CN113673587B - Household basic daily electricity quantity calculation method - Google Patents
Household basic daily electricity quantity calculation method Download PDFInfo
- Publication number
- CN113673587B CN113673587B CN202110922913.9A CN202110922913A CN113673587B CN 113673587 B CN113673587 B CN 113673587B CN 202110922913 A CN202110922913 A CN 202110922913A CN 113673587 B CN113673587 B CN 113673587B
- Authority
- CN
- China
- Prior art keywords
- user
- characteristic index
- electricity consumption
- data
- power consumption
- 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
- 230000005611 electricity Effects 0.000 title claims abstract description 84
- 238000004364 calculation method Methods 0.000 title claims abstract description 14
- 238000003066 decision tree Methods 0.000 claims abstract description 25
- 238000013145 classification model Methods 0.000 claims abstract description 13
- 238000000034 method Methods 0.000 description 7
- 241000282326 Felis catus Species 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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 provides a household basic electricity consumption calculation method, which comprises the following steps: A. acquiring user electricity consumption data from an electricity consumption information acquisition system, wherein the user electricity consumption data comprise user numbers, electricity consumption dates, daily electricity consumption and user leaving conditions; B. c, calculating a power consumption characteristic index according to the power consumption data of the user obtained in the step A; C. b, forming training data according to the power consumption characteristic index calculated in the step B, and training and obtaining a decision tree classification model; D. c, inputting a user electricity consumption characteristic index according to the decision tree analysis model obtained through training in the step C, and calculating the basic electricity consumption of the user. The household basic electricity consumption calculation method can realize the calculation of household basic electricity consumption.
Description
Technical Field
The invention relates to the technical field of large power data application, in particular to a household basic daily electricity consumption calculation method.
Background
The household basic daily electricity quantity refers to the electricity consumption of equipment which may be normally opened, such as a set top box, a light cat, a router, a refrigerator and the like, in a home in a non-personnel state. The change of the home state is reflected on the daily electricity. In general, the basic daily electricity is a very important reference index when analyzing the user's home state or the house empty condition.
The Chinese patent application No. 201510056866.9 discloses a power grid daily electricity quantity prediction method based on air temperature change, which constructs a prediction model between air temperature and daily electricity quantity and predicts economic electricity quantity and air temperature electricity quantity according to air temperature and economic development situation. The Chinese patent application 20170280878.9 discloses a method for predicting daily electricity consumption of a platform area based on comfort of human body, which calculates air temperature compensation amount according to temperature sensing and corrects the predicted daily electricity consumption. The Chinese patent of the invention with the application number of 201711108363.7 'household daily load curve fine prediction method based on user behaviours' calculates a probability matrix of the start of household activities and the duration of the household activities according to resident time use survey reports, and obtains a household total load curve by predicting daily load curves of all household appliances.
The related method of the daily electricity related to the prior art, the prediction of the total daily electricity of the power grid and the platform area aiming at the invention patent with application numbers 201510056866.9 and 20170280878.9, does not relate to the judgment of the basic daily electricity of the household user; the patent of 201711108363.7 is mainly used for predicting household daily load, and does not distinguish base load, cooling load, heating load and the like, so that the patent cannot be used for calculating the base daily electric quantity.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a household basic daily electricity consumption calculation method, which is characterized in that a decision tree model is trained and obtained by calculating the characteristic index of the daily electricity consumption, and the household basic daily electricity consumption is judged by the trained decision tree model, so that the household basic daily electricity consumption can be calculated.
The invention adopts the technical scheme that:
a household basic daily electricity quantity calculation method comprises the following steps:
A. acquiring user electricity consumption data from an electricity consumption information acquisition system, wherein the user electricity consumption data comprises a user number, an electricity consumption date, daily electricity consumption and a user leaving condition;
B. c, calculating a power consumption characteristic index according to the power consumption data of the user obtained in the step A;
C. b, forming training data according to the power consumption characteristic index calculated in the step B, and training and obtaining a decision tree classification model;
D. c, inputting a user electricity consumption characteristic index according to the decision tree analysis model obtained through training in the step C, and calculating the basic electricity consumption of the user.
