CN107679666A - A kind of power consumption prediction method based on Shapley values and economic development - Google Patents
A kind of power consumption prediction method based on Shapley values and economic development Download PDFInfo
- Publication number
- CN107679666A CN107679666A CN201710950656.3A CN201710950656A CN107679666A CN 107679666 A CN107679666 A CN 107679666A CN 201710950656 A CN201710950656 A CN 201710950656A CN 107679666 A CN107679666 A CN 107679666A
- Authority
- CN
- China
- Prior art keywords
- demand forecasting
- electricity demand
- economic development
- scheme
- model
- 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 23
- 230000005611 electricity Effects 0.000 claims abstract description 156
- 238000009499 grossing Methods 0.000 claims abstract description 10
- 238000012417 linear regression Methods 0.000 claims abstract description 8
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims abstract description 7
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000001373 regressive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material 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)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to economic development and power consumption prediction neighborhood, and in particular to a kind of power consumption prediction method based on Shapley values and economic development.The present invention is directed to the height of economic development, in, low scheme, with reference to prediction basic demand and different model application characteristics, select electricity elasticity coefficients model, Linear Regression Model in One Unknown, grey forecasting model, the two-parameter linearized index smoothing models of HOLT, ARIMA models totally five kinds of preferable forecast models of Model suitability, and the theory of the Shapley values in game theory is introduced to determine weight of each Forecasting Methodology in final predicted value, electricity demand forecasting scheme is provided for each economic trend, the final electricity demand forecasting result of gained can preferably reflect the growth situation of change of power consumption, from the angle Accurate Prediction electricity market state between supply and demand of economic development, for planning, decision part provides effective scientific basis.
Description
Technical field
The present invention relates to economic development and power consumption prediction neighborhood, and in particular to one kind is based on Shapley values and economic development
Power consumption prediction method.
Background technology
The emphasis of Electrical Market Forecasting is load forecast, and load prediction is advised according to the development and change of electric load
Rule, it is contemplated that or judge the activity of its future developing trend and situation, it is Power System Planning, electricity consumption plan, the basic work of scheduling
Make.By the studied object of load prediction work is uncertainty event, this just makes load prediction have obvious inaccuracy
The characteristics of.In addition, the economic situation change of our times is increasingly complicated, the development to electricity market generates strong influence,
So that judge the difficulty increase of power load rule.Therefore, consider economic development to pre- in current electricity market load prediction
The influence of gauge rule is advantageous to the accurate judgement load rule of development, and the foundation of science is provided for the prediction of electricity market.
The conventional flexible Y-factor method Y of Methods of electric load forecasting of power system at present, grey forecasting model, neutral net
Deng carrying out the information excavating of depth to the changing rule of electric load from different perspectives respectively, and then draw load prediction results.
However, the above method has respective applicable limitation, part useful information is likely to result in only with single Forecasting Methodology
Lose, fail comprehensively to consider all kinds of influence factors.That is, no matter precision of prediction is big or small, in each individual event prediction
The information of system independence is all included, can cause the waste of information if some model is only considered, and if will be different pre-
Survey Combination of Methods get up then can sophisticated systems estimated performance.
The main bugbear of combined prediction is exactly the solution of weighted average coefficients so that combination forecasting can be more effective
Improve precision of prediction.Existing combined prediction weight method such as has at weight average combinatorial forecast, the variance-covariance optimum combined forecasting
Method, regression combination predicted method, the preferred predicted method of fuzzy group etc..Shapley values are under various possible alliance's order, participate in this
Contributrion margin sum divided by various possible alliance's combinations to alliance.It is mainly used in cooperation benefit between each partner
Distribution, and distribution of the common cost between each partner caused by a certain facility is used simultaneously.At present by Shapley values
It is applied in load prediction, combination forecasting is obtained by determining the weights of forecast model, so as to carries out load to somewhere
Value prediction, do not consider influence of the economic development to electricity market, analysis is not yet refined to the electricity consumption situation of each department and industry.
