CN107423862A - Methods of electric load forecasting based on economic data - Google Patents
Methods of electric load forecasting based on economic data Download PDFInfo
- Publication number
- CN107423862A CN107423862A CN201710685610.3A CN201710685610A CN107423862A CN 107423862 A CN107423862 A CN 107423862A CN 201710685610 A CN201710685610 A CN 201710685610A CN 107423862 A CN107423862 A CN 107423862A
- Authority
- CN
- China
- Prior art keywords
- msub
- economic data
- mrow
- electric load
- forecast
- 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 31
- 230000005611 electricity Effects 0.000 claims abstract description 28
- 238000004445 quantitative analysis Methods 0.000 claims abstract description 8
- 238000010248 power generation Methods 0.000 claims description 12
- 238000012417 linear regression Methods 0.000 claims description 10
- 230000002596 correlated effect Effects 0.000 claims description 7
- 238000010219 correlation analysis Methods 0.000 claims description 4
- 230000000875 corresponding effect Effects 0.000 claims description 3
- 238000009795 derivation Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000013277 forecasting method Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- 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
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Mathematical Optimization (AREA)
- General Business, Economics & Management (AREA)
- Pure & Applied Mathematics (AREA)
- Operations Research (AREA)
- Mathematical Analysis (AREA)
- Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Water Supply & Treatment (AREA)
- Algebra (AREA)
- Public Health (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a kind of Methods of electric load forecasting based on economic data, including the selected economic data parameter related to load forecast;Relation between each economic data parameter of quantitative analysis and electricity consumption;Electric load is predicted using a variety of forecast models;Calculate the respective weighted value of various forecast models;Calculate final Electric Load Forecasting measured value.The present invention passes through the load forecasting method to type, electric load is predicted based on economic data, and the final load forecast result based on economic data is obtained with reference to all kinds of load prediction results using the method for science, therefore the inventive method more accurately can be predicted than existing single load forecasting method to electric load, and precision of prediction is high, implementation result is good.
Description
Technical field
Present invention relates particularly to a kind of Methods of electric load forecasting based on economic data.
Background technology
With the development and the improvement of people's living standards of national economy technology, electric energy has become people's production and life
One of essential secondary energy sources in work, the production and living to people bring endless facility.
It is the important mark for weighing a national economy development degree exactly because electric power is the mainstay of the national economy and basis
One of will, therefore in general electricity consumption is closely related with economic development.On the one hand, when supply of electric power deficiency, economy hair
Exhibition will be restricted.On the other hand, economic development is the power of electric power development, will drive the growth of electricity consumption.When economy is sent out
When putting on display existing crisis, electricity consumption will also be suppressed by certain so, influence of the research macroeconomy to electricity consumption has
Significance.
The theoretical research of electric power demand forecasting starts from 20 middle of century, and a series of Forecasting Methodologies are applied to electricity needs
In prediction.At present, the main models of electric power demand forecasting have regression model, elastic coefficient model, time series models, output value list
Consume model etc..But the difference of the characteristics of due to each forecast model and the complexity of electric load, the prediction result of each method
Often being greatly differed from each other apart from real network load, its precision of prediction does not often reach the requirement of actual electric network load prediction, because
This seriously constrains the development of power network.
The content of the invention
High, the good electric load based on economic data of implementation result it is an object of the invention to provide a kind of precision of prediction
Forecasting Methodology.
This Methods of electric load forecasting based on economic data provided by the invention, comprises the following steps:
S1. the economic data parameter related to load forecast is selected;
S2. the relation between each economic data parameter selected quantitative analysis step S1 and electricity consumption;
S3. X kind forecast models are used, the economic data parameter selected according to step S1, electric load are predicted, institute
It is the natural number not less than 2 to state X;
S4. each economic data obtained according to the prediction result of the obtained each forecast models of step S3 and step S2 is joined
Relation between number and electricity consumption, calculate the respective weighted value of X kind forecast models;
S5. the X kind forecast models obtained according to the obtained weighted values of step S4 and step S3 predict obtained electric load
Prediction result, calculate final Electric Load Forecasting measured value.
Economic data parameter described in step S1, power system investment is specifically included, price data, demographic data, is occupied
People's consumption index and the industrial consumption index.
The relation between each economic data parameter and electricity consumption described in step S2, specially using correlation analysis
Relation between each economic data parameter of theoretical quantitative analysis and electricity consumption.
