CN109359780B - Residential electricity consumption prediction method based on electrical appliance index - Google Patents
Residential electricity consumption prediction method based on electrical appliance index Download PDFInfo
- Publication number
- CN109359780B CN109359780B CN201811367413.8A CN201811367413A CN109359780B CN 109359780 B CN109359780 B CN 109359780B CN 201811367413 A CN201811367413 A CN 201811367413A CN 109359780 B CN109359780 B CN 109359780B
- Authority
- CN
- China
- Prior art keywords
- electricity consumption
- index
- hea
- calculating
- residents
- 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.)
- Active
Links
Images
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 invention relates to a resident electricity consumption prediction method based on an electrical appliance index, which comprises the following steps: 1) counting the number N of the main household appliancesiAnd the average power Pi(ii) a 2) Acquiring the service time of the household appliance, and calculating various household appliance frequency factors; 3) calculating a correction factor lambda of a household appliancei(ii) a 4) Calculating an electrification index HEA; 5) constructing a multiple linear regression model, and calculating the electricity utilization index HEA and the total number of residents AjIncome B dominated by harmonyjAs input to the multiple linear regression model, the electricity consumption of the residents YjAnd training as an output value, and predicting the electricity consumption of residents according to the trained multivariate linear regression model. Compared with the prior art, the method has the advantages of comprehensive consideration, high correlation, accuracy, effectiveness and the like.
Description
Technical Field
The invention relates to resident electricity consumption prediction, in particular to a resident electricity consumption prediction method based on an electrical appliance index.
Background
Factors influencing the electricity consumption of residents are various and include disposable income of a family, the size of a building area, the climate of a residential area, the scale of the family, the holding rate and the utilization rate of household appliances, the life habits of the family, policy propaganda and the like. The household appliances are used as loads for residential electricity, and the remaining quantity of the household appliances is the largest factor influencing the residential electricity consumption. However, the effective holding capacity of the household appliances is lack of a unified evaluation standard, effective comparison cannot be performed between different household appliances, and if the household appliances are simply dependent on power and comparison, the use frequency and the use duration of the household appliances are neglected, so that the household appliances are too one-sided. When the resident electricity consumption is predicted, the reserved quantity and the service time of the household appliances are taken as main factors, and a feasible method is not available for quantification. To realize accurate and effective prediction of the electricity consumption of residents, the comprehensive consideration of the holding capacity and the service time of household appliances is required.
Aiming at the influence of the effective reserve of household appliances on the electricity consumption of residents, many domestic and foreign scholars put forward their own opinions. In the Yan, the ' middle-term and long-term prediction of power consumption in Beijing City ' of the country ' of the republic of science, the change of the quantity of household appliances is considered to directly cause the change of the power consumption in the life of residents, and the quantity of the household appliances is related to the income level of the residents. The quantity of the household appliances is used as a variable, the correlation degree of the reserved quantity of various household appliances and the resident electricity consumption is calculated by utilizing grey correlation, and the Beijing city domestic electricity consumption is predicted by taking a factor with the correlation degree larger than 0.9 as one of various key factors. Li Wen Yuan is divided into three types of household appliances according to the popularity degree of the household appliances in residential electricity load analysis, and a formula for calculating the electricity load calculation capacity of each household of a residence according to the popularity rate of the household appliances is provided. There is great uncertainty about the purchase and use of each household appliance, and the algorithm, although it works in theory, is difficult to implement in the design. Su Ming et al found that the number of household appliances has a saturation value in the prediction research of residential electricity consumption of residents in the city of four provinces and one city in east China based on the Logit model, and found out representative household electricity consumption characteristics according to annual household appliance electricity consumption and lighting electricity consumption. The electricity utilization characteristics of the household appliances mainly comprise power magnitude and use frequency, but the electricity utilization characteristics only start from the view point of electricity quantity and cannot be used as an index to predict future electricity quantity. Do Lihufang et al in China that the electricity utilization mode of residents is consistent with the requirements of novel urbanization? The multivariate selection model of the purchasing decision of the household appliances of the residents is constructed by utilizing the multivariate selection model in the empirical research on the household appliances of the towns and the urban residents and the electricity utilization conditions, the saturation values of the reserves of various household appliances are estimated, and the potential electricity consumption of the household appliances is estimated on the basis. But the method ignores the power change, the use frequency change and the annual use hours change of various household appliances along with the social development, so that a large error exists in the estimation of the potential power consumption of the household appliances.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a residential electricity consumption prediction method based on an electrical appliance index.
