A Load Forecasting Method for Household Electrical Equipment

Abstract

The invention discloses a home electrical equipment load prediction method. The method comprises the steps of collecting environment data representing all environments in which home electrical equipment is; collecting electricity load data of the home electrical equipment in each environment; cleansing the collected electricity load data; performing attribute value encoding on the cleansed electricity load data; building more than one self-encoder model, and initializing parameters of the self-encoder models sequentially; training the self-encoder models sequentially; building a deep stacked self-encoder model based on all the trained self-encoder models so as to set initialization parameters; performing deep training on the deep stacked self-encoder model; and predicting electricity load of the home electrical equipment by using the trained deep stacked self-encoder model. In the existing electricity load prediction technology, a precise model is hard to build to predict the electricity load due to the complex and volatile electricity load. The home electrical equipment load prediction method resolves the above technological problem.

Description

technical field [0001] The invention belongs to the load forecasting technology of household electrical equipment, in particular to a load forecasting method of household electrical equipment. Background technique [0002] Accurate forecasting of power load is of great significance to power production and safe operation of power systems. However, due to the complexity and variability of power load, it is difficult to establish an accurate model to predict it. The traditional load forecasting methods have certain defects, which leads to the unresolved problem of load forecasting. At the same time, with the proposal of the "Internet +" slogan and the rapid development of the energy Internet, more and more electrical equipment is connected to the Internet. In this process, a large amount of electricity consumption data is bound to be generated. The load change characteristics of various electrical equipment are deeply excavated from a large amount of data, so as to realize the...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a load forecasting method for household electric equipment, so as to solve the problems in the prior art for electric load forecasting due to the complexity and variability of the electric load, and the traditional load forecasting methods all have certain defects, which are very difficult to solve. It is difficult to establish an accurate model to predict it and other technical problems

Images