Using between each economic data parameter of correlation analysis theory quantitative analysis and electricity consumption described in step S2
Relation, the relation between each economic data parameter and electricity consumption is specially calculated using following formula:
Pearson correlation coefficients of the r between economic data parameter x and electricity consumption y in formula, n are natural number;And if r>0
Represent x and y positive correlations, r<0 represents that x and y is negatively correlated;| r | < 0.3 shows between x and y without linear relationship;0.3≤|r|
< 0.5 represents that x and y is lower correlation;0.5≤| r | < 0.8 is that moderate is related;0.8≤| r | < 1 is highly correlated:| r |=1
To be perfectly correlated.
Forecast model described in step S3, including Linear Regression Model in One Unknown, elastic coefficient model, time series are linear
Model and grey forecasting model.
Described use Linear Regression Model in One Unknown is predicted to electric load, is specially carried out using following steps pre-
Survey:
A. data (x is observed to n groups samplei,yi) setting model;
Y=a+bx+ ε
ε~N (0, σ in formula2), and parameter a, b and σ are parameter to be estimated;
B. parameter must be estimated with least square methodWithSo as to obtain equations of linear regression of the y to x
C. the model obtained to step B carries out hypothesis testing and corrected;
D. to given future position x=x0, under confidence level (1- α), obtain corresponding predicted valueAnd it is calculated
Prediction confidence intervals and prediction standard deviation;Described α value is 0.2.
Described is predicted using elastic coefficient model to electric load, is specially predicted using following steps:
A. the predicted value of known power generation coefficient of elasticity is β, and the average growth rate per annum of gross national product is in time span of forecast
αk, then using the average growth rate per annum α of following formula calculating power generationp
αp=β * αk
B. the electric power and electricity needed for project period are predicted using equation below:
Wt=Wo(1+βαk)t
W in formulatThe electric power and unit needed for project period is ten thousand kWh, WoBased on year actual power generation and unit be
The power generation coefficient of elasticity that kWh, β use for project period, αkFor the gross national product average growth rate per annum that project period is estimated, t
Based on year to plan year year.
The respective weighted value of calculating X kind forecast models described in step S4, specially calculates weighted value in the following way:
At any time, the variance of each forecast model is for I settingEach economic data parameter and electric power
The coefficient correlation of demand is r1,r2,r3,r4, the weight of each forecast model is k1,k2,k4,k4, then using following formula calculating group
Close the variance δ of prediction result2:
K in formula1+k2+k3+k4=1, ρ12、ρ23、ρ34、ρ14、ρ24And ρ13It is the coefficient correlation of forecast model two-by-two respectively,
Variance δ in II pair of step I2Formula respectively to k1,k2,k4,k4Derivation and make its be 0, so as to obtain each prediction
The weighted value k of model1,k2,k4,k4。
Final Electric Load Forecasting measured value is calculated described in step S5, is specially calculated most using linear weighted function average algorithm
Whole Electric Load Forecasting measured value.
This Methods of electric load forecasting based on economic data provided by the invention, passes through the load prediction side to type
Method, electric load is predicted based on economic data, and obtained using the method for science with reference to all kinds of load prediction results
To the final load forecast result based on economic data, therefore the inventive method is than existing single load prediction side
Method more accurately can be predicted to electric load, and precision of prediction is high, and implementation result is good.
Brief description of the drawings
Fig. 1 is the method flow diagram of the inventive method.
