger reasons for causing whole society's electricity consumption to increase, and unit output value power consumption is almost close to be become in 10% level
The Granger reasons that electricity needs increases, secondary industry proportion are not to constitute whole society's electricity consumption to increase in statistical significance
Granger reasons.And in the combined influence of factors above, by regional GDP, secondary industry proportion, population, list
Position output value power consumption collectively forms the Granger reasons that whole society's electricity consumption increases.
13 VAR lag order selection criterions of table
14 co integration test of table (inspection of characteristic root mark) result
15 co integration test of table (Maximum characteristic root inspection) result
Table 16 assists whole vectorial coefficient estimated result
| Q | GDP | S2 | POP | EF |
| 1.000000 | -0.903087 | -11.09218 | -0.086402 | 0.109687 |
17 Granger Causality Tests result of table (dependent variable is independent variable)
Step S6：Co-integration model is established based on Eviews, then carries out the prediction of key index, it is whole using established association
Model predicts the medium-term and long-term electricity needs in prediction area.In the model pair that 1990-2015 historical datas are set up
2016 annual electricity loads are predicted that predicted value is 204,300,000,000 kilowatt hours, and actual value is 196,900,000,000 kilowatt hours, relative error rate
3.78%.
Step S7：Error correction model is established based on Eviews, corrects prediction result in S6.The 2016 of VEC models calculating
Annual electricity load predicted value is 199,900,000,000 kilowatt hours, and relative error rate 1.52% effectively improves predictablity rate.It is basic herein
On, the regional GDP, secondary industry proportion, population, unit output value power consumption between 2017-2035 are using corresponding different
Method simultaneously combines local planning to be predicted that predictive display this area GDP total output value speedups in 2035 are adjusted to 4.0%, two
Production proportion drops to 40% or so, and population rises to 42,670,000 people, and unit output value power consumption declines 33%, before influence factor prediction
It is 1.7% or so that electricity needs, which is put, in 2035 annual growths, 403,700,000,000 kilowatt hour of electricity needs total amount.
The co-integration model of electricity needs is built based on the areas A 1990-2015 history economic society and electricity needs data
And error correction model is established, real example verification is carried out with 2016 annual electricity loads, on this basis to the areas A electricity in 2035 at a specified future date
Power demand is predicted.
Although the present invention is disclosed as above with preferable embodiment, it is not for limiting the present invention, any this field
Technical staff without departing from the spirit and scope of the present invention, may be by the methods and technical content of the disclosure above to this hair
Bright technical solution makes possible variation and modification, therefore, every content without departing from technical solution of the present invention, and according to the present invention
Technical spirit any simple modifications, equivalents, and modifications made to the above embodiment, belong to technical solution of the present invention
Protection domain.The foregoing is merely presently preferred embodiments of the present invention, all impartial changes done according to scope of the present invention patent
Change and modify, should all belong to the covering scope of the present invention.
Claims (9)
1. a kind of long term electric power demand forecasting method, which is characterized in that include the following steps：
Step S1：Typical advanced developed country economic society and electricity needs index development course table are established, according to Qian Nali works
Industry stage theory judges the stage residing for country variant；
Step S2：The across comparison countries and regions for determining prediction area, determine the development trend of key index；
Step S3：Determine the major influence factors and key index that the regional electricity needs of prediction increases；
Step S4：The stationary test of key index data is carried out based on Eviews, rejects the index for being unsatisfactory for co integration test；
Step S5：Johansen co integration tests are carried out based on Eviews, is determined and is assisted whole relationship and carry out Granger Causality Tests；
Step S6：Co-integration model is established based on Eviews, carries out the prediction of key index, is carried out based on long-run equilibrium relationship at a specified future date
Electric power demand forecasting；
Step S7：Error correction model is established based on Eviews, corrects prediction result in S6.
2. according to the method described in claim 1, it is characterized in that, in step S1, the economic society and electricity needs index
Development course table includes national territorial area, GDP, GDP per capita, economic growth rate, the industrial structure, Urbanization Rate, population, population growth
Rate, Analyzing Total Electricity Consumption and speedup, maximum load, power structure, per capita household electricity consumption, GDP synthesis power consumption, energy-consuming increase
Rate determines the developing stage residing for country variant according to Qian Nali industrialization phases.