The purpose of the invention can be realized by the following technical scheme:
a residential electricity consumption prediction method based on an electrical appliance index comprises the following steps:
1) counting the number N of the main household appliancesiAnd the average power Pi；
2) Acquiring the service time of the household appliance, and calculating various household appliance frequency factors;
3) calculating a correction factor lambda of a household appliancei；
4) Calculating an electrification index HEA;
5) constructing a multiple linear regression model, and calculating the electricity utilization index HEA and the total number of residents AjIncome B dominated by harmonyjAs input to the multiple linear regression model, the electricity consumption of the residents YjAnd training as an output value, and predicting the electricity consumption of residents according to the trained multivariate linear regression model.
In the step 1), the household appliances with the average power less than 40W are ignored during statistics.
In the step 2), the frequency factor f of the ith household applianceiThe calculation formula of (A) is as follows:
wherein h isiThe number of annual hours of use of the household appliance.
In the step 3), the correction factor lambdaiThe calculation formula of (A) is as follows:
λi＝λi1λi2
wherein λ isi1As a correction factor for power, λi2Is a correction factor for the frequency factor.
In the step 4), the calculation formula of the electrification index HEA is as follows:
wherein n is the total number of the types of the household appliances.
In the step 5), the expression of the multiple linear regression model is as follows:
Yj＝θ0+θ1Aj+θ2Bj+θ3HEAj
wherein the subscript j represents year, [ theta ]0Is a constant term, θ1、θ2、θ3Are regression coefficients.
The step 4) further comprises the following steps:
calculating a correlation coefficient r (HEA, Y) between the electrical utilization index HEA and the residential electricity consumption Y according to the Pearson correlation coefficient, wherein the correlation coefficient r (HEA, Y) is used for expressing the degree of correlation between the electrical utilization index and the residential electricity consumption, and the calculation formula of the correlation coefficient r (HEA, Y) is as follows:
compared with the prior art, the invention has the following advantages:
the invention provides a measuring standard for the effective keeping degree of household appliances, namely an electrical appliance index, and simultaneously, the index is used for predicting the electricity consumption of residents. The electrical appliance index comprehensively considers the keeping quantity, the rated power and the use frequency of the household appliances, and can be used as the standard of the effective keeping degree of the household appliances of residents to judge the electrical appliance degree of the residents, so that the living standard of the residents is reflected. Meanwhile, the electrical index has extremely high correlation with the resident electricity consumption, and can be used as an important basis for predicting the resident electricity consumption. The electrical appliance index is used for predicting the electricity consumption of residents, so that the accuracy and the effectiveness of the electricity consumption prediction result of the residents can be improved.
Drawings
Fig. 1 shows the index of the electric performance of a certain city over years.
FIG. 2 is a flow chart of the method of the present invention.
The notation in the figure is:
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments.
As shown in fig. 2, the invention provides a calculation method of an electrical appliance index and the calculation method is used for predicting the electricity consumption of residents, and the method comprises the following specific steps:
survey the hold and power of the main household appliances: the per household holding quantity N of the main household appliances is investigated by statistical yearbookiWhere i 1, 2.., n, represents the kind of household appliances, such as air conditioners, refrigerators, and the like. Looking up the power of each main household appliance, and calculating the average power P of each main household applianceiThe household appliances with the average power less than 40W can be ignored in calculation because the contribution to the electricity consumption of residents is small.
