{"id":99,"date":"2024-12-16T09:15:17","date_gmt":"2024-12-16T09:15:17","guid":{"rendered":"https:\/\/wp.lancs.ac.uk\/net0i\/?page_id=99"},"modified":"2026-01-06T16:17:35","modified_gmt":"2026-01-06T16:17:35","slug":"energy-usage-clustering-dashboard","status":"publish","type":"page","link":"https:\/\/wp.lancs.ac.uk\/net0i\/energy-usage-clustering-dashboard\/","title":{"rendered":"Energy Usage Clustering Dashboard"},"content":{"rendered":"

\"\"<\/a><\/p>\n

<\/i>github: https:\/\/github.com\/Cuauhtemoctzin\/Energy_Usage_Clustering<\/a>
\nZenodo: https:\/\/doi.org\/10.5281\/zenodo.14396956\u00a0\u00a0<\/a><\/p>\n

Understanding the usage patterns of buildings is key to developing energy management strategies. Complex building settings may display similar energy usage patterns for specific cycles, such as daily, weekly, monthly, and other periods like scholar terms. However, other building-specific factors might cause consumption patterns to differ according to internal activities such as research, teaching, catering, or administrative activities.<\/p>\n

Other external or internal factors might cause energy usage to differ and be considered anomalous. When a building shows an abnormal pattern, other buildings might be affected in response to the anomaly. For instance, electric failure in a library might cause students to search for alternative venues to study. Therefore, identifying groups of buildings with strong usage associations can help develop contingency plans.<\/p>\n

To understand the associations in usage patterns across buildings and support the development of energy management strategies. The Net0i team<\/a> developed an Energy Clustering Dashboard<\/a> to identify abnormal behaviours in energy usage by comparing the energy usage patterns across buildings. The dashboard assigns an anomaly score to each building, indicating the potential of the consumption pattern being anomalous. Then, to understand the factors driving the building consumption, a regression tree clusters the buildings based on the anomaly score and other known characteristics.<\/p>\n

\"\"<\/a><\/p>\n

Buildings showing similar behaviour with a minimal risk of being anomalous will tend to be in nodes at the left of the tree with lighter shadowing. Meanwhile, anomalous buildings will tend to be assigned to nodes located to the right of the tree with a darker shadow. The dashboard allows highlighting specific nodes to show the buildings belonging to such nodes. Low-anomaly risk buildings share a regular and synchronized pattern. In contrast, high-risk buildings tend to be isolated from the rest or clustered with other buildings displaying similar anomalies.<\/p>\n

Tutorial<\/h3>\n