Loading...
Paper Type
Complete
Abstract
Power outages significantly impact communities. Traditional methodologies for anticipating power disruptions have often leaned on labor-intensive inspections and subjective evaluations, a process that proves to be ineffective. The rise of artificial intelligence (AI) and abundant data now enables efficient power outage forecasting. This article explores AI techniques in outage prediction, utilizing historical, climatic, and maintenance data. Historical data, particularly outage records, serve as invaluable resources for uncovering recurring patterns and trends in power disruptions. Concurrently, climate data contributes to the anticipation of weather-related events that can lead to outages, while maintenance data assists in identifying equipment prone to failure, enabling proactive maintenance measures to prevent outages. The research builds upon the authors' prior work by integrating new data and techniques. In specific regions analyzed, predictions showed a remarkable 30% improvement, with an accuracy rate exceeding 88%. This underscores AI's potential to improve outage prediction for more effective community solutions.
Paper Number
1202
Recommended Citation
Leite, Joao Paulo R. R.; Nichio, Gabriel Favoretti; de Oliveira, Edvard Martins; Carvalho, Luiz Olmes; and Pagan, Rafael P., "AI for Power Outage Prediction: Leveraging Data Insights and Integration" (2024). AMCIS 2024 Proceedings. 17.
https://aisel.aisnet.org/amcis2024/dsa/dsa/17
AI for Power Outage Prediction: Leveraging Data Insights and Integration
Power outages significantly impact communities. Traditional methodologies for anticipating power disruptions have often leaned on labor-intensive inspections and subjective evaluations, a process that proves to be ineffective. The rise of artificial intelligence (AI) and abundant data now enables efficient power outage forecasting. This article explores AI techniques in outage prediction, utilizing historical, climatic, and maintenance data. Historical data, particularly outage records, serve as invaluable resources for uncovering recurring patterns and trends in power disruptions. Concurrently, climate data contributes to the anticipation of weather-related events that can lead to outages, while maintenance data assists in identifying equipment prone to failure, enabling proactive maintenance measures to prevent outages. The research builds upon the authors' prior work by integrating new data and techniques. In specific regions analyzed, predictions showed a remarkable 30% improvement, with an accuracy rate exceeding 88%. This underscores AI's potential to improve outage prediction for more effective community solutions.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
SIGDSA