The content of the invention
In order to solve the above problems, the invention provides a kind of power consumption prediction side based on Shapley values and economic development
Method, concrete technical scheme are as follows:
It is a kind of to be comprised the following steps based on Shapley values and the power consumption prediction method of economic development:
(1) overall economic development scheme is formulated, the economic development scheme includes the high scheme of economic development, economic development
Middle scheme, the low scheme of economic development;The GDP annual average rates of increase and GDP predicted values of each economic development scheme are predicted,
And then the economic development situation of each department and every profession and trade is segmented, the corresponding GDP annual average rates of increase and predicted value for predicting each department,
GDP predicted values are:
GDPj=GDPi×αj-i; ①
In formula, GDPjFor j GDP predicted values, GDPiFor known i GDP values, αj-iFor selected economic development side
Prediction GDP annual average rates of increase corresponding to case;
(2) electricity demand forecasting model is established, according to each department, the history power consumption data of every profession and trade, in economic development height
Carried out respectively with electricity demand forecasting model under scheme, economic development three kinds of economic development schemes of low scheme in scheme, economic development
Area, the electricity demand forecasting of every profession and trade;The electricity demand forecasting model includes electricity elasticity coefficients model, one-variable linear regression mould
The two-parameter linearized index smoothing model of type, grey forecasting model, HOLT, ARIMA models;
(3) weight of the electricity demand forecasting result obtained by the theoretical each electricity demand forecasting model of determination of Shapley values, from
And obtain final electricity demand forecasting result corresponding to each economic development scheme.
Further, the step (3) specifically includes following steps:
(1) absolute value of i-th of electricity demand forecasting model predictive error is calculated:
In formula, m be specific electricity demand forecasting value sample number, eijIt is j-th of electricity consumption under i-th kind of electricity demand forecasting model
Measure the residual error of predicted value;N is the number of electricity demand forecasting model;EiFor the absolute of i-th electricity demand forecasting model predictive error
Value;
(2) consensus forecast overall error E is calculated, consensus forecast overall error is exhausted for all electricity demand forecasting model predictive errors
The average value of value, such as following formula are represented:
In formula, n is the number of electricity demand forecasting model;EiFor the absolute value of i-th of electricity demand forecasting model predictive error;
(3) consensus forecast overall error E is regarded as according to Shapley values theory by total revenue and is assigned to single electricity demand forecasting mould
In type, determine that the electricity demand forecasting result that each electricity demand forecasting model obtains finally is used relative to corresponding to each economic development scheme
The weight of power quantity predicting result;Shapley values error distributes formula:
In formula, E ' i are the Shapley values of i-th kind of electricity demand forecasting model, are that i-th kind of electricity demand forecasting model is got
Average forecasting error amount;S refers to the set of all electricity demand forecasting models comprising i-th kind of electricity demand forecasting model;| s | for ginseng
With the number for the electricity demand forecasting model for distributing consensus forecast overall error E;S- { i } refers to the set in all electricity demand forecasting models
It is middle to remove the set for including electricity demand forecasting model in i-th;E (s) is that all electricity demand forecasting models participate in predicting electricity consumption jointly
Measure the margin of error reached;E (s- { i }) is that participation after i-th kind of electricity demand forecasting model is removed in all electricity demand forecasting models
The margin of error that prediction power consumption reaches;
(4) it is corresponding relative to corresponding economic development scheme to calculate the electricity demand forecasting result that each electricity demand forecasting model obtains
Final electricity demand forecasting result weight:
In formula, λiFor electricity demand forecasting model in i-th electricity demand forecasting result relative to corresponding economic development scheme pair
The weight for the final electricity demand forecasting result answered;
(5) final electricity demand forecasting result corresponding to corresponding economic development scheme is calculated:
Wherein,YtFor final electricity demand forecasting value, Y corresponding to corresponding economic development schemeitIt is i-th kind of electricity consumption
Measure the electricity demand forecasting value obtained by forecast model.