Embodiment
It is the method flow diagram of the inventive method as shown in Figure 1:This electric power based on economic data provided by the invention
Load forecasting method, comprise the following steps:
S1. the economic data parameter related to load forecast is selected, specifically includes power system investment, price number
According to, demographic data, consumption of resident index and the industrial consumption index etc.;
S2. it is using the correlation analysis theory quantitative analysis step S1 each economic data parameters selected and electricity consumption
Between relation, the relation between each economic data parameter and electricity consumption is specially calculated using following formula:
Pearson correlation coefficients of the r between economic data parameter x and electricity consumption y, n=10 in formula;And if r>0 represents
X and y positive correlations, r<0 represents that x and y is negatively correlated;| r | < 0.3 shows between x and y without linear relationship;0.3≤| r | < 0.5
Expression x and y is lower correlation;0.5≤| r | < 0.8 is that moderate is related;0.8≤| r | < 1 is highly correlated:| r |=1 is complete
It is related;
S3. X kind forecast models are used, the economic data parameter selected according to step S1, electric load are predicted, institute
It is the natural number not less than 2 to state X;In the present embodiment, using including Linear Regression Model in One Unknown, elastic coefficient model, time
Including the linear model and grey forecasting model of sequence 4 in forecast model;
Described use Linear Regression Model in One Unknown is predicted to electric load, is specially carried out using following steps pre-
Survey:
A. data (x is observed to n groups samplei,yi) setting model;
Y=a+bx+ ε
ε~N (0, σ in formula2), and parameter a, b and σ are parameter to be estimated;
B. parameter must be estimated with least square methodWithSo as to obtain equations of linear regression of the y to x
C. the model obtained to step B carries out hypothesis testing and corrected;
D. to given future position x=x0, under confidence level (1- α), obtain corresponding predicted valueAnd it is calculated
Prediction confidence intervals and prediction standard deviation;Described α value is 0.2;
Described is predicted using elastic coefficient model to electric load, is specially predicted using following steps:
A. the predicted value of known power generation coefficient of elasticity is β, and the average growth rate per annum of gross national product is in time span of forecast
αk, then using the average growth rate per annum α of following formula calculating power generationp
αp=β * αk
B. the electric power and electricity needed for project period are predicted using equation below:
Wt=Wo(1+βαk)t
W in formulatThe electric power and unit needed for project period is ten thousand kWh, WoBased on year actual power generation and unit be
The power generation coefficient of elasticity that kWh, β use for project period, αkFor the gross national product average growth rate per annum that project period is estimated, t
Based on year to plan year year;
S4. each economic data obtained according to the prediction result of the obtained each forecast models of step S3 and step S2 is joined
Relation between number and electricity consumption, calculate the respective weighted value of X kind forecast models;Weight is specially calculated in the following way
Value:
At any time, the variance of each forecast model is for I settingEach economic data parameter and electric power
The coefficient correlation of demand is r1,r2,r3,r4, the weight of each forecast model is k1,k2,k4,k4, then using following formula calculating group
Close the variance δ of prediction result2:
K in formula1+k2+k3+k4=1, ρ12、ρ23、ρ34、ρ14、ρ24And ρ13It is the coefficient correlation of forecast model two-by-two respectively,
Variance δ in II pair of step I2Formula respectively to k1,k2,k4,k4Derivation and make its be 0, so as to obtain each prediction
The weighted value k of model1,k2,k4,k4;
S5. the X kind forecast models obtained according to the obtained weighted values of step S4 and step S3 predict obtained electric load
Prediction result, final Electric Load Forecasting measured value is calculated using linear weighted function average algorithm, specially carried out using following formula
Calculate:
F=k1f1+k2f2+k3f3+k4f4
The inventive method is further described below in conjunction with a specific embodiment:Table 1 is 1~August lake in 2015
Each city's electric loads of Nan Sheng.
Each city's electric load in 1 2015 years 1~August Hunan Province of table
The present invention using each main cities Power system load data in 1~August Hunan Province in 2015 come verify herein carry economy-
Electric power conducts the accuracy of forecast model, and prediction result is as shown in table 1.The present invention is simultaneously using Linear Regression Model in One Unknown, bullet
Property coefficient model, time series models and grey forecasting model are predicted.Have in table each Individual forecast result and carry through
Ji-electric power conduction forecast model prediction result, it is convenient to compare.
Table 2 is various forecast model relative errors.
The various forecast model relative errors of table 2
It is 961.1 hundred million kilowatt hours, each city or regional electricity consumption that the whole society of 1~August Hunan Province in 2015, which adds up power consumption,
Amount situation respectively has feature.Some urban power consumption are in obvious " industrialization " feature, and some city tertiary industry and resident living
Electricity consumption proportion is larger.Therefore the relative error of every kind of forecast model prediction result respectively has height.Can from above prediction result
Go out, the prediction result for the economy-electric power conduction forecast model that the present invention is carried can be good at approaching actual power consumption, this be because
On the basis of being built upon maximum information utilization for economy-electric power conduction forecast model, it assembles the letter that single model includes
Breath, carry out adaptive optimization combination.
