CN109359780A - A kind of electricity consumption of resident prediction technique based on electrification index - Google Patents
A kind of electricity consumption of resident prediction technique based on electrification index Download PDFInfo
- Publication number
- CN109359780A CN109359780A CN201811367413.8A CN201811367413A CN109359780A CN 109359780 A CN109359780 A CN 109359780A CN 201811367413 A CN201811367413 A CN 201811367413A CN 109359780 A CN109359780 A CN 109359780A
- Authority
- CN
- China
- Prior art keywords
- resident
- electricity consumption
- electrical appliance
- household electrical
- electrification
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The present invention relates to a kind of electricity consumption of resident prediction techniques based on electrification index, comprising the following steps: 1) counts the equal ownership N of one hundred houses of main household electrical applianceiWith mean power Pi；2) the use duration for obtaining household electrical appliance, calculates various household electrical appliance frequency factors；3) the modifying factor λ of household electrical appliance is calculatedi；4) electrified index HEA is calculated；5) multiple linear regression model is constructed, by electrification index HEA, the total amount A of residentjWith per capita disposable income BjAs the input of multiple linear regression model, electricity consumption of resident YjIt is trained as output valve, and electricity consumption of resident prediction is carried out according to trained multiple linear regression model.Compared with prior art, the present invention has many advantages, such as to comprehensively consider, correlation is high, accurate effective.
Description
Technical field
The present invention relates to electricity consumption of resident predictions, predict more particularly, to a kind of electricity consumption of resident based on electrification index
Method.
Background technique
The factor for influencing electricity consumption of resident is varied, including disposable household income, construction area size, residential area gas
Time, household size, household electrical appliances hold rate and utilization rate, family life habit and policy propaganda etc..Household electrical appliance are used as resident
The load of electricity, ownership are the biggest factors for influencing electricity consumption of resident.However effective ownership of household electrical appliance lacks unification
Evaluation criterion can not be compared effectively between different household electrical appliance, if relying on power and comparison merely, ignore household electrical appliance
Frequency of use and use duration are then excessively unilateral.When carrying out electricity consumption of resident prediction, when with the ownership of household electrical appliance and use
Between be used as principal element, lack feasible method quantified.It realizes accurately and effectively electricity consumption of resident prediction, needs from household
The ownership of electric appliance and considered comprehensively using the time.
For influence of effective ownership for electricity consumption of resident of household electrical appliance, many domestic and foreign scholars propose oneself
Viewpoint.Yan Yan thinks that the variation of household electrical appliance quantity will be direct in " the long phase surveys Subcommittee-to in advance and studies carefully in residents in Beijing domestic load "
Lead to the variation of resident living power utility amount, the quantity of household electrical appliance and the income level of resident are related.By household electrical appliance number in text
Amount is used as variable, calculates the ownership of all kinds of household electrical appliance and the degree of association of electricity consumption of resident, using grey correlation with the degree of association
Greater than 0.9 factor as one of all kinds of key factors, Beijing's domestic load is predicted.Li Fengyuan is in " residential electric power load
Analysis " in be divided into three classes household electrical appliance according to household electrical appliance popularity, propose to calculate house by household electrical appliance popularity rate every
The formula of family Calculation of electric charge capacity.But each household house household electrical appliance purchasing and using there is very big uncertainty, should
Algorithm is but difficult to carry out in the design although theoretically setting up.Su Ming etc. is in " the East China Si Sheng mono- based on Logit model
City's resident living power utility forecasting research " in discovery household electrical appliance quantity have saturation value, according to year Household Appliance amount and shine
Bright electricity consumption acquires representative household electricity feature.It is proposed household electrical appliance mainly includes watt level and use frequency with electrical feature
Rate, but this with electrical feature only from electricity angle, can not be as a kind of index as reference pair future power quantity predicting.Beam
Is intelligent virtue equal " China's residential electricity consumption mode is consistent with novel urbanization requirement? --- it is set based on urban household electricity consumption
Standby and electricity consumption situation positive research " in using polynary preference pattern building residential households household electrical appliance purchase decision polynary choosing
Model is selected, estimates the saturation value of all kinds of household electrical appliance ownerships, and estimates the potential electricity consumption of household electrical appliance on the basis of this again.But
This method is ignored with social development, and various household electric appliance power variations, frequency of use change the change with annual utilization hours
Change, therefore there are large errors for the potential electricity consumption estimation of household electrical appliance.