Further, the GDP annual average rates of increase of the high scheme of the economic development are more than 8.5%.
Further, the GDP annual average rates of increase of scheme are 7.5%-8.5% in the economic development.
Further, the GDP annual average rates of increase of the low scheme of the economic development are 4%-7.5%.
Beneficial effects of the present invention are:
The present invention proposes a kind of power consumption prediction method based on Shapley values and economic development, for economic development
High, medium and low scheme, the data based on each department, every profession and trade history electricity consumption data, subdivision each department, the economic hair of every profession and trade
Exhibition trend, structure electricity elasticity coefficients model, Linear Regression Model in One Unknown, grey forecasting model, the two-parameter linearized indexs of HOLT
Smoothing model and ARIMA forecast models, Shapley values are introduced to using the electricity demand forecasting knot that each electricity demand forecasting model obtains
Fruit confirmed relative to the weight of final electricity demand forecasting result, so as to draw each department under each economic development scheme, each
Industry Analyzing Total Electricity Consumption predicted value, the final electricity demand forecasting result of gained can preferably reflect the growth change of power consumption
Situation, from the angle Accurate Prediction electricity market state between supply and demand of economic development, for planning, decision part provide effective science according to
According to.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the present invention.
Embodiment
In order to be better understood from the present invention, the invention will be further described with specific embodiment below in conjunction with the accompanying drawings:
As shown in figure 1, a kind of comprised the following steps based on Shapley values and the power consumption prediction method of economic development:
1st, overall economic development scheme is formulated, economic development scheme includes side in the high scheme of economic development, economic development
Case, the low scheme of economic development;The GDP annual average rates of increase and GDP predicted values of each economic development scheme are predicted, and then
The economic development situation of each department and every profession and trade is segmented, accordingly predicts the GDP annual average rates of increase and predicted value of each department, according to
The economic total scale in China, birthrate of population, economic growth structure, each economic development speedup division are as follows:GDP annual average rates of increase
It is comparatively fast to increase for more than 8.5%, is the high scheme of economic development, GDP annual average rates of increase is that 7.5%-8.5% is quickly to increase
It is long, it is scheme in economic development, GDP annual average rates of increase are that 4%-7.5% is steady-state growth, are the low scheme of economic development.
When developing progress GDP speedup predictions to Regional Economic, with reference to the economic scale and economic growth structure of reality, increase in each economy
Suitable GDP annual average rates of increase are chosen in fast section and correspond to scheme, economic development in the high scheme of economic development, economic development
Low scheme.
GDP predicted values are:
GDPj=GDPi×αj-i; ①
In formula, GDPjFor j GDP predicted values, GDPiFor known i GDP values, αj-iFor selected economic development side
Prediction GDP annual average rates of increase corresponding to case.
In the present embodiment, the growth goal of the planning GDP annual average rates of increase in somewhere is set to 7.5%, then chooses warp
The GDP annual average rates of increase that Ji develops high scheme are 9%, the GDP annual average rates of increase of scheme are 7.5%, passed through in economic development
The GDP annual average rates of increase that Ji develops low scheme are 6%, it is known that the somewhere GDP values of 2015 are 16803.12 hundred million yuan, full society
Meeting electricity consumption value is 166.82 hundred million kilowatt hours, then lower 2016 GDP to the year two thousand twenty somewhere of each economic development scheme are predicted
It is worth as shown in table 1 below:
1 2016 years GDP predicted values for arriving the year two thousand twenty somewhere of table
2nd, electricity demand forecasting model is established, according to each department, the history power consumption data of every profession and trade, in economic development Gao Fang
In case, economic development various regions are carried out under scheme, economic development three kinds of economic development schemes of low scheme with electricity demand forecasting model
Area, the electricity demand forecasting of every profession and trade;Electricity demand forecasting model includes electricity elasticity coefficients model, Linear Regression Model in One Unknown, ash
The two-parameter linearized index smoothing model of color forecast model, HOLT, ARIMA models.