2) Calculating the frequency factor of the household appliance: the service time of different household appliances is not uniform, for example, the service frequency of the air conditioner in summer and winter is obviously higher than that in spring and autumn, the frequency factor of the household appliance calculated in a short period does not have representativeness, so the service time of the household appliance is obtained in the form of family visit investigation, the annual service time of the household appliance is obtained by data integration treatment, and the frequency factors f of various household appliances are calculated according to the formula (1)i。
In the formula, hiThe number of annual hours of use of the household appliance.
3) Calculating a correction factor of the household appliance: along with the improvement of the technology, the household appliances develop towards multi-functionalization and energy conservation, and the power of the household appliances in different periods is different. However, the replacement of the household appliances is performed step by step, and a calculation method for the electrical appliance index cannot be implemented, so that the concept of the power correction factor is proposed. Along with the increase of the income level of residentsWith the improvement of living standard, the use frequency of household appliances is continuously increased, and the correction factor of the use frequency factor corrects the use frequency of the household appliances over the years. Calculating a total correction factor lambda using the correction factors of the power and frequency factors according to equation (2)i。
λi＝λi1λi2 (2)
In the formula, λi1As a correction factor for power, λi2Is a correction factor for the frequency factor.
4) Calculating an electrical conversion index: calculating the hundred-household average holding quantity N of various household appliances according to the steps 1) to 3)iAverage power PiFrequency factor fiCorrection factor lambdaiAnd calculating the electrical susceptibility index according to the formula (3).
In the formula, HEA is the electrical appliance index, and n is the number of types of household appliances.
5) And (3) correlation analysis: and calculating a correlation coefficient between the electrical utilization index HEA and the resident electricity consumption Y by utilizing the Pearson correlation coefficient, and calculating the degree of closeness of the correlation between the electrical utilization index and the resident electricity consumption according to a formula (4).
In the formula, Cov (HEA, Y) is covariance of HEA and Y, Var [ HEA ] is variance of HEA, and Var [ Y ] is variance of Y.
6) Predicting the electricity consumption of residents: and (3) selecting a prediction model, and predicting future resident electricity consumption by taking the electrical appliance index obtained by calculation according to the formula (3) as one of the input parameters. The following describes the procedure with a multiple linear regression prediction model as an example.
In the multiple linear regression prediction model, the total number A of residents in a certain city is selectedjIncome for everyone BjElectrical index HEAjAs input parameter, the electricity consumption of residents in a certain city YjTraining is performed as an output value, where j represents the year. The multiple linear regression model is shown in equation (5),
Yj＝θ0+θ1Aj+θ2Bj+θ3HEAj (5)
in the formula, theta0Is a constant term, θ1、θ2、θ3Are regression coefficients.
And inputting the total number of residents, the per capita income and the electrical appliance index data values of the year to be predicted into the trained model to obtain the predicted value of the electricity consumption of the residents in a certain city of the year.
7) Evaluation of prediction results: and (4) respectively calculating the absolute error and the error rate of the electricity consumption prediction of the residents in a certain city according to the formulas (6) and (7) by combining the predicted electricity consumption value of the residents obtained in the step 6) with the actual electricity consumption of the residents in the year.
ΔY＝|YPrediction value-YActual value| (6)
Wherein Δ Y is an absolute error, δ (Y) is an error rate, and Y isPrediction valuePredicted value of electricity consumption for residents, YActual valueThe electricity consumption is the actual resident electricity consumption.
And evaluating the accuracy of the prediction method through the absolute error and the error rate, wherein the smaller the absolute error and the error rate is, the more accurate the prediction result is proved to be.
Example (b):
1) investigating the holding capacity and power of the main household appliances
The per household holding quantity N of the main household appliances is investigated by statistical yearbookiLooking up the power of each main household appliance, and calculating the average power P of each main household applianceiThe results are shown in Table 1. Wherein, the power of the recorder, the recording and playing camera, the video disc player, the video camera, the mobile phone and the like is less than 40W, the contribution to the resident electricity consumption is small, and the calculation can be carried outAre ignored.
