{"id":1720,"date":"2026-10-26T11:11:56","date_gmt":"2026-10-26T11:11:56","guid":{"rendered":"https:\/\/www.enedi.es\/en\/news\/\/?p=1720"},"modified":"2026-10-26T11:11:56","modified_gmt":"2026-10-26T11:11:56","slug":"a-clustering-based-framework-to-analyse-intra-building-variability-in-residential-energy-performance-using-geometric-descriptors","status":"publish","type":"post","link":"https:\/\/www.enedi.es\/en\/news\/publications\/a-clustering-based-framework-to-analyse-intra-building-variability-in-residential-energy-performance-using-geometric-descriptors","title":{"rendered":"A clustering-based framework to analyse intra-building variability in residential energy performance using geometric descriptors"},"content":{"rendered":"Understanding variability in residential energy performance at dwelling level remains challenging due to the combined influence of physical characteristics, occupant-related factors and data privacy constraints. This study uses a demonstrator building to propose clustering-based methodological framework to analyse intra-building variability while preserving data anonymity. Dwelling typologies are defined exclusively using geometric and solar exposure descriptors, avoiding the inclusion of energy variables and preventing feedback between classification and evaluation. Energy performance is subsequently assessed using Weather-Normalised Heating Energy Intensity and Degree-Hours of Discomfort analysed at daily resolution and aggregated at monthly and interannual scales. The methodology is demonstrated through its application to a social housing building over three consecutive winter seasons.\r\n\r\nResults reveal differentiated patterns of energy use across typologies, which remain consistent in their relative behaviour over time despite seasonal variations in magnitude. However, a substantial level of variability is observed within clusters, indicating that similar geometric configurations can be associated with markedly different energy performance outcomes. In contrast, thermal deficit remains generally low and appears as intermittent events, with no consistent relationship to the geometric descriptors considered. The combined analysis highlights a partial decoupling between energy use and indoor thermal conditions, indicating that energy consumption alone does not fully represent indoor performance. From a methodological perspective, the proposed framework enables the identification of useful typological patterns for several stakeholders while supporting privacy-aware analysis through cluster-based aggregation. The approach provides a methodological basis for analysing residential energy performance in privacy-sensitive contexts and supports the detection of atypical behaviour at building scale.\r\n\r\nhttps:\/\/doi.org\/10.1016\/j.enbuild.2026.118413","protected":false},"excerpt":{"rendered":"<p>Understanding variability in residential energy performance at dwelling level remains challenging due to the combined influence of physical characteristics, occupant-related factors and data privacy constraints. This study uses a demonstrator building to propose clustering-based methodological framework to analyse intra-building variability while preserving data anonymity. Dwelling typologies are defined exclusively using geometric and solar exposure descriptors, [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":1721,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[73],"tags":[64,65,68],"class_list":["post-1720","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-publications","tag-building-physics","tag-hvac-systems","tag-simulation-and-modelling"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.enedi.es\/en\/wp-json\/wp\/v2\/posts\/1720","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.enedi.es\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.enedi.es\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.enedi.es\/en\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.enedi.es\/en\/wp-json\/wp\/v2\/comments?post=1720"}],"version-history":[{"count":1,"href":"https:\/\/www.enedi.es\/en\/wp-json\/wp\/v2\/posts\/1720\/revisions"}],"predecessor-version":[{"id":1724,"href":"https:\/\/www.enedi.es\/en\/wp-json\/wp\/v2\/posts\/1720\/revisions\/1724"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.enedi.es\/en\/wp-json\/wp\/v2\/media\/1721"}],"wp:attachment":[{"href":"https:\/\/www.enedi.es\/en\/wp-json\/wp\/v2\/media?parent=1720"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.enedi.es\/en\/wp-json\/wp\/v2\/categories?post=1720"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.enedi.es\/en\/wp-json\/wp\/v2\/tags?post=1720"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}