(1) electricity elasticity coefficients model is:
Am=A0(1+ktkgzch)n; ②
Wherein, AmTo predict the year power consumption in the end of term;A0For the year power consumption at the beginning of time span of forecast;kgzchFor GDP average annual growth rates
Rate;N is the year of time span of forecast;ktFor electricity elasticity coefficients;Electricity elasticity coefficients ktRefer to the annual average rate of increase of year power consumption
kzchWith GDP annual average rates of increase kgzchRatio, i.e.,
(2) Linear Regression Model in One Unknown is the unitary line drawn by the annual GDP values in historical data and power consumption fitting
Property equation, if Y1For power consumption, X is GDP values, then X and Y1Linear Regression Model in One Unknown be:
Y1=a+bX; ③
A, b is the coefficient correlation that fitting power consumption and GDP are worth going out, if it is desired to the electricity demand forecasting value of certain year, substituting into should
The GDP predicted values in year can try to achieve.
(3) grey forecasting model general principle formula is as follows:
If time series X(0)There is n observation:
X(0)={ X(0)(1),X(0)(2),...,X(0)(n)}; ④
The new sequence as follows that adds up to obtain:
X(1)={ X(1)(1),X(1)(2),...,X(1)(n)}; ⑤
In formula,
Then the differential equation of grey forecasting model is:
Wherein, a is development gray scale, and b is interior raw control gray scale;
The above differential equation is expressed as matrix form, and a and b estimate are tried to achieve with least square method, is then substituted into
In the differential equation, calculating is tried to achieve:
Reduced again by regressive, determine original data series X(0)Grey forecasting model be:
(4) the two-parameter linearized index smoothing models of HOLT are smooth by being carried out to history power consumption and its trend, draw flat
Sliding parameter, and then it is fitted predictive equation.Forecast model is specific as follows:
If Load Time Series XtFor then smoothing formula is:
Then, forecast model is:
In formula:λ is smoothing parameter, is to history power consumption sequence and the smooth gained of trend;StIt is data smoothing value;bt
It is trend smooth value;M is the advanced issue of prediction;Xt+mFor m phase electricity demand forecastings value after historical data.If for example, it is chosen for
2011-2015 power consumption data, the 2016-2018 that need to be predicted corresponds to m values can draw corresponding year power consumption for 1,2,3
Predicted value.
Initial value is:
In formula:X1For the power consumption of First Year in selected historical data, X2For the use of Second Year in selected historical data
Electricity, X3For the power consumption of the 3rd year in selected historical data, X4For the power consumption of the 4th year in selected historical data.
(5) ARIMA models are as follows:
In formula:YtFor t Prediction of annual electricity consumption values;Xt-1For t-1 power consumption;It is undetermined coefficient;
atRepresent enchancement factor.According to the power consumption in each year before t, t electricity demand forecasting value can be obtained.