TABLE 1 Total household holdup of major household appliances in a certain city
2) Calculating frequency factor of household electrical appliance
The service time of different household appliances is obtained in a form of family visiting investigation, and the investigation results are integrated to obtain the annual service time parameters of the main household appliances. As shown in table 2, the 2016 air-conditioning service time obtained by the investigation is obtained by calculating the time within 2 hours according to 1 hour, calculating the time within 2-4 hours according to 3 hours, and repeating the same, calculating the time period after the calculation according to 6 hours and 10 hours, calculating the time period above 12 hours according to 14 hours, and calculating the air-conditioning service time of 3 months in summer and 2 months in winter:
h1＝(1×0.03+3×0.11+6×0.28+10×0.39+14×0.19)×30×5＝1290；
the refrigerator works continuously in one year, and the annual service life is 8760 hours.
TABLE 2 survey result table of air conditioner using time of day
The frequency factors are calculated according to equation (1) respectively.
Wherein, i-1 represents that the household appliance is an air conditioner, and i-2 represents that the household appliance is a refrigerator.
3) Calculating correction factors for household appliances
Aiming at different household appliances, the small classification market occupation ratio of each household appliance in the past year is obtained, and the power correction factor is determined. Taking an air conditioner as an example, according to the supply and demand forecast and strategic investment report of the variable frequency air conditioner market in China in 2017 and 2022, the proportion of the variable frequency air conditioner in 2010 is about 30%, the proportion of the variable frequency air conditioner in 2016 is increased to 65.57%, and the average annual growth rate is 5.93%. The power consumption of the variable frequency air conditioner is assumed to be 80% of that of the fixed frequency air conditioner. Then 2015 air conditioner correction factor for its power versus 2016
λ11＝0.8×(0.6557-0.0593)+1×[1-(0.6557-0.0593)]＝0.880，
The service time of the air conditioner is related to the per-capita income level, the per-capita dominant income of a certain city in 2015 is 49867.2 yuan, the rate of increase of 54305.3 yuan in 2017 is 8.90%, the service time of the air conditioner is positively related to the per-capita dominant income, the rate of increase of the service time of the air conditioner from 2015 to 2016 is 8.90%, and then the correction factor of the frequency factor of the air conditioner in 2015 relative to 2016 is obtained by looking up the statistical yearbook of the certain city in the past
λ12＝1/(1+0.089)＝0.918。
Calculating the total correction factor by using the correction factors of the power and the frequency factor according to the formula (2) to obtain the correction factor of the air conditioner in 2015 relative to 2016
λ1＝λ11λ12＝0.880×0.918＝0.808。
4) Calculating an electrical conversion index
Obtaining the per-household holding quantity N of the household appliances of a certain year according to the step 1)iAverage power PiAnd the frequency factor f obtained in step 2)iCorrection factor lambda obtained in step 3)iAnd calculating the electricity utilization index of the year according to a formula (3). For 2016, the annual electrical performance index is obtained by the following equation.
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
The electrical indexes from 2000 to 2015 were obtained according to the 2016 electrical index calculation method, and the calculation results are shown in fig. 1.
5) Correlation analysis
Calculating the correlation between the electrical apparatus index HEA of the certain city obtained in the step 4) and the electricity consumption Y of the residents corresponding to the certain city by using the Pearson correlation coefficient, namely the formula (4). The obtained correlation coefficient was 0.997, and it was found that the two had a close tendency of change and were very strongly correlated.
6) Residential electricity consumption prediction
And 6) predicting the electricity consumption of residents in a certain city by using a multiple linear regression prediction model. Data before 2015 are selected as a training set of the model, and data of 2015 and 2016 are selected as a testing set to detect model accuracy. The total number of residents in a certain city A in the pastjIncome for everyone BjElectrical index HEAjAs input parameter, the electricity consumption of residents in a certain city YjAs a target, training and prediction of a multiple linear regression prediction model are performed.
