Energy use prediction with information theory and machine learning technique

2019 3rd International Conference on Energy and Environmental Science

能源学;生态环境科学

Tong, Y.W.^1 ; Yang, W.Y.^2 ; Zhan, D.L.^3

School of Economics and Management, Nanchang University, Nanchang, China^1

College of Automation, Shenyang Aerospace University, Shenyang, Liaoning, China^2

Department of Mathematics, Sichuan University, Chengdu, Sichuan, China^3

关键词: Building electric energy consumption;    Energy consumption model;    Energy use;    Machine learning models;    Machine learning techniques;    Temperature and humidities;    Temporal dynamics;    Temporal evolution;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/291/1/012031/pdf
DOI  :  10.1088/1755-1315/291/1/012031

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

Appliances energy consumption plays an increasingly important role in the overall building electric energy consumption and its temporal trending. However, predicting appliances energy consumption is complicated by lack of causal understanding of the appliances energy use as well as too many potential predictors that might be relevant to the appliances energy use. In this study, we apply information theory and advance machine learning neural network technique to first rank the importance of potential drivers that dominate appliances energy consumption and secondly model the temporal evolution of appliances energy consumption with a restricted set of environmental predictors. Our results showed that temperature and humidity were the two most important environmental drivers in the house appliances energy consumption modeling. Furthermore, using those environmental drivers, the machine learning model was able to accurately capture the temporal dynamics of appliances energy consumption.