Method for predicting power utilization mode of new user of grid under internet environment

Abstract

The invention provides a method for predicting the power utilization mode of a new user of grid under the internet environment. The method includes the following steps: constructing a relation network between an existing internet user and the labels thereof; separately computing the number W of same labels between each existing user and a new user, then arranging the order of the existing users which correspond to elements in the number W in the descending order, cancelling the number M of existing users to form a user group A, computing the number Nij of the same labels between any two users in the user group A and the power utilization behavior similarity Sij of the users represented by the two nodes, then computing the mutual relation weight between the two nodes; computing the average value of daily load curves of users in a user group B and taking the average value as the prediction value of the power utilization mode of the new grid user. According to the invention, the method can predict the power utilization mode of the new grid user through the attribute labels of the user in combination of the analysis of similar user group when there is no historic load of the user, so that the method can help power entities to provide personalized power utilization service recommendation to the new grid user.

Description

technical field [0001] The invention belongs to the technical field of intelligent power consumption, and in particular relates to a method for predicting power consumption patterns of new grid-connected power users under the Internet environment. Background technique [0002] With the continuous advancement of the national energy Internet strategy and the power system reform policy, the direction of power market reform has become increasingly clear. Power users purchase electricity and use electricity value-added services on the Internet electricity sales platform, which has a variety of user data, including user attribute data such as population, housing area, housing market average price, and heating type. Classify user data types and quantitatively divide intervals to form a label table that defines users. Based on this, users are classified and the electricity consumption behavior preferences and Internet behavior preferences of user groups are analyzed and predicted. ...

AI Technical Summary

Problems solved by technology

At present, the analysis of power consumption patterns is mainly based on a large amount of historical load data of users, using data analysis methods such as clustering to identify the power consumption patterns of users, but for users without historical power load data, it is difficult to conduct electricity consumption patterns. Evaluation, which is not conducive to providing personalized services for new users

Images