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 referred to based on electrification
Several electricity consumption of resident prediction techniques.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of electricity consumption of resident prediction technique based on electrification index, comprising the following steps:
1) the equal ownership N of one hundred houses of main household electrical appliance is countediWith mean power Pi；
2) the use duration for obtaining household electrical appliance, calculates various household electrical appliance frequency factors；
3) the modifying factor λ of household electrical appliance is calculatedi；
4) electrified index HEA is calculated；
5) multiple linear regression model is constructed, by electrification index HEA, the total amount A of residentjWith per capita disposable income Bj
As the input of multiple linear regression model, electricity consumption of resident YjIt is trained as output valve, and according to trained polynary
Linear regression model (LRM) carries out electricity consumption of resident prediction.
In the step 1), the household electrical appliance that mean power is less than 40W are ignored in statistics.
In the step 2), i-th kind of household electrical appliance frequency factor fiCalculating formula are as follows:
Wherein, hiFor the annual utilization hours of household electrical appliance.
In the step 3), modifying factor λiCalculating formula are as follows:
λi=λi1λi2
Wherein, λi1For the modifying factor of power, λi2For the modifying factor of frequency factor.
In the step 4), the calculating formula of electrified index HEA are as follows:
Wherein, n is the type sum of household electrical appliance.
In the step 5), the expression formula of multiple linear regression model are as follows:
Yj=θ0+θ1Aj+θ2Bj+θ3HEAj
Wherein, the subscript j expression of years, θ0For constant term, θ1、θ2、θ3For regression coefficient.
The step 4) is further comprising the steps of:
The relative coefficient r between electrification index HEA and electricity consumption of resident Y is calculated according to Pearson correlation coefficient
(HEA, Y), to indicate the related intimate degree of electrification index and electricity consumption of resident, the relative coefficient r (HEA, Y)
Calculating formula are as follows:
Compared with prior art, the invention has the following advantages that
The present invention proposes that a kind of household electrical appliance effectively possess the module of degree --- electrification index, while utilizing should
Exponent pair electricity consumption of resident is predicted.Ownership, rated power and the frequency of use of electrification exponent pair household electrical appliance into
It has gone and has comprehensively considered, which can effectively possess the standard of degree as resident's household electrical appliance, to judge residential households electric appliance
The size of change degree, to reflect the height of Living consumption.Electrification index and electricity consumption of resident have high simultaneously
Correlation can be used as the important evidence of electricity consumption of resident prediction.Electrification index is used for electricity consumption of resident prediction, can be improved
The accuracy and validity of electricity consumption of resident prediction result.
Detailed description of the invention
The city Tu1Wei Mou electrification index over the years.
Fig. 2 is flow chart of the method for the present invention.
Description of symbols in figure:
Specific embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.
As shown in Fig. 2, the invention proposes a kind of calculation method of electrification index and to be used for electricity consumption of resident pre-
It surveys, comprises the following specific steps that:
It investigates the ownership and power of main household electrical appliance: being protected by one hundred houses that statistical yearbook investigates main household electrical appliance
The amount of having Ni, wherein i=1,2 ..., n, represent the type of household electrical appliance, such as air-conditioning, refrigerator.Consult each main household electrical appliance
Power calculates the mean power P of each main household electrical appliancei, mean power is less than the household electrical appliance of 40W, due to residential electricity consumption
The contribution of amount is smaller, can ignore when being calculated.
