Multiple forecast method of line loss rates based on interval extension theory

Abstract

The invention discloses a multiple forecast method of line loss rates based on an interval extension theory. The multiple forecast method comprises the following steps: an interval extension forecasting model is established according to clustered data, and classical domains, joint domains and material elements to be forecast are established; weight coefficients of influencing factors are determined through calculation of correlation degrees, and types corresponding to the line loss rates of years to be forecast are determined; the corresponding classical domains and joint domains are constructed according to a plurality of subsets of a set P divided by cluster analysis, then the material elements to be forecast are determined, subsets to which samples to be forecast belong are determined according to correlation function values, and a cluster forecast result is obtained. The problem that influence factor values of forecast objects cannot be accurately determined is solved through the interval extension theory, the method is scientific and reasonable, has stronger adaptability, is suitable for calculating line loss rates of years or months in different regions, and the multiple forecast can be achieved, so that the result is more accurate.

Description

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

AI Technical Summary

Benefits of technology

This patented technology allows users to predict how much time they will lose their phone lines over some period based on past experience with similar devices used during testing. It then uses this knowledge to create an algorithm called regression analysis which assigns future values along specific intervals instead of just one unit (the original estimate). By doing these calculations repeatedly until it reaches what's right, we get better estimates about who lost them compared to other people.

Problems solved by technology

This patents discuss two main challengings: 1) how to efficiently plan new lines or optimize power grids without causing issues like increased losses due to poorly designed equipment or environmental impacts that affect their healthiness and productivity levels during use. 2) Current approaches only involve linear regression models and estimations involving multiple variables, making them hard to interpret precisely.

Images