Loading...
Paper Type
Complete
Abstract
Energy distribution is marked by the amount of variables that affect quality of service. Companies face many financial losses, from infrastructure damage, regulation penalties, and logistics failures. One less notice expense is caused by the utility team's displacement to maintenance. Frequently, the team finds that there is nothing to do, either because there was no problem or that is already fixed. As the energy providers have a huge amount of data of outage incidents, there is an opportunity to apply artificial intelligence to aid in the identification of unproductive teams displacement. This paper proposes a k-modes-based clustering algorithm to identify occurrences that lead to a false alarm, giving time to human intervention to reduce logistic losses. Our results show that the Unproductive Displacement Forecaster is capable of clustering more than 17% of data available that have a high possibility of resulting in a false positive, with approximately 75% accuracy.
Paper Number
1789
Recommended Citation
César do Nascimento, Andre Augusto; Nichio, Gabriel Favoretti; de Oliveira, Edvard Martins; Kuehne, Bruno Tardiole; and Pagan, Rafael P., "UDF: a k-modes-Based Algorithm to Reduce Unproductive Displacement of Power Utility Teams" (2024). AMCIS 2024 Proceedings. 16.
https://aisel.aisnet.org/amcis2024/dsa/dsa/16
UDF: a k-modes-Based Algorithm to Reduce Unproductive Displacement of Power Utility Teams
Energy distribution is marked by the amount of variables that affect quality of service. Companies face many financial losses, from infrastructure damage, regulation penalties, and logistics failures. One less notice expense is caused by the utility team's displacement to maintenance. Frequently, the team finds that there is nothing to do, either because there was no problem or that is already fixed. As the energy providers have a huge amount of data of outage incidents, there is an opportunity to apply artificial intelligence to aid in the identification of unproductive teams displacement. This paper proposes a k-modes-based clustering algorithm to identify occurrences that lead to a false alarm, giving time to human intervention to reduce logistic losses. Our results show that the Unproductive Displacement Forecaster is capable of clustering more than 17% of data available that have a high possibility of resulting in a false positive, with approximately 75% accuracy.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
SIGDSA