Factor analysis in home energy consumption by information entropy and Bayesian network

In order to save volume of home energy consumption effectively, this paper proposes the method for being aware of factors with influence on energy consumption and then confirms if it works for practical data by numerical experimentation. The basic idea is based on the combination of information entropy for the former and on Bayesian network for the latter. Using 345 responses for the questionnaire which include twenty four months home energy consumption log and thirteen factors (house attributes, consumer attributes and consumer consciousness), the proposed method has found that the factor “house structure” has biggest influence on energy consumption. Moreover, it has found the combination of factors which have influence on energy consumption.