Building Energy Consumption Prediction Study Based On Rough Set And Deep Learning

The accurate prediction of building energy consumption can help building energy saving work.However,there are many and miscellaneous factors affecting building energy consumption,which limits the accurate prediction of building energy consumption to a certain extent.Rough set theory can help find the key factors that affect building energy consumption.In addition,with the continuous development of artificial neural networks,the latest deep learning technology in intelligent algorithms has a "deep" architecture and powerful feature extraction capabilities.Introducing it to participate in building energy consumption prediction will hopefully improve the prediction accuracy.The study first used 100 sets of data from 100 civil public buildings for rough set reduction,and then collected data from a laboratory building of a university in Dalian for nearly a year to train and test deep neural networks.In this paper,the rough set theory is used to reduce the redundant influencing factors of building energy consumption,and find the important influencing factors of building energy consumption.Then these key factors will be used as the input of the deep neural network,and the building energy consumption as the output of the deep neural network.In this way,several different forms of building energy consumption prediction are carried out for a laboratory building in a university in Dalian,including short-term and medium-term.And the prediction accuracy of the deep neural network is compared with the prediction accuracy of several traditional neural networks.The results show that the building energy consumption prediction method based on rough set and deep learning is accurate,effective,and has high practicability.This can bring a practical solution for building energy consumption prediction.