Optimizing Carbon Emissions and Cost Reductions for Household Energy Demand Using Machine Learning (Proposals Track)

Shivani Chotalia (Clean AI Initiative); Kyungmin Lee (University of Delaware); Soazig Kaam (N/A); Victor Hutse (Radix); David Quispe (University of Toronto)

NeurIPS 2024 Recorded Talk Cite
Buildings Time-series Analysis

Abstract

Residential buildings account for 17-20% of global greenhouse gas (GHG) emissions, posing a significant challenge in transitioning all buildings to net zero. While heat pumps and building retrofits can significantly reduce emissions, homeowners are often unaware of their energy usage and the potential for cost reduction. Supervised machine learning methods have the potential to provide actionable insights for individual energy end users, enabling them to reduce both GHG emissions and energy costs. We propose a novel framework that utilizes baseline, intervention, and optimization models to predict emissions and cost estimates for individual energy end users. This paper presents a novel application of an optimization model for energy bills through machine learning methods: (1) classification of time series data for electricity and gas usage baselines, (2) prediction of GHG emission reductions, and (3) prediction of energy cost reductions. This study suggests energy retrofit policy implications using machine learning as an enabling technology for empowering decision-makers and end-users to tackle climate change.