The model predicts 184.191 hundred million kilowatt hours of the residents in a certain city in 2015 years and 212.489 million kilowatt hours of the residents in a certain city in 2016 years.
7) Evaluation of prediction results
The actual electricity consumption of a city in 2015 and 2016 is 185.49 hundred million kilowatt hours and 217.72 million kilowatt hours. The absolute error and error rate of the prediction result of the present invention can be obtained according to the formula (6) and the formula (7), respectively, as shown in table 3.
TABLE 3 prediction error Table
| Absolute | Error rate | ||
| 2015 | 1.299 hundred million kilowatt-hours | 0.7％ | |
| 2016 | 5.231 hundred million kilowatt-hours | 2.4％ |
As can be seen from Table 3, the prediction results of the present invention have high accuracy.
The invention provides a concept of an electrical appliance index and a calculation method thereof aiming at the problem of prediction of resident electricity consumption. The method comprises the steps of firstly surveying the quantity and the power of main household appliances, then calculating the frequency factor of each household appliance according to the annual service life, calculating a correction factor according to the development condition and the per capita dominable income level of the household appliances, and calculating the electrical appliance index by using the factors. And (3) carrying out correlation analysis on the electrical appliance index and the resident electricity consumption to obtain a very high correlation coefficient. And finally, inputting the electrical appliance index serving as an input parameter of the resident electricity consumption into the prediction model to obtain a predicted value of the resident electricity consumption.
The invention clearly provides the concept of the electrical appliance index, and the electrical appliance index can measure the effective retention degree of household appliances so as to judge the electrical appliance degree of residents and reflect the living standard of the residents. The electrical appliance index has extremely high correlation with the resident electricity consumption, can be used as an important reference factor for predicting the resident electricity consumption, and the comparison finds that the predicted value of the resident electricity consumption obtained by predicting the electrical appliance index is closer to the true value than the predicted result of the quantity of the household appliances. The electric appliance index is provided, and the accuracy and the effectiveness of the residential electricity consumption prediction result are improved. The method can be used for predicting the electricity consumption of residents and can also be popularized to the prediction of the social electricity consumption.
Claims (4)
1. A residential electricity consumption prediction method based on an electrical appliance index is characterized by comprising the following steps:
1) counting the number N of the main household appliancesiAnd the average power Pi；
2) Obtaining the service time of the household appliance, calculating various household appliance frequency factors, i-th household appliance frequency factor fiThe calculation formula of (A) is as follows:
wherein h isiThe number of annual hours of use of the household appliance;
3) calculating a correction factor lambda of a household applianceiCorrection factor lambdaiThe calculation formula of (A) is as follows:
λi＝λi1λi2
wherein λ isi1As a correction factor for power, λi2A correction factor that is a frequency factor;
4) calculating the electrification index HEA, wherein the calculation formula of the electrification index HEA is as follows:
wherein n is the total number of types of the household appliances;
5) constructing a multiple linear regression model, and calculating the electricity utilization index HEAjAnd the total number of residents AjIncome B dominated by harmonyjAs input to the multiple linear regression model, the electricity consumption of the residents YjTraining is carried out as an output value, and the resident electricity consumption is predicted according to a trained multiple linear regression model, wherein a subscript j represents the year.
2. The method as claimed in claim 1, wherein the step 1) is to ignore the household appliances with average power less than 40W in statistics.
3. The method as claimed in claim 1, wherein in the step 5), the expression of the multiple linear regression model is as follows:
Yj＝θ0+θ1Aj+θ2Bj+θ3HEAj
wherein, theta0Is a constant term, θ1、θ2、θ3Are regression coefficients.
