Occupancy detection of residential buildings using smart meter data: A large-scale study

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@Article{RAZAVI:2019:EB,

• author = "Rouzbeh Razavi and Amin Gharipour and Martin Fleury and Ikpe Justice Akpan",
• title = "Occupancy detection of residential buildings using smart meter data: A large-scale study",
• journal = "Energy and Buildings",
• year = "2019",
• volume = "183",
• pages = "195--208",
• keywords = "genetic algorithms, genetic programming, Buildings occupancy, Smart meters, Privacy, Data mining",
• ISSN = "0378-7788",
• URL = "http://www.sciencedirect.com/science/article/pii/S0378778818316724",
• DOI = "doi:10.1016/j.enbuild.2018.11.025",
• abstract = "Advanced Metering Infrastructures (AMIs) are installed to gather localized and frequently acquired energy consumption data. Despite many potential benefits, the installation of such meters has resulted in growing privacy concerns amongst the public. By analyzing the electricity consumption behavior of more than 5000 households over an 18-month period and deploying a wide array of machine learning methods, this paper examines whether high-frequency meter data are sufficient to predict the home-occupancy status of households not only in the present but also in the future. The authors believe that this is the first study at such a scale on this issue. The study proposes a genetic programming approach for feature engineering when training the models. The results reveal a high predictive power for smart meter data in establishing the present and future occupancy status of households. Also, the analysis of the demographic data suggests that households known to be least concerned with privacy are the ones who are more vulnerable to smart meter privacy implications",

}

Genetic Programming entries for Rouzbeh Razavi Amin Gharipour Martin Fleury Ikpe Justice Akpan

Citations