3. according to the method described in claim 2, it is characterized in that, in step S2, the across comparison country in prediction area is determined
It is with regional mode：The countries and regions development of selection is ahead of prediction area, economic growth rate and energy-consuming growth rate
It is fallen after rise in low speed build phase after have passed through rapid growth, GDP per capita is located at higher level, energy-consuming growth rate and electric power
Consumption increase rate is in low speed growth.
4. according to the method described in claim 3, it is characterized in that, in step S3, determine what the regional electricity needs of prediction increased
Major influence factors and key index are determined by the method including grey correlation, regression analysis and expert judgments.
5. according to the method described in claim 4, it is characterized in that, stationary test process is in step S4：Based on Eviews
ADF is used to examine for the historical data for choosing corresponding influence factor or whether PP examines determining sequence for stationary sequence, unstable sequence
Whether row are single whole sequence, and meet single whole sequence is determined as several ranks singly whole sequence, to being unsatisfactory for single whole sequence or different rank
Influence factor rejected；Singly have suffered journey refer to can reach stable nonstationary random process by difference, if one
Original series are steady, referred to as I (0) process；If an original time series non-stationary becomes stable by first difference,
As shown in formula (1), ytFor non-stationary random series, Δ ytFor stationary random sequence, then ytFor I (1) process；
Δyt=yt-yt-1 (1)。
6. according to the method described in claim 5, it is characterized in that, carrying out Johansen based on Eviews in step S5 assists whole inspection
Testing step is：Best lag order p is determined according to information standard method to key factor, establishes VAR (p) models, is carried out
Johansen co integration tests, it is determined whether there is the whole relationship of association, continues to adjust related keyword index if being not present, if in the presence of
To the whole vector β of association；VAR (p) model tormulations are：
7. according to the method described in claim 6, it is characterized in that, carrying out Granger causes and effects to VAR (p) models in step S5
It examines, Granger Causality Tests are expressed as, for VAR (p) models of k variable, it is assumed that ytOptimum prediction the result is that
Y is not present in multiscalar VAR (p) modelsjtTo yitThe causal necessary conditions of Granger be
8. the method according to the description of claim 7 is characterized in that establishing co-integration model based on Eviews in step S6, carry out
The prediction of key index can determine different prediction techniques according to different indexs, and on key index fundamentals of forecasting, utilization is built
Vertical co-integration model predicts the medium-term and long-term electricity needs in prediction area, and determines the regional future developing trend of prediction.
9. according to the method described in claim 8, it is characterized in that, establish error correction model based on Eviews in step S7,
Contain the VAR models for assisting whole constraint, prediction result is modified；VEC model tormulations are
ecmt-1=β ' yt-1 (6)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810453676.4A CN108717585A (en) | 2018-05-14 | 2018-05-14 | A kind of long term electric power demand forecasting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810453676.4A CN108717585A (en) | 2018-05-14 | 2018-05-14 | A kind of long term electric power demand forecasting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108717585A true CN108717585A (en) | 2018-10-30 |
Family
ID=63899863
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810453676.4A Pending CN108717585A (en) | 2018-05-14 | 2018-05-14 | A kind of long term electric power demand forecasting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108717585A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086954A (en) * | 2018-11-08 | 2018-12-25 | 暨南大学 | Prediction technique, device, equipment and medium based on cash flow indicated yield |
| CN110210661A (en) * | 2019-05-28 | 2019-09-06 | 新奥数能科技有限公司 | A kind of Mid-long term load forecasting method and device for using energy characteristic based on user |
| CN110231503A (en) * | 2019-07-08 | 2019-09-13 | 南方电网科学研究院有限责任公司 | Stealing user recognition positioning method of the area Gao Suntai based on Granger CaFpngerusality test |
| CN111222711A (en) * | 2020-01-16 | 2020-06-02 | 大连理工大学 | Index linkage analysis-based multi-objective optimization method for peak shaving scheduling of electric power system |