4. The residential power consumption prediction method based on the electrical index as claimed in claim 1, wherein said step 4) further comprises the steps of:
calculating a correlation coefficient r (HEA, Y) between the electrical utilization index HEA and the residential electricity consumption Y according to the Pearson correlation coefficient, wherein the correlation coefficient r (HEA, Y) is used for expressing the degree of correlation between the electrical utilization index and the residential electricity consumption, and the calculation formula of the correlation coefficient r (HEA, Y) is 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 CN109359780A (en) | 2019-02-19 |
| CN109359780B true 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) |
Families Citing this family (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 (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI481881B (en) * | 2013-11-22 | 2015-04-21 | Inst Information Industry | Power consumption prediction apparatus, method, and computer program product thereof |
| US20160328723A1 (en) * | 2014-04-14 | 2016-11-10 | Frank Patrick Cunnane | Methods and systems for analyzing economic phenomena |
| US20170030949A1 (en) * | 2015-07-29 | 2017-02-02 | Alcatel-Lucent Usa Inc. | Electrical load prediction including sparse coding |
-
2018
- 2018-11-16 CN CN201811367413.8A patent/CN109359780B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 (1)
| Title |
|---|
| 苏铭.基于Logit模型的华东四省一市居民生活用电预测研究.《华东电力》.2014,第42卷(第4期),627-633. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109359780A (en) | 2019-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Quantitative energy performance assessment methods for existing buildings | |
| Aydinalp et al. | Modeling of the appliance, lighting, and space-cooling energy consumptions in the residential sector using neural networks | |
| US9625889B2 (en) | Applications of non-intrusive load monitoring and solar energy disaggregation | |
| Roberts et al. | Characterisation of Australian apartment electricity demand and its implications for low-carbon cities | |
| Μπίθας et al. | Estimating urban residential water demand determinants and forecasting water demand for Athens metropolitan area, 2000-2010 | |
| CN109359780B (en) | Residential electricity consumption prediction method based on electrical appliance index | |
| Qian et al. | Power consumption and energy efficiency of VRF system based on large scale monitoring virtual sensors | |
| CN109858728A (en) | Load forecasting method based on branch trade Analysis of Electrical Characteristics | |
| Swan | Residential sector energy and GHG emissions model for the assessment of new technologies | |
| CN112465385B (en) | Demand response potential analysis method applying intelligent ammeter data | |
| Beckel et al. | Automated customer segmentation based on smart meter data with temperature and daylight sensitivity | |
| WO2015167048A1 (en) | Adaptive method for predicting demand for energy | |
| CN105894137A (en) | Residential electricity demand forecasting method and system | |
| Ramapragada et al. | Investigation on air conditioning load patterns and electricity consumption of typical residential buildings in tropical wet and dry climate in India | |
| Wang et al. | Aggregated large-scale air-conditioning load: Modeling and response capability evaluation of virtual generator units | |
| Sanzana et al. | Effects of external weather on the water consumption of thermal-energy-storage air-conditioning system | |
| CN112421608A (en) | Family load prediction method based on Markov from bottom to top | |
| Wang et al. | A procedure set to construct the optimal energy saving retrofit strategy for old residential buildings in China | |
| Li et al. | The impacts of temperature on residential electricity consumption in Anhui, China: does the electricity price matter? | |
| CN110533247A (en) | A kind of monthly electricity demand forecasting method compensated using temperature record abnormal point | |
| Ren et al. | Refrigerator cost trap for low-income households: Developments in measurement and verification of appliance replacements | |
| CN113449909B (en) | Cold load prediction method of cold accumulation air conditioner based on improved long-term and short-term memory network | |
| Ou et al. | Non-intrusive Load Decomposition Based Demand Responsiveness Assessment of Regional Residents | |
| Gong et al. | An energy efficiency solution based on time series data mining algorithm on elementary school building | |
| Naderi et al. | Clustering based analysis of residential duck curve mitigation through solar pre-cooling: A case study of Australian housing stock |
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 |