Further, the step B calculates a power consumption characteristic index for the power consumption data of the user obtained in the step a, and specifically includes:
step A, acquiring power consumption data of N users on T days, wherein N users are recorded as {1,2,..N }, the number of days of the power consumption data is recorded as {1,2,..T }, and the power consumption of the user N on the T th day is recorded as W n,t ，1≤n≤N，1≤t≤T。
For 1<t T, calculating a first characteristic index for user n on day T:
for 1.ltoreq.t < T, calculating a second characteristic index for user n on day T:
for 1< t, calculating a third feature index for user n on day t:
PT n,t ＝min(PF n,t ,PS n,t )
for 1< t, calculating a fourth feature index for user n on day t:
if no user is at home on day t, PO n,t =1, otherwise PO n,t ＝0。
Further, in the step C, training data is formed according to the power consumption characteristic index calculated in the step B, and a decision tree classification model is trained and obtained, specifically:
according to the calculated characteristic index, W n,t And PT n,t As input data of model, PO n,t As output data, a MATLAB decision tree training module is adopted, input data and output data are imported, and a decision tree classification model y=f (x) is obtained through training 1 ,x 2 ) Wherein x is 1 And x 2 Representing the daily electricity consumption data and the third characteristic index of the electricity consumption of the user respectively, y represents the fourth characteristic index of the user, and x 1 ＝W n,t ，x 2 ＝PT n,t ，y＝PO n,t 。
Further, in the step D, according to the decision tree analysis model obtained by training in the step C, the electricity consumption of the user and the third characteristic index are input, and the basic electricity consumption of the user is calculated, specifically:
daily electricity quantity data W of a user n n,t And a third characteristic index PT n,t Inputting the classification model of the decision tree to obtain PO n,t ＝F(W n,t ,PT n,t )。
If for 1<t<T, ifThe basic daily electricity quantity cannot be calculated in the period, and the above steps are repeated for recalculation in the period of time to be replaced:
if for 1<t<T, ifThe base daily electricity consumption of the user n is:
the invention provides a household basic electricity consumption calculation method, which can realize the calculation of household basic electricity consumption and verify the effectiveness of the invention through actual data.
Drawings
Fig. 1 is a flow chart of an embodiment of a method for calculating a household electricity consumption.
Detailed Description
The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings.
Referring to fig. 1, a flow chart of one embodiment of a method for calculating household electricity consumption of a household base according to the present invention includes the following steps:
A. acquiring user electricity consumption data from an electricity consumption information acquisition system, wherein the user electricity consumption data comprises a user number, an electricity consumption date, daily electricity consumption and a user leaving condition;
B. and C, calculating a power consumption characteristic index for the power consumption data of the user obtained in the step A, wherein the power consumption characteristic index specifically comprises the following steps:
step A, acquiring power consumption data of N users for T days, wherein N users can be recorded as {1,2,..N }, the number of days of the power consumption data can be recorded as {1,2,..T }, and the power consumption of the user N on the T th day is recorded as W n,t (1≤n≤N，1≤t≤T)。
For 1<t≤T, calculating a first characteristic index of the user n on the T th day PFn,t ：
For 1.ltoreq.t<T, calculating a second characteristic index PS of the user n on the T th day n,t ：
For 1<t<T, calculating a third characteristic index of the user n on the T th day PTn,t ：
PT n,t ＝min(PF n,t ,PS n,t )
For 1<t<T, calculating a fourth characteristic index of the user n on the T th day POn,t ：
If no user is at home on day t, PO n,t =1, otherwise PO n,t ＝0。
C. B, forming training data according to the power consumption characteristic indexes calculated in the step B, and training and obtaining a decision tree classification model, wherein the training data specifically comprises the following steps:
and B, according to the characteristic index calculated in the step B, W n,t And a third characteristic index PT n,t As input data of the model, a fourth characteristic index PO n,t As output data, a MATLAB decision tree training module is adopted, input data and output data are imported, and a decision tree classification model y=f (x) is obtained through training 1 ,x 2 ) Wherein x is 1 And x 2 The data of daily electricity consumption and the third characteristic index of electricity consumption respectively represent users, namely x 1 ＝W n,t ，x 2 ＝PT n,t Y represents the fourth characteristic index PO of the user n,t I.e. y=po n,t 。
D. C, inputting the electricity consumption of the user and a third characteristic index according to the decision tree analysis model obtained by training in the step C, and calculating the basic daily electricity consumption of the user, wherein the method specifically comprises the following steps:
daily electricity consumption data of a user n andthree-feature index input decision tree classification model y=f (x 1 ,x 2 ) PO can be obtained n,t ＝F(W n,t ,PT n,t )。
If for 1<t<T, ifThe basic daily electricity quantity cannot be calculated in the period, and the above steps are repeated for recalculation in the period of time to be replaced:
if for 1<t<T, ifThe base daily electricity consumption of the user n is:
the technical scheme and effects of the present invention are described in detail below with a specific embodiment:
and step A, acquiring user electricity consumption data from an electricity consumption information acquisition system, wherein the user electricity consumption data comprises information such as user numbers, dates, daily electricity consumption, whether people exist in a user's home or not, and the like, as shown in a table 1, and acquiring whether the people exist in the user's home or not through the streaming data.
