Effective Features to Predict Residential Energy Consumption Using Machine Learning

Humans have a greater influence on energy consumption in residential buildings than other types of buildings. Although existing studies focus on how energy consumption is affected by building technologies and occupant demographics, few studies have incorporated the impact of occupant energy use patterns. The goal of this study is to identify the features that affect energy consumption in residential buildings and to measure their predictive performance. The researchers examined the impact of occupants’ energy use behaviors and the energy use patterns of home appliances on home energy consumption. The patterns reflect on a combination of appliances, their use times and frequencies, and the configurations set by users. Data from the Residential Energy Consumption Survey (RECS) are analyzed to select features for prediction, using multiple machine learning algorithms including support vector machine (SVM) and random forest. The results provide a list of features that efficiently predict energy consumption in residential buildings. The selected 32 features achieve 98% of the prediction performance of that from the entire 271 features. This list of effective features can be used to improve the effectiveness of energy saving programs and to educate occupants about their energy use patterns. The relationship between occupants’ behavior patterns and energy use patterns revealed from this study provides the groundwork for researchers to further explore the prediction of occupant behavior from energy consumption. INTRODUCTION AND BACKGROUND The residential sector accounts for 39% of the total electricity consumption in the United States, according to the U.S. Department of Energy (U.S.DOE 2017). Occupants have a greater impact on the energy consumption in residential buildings than in other types of buildings (Zhao et al. 2018). Energy consumption in individual household depends on various factors, including environmental conditions, building technology, resident demographics, Heating, Ventilation and Air Conditioning (HVAC) systems, appliances in the home (Zhao et al. 2017). Among the factors, the usage pattern of HVAC systems and appliances are more related to occupant behavior and energy costs of households (McCoy et al. 2018). However, a comprehensive understanding of the features affecting home energy consumption is lacking, without which it is less likely to develop effective energy efficiency programs and provide relevant educational information to occupants. The goal of this research is to identify the features that effectively affect energy consumption in residential buildings as measured by their predictive performance. In particular, behavior-related features from appliances and their usage patterns are separately examined to see the effects of occupant behavior on energy consumption. Computing in Civil Engineering 2019 D ow nl oa de d fr om a sc el ib ra ry .o rg b y V ir gi ni a Po ly I ns t & S t U ni v on 0 6/ 25 /1 9. C op yr ig ht A SC E . F or p er so na l u se o nl y; a ll ri gh ts r es er ve d. Computing in Civil Engineering 2019 285 © ASCE This paper consists of three sections: (1) the descriptions of data and variables; (2) the selection of critical features for electricity consumption; and (3) the measurement and comparison of predictive performance of the selected features.