2) calculate household electrical appliance frequency factor: different household electrical appliance use the time uneven, such as making for winter in air-conditioning summer
It is apparently higher than spring and autumn with frequency, takes short cycle to calculate household electrical appliance frequency factor and does not have representativeness, therefore walked using family
The form for visiting investigation obtains the use duration of household electrical appliance, and the year for handling Data Integration to obtain household electrical appliance using the time, presses
Various household electrical appliance frequency factor f are calculated according to formula (1)i。
In formula, hiFor the annual utilization hours of household electrical appliance.
3) calculate the modifying factor of household electrical appliance: household electrical appliance develop towards multifunction, energy-saving with the improvement of technology,
The household electric appliance power of different times is different.But the replacement of household electrical appliance gradually carries out, and can not carry out electrification index
The calculation method of single solution for diverse problems, therefore propose the concept of power correction factor.With the raising and living standard of income level of resident
Promotion, the frequency of use of household electrical appliance is also continuously increased, the modifying factor of the frequency of use factor to frequency of use over the years into
Row amendment.According to formula (2), total modifying factor λ is calculated using the modifying factor of power and the modifying factor of frequency factori。
λi=λi1λi2 (2)
In formula, λi1For the modifying factor of power, λi2For the modifying factor of frequency factor.
4) calculate electrification index: according to step 1) to step 3), one hundred houses that various household electrical appliance are calculated are possessed
Measure Ni, mean power Pi, frequency factor fi, modifying factor λi, electrification index is calculated according to formula (3).
In formula, HEA is electrification index, and n is the species number of household electrical appliance.
5) correlation analysis: the phase between electrification index HEA and electricity consumption of resident Y is calculated using Pearson correlation coefficient
Property coefficient is closed, the related intimate degree of electrification index and electricity consumption of resident is calculated according to formula (4).
In formula, Cov (HEA, Y) is the covariance of HEA and Y, and Var [HEA] is the variance of HEA, and Var [Y] is the variance of Y.
6) electricity consumption of resident is predicted: selection prediction model, will be by electrification index that formula (3) are calculated as it
In an input parameter, predict the following electricity consumption of resident.Illustrate this step by taking Multiple Linear Regression Forecasting Models of Chinese as an example below.
In Multiple Linear Regression Forecasting Models of Chinese, the total amount A of certain city resident is selectedj, per capita disposable income Bj, electrification
Index HEAjAs input parameter, certain city electricity consumption of resident YjIt is trained as output valve, wherein j represents the time.Multiple linear
Shown in regression model such as formula (5),
Yj=θ0+θ1Aj+θ2Bj+θ3HEAj (5)
In formula, θ0For constant term, θ1、θ2、θ3For regression coefficient.
The total amount of the resident that need to predict the time, per capita disposable income, electrification exponent data value are input to and are trained
Model, the predicted value of the city the Nian Mou electricity consumption of resident can be obtained.
7) prediction result is evaluated: the electricity consumption of resident predicted value according to obtained in step 6) combines this year practical residential electricity consumption
Amount, according to formula (6), (7), the city Qiu Mou electricity consumption of resident is predicted respectively absolute error and error rate.
Δ Y=| YPredicted value-YActual value| (6)
In formula, Δ Y is absolute error, and δ (Y) is error rate, YPredicted valueFor electricity consumption of resident predicted value, YActual valueFor practical resident
Electricity consumption.
The accuracy of prediction technique is evaluated by absolute error and error rate, absolute error and error rate are smaller then
Prove that prediction result is more accurate.
Embodiment:
1) ownership and power of main household electrical appliance are investigated
The equal ownership N of one hundred houses for investigating main household electrical appliance by statistical yearbooki, consult the function of each main household electrical appliance
Rate calculates the mean power P of each main household electrical appliancei, the results are shown in Table 1.Wherein, recorder, recording playback camera, video disc player,
Video camera, mobile phone constant power are less than 40W, smaller to the contribution of electricity consumption of resident, can ignore when being calculated.