3rd, used by the theoretical electricity demand forecasting result for determining that each electricity demand forecasting model obtains of Shapley values for final
The weight of power quantity predicting result, so as to obtain final electricity demand forecasting result corresponding to each economic development scheme;Specifically include with
Lower step:
(1) absolute value of i-th of electricity demand forecasting model predictive error is calculated:
In formula, m be specific electricity demand forecasting value sample number, eijIt is j-th of electricity consumption under i-th kind of electricity demand forecasting model
Measure the residual error of predicted value;N is the number of electricity demand forecasting model;EiFor the absolute of i-th electricity demand forecasting model predictive error
Value;
(2) consensus forecast overall error E is calculated, consensus forecast overall error is exhausted for all electricity demand forecasting model predictive errors
The average value of value, such as following formula are represented:
In formula, n is the number of electricity demand forecasting model;EiFor the absolute value of i-th of electricity demand forecasting model predictive error;
(3) consensus forecast overall error E is regarded as according to Shapley values theory by total revenue and is assigned to single electricity demand forecasting mould
In type, determine that the electricity demand forecasting result that each electricity demand forecasting model obtains finally is used relative to corresponding to each economic development scheme
The weight of power quantity predicting result;Shapley values error distributes formula:
In formula, E 'iIt is that i-th kind of electricity demand forecasting model is got for the Shapley values of i-th kind of electricity demand forecasting model
Average forecasting error amount;S refers to the set of all electricity demand forecasting models comprising i-th kind of electricity demand forecasting model;| s | for ginseng
With the number for the electricity demand forecasting model for distributing consensus forecast overall error E;S- { i } refers to the set in all electricity demand forecasting models
It is middle to remove the set for including electricity demand forecasting model in i-th;E (s) is that all electricity demand forecasting models participate in predicting electricity consumption jointly
Measure the margin of error reached;E (s- { i }) is that participation after i-th kind of electricity demand forecasting model is removed in all electricity demand forecasting models
The margin of error that prediction power consumption reaches;
(4) it is corresponding relative to corresponding economic development scheme to calculate the electricity demand forecasting result that each electricity demand forecasting model obtains
Final electricity demand forecasting result weight:
In formula, λiFor electricity demand forecasting model in i-th electricity demand forecasting result relative to corresponding economic development scheme pair
The weight for the final electricity demand forecasting result answered;
(5) final electricity demand forecasting result corresponding to corresponding economic development scheme is calculated:
Wherein,YtFor final electricity demand forecasting value, Y corresponding to corresponding economic development schemeitIt is i-th kind of electricity consumption
Measure the electricity demand forecasting value obtained by forecast model.
The growth goal of the planning GDP annual average rates of increase in somewhere is set to 7.5%, then chooses the high scheme of economic development
GDP annual average rates of increase are 9%, electricity elasticity coefficients 0.8, using GDP and Analyzing Total Electricity Consumption historical data as initial data,
Assuming that electricity elasticity coefficients are 0.8, whole society's power demand is carried out using the electricity demand forecasting model of each department of proposition more
Scenario Prediction, using the theoretical weights for determining single electricity demand forecasting model of Shapley in game theory, it is computed flexible power
Modulus Model, Linear Regression Model in One Unknown, grey forecasting model, HOLT two-parameter linearized index smoothing model, ARIMA models
Weight is respectively 0.17,0.21,0.18,0.22,0.22, then the electricity demand forecasting of the high scheme-the year two thousand twenty in 2016 of economic development
It is worth as shown in table 2 below:
The electricity demand forecasting value of the high scheme-the year two thousand twenty in 2016 of the economic development of table 2
The present invention is not limited to above-described embodiment, the foregoing is only the preferable case study on implementation of the present invention
, it is not intended to limit the invention, any modification for being made within the spirit and principles of the invention, equivalent substitution and changes
Enter, should be included in the scope of the protection.
Claims (5)
- A kind of 1. power consumption prediction method based on Shapley values and economic development, it is characterised in that:Comprise the following steps:(1) overall economic development scheme is formulated, the economic development scheme includes side in the high scheme of economic development, economic development Case, the low scheme of economic development;The GDP annual average rates of increase and GDP predicted values of each economic development scheme are predicted, and then Segment the economic development situation of each department and every profession and trade, the corresponding GDP annual average rates of increase and predicted value for predicting each department, GDP Predicted value is:GDPj=GDPi×αj-i;①In formula, GDPjFor j GDP predicted values, GDPiFor known i GDP values, αj-iFor selected economic development scheme pair The prediction GDP annual average rates of increase answered;(2) establish electricity demand forecasting model, according to each department, the history power consumption data of every profession and trade, the high scheme of economic development, In economic development under scheme, economic development three kinds of economic development schemes of low scheme with electricity demand forecasting model carry out each department, The electricity demand forecasting of every profession and trade;The electricity demand forecasting model includes electricity elasticity coefficients model, Linear Regression Model in One Unknown, ash The two-parameter linearized index smoothing model of color forecast model, HOLT, ARIMA models;(3) by the weight of the theoretical electricity demand forecasting result for determining each electricity demand forecasting model and obtaining of Shapley values, so as to obtain Obtain final electricity demand forecasting result corresponding to each economic development scheme.
