Loading...
Paper Type
ERF
Abstract
Energy poverty occurs when households do not have access to, or cannot afford the energy services necessary to support their daily needs, including heating/cooling, washing, cooking, lighting and other activities. Energy poverty is a hidden, but important social problem because living in conditions without adequate energy access can lead to other health and social problems. Addressing energy poverty in a meaningful way requires first detecting households in precarious situations and then putting in place appropriate strategies to support them. In this research, we explore the potential for using artificial intelligence (AI) to model energy patterns that reflect situations of poverty. Using simulated energy consumption data in the New Zealand context, we show that AI, specifically machine learning models can achieve high predictive accuracy. We discuss challenges associated with using finer-grained approaches and opportunities for better prediction, prevention, and remediation of energy poverty.
Paper Number
1718
Recommended Citation
Savarimuthu, Bastin Tony Roy and Corbett, Jacqueline, "Tackling Energy Poverty with Artificial Intelligence: Challenges and Opportunities" (2024). AMCIS 2024 Proceedings. 8.
https://aisel.aisnet.org/amcis2024/sig_green/sig_green/8
Tackling Energy Poverty with Artificial Intelligence: Challenges and Opportunities
Energy poverty occurs when households do not have access to, or cannot afford the energy services necessary to support their daily needs, including heating/cooling, washing, cooking, lighting and other activities. Energy poverty is a hidden, but important social problem because living in conditions without adequate energy access can lead to other health and social problems. Addressing energy poverty in a meaningful way requires first detecting households in precarious situations and then putting in place appropriate strategies to support them. In this research, we explore the potential for using artificial intelligence (AI) to model energy patterns that reflect situations of poverty. Using simulated energy consumption data in the New Zealand context, we show that AI, specifically machine learning models can achieve high predictive accuracy. We discuss challenges associated with using finer-grained approaches and opportunities for better prediction, prevention, and remediation of energy poverty.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
SIGGREEN