The main equal ownership of household electrical appliance one hundred houses in certain city of table 1
2) household electrical appliance frequency factor is calculated
Different household electrical appliance are obtained by way of investigating home visit uses the time, integrates to investigation result
Processing, the year for obtaining each main household electrical appliance use time parameter.It is as shown in table 2 that investigation obtains air conditioning usage time in 2016,
By the time within 2 hours by 1 hour calculate, 2-4 hour according to 3 hours calculating, and so on, thereafter the period according to 6 hours,
It calculates within 10 hours, 12 hours or more whens were then calculated according to 14 hours, when being used with the air-conditioning in 3 months summers, 2 months winters
Between, it obtains:
h1=(1 × 0.03+3 × 0.11+6 × 0.28+10 × 0.39+14 × 0.19) × 30 × 5=1290；
Non-stop run among refrigerator 1 year, year are 8760 hours using the time.
2 air-conditioning of table uses time investigation result table using day
Frequency factor is calculated separately according to formula (1).
Wherein, i=1 represents the household electrical appliance as air-conditioning, and i=2 represents the household electrical appliance as refrigerator.
3) modifying factor of household electrical appliance is calculated
For different household electrical appliance, the subclassification market accounting of each household electrical appliance over the years is obtained, determines the amendment of its power
The factor.By taking air-conditioning as an example, according to " 2017-2022 China convertible frequency air-conditioner market supply and demand prediction and strategic investment report ", 2010
Year convertible frequency air-conditioner accounting 30% or so, convertible frequency air-conditioner ratio in 2016 increases to 65.57%, annual average rate of increase 5.93%.It is assumed that
Convertible frequency air-conditioner electricity consumption is the 80% of fixed frequency air conditioner electricity consumption.Then modifying factor of the air-conditioning in 2015 relative to its power in 2016
λ11=0.8 × (0.6557-0.0593)+1 × [1- (0.6557-0.0593)]=0.880,
Air conditioning usage time is horizontal related to per capita income, consults certain city's statistical yearbook over the years and obtains 2015 cities Nian Mou per capita
Disposable income is 49867.2 yuan, 2017 54305.3 yuan, growth rate 8.90%, air-conditioning using the time and can propping up per capita
It is positively correlated with income, if growth rate of the air conditioning usage time from 2015 to 2016 year is also 8.90%, then air-conditioning phase in 2015
For the modifying factor of frequency factor in 2016
λ12=1/ (1+0.089)=0.918.
According to formula (2), total modifying factor is calculated using the modifying factor of power and the modifying factor of frequency factor, is obtained
To air-conditioning in 2015 relative to modifying factor in 2016
λ1=λ11λ12=0.880 × 0.918=0.808.
4) electrification index is calculated
The equal ownership N of one hundred houses according to the household electrical appliance that step 1) obtains certain yeari, mean power PiAnd step 2) obtains
Frequency factor fi, modifying factor λ that step 3) obtainsi, this year electrification index is calculated according to formula (3).For 2016,
This year electrification index is acquired by following formula.
HEA2016=197 × 1500 × 0.1473 × 1+183 × 100 × 0.22 × 1+99 × 140 × 1 × 1+93 × 400
×0.013×1+78×200×0.16×1+87×800×0.02×1+93×1500×0.24×1+131×300×0.17
× 1=105945.75
According to the calculation method of electrification index in 2016,2000 to 2015 electrification indexes are found out respectively, are counted
It is as shown in Figure 1 to calculate result.
5) correlation analysis
Certain city that step 4) is obtained electrification index HEA over the years and corresponding certain city electricity consumption of resident Y, utilize Pearson came phase
Relationship number, i.e. formula (4) calculate its correlation.Obtained relative coefficient is 0.997, it is seen that the variation tendency of the two is close,
Relevance is very strong.
6) electricity consumption of resident is predicted
Certain city's electricity consumption of resident is predicted using Multiple Linear Regression Forecasting Models of Chinese by summary of the invention step 6).Selection
Training set of the data as model before 2015,2015 with 2016 annual datas as test set, with detection model accuracy.
