Linear regression electric quantity prediction method and system based on power utilization characteristic clustering

Abstract

The invention provides a linear regression electric quantity prediction method and system based on power utilization characteristic clustering. On the basis of accumulated multi-type and massive customer power consumption information, the power consumption information is improved. Sub-space clustering is carried out according to the user power utilization characteristic evaluation indexes to acquire multiple categories, various user power utilization modes are further formed. According to different power consumption modes, users are subjected to group division, strong correlation factors of different group users are judged by utilizing a mutual information matrix, then a multiple linear regression algorithm is adopted to predict the power consumption, a plurality of linear regression models are established for each user group data to predict, the prediction result is more accurate, and prediction effect is better.

Description

technical field [0001] The present disclosure relates to the related technical field of electric power system power supply and distribution, in particular, it relates to a linear regression power prediction method and system based on clustering of electric characteristics. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] With the rapid development of the national economy and energy industry, power users have an increasing demand for electric energy. For power supply companies, the prediction of user power consumption is particularly important. The prediction of power consumption can not only help power companies to better To better understand and serve users, to formulate corresponding plans for the development of the power grid, specifically to dispatch power distribution, and to help the government formulate relevant policies, such as th...

AI Technical Summary

Problems solved by technology

[0004] The electricity consumption behavior of users is different. Even for users in the same industry, this difference will become more and more obvious as time goes by. Most of the existing electricity consumption forecasts are based on industry characteristics for pattern recognition, which is not very good. Mining user information

The power consumption characteristics of users are not only related to relevant factors in the industry, but also related to other social and economic factors. The power consumption characteristics of users in different regions and different industries have similar changing trends, and the characteristics of users' power consumption are diversified. Correlative power forecasting methods pose challenges

Images