作者: Nuno M.M. Ramos , Ricardo M.S.F. Almeida , M. Lurdes Simões , Pedro F. Pereira
DOI: 10.1016/J.SCS.2017.01.007
关键词:
摘要: Abstract Temperature and relative humidity values, from a sample of 24 flats with homogeneous architectural features social strata, were continuously measured during the heating season typical summer period. The results proved existence discomfort season, revealing energy poverty patterns, but at same time sensible differences that could only be explained by user actions. This led to deeper analysis data in search relevant patterns causes for inhomogeneity. A methodology exploring resulting large set is proposed present paper, based on application mining techniques. calculation meaningful percentiles hygrothermal variables, followed principal components analysis, allowed cluster flats. As result, clusters specific pattern found, which meant factors leading such performance explored, thus importance users their behaviour.