CN109492818A - Based on energy development and the entitled electricity demand forecasting method of Shapley value - Google Patents
Based on energy development and the entitled electricity demand forecasting method of Shapley value Download PDFInfo
- Publication number
- CN109492818A CN109492818A CN201811367473.XA CN201811367473A CN109492818A CN 109492818 A CN109492818 A CN 109492818A CN 201811367473 A CN201811367473 A CN 201811367473A CN 109492818 A CN109492818 A CN 109492818A
- Authority
- CN
- China
- Prior art keywords
- energy
- demand forecasting
- model
- development
- electricity demand
- 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
- 230000005611 electricity Effects 0.000 title claims abstract description 102
- 238000011161 development Methods 0.000 title claims abstract description 69
- 238000013277 forecasting method Methods 0.000 title claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 4
- 238000005265 energy consumption Methods 0.000 claims description 33
- 238000004458 analytical method Methods 0.000 claims description 20
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims description 17
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000012417 linear regression Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 238000000611 regression analysis Methods 0.000 claims description 2
- 230000007774 longterm Effects 0.000 abstract description 3
- 238000000034 method Methods 0.000 description 13
- 230000012010 growth Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000007773 growth pattern Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002087 whitening effect Effects 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression 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—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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Mathematical Analysis (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Tourism & Hospitality (AREA)
- Computational Mathematics (AREA)
- Databases & Information Systems (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to one kind based on energy development and the entitled electricity demand forecasting method of Shapley value, comprising the following steps: based on the major economic factor for influencing the energy and electricity consumption development, economic forecasting situation；Energy development situation is predicted using multivariate regression models；According to history electricity consumption data and multi-energy data, based on the prediction result of the economic development situation and energy development situation, region electricity consumption development prediction is carried out using a variety of electricity demand forecasting models, obtains multiple electricity demand forecasting values；It is weighted processing by the theoretical multiple electricity demand forecasting values of Shapley value, obtains final electricity demand forecasting result.Compared with prior art, the present invention finally resulting electricity demand forecasting result can preferably consider in long-term electricity consumption increase situation of change, foundation can be provided for power grid long term planning target, electricity consumption conditions of demand are accurately analyzed from economy and energy multi-angle, provide effective reference for Electric Power Network Planning.
Description
Technical field
The present invention relates to Load Prediction In Power Systems technical field, more particularly, to one kind based on energy development with
The entitled electricity demand forecasting method of Shapley value.
Background technique
A branch of the electricity demand forecasting as load forecast, is the important previous work of Power System Planning.With
Electricity scale is influenced by many factors, including population, GDP, urbanization rate etc..Electricity demand forecasting can be power grid long term planning
Target provides foundation, provides effective reference for Electric Power Network Planning.
The typical autocorrelation model of saturation load forecasting is Logistic curve model, has research to choose Logistic curve
Model carries out saturation load forecasting, according to the S type curvilinear characteristic of traditional load growth, the following different development scene of setting into
Row prediction；There are also researchs simultaneously by establishing the correlation model between influence factor and load, carries out saturation load forecasting, such as selects
Pass through the side that Analyzing Total Electricity Consumption is directly predicted, tertiary industry power consumption prediction, per capita household electricity consumption are predicted respectively with econometrics model
Method predicts Analyzing Total Electricity Consumption saturation value, is then combined tax power by comentropy and obtains combined prediction value.The above method is each
There is limitation, mostly predicted only with single prediction technique, is easy to be influenced by the intrinsic development trend of model.And it is current
Electricity demand forecasting field, multipair electricity consumption directly analyzed, it is rare from electric energy in total energy consumption accounting angle
Carry out the research of electricity demand forecasting.
Summary of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide one kind to be based on energy development
With the entitled electricity demand forecasting method of Shapley value, comprehensively considers electric energy accounting growth pattern in energy forecast, overcome list
The limitation of one prediction model.
