Method, system and equipment for predicting number of people at home for energy management, and medium

Abstract

The invention discloses a method, a system and equipment for predicting the number of people at home for energy management, and a medium, and the method comprises the steps: firstly obtaining and processing data which mainly comprises family member information, household power consumption data, member home-leaving distance data, meteorological data and the like; then, constructing and training a home number prediction model which is composed of three layers of LSTMs and based on power consumption data and a home number prediction model which is composed of four layers of LSTMs and based on the distance between members; and then, constructing and training an integrated prediction model of the number of people at home, which is composed of four layers of DNNs, and finally realizing hour-by-hour prediction of the number of people at home. According to the method, the ensemble learning method is adopted, the prediction results of the number of people at home of different models and different sides are used for synthesizing the final prediction result, and compared with a single method for prediction, the precision of the prediction method is improved.

Description

technical field [0001] The present invention relates to the technical field of energy management, in particular to an energy management-oriented prediction method, system, equipment and medium for the number of people at home. Background technique [0002] Household energy consumption accounts for about 30% of the total energy consumption in society. The traditional household energy system adopts extensive control methods. No matter how many people are at home, or even when no one is at home, water heaters, heating, water boilers and other equipment are set according to tracking. Value-based operation, the essence of this method is to use redundancy to meet user needs, resulting in a lot of energy waste, and there are some security risks. As smart home appliances, smart sockets, smart switches and other devices continue to enter the home, it provides an opportunity for the home to manage energy and improve energy conservation and safety. [0003] An important purpose of hom...

AI Technical Summary

Problems solved by technology

The number of people in public places is the result of a large number of individual activities, which implies the law of social dynamics. It has relatively stable statistical characteristics, but with fewer family members, its randomness is stronger, and it is necessary to take into account various influences related to family members. factors, it is difficult to continue to use the existing methods for predicting the number of people in public places

Images