LINQS

STATISTICAL RELATIONAL LEARNING GROUP @ UMD



 

Disambiguating Energy Disaggregation: A Collective Probabilistic Approach

Sabina Tomkins, Jay Pujara, Lise Getoor
International Joint Conference on Artifi cial Intelligence - 2017
Download the publication : tomkins-ijcai17.pdf [382Ko]  
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 date. 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, showing stateof- the-art performance.

BibTex references

@InProceedings{tomkins:ijcai17,
  author       = "Tomkins, Sabina and Pujara, Jay and Getoor, Lise",
  title        = "Disambiguating Energy Disaggregation: A Collective Probabilistic Approach",
  booktitle    = "International Joint Conference on Artificial Intelligence",
  year         = "2017",
}

Other publications in the database