Claims (8)
1. a kind of Methods of electric load forecasting based on economic data, comprises the following steps:
S1. the economic data parameter related to load forecast is selected;
S2. the relation between each economic data parameter selected quantitative analysis step S1 and electricity consumption;
S3. X kind forecast models are used, the economic data parameter selected according to step S1, electric load are predicted, the X
For the natural number not less than 2;
S4. each economic data parameter obtained according to the prediction result of the obtained each forecast models of step S3 and step S2 with
Relation between electricity consumption, calculate the respective weighted value of X kind forecast models;
S5. the X kind forecast models obtained according to the obtained weighted values of step S4 and step S3 predict obtained load forecast
As a result, final Electric Load Forecasting measured value is calculated.
2. the Methods of electric load forecasting according to claim 1 based on economic data, it is characterised in that described in step S1
Economic data parameter, specifically include power system investment, price data, demographic data, consumption of resident index and industry disappear
Take index.
3. the Methods of electric load forecasting according to claim 2 based on economic data, it is characterised in that described in step S2
Quantitative analysis economic data parameter and electricity consumption between relation, for use each warp of correlation analysis theory quantitative analysis
Relation between data parameters of helping and electricity consumption, each economic data parameter is specially calculated using following formula and disappeared with electric power
Relation between taking:
<mrow>
<mi>r</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mi>n</mi>
<mi>&Sigma;</mi>
<mi>x</mi>
<mi>y</mi>
<mo>-</mo>
<mi>&Sigma;</mi>
<mi>x</mi>
<mi>&Sigma;</mi>
<mi>y</mi>
</mrow>
<mrow>
<msqrt>
<mrow>
<msup>
<mi>n&Sigma;x</mi>
<mn>2</mn>
</msup>
<mo>-</mo>
<msup>
<mrow>
<mo>(</mo>
<mi>&Sigma;</mi>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<msqrt>
<mrow>
<msup>
<mi>n&Sigma;y</mi>
<mn>2</mn>
</msup>
<mo>-</mo>
<msup>
<mrow>
<mo>(</mo>
<mi>&Sigma;</mi>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mrow>
</mfrac>
</mrow>
Pearson correlation coefficients of the r between economic data parameter x and electricity consumption y in formula, n are natural number;And if r>0 represents
X and y positive correlations, r<0 represents that x and y is negatively correlated;| r | < 0.3 shows between x and y without linear relationship;0.3≤| r | < 0.5
Expression x and y is lower correlation;0.5≤| r | < 0.8 is that moderate is related;0.8≤| r | < 1 is highly correlated:| r |=1 is complete
It is related.
4. the Methods of electric load forecasting according to claim 3 based on economic data, it is characterised in that described in step S3
Forecast model, including the linear model of Linear Regression Model in One Unknown, elastic coefficient model, time series and gray prediction mould
Type.
5. the Methods of electric load forecasting according to claim 4 based on economic data, it is characterised in that described use
Linear Regression Model in One Unknown is predicted to electric load, is specially predicted using following steps:
A. data (x is observed to n groups samplei,yi) setting model;
Y=a+bx+ ε
ε~N (0, σ in formula2), and parameter a, b and σ are parameter to be estimated;
B. parameter must be estimated with least square methodWithSo as to obtain equations of linear regression of the y to x
C. the model obtained to step B carries out hypothesis testing and corrected;
D. to given future position x=x0, under confidence level (1- α), obtain corresponding predicted valueAnd it is calculatedIt is pre-
Survey confidential interval and prediction standard deviation;Described α value is 0.2.
6. the Methods of electric load forecasting according to claim 4 based on economic data, it is characterised in that described use
Elastic coefficient model is predicted to electric load, is specially predicted using following steps:
A. the predicted value of known power generation coefficient of elasticity is β, and the average growth rate per annum of gross national product is α in time span of forecastk, then
The average growth rate per annum α of power generation is calculated using following formulap
αp=β * αk
B. the electric power and electricity needed for project period are predicted using equation below:
Wt=Wo(1+βαk)t
W in formulatThe electric power and unit needed for project period is ten thousand kWh, WoBased on year actual power generation and unit be kWh, β
The power generation coefficient of elasticity used for project period, αkFor the gross national product average growth rate per annum that project period is estimated, based on t
The year in year to planning year.