The purpose of the present invention can be achieved through the following technical solutions:
One kind is based on energy development and the entitled electricity demand forecasting method of Shapley value, comprising the following steps:
1) based on the major economic factor for influencing the energy and electricity consumption development, economic forecasting situation；
2) major economic factor based on area to be predicted predicts energy development situation using multivariate regression models；
3) history electricity consumption data and multi-energy data are acquired, it is pre- based on the economic development situation and energy development situation
It surveys as a result, constructing a variety of electricity demand forecasting models, progress region electricity consumption development prediction obtains multiple electricity demand forecasting values；
4) processing is weighted to multiple electricity demand forecasting values that step 3) obtains by Shapley value theory, obtained most
Whole electricity demand forecasting result.
Further, the major economic factor includes population, GDP, GDP per capita, tertiary industry accounting, urbanization rate and unit
GDP energy consumption.
Further, in the step 1), economic forecasting situation is specifically included:
The outside forecast of population, urban population is carried out using Logistic curve model；
According to regional economic development situation, in corresponding developed country's history economics stage, GDP is predicted；
Ratio by calculating urban population and population obtains the urbanization rate of prediction；
Ratio by calculating GDP and population obtains the GDP per capita of prediction；
According to regional economic development situation, in corresponding developed country's history economics stage, tertiary industry accounting development is predicted；With
And
According to regional energy consumption intensity and regional 5 years development plans, per Unit GDP Energy Consumption development is predicted.
Further, in the step 2), each industrial final energy consumption total amount and the major economic factor are carried out
Correlation analysis predicts that energy development situation, the industrial final energy consumption total amount include a production using multivariate regression models
Final energy consumption total amount, two produce final energy consumption total amount, tertiary industry final energy consumption total amount and resident living terminal energy sources
Total quantity consumed.
Further, in the step 2), linear regression analysis and/or nonlinear regression are used based on multivariate regression models
Analysis prediction energy development situation.
Further, the electricity demand forecasting model includes the electricity consumption based on energy development situation and the analysis of electric energy accounting
Prediction model, the electricity demand forecasting model based on Logistics and the electricity demand forecasting model based on gray theory.
Further, in the electricity demand forecasting model based on energy development situation and the analysis of electric energy accounting, electric energy is accounted for
It is more corresponding with developed country's history economics stage than analysis base area area economic development situation.
Further, the step 4) specifically:
401) the average relative error value absolute value MAPE of i-th of electricity demand forecasting model is calculatedi:
In formula, m indicates each model history electricity consumption sample year, i=1,2 ..., n, and n indicates the total number of model, EjTable
Show the predicted value in jth year, Ej0Indicate the actual value in jth year；
402) overall average absolute relative error MAPE is calculated:
403) overall average absolute relative error is considered as by total revenue according to Shapley value theory, each model is considered as each
Partner, Shapley value calculation formula are as follows:
In formula, φiFor the Shapley value of i-th kind of model；S indicates the set of all models comprising i-th kind of model, s-
{ i } indicates the set that i-th kind of model is taken out in all s set；MAPE (s) indicates that all s set are common and participates in predicting to reach
The margin of error；MAPE (s- { i }) indicates the margin of error reached after i-th kind of model of taking-up in all s set, | s | it indicates in s set
Number of Models, | s |=1,2 ..., n；
404) weight of each model is calculated:
In formula, λiFor the weight of i-th kind of model；
405) according to gained weight, final electricity consumption is calculated:
In formula, EtIndicate the predicted value of final t, EitIndicate the predicted value of i-th kind of model t.
The method of the present invention combines the basic demand of prediction and the application characteristic of different models, is utilized respectively the energy of multiple regression
Source prediction model and electric energy accounting analysis method, Logistics electricity consumption model and grey electricity demand forecasting model are to electricity consumption
Modeling and forecasting is carried out, and is combined tax power by Shapley enabling legislation, obtains final electricity demand forecasting value.With the prior art
Compare, the present invention have with following the utility model has the advantages that
(1) comprising the prediction and analysis that develop future source of energy in prediction model of the present invention, guarantee to guarantee in electric energy accounting
Stablize or predict under the premise of increasing the following electricity consumption；
(2) present invention is combined prediction using multi-model, avoids the limitation of single model.