The total amount A of certain city resident over the yearsj, per capita disposable income Bj, electrification index HEAjAs input parameter, certain city resident
Electricity consumption YjAs target, the training and prediction of Multiple Linear Regression Forecasting Models of Chinese are carried out.
2015 city Nian Mou electricity consumption of resident, 184.191 hundred million kilowatt hour, 2016 city Nian Mou residents are obtained by the model prediction
212.489 hundred million kilowatt hour of electricity consumption.
7) prediction result is evaluated
2015 and the 2016 practical electricity consumption of resident in the city Nian Mou are 185.49 hundred million kilowatt hours and 217.72 hundred million kilowatt hours.According to
Formula (6) and formula (7) can respectively obtain the absolute error and error rate of prediction result of the present invention, as shown in table 3.
3 prediction result errors table of table
| Absolute error | Error rate | |
| 2015 | 1.299 hundred million kilowatt hours | 0.7% |
| 2016 | 5.231 hundred million kilowatt hours | 2.4% |
As shown in Table 3, prediction result of the invention accuracy with higher.
The present invention is directed to the forecasting problem of electricity consumption of resident, proposes the concept and its calculation method of electrification index.It is first
Quantity first is carried out to main household electrical appliance and its power is investigated, each household electrical appliance are then calculated using the time according to year
Frequency factor, development and per capita disposable income level according to household electrical appliance find out modifying factor, utilize above-mentioned factor
Electrification index is calculated.Correlation analysis is carried out to electrification index and electricity consumption of resident, it is non-to obtain its relative coefficient
Chang Gao.Finally the input parameter using electrification index as electricity consumption of resident is input to prediction model, obtains electricity consumption of resident
Predicted value.
The present invention clearly proposes the concept of electrification index, and electrification index can measure effective guarantor of home household appliance
There is degree, to judge the size of residential households electrification degree, reflects the height of Living consumption.Electrification index and resident
Electricity consumption has high correlation, can be used as the important references factor of electricity consumption of resident prediction, and comparison discovery utilizes electrification
The electricity consumption of resident predicted value ratio that exponential forecasting obtains utilizes household electrical appliance quantitative forecast result closer to true value.Electrification refers to
Several propositions plays an important role to the accuracy and validity that improve electricity consumption of resident prediction result.The present invention can be not only used for
Electricity consumption of resident prediction can also extend to the prediction of society's electricity consumption amount.
Claims (7)
1. a kind of electricity consumption of resident prediction technique based on electrification index, which comprises the following steps:
1) the equal ownership N of one hundred houses of main household electrical appliance is countediWith mean power Pi；
2) the use duration for obtaining household electrical appliance, calculates various household electrical appliance frequency factors；
3) the modifying factor λ of household electrical appliance is calculatedi；
4) electrified index HEA is calculated；
5) multiple linear regression model is constructed, by electrification index HEA, the total amount A of residentjWith per capita disposable income BjAs
The input of multiple linear regression model, electricity consumption of resident YjIt is trained as output valve, and according to trained multiple linear
Regression model carries out electricity consumption of resident prediction.
2. a kind of electricity consumption of resident prediction technique based on electrification index according to claim 1, which is characterized in that institute
In the step 1) stated, the household electrical appliance that mean power is less than 40W are ignored in statistics.
3. a kind of electricity consumption of resident prediction technique based on electrification index according to claim 1, which is characterized in that institute
In the step 2) stated, i-th kind of household electrical appliance frequency factor fiCalculating formula are as follows:
Wherein, hiFor the annual utilization hours of household electrical appliance.
4. a kind of electricity consumption of resident prediction technique based on electrification index according to claim 3, which is characterized in that institute
In the step 3) stated, modifying factor λiCalculating formula are as follows:
λi=λi1λi2
Wherein, λi1For the modifying factor of power, λi2For the modifying factor of frequency factor.