7. the Methods of electric load forecasting according to claim 4 based on economic data, it is characterised in that described in step S4
The respective weighted value of calculating X kind forecast models, specially calculate weighted value in the following way:
At any time, the variance of each forecast model is for I settingEach economic data parameter and electricity needs
Coefficient correlation be r1,r2,r3,r4, the weight of each forecast model is k1,k2,k4,k4, then it is pre- combination to be calculated using following formula
Survey the variance δ of result2:
<mfenced open = "" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msup>
<mi>&delta;</mi>
<mn>2</mn>
</msup>
<mo>=</mo>
<msub>
<mi>k</mi>
<mn>1</mn>
</msub>
<msub>
<mi>r</mi>
<mn>1</mn>
</msub>
<msubsup>
<mi>&delta;</mi>
<mn>1</mn>
<mn>2</mn>
</msubsup>
<mo>+</mo>
<msub>
<mi>k</mi>
<mn>2</mn>
</msub>
<msub>
<mi>r</mi>
<mn>2</mn>
</msub>
<msubsup>
<mi>&delta;</mi>
<mn>2</mn>
<mn>2</mn>
</msubsup>
<mo>+</mo>
<msub>
<mi>k</mi>
<mn>3</mn>
</msub>
<msub>
<mi>r</mi>
<mn>3</mn>
</msub>
<msubsup>
<mi>&delta;</mi>
<mn>3</mn>
<mn>2</mn>
</msubsup>
<mo>+</mo>
<msub>
<mi>k</mi>
<mn>4</mn>
</msub>
<msub>
<mi>r</mi>
<mn>4</mn>
</msub>
<msubsup>
<mi>&delta;</mi>
<mn>4</mn>
<mn>2</mn>
</msubsup>
<mo>+</mo>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mn>2</mn>
<msub>
<mi>&rho;</mi>
<mn>12</mn>
</msub>
<msub>
<mi>k</mi>
<mn>1</mn>
</msub>
<msub>
<mi>k</mi>
<mn>2</mn>
</msub>
<mo>+</mo>
<mn>2</mn>
<msub>
<mi>&rho;</mi>
<mn>23</mn>
</msub>
<msub>
<mi>k</mi>
<mn>2</mn>
</msub>
<msub>
<mi>k</mi>
<mn>3</mn>
</msub>
<mo>+</mo>
<mn>2</mn>
<msub>
<mi>&rho;</mi>
<mn>34</mn>
</msub>
<msub>
<mi>k</mi>
<mn>3</mn>
</msub>
<msub>
<mi>k</mi>
<mn>4</mn>
</msub>
<mo>+</mo>
<mn>2</mn>
<msub>
<mi>&rho;</mi>
<mn>14</mn>
</msub>
<msub>
<mi>k</mi>
<mn>1</mn>
</msub>
<msub>
<mi>k</mi>
<mn>4</mn>
</msub>
<mo>+</mo>
<mn>2</mn>
<msub>
<mi>&rho;</mi>
<mn>24</mn>
</msub>
<msub>
<mi>k</mi>
<mn>2</mn>
</msub>
<msub>
<mi>k</mi>
<mn>4</mn>
</msub>
<mo>+</mo>
<mn>2</mn>
<msub>
<mi>&rho;</mi>
<mn>13</mn>
</msub>
<msub>
<mi>k</mi>
<mn>1</mn>
</msub>
<msub>
<mi>k</mi>
<mn>3</mn>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
K in formula1+k2+k3+k4=1, ρ12、ρ23、ρ34、ρ14、ρ24And ρ13It is the coefficient correlation of forecast model two-by-two respectively,
Variance δ in II pair of step I2Formula respectively to k1,k2,k4,k4Derivation and make its be 0, so as to obtain each forecast model
Weighted value k1,k2,k4,k4。
8. the Methods of electric load forecasting according to claim 7 based on economic data, it is characterised in that described in step S5
The final Electric Load Forecasting measured value of calculating, final load forecast is specially calculated using linear weighted function average algorithm
Value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710685610.3A CN107423862A (en) | 2017-08-11 | 2017-08-11 | Methods of electric load forecasting based on economic data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710685610.3A CN107423862A (en) | 2017-08-11 | 2017-08-11 | Methods of electric load forecasting based on economic data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107423862A true CN107423862A (en) | 2017-12-01 |
Family
ID=60437858
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710685610.3A Pending CN107423862A (en) | 2017-08-11 | 2017-08-11 | Methods of electric load forecasting based on economic data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107423862A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108491969A (en) * | 2018-03-16 | 2018-09-04 | 国家电网公司 | Spatial Load Forecasting model building method based on big data |
CN110705720A (en) * | 2019-08-07 | 2020-01-17 | 广州朗道信息科技有限公司 | Vehicle push repairing method and system based on vehicle-to-commercial insurance ratio |
CN111784019A (en) * | 2019-12-26 | 2020-10-16 | 国网北京市电力公司 | Power load processing method and device |
CN113869687A (en) * | 2021-09-18 | 2021-12-31 | 深圳供电局有限公司 | Method and device for analyzing power load component index, computer equipment and medium |