(3) present invention assigns power using Shapley value income analysis, has certain superiority in prediction result precision.
Detailed description of the invention
Fig. 1 is flow diagram of the invention.
Specific embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to
Following embodiments.
The present invention provides one kind based on energy development and the entitled electricity demand forecasting method of Shapley value, in conjunction with prediction
The application characteristic of basic demand and different models chooses main economic and energy influence factor, is utilized respectively the energy of multiple regression
Source prediction model and electric energy accounting analysis method, Logistics electricity consumption model and grey electricity demand forecasting model are to electricity consumption
Modeling and forecasting is carried out, tax power is combined by Shapley enabling legislation, obtains final electricity demand forecasting value.As shown in Figure 1, should
Prediction technique the following steps are included:
1, the major economic factor for influencing the energy and electricity consumption development is chosen in analysis, specifically:
Step S101 chooses population, GDP, GDP per capita, tertiary industry accounting, urbanization rate and per Unit GDP Energy Consumption as main
Economic factor；
Step S102, economic forecasting situation specifically predict the development of each economic factor, specifically:
The outside forecast of population, urban population is carried out using Logistic curve model, Logistic curve model is as follows；
In formula, a > 0, b > 0, k < 0, c are constant term；
According to regional economic development situation, corresponding developed country's history economics stage predicts that GDP annual growth and GDP are pre-
Measured value, GDP predicted value are as follows:
GDPi=GDPi-1×αi
In formula, GDPiFor 1 year GDP value, αiFor 1 year year GDP growth rate；
Urbanization rate show that GDP per capita passes through the ratio for calculating GDP and population by calculating the ratio of urban population and population
Value obtains；
According to regional economic development situation, in corresponding developed country's history economics stage, tertiary industry accounting development is predicted；
According to regional energy consumption intensity, and regional 5 years development plans, per Unit GDP Energy Consumption development is predicted.
2, the factor high with energy development correlation is analyzed, energy development situation is predicted using multivariate regression models, specifically
Ground:
Step S201 analyzes the factor high with energy development correlation, including the regional population of prediction, GDP, GDP per capita,
Tertiary industry accounting, urbanization rate and per Unit GDP Energy Consumption；
Step S202 predicts energy development situation using multivariate regression models, studies the recurrence of relationship between multiple variables
Analysis method carries out linear regression analysis and nonlinear regression analysis by regression model type respectively.
3, a variety of electricity demand forecasting models, acquisition history electricity consumption data and multi-energy data are constructed and is pre-processed, progress area
Domain electricity consumption development prediction, specifically includes:
Step S301 carries out the electricity demand forecasting based on energy development situation and the analysis of electric energy accounting, energy development situation
For the prediction result of step 2, the analysis of electric energy accounting corresponds to developed country's history economics stage according to regional economic development situation and pushes away
It obtains；
Step S302 carries out the electricity demand forecasting based on Logistics model；
Step S303 carries out the electricity demand forecasting based on gray model, specifically:
The degree of association between electricity consumption and influence factor is calculated first, if electricity consumption target data column X0={ X0(t), t=
1,2 ..., n }, factor index data column Xi={ Xi(t), t=1,2 ..., n, i=1,2 ..., m }, show there is m kind index, every kind
Index has the historical data of n.Nondimensionalization is carried out to index and electricity consumption, equalization processing is carried out to data sequence:
Then in jth year, index XiWith electricity consumption X0Between incidence coefficient see below formula:
Index XiWith electricity consumption X0Between the degree of association are as follows:
According to the electricity consumption acquired and between each index the degree of association, successively sorted to index, the high row of the degree of association
Sequence is first.Before order 1, preceding 2 to preceding n index is successively taken, is constructed GM (1,2), GM (1,3) to GM (1, n+1) model, is calculated quasi-
The model of conjunction and the residual sum mean residual of actual, historical data, select the smallest model of residual error.
Specific calculating process: initial data is stored in a matrixWherein
Dependent variable electricity consumption,For independent variable index.After carrying out nondimensionalization, the same single order that carries out adds up
Etc. data be intended to handle.