- 2. a kind of power consumption prediction method based on Shapley values and economic development according to claim 1, its feature exist In:It is characterized in that:The step (3) specifically includes following steps:(1) absolute value of i-th of electricity demand forecasting model predictive error is calculated:In formula, m be specific electricity demand forecasting value sample number, eijIt is that j-th of power consumption is pre- under i-th kind of electricity demand forecasting model The residual error of measured value;N is the number of electricity demand forecasting model;EiFor the absolute value of i-th of electricity demand forecasting model predictive error;(2) consensus forecast overall error E is calculated, consensus forecast overall error is the absolute value of all electricity demand forecasting model predictive errors Average value, as following formula represent:In formula, n is the number of electricity demand forecasting model;EiFor the absolute value of i-th of electricity demand forecasting model predictive error;(3) consensus forecast overall error E is regarded as according to Shapley values theory by total revenue and is assigned to single electricity demand forecasting model In, determine electricity demand forecasting result that each electricity demand forecasting model obtains relative to final electricity consumption corresponding to each economic development scheme Measure the weight of prediction result;Shapley values error distributes formula:In formula, E 'iIt is being averaged of getting of i-th kind of electricity demand forecasting model for the Shapley values of i-th kind of electricity demand forecasting model Predict the margin of error;S refers to the set of all electricity demand forecasting models comprising i-th kind of electricity demand forecasting model;| s | to participate in the distribution The number of consensus forecast overall error E electricity demand forecasting model;S- { i } refers to be removed in the set of all electricity demand forecasting models Include the set of electricity demand forecasting model in i-th;E (s) is that all electricity demand forecasting models participate in predicting that power consumption reaches jointly The margin of error;E (s- { i }) is that participation prediction is used after i-th kind of electricity demand forecasting model is removed in all electricity demand forecasting models The margin of error that electricity reaches;(4) calculate electricity demand forecasting result that each electricity demand forecasting model obtains relative to corresponding to corresponding economic development scheme most The weight of whole electricity demand forecasting result:In formula, λiFor electricity demand forecasting model in i-th electricity demand forecasting result relative to corresponding to corresponding economic development scheme most The weight of whole electricity demand forecasting result;(5) final electricity demand forecasting result corresponding to corresponding economic development scheme is calculated:Wherein,YtFor final electricity demand forecasting value, Y corresponding to corresponding economic development schemeitIt is that i-th kind of power consumption is pre- Survey the electricity demand forecasting value that model obtains.
- 3. a kind of power consumption prediction method based on Shapley values and economic development according to claim 1, its feature exist In:The GDP annual average rates of increase of the high scheme of economic development are more than 8.5%.
- 4. a kind of power consumption prediction method based on Shapley values and economic development according to claim 1, its feature exist In:The GDP annual average rates of increase of scheme are 7.5%-8.5% in the economic development.