-
2017
- 2017-08-11 CN CN201710685610.3A patent/CN107423862A/en active Pending
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108491969A (en) * | 2018-03-16 | 2018-09-04 | 国家电网公司 | Spatial Load Forecasting model building method based on big data |
CN108491969B (en) * | 2018-03-16 | 2021-12-24 | 国家电网公司 | Big data-based space load prediction model construction method |
CN110705720A (en) * | 2019-08-07 | 2020-01-17 | 广州朗道信息科技有限公司 | Vehicle push repairing method and system based on vehicle-to-commercial insurance ratio |
CN111784019A (en) * | 2019-12-26 | 2020-10-16 | 国网北京市电力公司 | Power load processing method and device |
CN111784019B (en) * | 2019-12-26 | 2024-08-06 | 国网北京市电力公司 | Power load processing method and device |
CN113869687A (en) * | 2021-09-18 | 2021-12-31 | 深圳供电局有限公司 | Method and device for analyzing power load component index, computer equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107423862A (en) | Methods of electric load forecasting based on economic data | |
Kim et al. | LSTM based short-term electricity consumption forecast with daily load profile sequences | |
CN102722759B (en) | Method for predicting power supply reliability of power grid based on BP neural network | |
WO2017054537A1 (en) | Long-time scale photovoltaic output time sequence modelling method and apparatus | |
CN110210993B (en) | Urban short-term gas load prediction method based on cyclic neural network model | |
Phuangpornpitak et al. | A study of load demand forecasting models in electric power system operation and planning | |
CN102129511B (en) | System for forecasting short-term wind speed of wind power station based on MATLAB | |
CN107862466A (en) | The source lotus complementary Benefit Evaluation Method spanning space-time of consideration system bilateral randomness | |
CN109978242A (en) | The photovoltaic power generation cluster power forecasting method and device of scale are risen based on statistics | |
CN107563565A (en) | A kind of short-term photovoltaic for considering Meteorology Factor Change decomposes Forecasting Methodology | |
CN105160423A (en) | Photovoltaic power generation prediction method based on Markov residual error correction | |
CN103853939A (en) | Combined forecasting method for monthly load of power system based on social economic factor influence | |
CN105608333B (en) | A kind of meteorological sensitive electricity method for digging for considering multizone difference | |
CN101976301A (en) | Method and device for preprocessing historical data in yearly load forecasting | |
CN105846425A (en) | Economic dispatching method based on general wind power forecasting error model | |
CN106611243A (en) | Residual correction method for wind speed prediction based on GARCH (Generalized ARCH) model | |
CN104598998A (en) | Energy demand forecasting method based on economic growth indicators | |
CN109492818A (en) | Based on energy development and the entitled electricity demand forecasting method of Shapley value | |
CN103679289B (en) | Methods of electric load forecasting based on multiple regression extrapolation | |
CN110969312A (en) | Short-term runoff prediction coupling method based on variational modal decomposition and extreme learning machine | |
CN110751327A (en) | Long-term load combination prediction method based on multiple linear regression and gray Verhulst model | |
CN109063924A (en) | Power distribution network based on meteorological data repairs work order quantitative forecasting technique | |
CN107748931A (en) | A kind of income of electricity charge Forecasting Methodology based on least square method | |
CN105279582B (en) | Super short-period wind power prediction technique based on dynamic correlation feature | |
CN104200283B (en) | A kind of long-medium term power load forecasting method based on factor primary attribute model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171201 |
|
WD01 | Invention patent application deemed withdrawn after publication |