The whitening pattern of GM (1, N) model sees below formula, b1Influence coefficient for electricity consumption to itself, b2、b3To bmFor each finger
Mark the influence coefficient to electricity consumption.
The calculation formula for influencing coefficient is as follows:
[b1 b2.......bm]T=(BTB)-1BTYn
The albefaction model of GM (1, N) is solved, it is availableCalculation formula:
Calculating can be obtained and anti-cumulative derive.
It derivesAfterwards, its mean residual between historical data should be calculated:
It selects the smallest gray model of residual error as final gray model, carries out outside forecast.
4, tax power is carried out to a variety of electricity demand forecasting models by Shapley value theory, obtains final electricity demand forecasting knot
Fruit.Specifically include following process:
Calculate the average relative error value absolute value MAPE of i-th of electricity demand forecasting modeli:
In formula, m indicates each model history electricity consumption sample year, and n indicates the total number of model, EjIndicate the pre- of jth year
Measured value, Ej0Indicate the actual value in jth year；
Calculate overall average absolute relative error MAPE:
In formula, n indicates the total number of model；
Regard overall average absolute relative error as total revenue according to Shapley value theory, each model is considered as each cooperation
Quotient；Shapley value calculation formula are as follows:
In formula, φiFor the Shapley value of i-th kind of model；S indicates the set of all models comprising i-th kind of model, s-
{ i } indicates the set that i-th kind of model is taken out in all s set；MAPE (s) indicates that all s aggregation models participate in predicting jointly
The margin of error reached；MAPE (s- { i }) indicates the margin of error reached after i-th kind of model of taking-up in all s aggregation models, | s | table
Show the Number of Models in s set.
Calculate the weight of each model:
According to gained weight, final electricity consumption is calculated:
In formula, EtIndicate the predicted value of final t, EitIndicate the predicted value of i-th kind of model t.
Specific embodiment is given below to illustrate specific implementation process of the invention:
A province in China 1995-2017 population, GDP, GDP per capita, tertiary industry accounting, urbanization rate are chosen according to step S101
It is major economic factor with per Unit GDP Energy Consumption, outside forecast is carried out according to step S102；
According to step S202, by 2000-2016 embodiment province divide industrial final energy consumption total amount and population, GDP,
GDP per capita, tertiary industry accounting, urbanization rate and per Unit GDP Energy Consumption carry out correlation analysis, and analysis obtains influencing a production terminal energy sources
The factor of total quantity consumed is a production GDP and per Unit GDP Energy Consumption, and influencing the factor that two produce final energy consumption total amounts is population, two
GDP and per Unit GDP Energy Consumption are produced, the factor for influencing tertiary industry final energy consumption total amount is population, tertiary industry GDP and per Unit GDP Energy Consumption,
The factor for influencing resident living final energy consumption total amount is population, total GDP and per Unit GDP Energy Consumption.Multiple regression fitting result
It is as shown in table 1:
1 final energy consumption total amount multiple regression fitting result of table
According to step S301, embodiment province terminal electric energy accounting in 2016 is 28.59%, the industrial structure one in 2017
Produce: two produce: tertiary industry 4.7:45:50.3, (7.94:42.62:49.43) close with South Korea's structure in 1991, with Germany 1980
Structure is close (2.2:44.8:53)；After comparative analysis, judge that embodiment province electric energy accounting will increase, but growth rate is slow
Slowly, comparison selects the growth rate of Germany as reference, and the percentage that 2017-2030 increases increases by 3 percentages with reference to Germany
Point.
The results are shown in Table 2 for electricity demand forecasting based on energy development and the analysis of electric energy accounting
Electricity demand forecasting result of the table 2 based on energy development and the analysis of electric energy accounting
The average relative error value absolute value MAPE of model1It is 4.2194%.
According to step S302, the electricity demand forecasting based on Logistics model is carried out, prediction result is as shown in table 3:
Electricity demand forecasting result of the table 3 based on Logistics
The average relative error value absolute value MAPE of model2It is 9.4569%.
According to step S303, the electricity demand forecasting based on gray model is carried out, prediction result is as shown in table 4:
Electricity demand forecasting result of the table 4 based on gray theory
The average relative error value absolute value MAPE of model3It is 6.3502%.
Tax power is carried out to a variety of electricity demand forecasting models by Shapley value theory, obtains final electricity demand forecasting result.
Specifically include following process:
MAPE=MAPE (1,2,3)=each model of (4.2194%+9.4569%+6.3502%)/3=6.6755%
Shapley value calculating process is as follows:
Similarly, it can be calculated:
φ2=5.23837%, φ3=1.87272%
The weight computations of each model are as follows:
The results are shown in Table 5 for final electricity demand forecasting.
Table 5 is based on the entitled combined prediction result of Shapley value
The preferred embodiment of the present invention has been described in detail above.It should be appreciated that those skilled in the art without
It needs creative work according to the present invention can conceive and makes many modifications and variations.Therefore, all technologies in the art
Personnel are available by logical analysis, reasoning, or a limited experiment on the basis of existing technology under this invention's idea
Technical solution, all should be within the scope of protection determined by the claims.
Claims (8)
1. one kind is based on energy development and the entitled electricity demand forecasting method of Shapley value, which is characterized in that including following step
It is rapid:
1) based on the major economic factor for influencing the energy and electricity consumption development, economic forecasting situation；
2) major economic factor based on area to be predicted predicts energy development situation using multivariate regression models；
3) history electricity consumption data and multi-energy data, the prediction knot based on the economic development situation and energy development situation are acquired
Fruit constructs a variety of electricity demand forecasting models, carries out region electricity consumption development prediction, obtains multiple electricity demand forecasting values；
4) processing is weighted to multiple electricity demand forecasting values that step 3) obtains by Shapley value theory, is finally used
Power quantity predicting result.
2. according to claim 1 existed based on energy development with the entitled electricity demand forecasting method of Shapley value, feature
In the major economic factor includes population, GDP, GDP per capita, tertiary industry accounting, urbanization rate and per Unit GDP Energy Consumption.
3. according to claim 2 existed based on energy development with the entitled electricity demand forecasting method of Shapley value, feature
In in the step 1), economic forecasting situation is specifically included:
The outside forecast of population, urban population is carried out using Logistic curve model；
According to regional economic development situation, in corresponding developed country's history economics stage, GDP is predicted；
Ratio by calculating urban population and population obtains the urbanization rate of prediction；
Ratio by calculating GDP and population obtains the GDP per capita of prediction；
According to regional economic development situation, in corresponding developed country's history economics stage, tertiary industry accounting development is predicted；And
According to regional energy consumption intensity and regional 5 years development plans, per Unit GDP Energy Consumption development is predicted.
4. according to claim 1 existed based on energy development with the entitled electricity demand forecasting method of Shapley value, feature
In in the step 2), by each industrial final energy consumption total amount and major economic factor progress correlation analysis, use
Multivariate regression models predicts that energy development situation, the industrial final energy consumption total amount include that a production final energy consumption is total
Amount, two produce final energy consumption total amount, tertiary industry final energy consumption total amount and resident living final energy consumption total amount.
5. according to claim 1 or 4 be based on energy development and the entitled electricity demand forecasting method of Shapley value, spy
Sign is, in the step 2), predicts energy using linear regression analysis and/or nonlinear regression analysis based on multivariate regression models
Source development.
6. according to claim 1 existed based on energy development with the entitled electricity demand forecasting method of Shapley value, feature
In the electricity demand forecasting model is included the electricity demand forecasting model analyzed based on energy development situation with electric energy accounting, is based on
The electricity demand forecasting model of Logistics and electricity demand forecasting model based on gray theory.
7. according to claim 6 existed based on energy development with the entitled electricity demand forecasting method of Shapley value, feature
In in the electricity demand forecasting model based on energy development situation and the analysis of electric energy accounting, electric energy accounting is analyzed according to area
Economic development situation is corresponding with developed country's history economics stage.