5. a kind of electricity consumption of resident prediction technique based on electrification index according to claim 4, which is characterized in that institute
In the step 4) stated, the calculating formula of electrified index HEA are as follows:
Wherein, n is the type sum of household electrical appliance.
6. a kind of electricity consumption of resident prediction technique based on electrification index according to claim 5, which is characterized in that institute
In the step 5) stated, the expression formula of multiple linear regression model are as follows:
Yj=θ0+θ1Aj+θ2Bj+θ3HEAj
Wherein, the subscript j expression of years, θ0For constant term, θ1、θ2、θ3For regression coefficient.
7. a kind of electricity consumption of resident prediction technique based on electrification index according to claim 1, which is characterized in that institute
The step 4) stated is further comprising the steps of:
The relative coefficient r (HEA, Y) between electrification index HEA and electricity consumption of resident Y is calculated according to Pearson correlation coefficient,
To indicate the related intimate degree of electrification index and electricity consumption of resident, the calculating formula of the relative coefficient r (HEA, Y)
Are as follows:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811367413.8A CN109359780B (en) | 2018-11-16 | 2018-11-16 | Residential electricity consumption prediction method based on electrical appliance index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811367413.8A CN109359780B (en) | 2018-11-16 | 2018-11-16 | Residential electricity consumption prediction method based on electrical appliance index |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109359780A true CN109359780A (en) | 2019-02-19 |
| CN109359780B CN109359780B (en) | 2021-10-08 |
Family
ID=65345606
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811367413.8A Active CN109359780B (en) | 2018-11-16 | 2018-11-16 | Residential electricity consumption prediction method based on electrical appliance index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109359780B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543908A (en) * | 2018-11-26 | 2019-03-29 | 国家电网有限公司 | A kind of prediction technique of the electricity consumption of resident based on resident's household electrical appliance accounting energy |
| CN110738581A (en) * | 2019-07-25 | 2020-01-31 | 天津大学 | Campus comprehensive building power consumption rating method based on multiple linear regression |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104655953A (en) * | 2013-11-22 | 2015-05-27 | 财团法人资讯工业策进会 | power consumption prediction device and method |
| CN105894137A (en) * | 2016-05-30 | 2016-08-24 | 中国南方电网有限责任公司电网技术研究中心 | Residential electricity demand forecasting method and system |
| US20160328723A1 (en) * | 2014-04-14 | 2016-11-10 | Frank Patrick Cunnane | Methods and systems for analyzing economic phenomena |
| CN106326996A (en) * | 2015-06-16 | 2017-01-11 | 中国电力科学研究院 | User load prediction method based on electric quantity information |
| US20170030949A1 (en) * | 2015-07-29 | 2017-02-02 | Alcatel-Lucent Usa Inc. | Electrical load prediction including sparse coding |
| CN107103387A (en) * | 2017-04-25 | 2017-08-29 | 国网江苏省电力公司泰州供电公司 | It is a kind of based on equipment general power per family and to move in the load forecasting method of coefficient |
| CN107194502A (en) * | 2017-05-04 | 2017-09-22 | 山东大学 | A kind of resident's Methods of electric load forecasting |
-
2018
- 2018-11-16 CN CN201811367413.8A patent/CN109359780B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104655953A (en) * | 2013-11-22 | 2015-05-27 | 财团法人资讯工业策进会 | power consumption prediction device and method |
| US20160328723A1 (en) * | 2014-04-14 | 2016-11-10 | Frank Patrick Cunnane | Methods and systems for analyzing economic phenomena |
| CN106326996A (en) * | 2015-06-16 | 2017-01-11 | 中国电力科学研究院 | User load prediction method based on electric quantity information |
| US20170030949A1 (en) * | 2015-07-29 | 2017-02-02 | Alcatel-Lucent Usa Inc. | Electrical load prediction including sparse coding |
| CN105894137A (en) * | 2016-05-30 | 2016-08-24 | 中国南方电网有限责任公司电网技术研究中心 | Residential electricity demand forecasting method and system |