Step B, calculating a power consumption characteristic index according to the power consumption data of the user, wherein the power consumption characteristic index is shown in a table 1:
TABLE 1 user Power consumption data and characteristic index calculation
C, according to the characteristic index and daily electricity quantity data calculated in the step B, adopting a MATLAB decision tree training module to import input data and output data, and training to obtainDecision tree classification model y=f (x 1 ,x 2 ) Wherein x is 1 And x 2 And y represents a fourth characteristic index of the user.
And D, inputting the daily electricity consumption of the user and the third characteristic index according to the trained decision tree analysis model, and calculating to obtain a fourth characteristic index of the user, wherein the fourth characteristic index is shown in the following table.
Table 2 basic daily electric quantity calculation
According to the daily electricity consumption of the user and the calculated fourth characteristic index, calculating the basic daily electricity consumption of the user as follows:
through community verification, the user does not have people in home on days 7-16, 28 and 29, and the accuracy of the calculation of the fourth characteristic index is verified.
The foregoing is merely illustrative embodiments of the present invention, and the present invention is not limited thereto, and any changes or substitutions that may be easily contemplated by those skilled in the art within the scope of the present invention should be included in the scope of the present invention.
Claims (1)
1. The household basic daily electricity consumption calculation method is characterized by comprising the following steps of:
A. acquiring user electricity consumption data from an electricity consumption information acquisition system, wherein the user electricity consumption data comprise user numbers, electricity consumption dates, daily electricity consumption and user leaving conditions;
B. c, calculating a power consumption characteristic index according to the power consumption data of the user obtained in the step A;
C. b, forming training data according to the power consumption characteristic index calculated in the step B, and training and obtaining a decision tree classification model;
D. c, inputting a user electricity consumption characteristic index according to the decision tree analysis model obtained by training in the step C, and calculating the basic electricity consumption of the user;
and B, calculating a power consumption characteristic index for the power consumption data of the user obtained in the step A, wherein the power consumption characteristic index specifically comprises the following steps:
step A, acquiring power consumption data of N users on T days, wherein N users can be recorded as {1,2, … N }, the number of days of the power consumption data can be recorded as {1,2, … T }, and the power consumption of the user N on the T th day is recorded as W n,t ，1≤n≤N，1≤t≤T；
For 1<T is less than or equal to T, and calculating a first characteristic index PF of the user n on the T th day n,t ：
For 1.ltoreq.t<T, calculating a second characteristic index PS of the user n on the T th day n,t ：
For 1<t<T, calculating a third characteristic index PT of the user n on the T th day n,t ：
PT n,t ＝min(PF n,t ,PS n,t )
For 1<t<T, calculating a fourth characteristic index PO of the user n on the T th day n,t ：
If no user is at home on day t, PO n,t =1, otherwise PO n,t ＝0；
And C, forming training data according to the power consumption characteristic index calculated in the step B, training and obtaining a decision tree classification model, wherein the training data comprises the following specific steps:
based on the calculated characteristic index(s),will W n,t And a third characteristic index PT n,t As input data of the model, a fourth characteristic index PO n,t As output data, a MATLAB decision tree training module is adopted, input data and output data are imported, and a decision tree classification model y=f (x) is obtained through training 1 ,x 2 ) Wherein x is 1 And x 2 Representing the third characteristic index of the daily electricity consumption data and the electricity consumption of the user respectively, and y represents the fourth characteristic index of the user, namely x 1 ＝W n,t ，x 2 ＝PT n,t ，y＝PO n,t ；
In the step D, according to the decision tree analysis model obtained by training in the step C, the characteristic index of the electricity consumption of the user is input, and the basic daily electricity consumption of the user is calculated, specifically:
daily electricity quantity data W of a user n n,t And a third characteristic index PT n,t Inputting the decision tree classification model to obtain a fourth characteristic index PO n,t ＝F(W n,t ,PT n,t )；
If for 1<t<T, ifThe basic daily electricity quantity cannot be calculated in the period, and the above steps are repeated for recalculation in the period of time to be replaced:
if for 1<t<T, ifThe base daily electricity consumption of the user n is:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110922913.9A CN113673587B (en) | 2021-08-12 | 2021-08-12 | Household basic daily electricity quantity calculation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110922913.9A CN113673587B (en) | 2021-08-12 | 2021-08-12 | Household basic daily electricity quantity calculation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113673587A CN113673587A (en) | 2021-11-19 |
| CN113673587B true CN113673587B (en) | 2024-02-02 |
Family
ID=78542420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110922913.9A Active CN113673587B (en) | 2021-08-12 | 2021-08-12 | Household basic daily electricity quantity calculation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113673587B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108564380A (en) * | 2018-04-11 | 2018-09-21 | 重庆大学 | A kind of telecommunication user sorting technique based on iteration decision tree |
| CN111178611A (en) * | 2019-12-23 | 2020-05-19 | 广西电网有限责任公司 | Method for predicting daily electric quantity |
| CN112257784A (en) * | 2020-10-22 | 2021-01-22 | 福州大学 | Electricity stealing detection method based on gradient boosting decision tree |
| CN112734135A (en) * | 2021-01-26 | 2021-04-30 | 吉林大学 | Power load prediction method, intelligent terminal and computer readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960514B (en) * | 2016-04-27 | 2022-09-06 | 第四范式（北京）技术有限公司 | Method and device for displaying prediction model and method and device for adjusting prediction model |
-
2021
- 2021-08-12 CN CN202110922913.9A patent/CN113673587B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108564380A (en) * | 2018-04-11 | 2018-09-21 | 重庆大学 | A kind of telecommunication user sorting technique based on iteration decision tree |
| CN111178611A (en) * | 2019-12-23 | 2020-05-19 | 广西电网有限责任公司 | Method for predicting daily electric quantity |
| CN112257784A (en) * | 2020-10-22 | 2021-01-22 | 福州大学 | Electricity stealing detection method based on gradient boosting decision tree |
| CN112734135A (en) * | 2021-01-26 | 2021-04-30 | 吉林大学 | Power load prediction method, intelligent terminal and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113673587A (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wyneken et al. | Loggerhead sea turtle environmental sex determination: implications of moisture and temperature for climate change based predictions for species survival | |
| CN106951611B (en) | Energy-saving design optimization method for buildings in severe cold regions based on user behaviors | |
| Reiter et al. | Estimating risks of identification disclosure in partially synthetic data | |
| Smallegange et al. | Towards a general, population-level understanding of eco-evolutionary change | |
| Suggitt et al. | Habitat associations of species show consistent but weak responses to climate | |
| Katz et al. | A mixed model for the relationship between climate and human cranial form | |
| Engler et al. | Comparative landscape genetics of three closely related sympatric Hesperid butterflies with diverging ecological traits | |
| CN108563755A (en) | A kind of personalized recommendation system and method based on bidirectional circulating neural network | |
| CN109714324A (en) | User network abnormal behaviour based on machine learning algorithm finds method and system | |
| CN105068513A (en) | Intelligent home energy management method based on social network behavior perception | |
| US10770898B2 (en) | Methods and systems for energy use normalization and forecasting | |
| Matos‐Maraví et al. | Species limits in butterflies (Lepidoptera: Nymphalidae): reconciling classical taxonomy with the multispecies coalescent | |
| Bell et al. | Australia's population future: Probabilistic forecasts incorporating expert judgement | |
| Thorve et al. | High resolution synthetic residential energy use profiles for the United States | |
| CN112651543A (en) | Daily electric quantity prediction method based on VMD decomposition and LSTM network | |
| CN111223523B (en) | Gene regulation network construction method and system based on multi-time-lag causal entropy | |
| CN113673587B (en) | Household basic daily electricity quantity calculation method | |
| Connor et al. | Complex effects of habitat amount and fragmentation on functional connectivity and inbreeding in a giant panda population | |
| CN116843388B (en) | Advertisement delivery analysis method and system | |
| Aeschbacher et al. | Approximate B ayesian computation for modular inference problems with many parameters: the example of migration rates | |
| Visser et al. | Complexity in hydroecological modelling: A comparison of stepwise selection and information theory | |
| Emaziye et al. | A critical analysis of climate change factors and its projected future values in Delta State, Nigeria | |
| Henson et al. | Predicting the dynamics of animal behaviour in field populations | |
| Ma | Generating disaggregate population characteristics for input to travel-demand models | |
| CN107423320A (en) | A kind of medical domain under big data framework is from media platform data push method |
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 |