8. according to claim 1 existed based on energy development with the entitled electricity demand forecasting method of Shapley value, feature
In the step 4) specifically:
401) the average relative error value absolute value MAPE of i-th of electricity demand forecasting model is calculatedi:
In formula, m indicates each model history electricity consumption sample year, i=1,2 ..., n, and n indicates the total number of model, EjIndicate jth
The predicted value in year, Ej0Indicate the actual value in jth year；
402) overall average absolute relative error MAPE is calculated:
403) overall average absolute relative error is considered as by total revenue according to Shapley value theory, each model is considered as each cooperation
Quotient, Shapley value calculation formula are as follows:
In formula, φiFor the Shapley value of i-th kind of model；S indicates the set of all models comprising i-th kind of model, s- { i } table
Show the set that i-th kind of model is taken out in all s set；MAPE (s) indicates the common error for participating in prediction and reaching of all s set
Amount；MAPE (s- { i }) indicates the margin of error reached after i-th kind of model of taking-up in all s set, | s | indicate the model in s set
Number, | s |=1,2 ..., n；
404) weight of each model is calculated:
In formula, λiFor the weight of i-th kind of model；
405) according to gained weight, final electricity consumption is calculated:
In formula, EtIndicate the predicted value of final t, EitIndicate the predicted value of i-th kind of model t.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811367473.XA CN109492818A (en) | 2018-11-16 | 2018-11-16 | Based on energy development and the entitled electricity demand forecasting method of Shapley value |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811367473.XA CN109492818A (en) | 2018-11-16 | 2018-11-16 | Based on energy development and the entitled electricity demand forecasting method of Shapley value |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109492818A true CN109492818A (en) | 2019-03-19 |
Family
ID=65696113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811367473.XA Pending CN109492818A (en) | 2018-11-16 | 2018-11-16 | Based on energy development and the entitled electricity demand forecasting method of Shapley value |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109492818A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717692A (en) * | 2019-10-23 | 2020-01-21 | 上海浦源科技有限公司 | Saturated power calculation method for unbalanced social industrial development |
| CN111047108A (en) * | 2019-12-24 | 2020-04-21 | 东南大学 | Optimal combination model-based electric energy ratio prediction method in terminal energy consumption |
| CN111144616A (en) * | 2019-11-29 | 2020-05-12 | 中国船舶重工集团公司第七一六研究所 | Enterprise energy consumption-oriented prediction method and system, computer equipment and storage medium |
| CN112327666A (en) * | 2020-10-22 | 2021-02-05 | 智慧航海（青岛）科技有限公司 | Method for determining target function weight matrix of power cruise system control model |
| CN113435653A (en) * | 2021-07-02 | 2021-09-24 | 国网新疆电力有限公司经济技术研究院 | Saturated power consumption prediction method and system based on logistic model |
| CN114186713A (en) * | 2021-11-17 | 2022-03-15 | 广西电网有限责任公司 | Medium-and-long-term power consumption prediction method considering perspective development scenario constraint |
-
2018
- 2018-11-16 CN CN201811367473.XA patent/CN109492818A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717692A (en) * | 2019-10-23 | 2020-01-21 | 上海浦源科技有限公司 | Saturated power calculation method for unbalanced social industrial development |
| CN111144616A (en) * | 2019-11-29 | 2020-05-12 | 中国船舶重工集团公司第七一六研究所 | Enterprise energy consumption-oriented prediction method and system, computer equipment and storage medium |
| CN111047108A (en) * | 2019-12-24 | 2020-04-21 | 东南大学 | Optimal combination model-based electric energy ratio prediction method in terminal energy consumption |
| CN111047108B (en) * | 2019-12-24 | 2023-12-12 | 东南大学 | Electric energy duty ratio prediction method in terminal energy consumption based on optimal combination model |
| CN112327666A (en) * | 2020-10-22 | 2021-02-05 | 智慧航海（青岛）科技有限公司 | Method for determining target function weight matrix of power cruise system control model |
| CN112327666B (en) * | 2020-10-22 | 2023-02-07 | 智慧航海（青岛）科技有限公司 | Method for determining target function weight matrix of power cruise system control model |