| CN107103387A (en) * | 2017-04-25 | 2017-08-29 | 国网江苏省电力公司泰州供电公司 | It is a kind of based on equipment general power per family and to move in the load forecasting method of coefficient |
| CN107194502A (en) * | 2017-05-04 | 2017-09-22 | 山东大学 | A kind of resident's Methods of electric load forecasting |
Non-Patent Citations (2)
| Title |
|---|
| GESCHE HUEBNER 等: "Understanding electricity consumption: A comparative contribution of building factors, socio-demographics, appliances, behaviours and attitudes", 《APPLIED ENERGY》 * |
| 苏铭: "基于Logit模型的华东四省一市具名生活用电预测研究", 《华东电力》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543908A (en) * | 2018-11-26 | 2019-03-29 | 国家电网有限公司 | A kind of prediction technique of the electricity consumption of resident based on resident's household electrical appliance accounting energy |
| CN110738581A (en) * | 2019-07-25 | 2020-01-31 | 天津大学 | Campus comprehensive building power consumption rating method based on multiple linear regression |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109359780B (en) | 2021-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pan et al. | Cluster analysis for occupant-behavior based electricity load patterns in buildings: A case study in Shanghai residences | |
| Swan et al. | Occupant related household energy consumption in Canada: Estimation using a bottom-up neural-network technique | |
| Matsumoto | How do household characteristics affect appliance usage? Application of conditional demand analysis to Japanese household data | |
| CN109193720B (en) | User side energy storage capacity configuration method based on typical daily load curve of enterprise user | |
| Sekki et al. | Measured energy consumption of educational buildings in a Finnish city | |
| Belaïd et al. | Features of residential energy consumption: Evidence from France using an innovative multilevel modelling approach | |
| TW201734427A (en) | Method for verifying and analyzing energy efficiency ratio (EER) of refrigerating and air conditioning unit allowing an owner to set the lowest standard for monthly or seasonal running EER values so as to save energy | |
| Lin et al. | Measurement of the direct rebound effect of residential electricity consumption: An empirical study based on the China family panel studies | |
| CN110264080A (en) | A kind of green building runnability evaluation method, device, equipment and storage medium | |
| CN106022536B (en) | Seasonal power consumption prediction method and system | |
| Sanstad et al. | Modeling an aggressive energy-efficiency scenario in long-range load forecasting for electric power transmission planning | |
| CN109858728A (en) | Load forecasting method based on branch trade Analysis of Electrical Characteristics | |
| Dahlström et al. | Advancing urban building energy modelling through new model components and applications: A review | |
| CN111539844B (en) | Moon electricity quantity prediction method based on K-L information quantity and ARIMA error correction | |
| Ruch et al. | A change-point principal component analysis (CP/PCA) method for predicting energy usage in commercial buildings: the PCA model | |
| CN109359780A (en) | A kind of electricity consumption of resident prediction technique based on electrification index | |
| Tao et al. | Graph convolutional network-based aggregated demand response baseline load estimation | |
| Zhang et al. | Exploring the impact of temperature change on residential electricity consumption in China: The ‘crowding-out’effect of income growth | |
| Abdeen et al. | Comparative review of occupant-related energy aspects of the National Building Code of Canada | |
| Jiang et al. | Stochastic modelling of flexible load characteristics of split-type air conditioners using grey-box modelling and random forest method | |
| Luo et al. | Many-objective day-ahead optimal scheduling of residential flexible loads integrated with stochastic occupant behavior models | |
| CN105894137A (en) | Residential electricity demand forecasting method and system | |
| TW201027014A (en) | Method for managing air conditioning power consumption | |
| Wang et al. | Aggregated large-scale air-conditioning load: Modeling and response capability evaluation of virtual generator units | |
| Zhang et al. | Projection of residential and commercial electricity consumption under SSPs in Jiangsu province, China |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |