Home > Research > Publications & Outputs > Lancaster University Energy Usage Clustering

Text available via DOI:

View graph of relations

Lancaster University Energy Usage Clustering

Research output: Exhibits, objects and web-based outputsSoftware

Published

Standard

Lancaster University Energy Usage Clustering. Granados Garcia, Guillermo Cuauhtemoctzin (Author); Smith, Paul (Developer). 2024. Zenodo.

Research output: Exhibits, objects and web-based outputsSoftware

Harvard

APA

Vancouver

Author

Bibtex

@misc{098d1fdce8604df18914714b151d415d,
title = "Lancaster University Energy Usage Clustering",
abstract = "This dashboard benchmarks and clusters the different sources used in the Lancaster University buildings. Given a data range chosen, an anomaly score is assigned to each building using a nearest-neighbor approach. In brief, an anomalous observation will have large distances compared with the rest of the observations, particularly with its nearest neighbors. The anomaly score is the sum of the distances of an observation with its nearest neighbors. The options and parameters provided are meant to explore different perspectives and explain the behavior of source usage at the University.Visit the dashboard at: https://cuauhtemoctzin.shinyapps.io/Energy_Usage_Clustering/",
keywords = "Anomaly Detection, Time series analysis, Cluster detection, Energy efficiency, Data Visualization",
author = "{Granados Garcia}, {Guillermo Cuauhtemoctzin} and Paul Smith",
year = "2024",
month = dec,
day = "12",
doi = "10.5281/zenodo.14396956",
language = "English",
publisher = "Zenodo",

}

RIS

TY - ADVS

T1 - Lancaster University Energy Usage Clustering

AU - Granados Garcia, Guillermo Cuauhtemoctzin

A2 - Smith, Paul

PY - 2024/12/12

Y1 - 2024/12/12

N2 - This dashboard benchmarks and clusters the different sources used in the Lancaster University buildings. Given a data range chosen, an anomaly score is assigned to each building using a nearest-neighbor approach. In brief, an anomalous observation will have large distances compared with the rest of the observations, particularly with its nearest neighbors. The anomaly score is the sum of the distances of an observation with its nearest neighbors. The options and parameters provided are meant to explore different perspectives and explain the behavior of source usage at the University.Visit the dashboard at: https://cuauhtemoctzin.shinyapps.io/Energy_Usage_Clustering/

AB - This dashboard benchmarks and clusters the different sources used in the Lancaster University buildings. Given a data range chosen, an anomaly score is assigned to each building using a nearest-neighbor approach. In brief, an anomalous observation will have large distances compared with the rest of the observations, particularly with its nearest neighbors. The anomaly score is the sum of the distances of an observation with its nearest neighbors. The options and parameters provided are meant to explore different perspectives and explain the behavior of source usage at the University.Visit the dashboard at: https://cuauhtemoctzin.shinyapps.io/Energy_Usage_Clustering/

KW - Anomaly Detection

KW - Time series analysis

KW - Cluster detection

KW - Energy efficiency

KW - Data Visualization

U2 - 10.5281/zenodo.14396956

DO - 10.5281/zenodo.14396956

M3 - Software

PB - Zenodo

ER -