| CN111612277A (en) * | 2020-05-29 | 2020-09-01 | 云南电网有限责任公司 | Spatial collaborative prediction method for predicting industry power consumption |
| CN112634077A (en) * | 2020-12-18 | 2021-04-09 | 四川大汇大数据服务有限公司 | Medium-and-long-term power supply and demand situation analysis method |
| CN113837497A (en) * | 2021-11-04 | 2021-12-24 | 云南电网有限责任公司电力科学研究院 | Power consumption prediction method and system based on time series |
-
2018
- 2018-05-14 CN CN201810453676.4A patent/CN108717585A/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086954A (en) * | 2018-11-08 | 2018-12-25 | 暨南大学 | Prediction technique, device, equipment and medium based on cash flow indicated yield |
| CN109086954B (en) * | 2018-11-08 | 2022-01-25 | 暨南大学 | Prediction method, device, equipment and medium for predicting yield based on fund flow |
| CN110210661A (en) * | 2019-05-28 | 2019-09-06 | 新奥数能科技有限公司 | A kind of Mid-long term load forecasting method and device for using energy characteristic based on user |
| CN110231503A (en) * | 2019-07-08 | 2019-09-13 | 南方电网科学研究院有限责任公司 | Stealing user recognition positioning method of the area Gao Suntai based on Granger CaFpngerusality test |
| CN111222711A (en) * | 2020-01-16 | 2020-06-02 | 大连理工大学 | Index linkage analysis-based multi-objective optimization method for peak shaving scheduling of electric power system |
| CN111222711B (en) * | 2020-01-16 | 2022-04-08 | 大连理工大学 | Index linkage analysis-based multi-objective optimization method for peak shaving scheduling of electric power system |
| CN111612277A (en) * | 2020-05-29 | 2020-09-01 | 云南电网有限责任公司 | Spatial collaborative prediction method for predicting industry power consumption |
| CN112634077A (en) * | 2020-12-18 | 2021-04-09 | 四川大汇大数据服务有限公司 | Medium-and-long-term power supply and demand situation analysis method |
| CN113837497A (en) * | 2021-11-04 | 2021-12-24 | 云南电网有限责任公司电力科学研究院 | Power consumption prediction method and system based on time series |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108717585A (en) | A kind of long term electric power demand forecasting method | |
| Wang et al. | A seasonal GM (1, 1) model for forecasting the electricity consumption of the primary economic sectors | |
| Hong et al. | Probabilistic electric load forecasting: A tutorial review | |
| Jamil et al. | Income and price elasticities of electricity demand: Aggregate and sector-wise analyses | |
| Acaravci et al. | The electricity consumption, real income, trade openness and foreign direct investment: The empirical evidence from Turkey | |
| González-Vidal et al. | Data driven modeling for energy consumption prediction in smart buildings | |
| Sheng et al. | Short-term load forecasting based on SARIMAX-LSTM | |
| D’Alpaos et al. | Prioritization of energy retrofit strategies in public housing: an AHP model | |
| CN107644297A (en) | A kind of energy-saving of motor system amount calculates and verification method | |
| CN109325880A (en) | A kind of Mid-long term load forecasting method based on Verhulst-SVM | |
| CN117977568A (en) | Power load prediction method based on nested LSTM and quantile calculation | |
| CN109447332A (en) | A kind of Middle-long Electric Power Load Forecast method suitable for S type load curve | |
| Lu | Research on GDP forecast analysis combining BP neural network and ARIMA model | |
| CN115358437A (en) | Power supply load prediction method based on convolutional neural network | |
| CN107895211A (en) | A kind of long-medium term power load forecasting method and system based on big data | |
| CN113887833A (en) | Distributed energy user side time-by-time load prediction method and system | |
| CN113887809A (en) | Power distribution network supply and demand balance method, system, medium and computing equipment under double-carbon target | |
| CN112950048A (en) | National higher education system health evaluation based on fuzzy comprehensive evaluation | |
| ŞİŞMAN | A comparison of ARIMA and grey models for electricity consumption demand forecasting: The case of Turkey | |
| Bianchi et al. | Load forecasting in district heating networks: Model comparison on a real-world case study | |
| CN111080037A (en) | Short-term power load prediction method and device based on deep neural network | |
| CN107944642A (en) | A kind of Forecasting Methodology and forecasting system of electric grid investment demand | |
| Yu | Evaluation and Analysis of Electric Power in China Based on the ARMA Model | |
| Liu et al. | A Short-Term Load Forecasting Method using Integrated SVR and LSTM Network | |
| Ren et al. | Short-term demand forecasting for distributed water supply networks: A multi-scale approach |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181030 |