Disambiguating Energy Disaggregation: A Collective Probabilistic Approach

Disambiguating Energy Disaggregation: A Collective Probabilistic Approach

Sabina Tomkins, Jay Pujara, Lise Getoor

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
Main track. Pages 2857-2863. https://doi.org/10.24963/ijcai.2017/398

Reducing household energy usage is a priority for improving the resiliency and stability of the power grid and decreasing the negative impact of energy consumption on the environment and public health.Relevant and timely feedback about the power consumption of specific appliances can help household residents to reduce their energy demand. Given only a total energy reading, such as that collected from a residential meter, energy disaggregation strives to discover the consumption of individual appliances. Existing disaggregation algorithms are computationally inefficient and rely heavily on high-resolution ground truth data. We introduce a probabilistic framework which infers the energy consumption of individual appliances using a hinge-loss Markov random field (HL-MRF), which admits highly scalable inference. To further enhance efficiency, we introduce a temporal representation which leverages state duration. We also explore how contextual information impacts solution quality with low-resolution data. Our framework is flexible in its ability to incorporate additional constraints; by constraining appliance usage with context and duration we can better disambiguate appliances with similar energy consumption profiles. We demonstrate the effectiveness of our framework on two public real-world datasets, reducing the error relative to a previous state-of-the-art method by as much as 50%.
Keywords:
Machine Learning: Time-series/Data Streams
Uncertainty in AI: Graphical Models
Multidisciplinary Topics and Applications: Computational Sustainability
Uncertainty in AI: Relational Inference