| CN113435653A (en) * | 2021-07-02 | 2021-09-24 | 国网新疆电力有限公司经济技术研究院 | Saturated power consumption prediction method and system based on logistic model |
| CN113435653B (en) * | 2021-07-02 | 2022-11-04 | 国网新疆电力有限公司经济技术研究院 | Method and system for predicting saturated power consumption based on logistic model |
| CN114186713A (en) * | 2021-11-17 | 2022-03-15 | 广西电网有限责任公司 | Medium-and-long-term power consumption prediction method considering perspective development scenario constraint |
| CN114186713B (en) * | 2021-11-17 | 2024-05-24 | 广西电网有限责任公司 | Medium-and-long-term electricity consumption prediction method considering distant view development scenario constraint |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492818A (en) | Based on energy development and the entitled electricity demand forecasting method of Shapley value | |
| Wang et al. | Evaluation and difference analysis of regional energy efficiency in China under the carbon neutrality targets: Insights from DEA and Theil models | |
| Gareta et al. | Forecasting of electricity prices with neural networks | |
| CN104657788B (en) | Key industry electricity demand forecasting method based on Industrial Cycle index | |
| CN103413188B (en) | A kind of monthly industrial power predicating method based on industry Business Process System | |
| CN105447594A (en) | Electric power system grey load prediction method based on exponential smoothing | |
| CN109726865A (en) | Customer charge probability density prediction technique, device and storage medium based on EMD-QRF | |
| Wei et al. | Forecasting the daily natural gas consumption with an accurate white-box model | |
| CN106355285B (en) | Power load prediction method based on parameter correction | |
| CN110991843A (en) | Saturated power demand prediction method considering urbanization development and electric energy substitution effect | |
| CN106557835B (en) | Electricity demand forecasting method and system based on consumer confidence index | |
| CN104881718A (en) | Regional power business index constructing method based on multi-scale leading economic indicators | |
| Saravanan et al. | Forecasting India's electricity demand using artificial neural network | |
| CN103853939A (en) | Combined forecasting method for monthly load of power system based on social economic factor influence | |
| CN109118012A (en) | A kind of industrial dynamics various dimensions energy consumption cost prediction technique, system, storage medium and terminal | |
| CN106202491A (en) | A kind of based on seasonal effect in time series data digging method and system | |
| CN112149890A (en) | Comprehensive energy load prediction method and system based on user energy label | |
| CN109376911A (en) | A kind of micro-capacitance sensor short-term load forecasting method based on EMD-KELMs-SDPSO | |
| CN104134102B (en) | Long-term electricity needs distribution forecasting method in power network based on LEAP models | |
| CN116739368A (en) | Industrial park carbon emission level monitoring and evaluating method based on energy big data | |
| Wu et al. | A hybrid BAG-SA optimal approach to estimate energy demand of China | |
| Mey et al. | Prediction of energy consumption for variable customer portfolios including aleatoric uncertainty estimation | |
| CN114239292A (en) | Comprehensive evaluation method and system for low-carbon economic operation-oriented multifunctional demand park | |
| CN109214610A (en) | A kind of saturation Methods of electric load forecasting based on shot and long term Memory Neural Networks | |
| Hu et al. | Adaptive corrected parameters algorithm applied in cooling load prediction based on black-box model: A case study for subway station |
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 | ||
| CB02 | Change of applicant information |
Address after: 200030 Dongchuan Road, Minhang District, Minhang District, Shanghai Applicant after: SHANGHAI JIAO TONG University Applicant after: STATE GRID JIANGSU ECONOMIC Research Institute Applicant after: SHANGHAI HUADONG ELECTRIC PRECIPITATION INDUSTRIAL Co.,Ltd. Applicant after: STATE GRID CORPORATION OF CHINA Address before: 200030 Huashan Road, Shanghai, No. 1954, No. Applicant before: SHANGHAI JIAO TONG University Applicant before: STATE GRID JIANGSU ECONOMIC Research Institute Applicant before: SHANGHAI HUADONG ELECTRIC PRECIPITATION INDUSTRIAL Co.,Ltd. Applicant before: STATE GRID CORPORATION OF CHINA |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190319 |
|
| RJ01 | Rejection of invention patent application after publication |