- 5. a kind of power consumption prediction method based on Shapley values and economic development according to claim 1, its feature exist In:The GDP annual average rates of increase of the low scheme of the economic development are 4%-7.5%.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710950656.3A CN107679666A (en) | 2017-10-13 | 2017-10-13 | A kind of power consumption prediction method based on Shapley values and economic development |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710950656.3A CN107679666A (en) | 2017-10-13 | 2017-10-13 | A kind of power consumption prediction method based on Shapley values and economic development |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107679666A true CN107679666A (en) | 2018-02-09 |
Family
ID=61140761
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710950656.3A Pending CN107679666A (en) | 2017-10-13 | 2017-10-13 | A kind of power consumption prediction method based on Shapley values and economic development |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107679666A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111983478A (en) * | 2020-07-07 | 2020-11-24 | 江苏大学 | Electrochemical energy storage power station SOC anomaly detection method based on Holt linear trend model |
CN112330153A (en) * | 2020-11-06 | 2021-02-05 | 广西电网有限责任公司电力科学研究院 | Non-linear orthogonal regression-based industry scale prediction model modeling method and device |
CN112464035A (en) * | 2020-11-18 | 2021-03-09 | 贵州电网有限责任公司 | Data mining method based on power grid regulation and control data |
CN113837470A (en) * | 2021-09-26 | 2021-12-24 | 深圳市汇能环保科技有限公司 | Method for predicting electric energy consumption of smart power grid |
-
2017
- 2017-10-13 CN CN201710950656.3A patent/CN107679666A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111983478A (en) * | 2020-07-07 | 2020-11-24 | 江苏大学 | Electrochemical energy storage power station SOC anomaly detection method based on Holt linear trend model |
CN112330153A (en) * | 2020-11-06 | 2021-02-05 | 广西电网有限责任公司电力科学研究院 | Non-linear orthogonal regression-based industry scale prediction model modeling method and device |
CN112464035A (en) * | 2020-11-18 | 2021-03-09 | 贵州电网有限责任公司 | Data mining method based on power grid regulation and control data |
CN113837470A (en) * | 2021-09-26 | 2021-12-24 | 深圳市汇能环保科技有限公司 | Method for predicting electric energy consumption of smart power grid |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103617564B (en) | The whole network load forecasting method based on region predicted load overall merit | |
CN102402726B (en) | Method for predicting electric quantity of large-scale distribution network based on regional load analysis | |
CN107679666A (en) | A kind of power consumption prediction method based on Shapley values and economic development | |
CN102509173B (en) | A kind of based on markovian power system load Accurate Prediction method | |
CN107862466A (en) | The source lotus complementary Benefit Evaluation Method spanning space-time of consideration system bilateral randomness | |
CN107909253A (en) | Intelligent distribution network scheduling controlling effect evaluation method based on interval based AHP | |
CN109492950A (en) | Prediction method capable of meeting space saturation load of large area range based on GIS technology | |
CN106951990A (en) | Electric load intelligent Forecasting and device | |
CN108596369B (en) | Space load prediction method based on multivariate model and blind number theory | |
CN111260198A (en) | Method and system for judging degree of rationality of line loss in transformer area synchronization and terminal equipment | |
CN105243609A (en) | User ordered power utilization decision method based on fuzzy hierarchical analysis | |
CN103530701B (en) | A kind of user's moon electricity demand forecasting method and system based on seasonal index number method | |
CN107748972A (en) | A kind of method based on Dual-energy source index prediction Analyzing Total Electricity Consumption | |
CN103530700B (en) | Urban distribution network saturation loading Comprehensive Prediction Method | |
CN114693122A (en) | Power grid planning method based on digital twinning technology | |
CN113723719B (en) | Distribution transformation-based near-intermediate load prediction method, device, equipment and medium | |
Yılmaz | Real measure of a transmission line data with load fore-cast model for the future | |
Lao et al. | The optimized multivariate grey prediction model based on dynamic background value and its application | |
Teng et al. | New energy benchmarking model for budget hotels | |
CN107480810A (en) | A kind of moon electricity demand forecasting method that double smoothing is improved using seasonal index number | |
CN106096774A (en) | A kind of large area region Analyzing Total Electricity Consumption Forecasting Methodology based on gridding method | |
CN113887809A (en) | Power distribution network supply and demand balance method, system, medium and computing equipment under double-carbon target | |
CN105654194A (en) | Power grid development index measurement method | |
Zhang et al. | Partial Least Squares regression load forecasting model based on the combination of grey Verhulst and equal-dimension and new-information model | |
Liu et al. | Time-variant slide fuzzy time-series method for short-term load forecasting |
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 |
Application publication date: 20180209 |
|
RJ01 | Rejection of invention patent application after publication |