Family population prediction method based on electric power big data
A prediction method and technology of population numbers, applied in the field of big data analysis, can solve the problem of difficult and reliable acquisition of per capita electricity consumption, achieve the effect of fast and timely iteration, low data quality requirements, and avoidance of manual screening
Inactive Publication Date: 2021-04-20
INFORMATION & COMM COMPANY OF STATE GRID HEILONGJIANG ELECTRIC POWER COMPANY +2
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Aiming at the problem that the existing family population prediction method relies on per capita power consumption, and per capita power consumption is difficult to obtain reliably, the present invention provides a family population prediction method based on electric power big data
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0030] Specific implementation mode 1. Combination Figure 1 to Figure 8 As shown, the present invention provides a family population prediction method based on electric power big data, including:
[0031] Collect the daily electricity consumption of all household users in the monitoring area within the preset period; take the electricity consumption as the abscissa and the frequency of the electricity consumption as the ordinate, and draw a normal distribution curve;
[0032] Based on population survey data, obtain the proportion of household users with different populations to all household users;
[0033] According to the proportion of users, determine the electricity consumption interval corresponding to the normal distribution curve of household users with different populations;
[0034] According to the electricity consumption interval, obtain the mean value and variance of the corresponding segment of the normal distribution curve, and then calculate the population pro...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a family population prediction method based on electric power big data, and belongs to the technical field of big data analysis. The method aims at solving the problems that an existing household population prediction method depends on per capita electricity consumption, and the per capita electricity consumption is difficult to obtain reliably. The method comprises the steps of drawing a normal distribution curve; determining an electricity consumption interval according to the user proportions of the family users with different population numbers in all the family users; obtaining population quantity probability density and power consumption curves of family users with different population numbers; the method compcollecting daily electricity consumption in a to-be-predicted family target period, obtaining a current mean value and a current variance, taking a value obtained by subtracting the current variance from the current mean value as a minimum value, taking a value obtained by adding the current variance to the current mean value as a maximum value, and determining corresponding electricity consumption intervals in different population number probability densities and electricity consumption curves, and taking the population of the household users corresponding to the curve when the area of the power consumption interval is maximum as a prediction result. The method achieves the prediction of the number of household population under the condition that the per capita power consumption is unknown.
Description
technical field [0001] The invention relates to a family population prediction method based on electric power big data, and belongs to the technical field of big data analysis. Background technique [0002] At present, household population prediction based on electricity data mainly relies on the per capita electricity consumption in the region, and the number of household population is predicted through the total household electricity consumption and per capita electricity consumption. However, the per capita electricity consumption in a region is extremely difficult to obtain, and the results are unreliable. In the absence of regional per capita electricity consumption, the prediction of household population cannot be achieved, so this method is usually not suitable for practical situations. [0003] At present, the household electricity consumption data in the area obtained by the machine learning method does not have a description of the population, so it does not have t...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q50/06G06Q50/26
Inventor 赵威姜洪水王云峰刘国辉吴伟东陈四根邵可心
Owner INFORMATION & COMM COMPANY OF STATE GRID HEILONGJIANG ELECTRIC POWER COMPANY