{"type":"ScholarlyArticle","title":"Disambiguating Energy Disaggregation: A Collective Probabilistic Approach","authors":[{"name":"Sabina Tomkins","slug":"sabina-tomkins","given":"Sabina","family":"Tomkins","affiliation":"University of California , Santa Cruz"},{"name":"Jay Pujara","slug":"jay-pujara","given":"Jay","family":"Pujara","affiliation":"University of California , Santa Cruz"},{"name":"Lise Getoor","slug":"lise-getoor","given":"Lise","family":"Getoor","affiliation":"University of California , Santa Cruz"}],"abstract":"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\r\nmeter, 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\r\nour framework on two public real-world datasets, reducing the error relative to a previous state-of-the-art method by as much as 50%.","doi":"10.24963/ijcai.2017/398","url":"https://ijcai.org/proceedings/2017/398","pdf":"https://ijcai.org/proceedings/2017/0398.pdf","markdown":"https://ijcai.org/proceedings/2017/398.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/398","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Machine Learning S-Z","track":"Main track","number":398,"pages":{"first":2857,"last":2863},"keywords":["Uncertainty in AI: Graphical Models","Machine Learning: Time-series/Data Streams","Uncertainty in AI: Relational Inference","Multidisciplinary Topics and Applications: Computational Sustainability"],"videos":[],"references":[{"position":1,"raw":"[Attari et al., 2010] Shahzeen Z. Attari, Michael L. DeKay, Cliff I. Davidson, and Wndi Bruine de Bruin. Public perceptions of energy consumption and savings. Proceedings of the National Academy of Sciences (PNAS), 2010.","title":"Public perceptions of energy consumption and savings","authors":"Z Shahzeen, Michael L Attari, Cliff I Dekay, Wndi Davidson, Bruine De Bruin","year":"2010","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bach et al., 2015] Stephen H. Bach, Matthias Broecheler, Bert Huang, and Lise Getoor. Hinge-loss Markov Random fields and probabilistic soft logic. ArXiv:1505.04406 [cs.LG], 2015.","title":"Hinge-loss Markov Random fields and probabilistic soft logic","authors":"H Stephen, Matthias Bach, Bert Broecheler, Lise Huang, Getoor","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Boyd et al., 2011] Stephen Boyd, Neal Parikh, Eric Chu, Borja Pe- leato, and Jonathan Eckstein. Distributed optimization and statis- tical learning via the alternating direction method of multipliers. Foundations and Trends in Machine Learning, 2011.","title":"Distributed optimization and statistical learning via the alternating direction method of multipliers","authors":"Stephen Boyd, Neal Parikh, Eric Chu, Borja Peleato, Jonathan Eckstein","year":"2011","venue":"Foundations and Trends in Machine Learning","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Brandon and Lewis, 1999] Gwendolyn Brandon and Alan Lewis. Reducing household energy consumption: A qualitative and quantitative field study. Journal of Environmental Psychology, 1999.","title":"Reducing household energy consumption: A qualitative and quantitative field study","authors":"Lewis ; Brandon, Gwendolyn Brandon, Alan Lewis","year":"1999","venue":"Journal of Environmental Psychology","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Darby, 2006] Sarah Darby. The effectiveness of feedback on en- ergy consumption. A Review for DERFA of the Literature on Metering, Billing, and direct Displays. Technical report, Oxford University, 2006.","title":"The effectiveness of feedback on energy consumption. A Review for DERFA of the Literature on Metering, Billing, and direct Displays","authors":"Sarah Darby","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dietz et al., 2009] Thomas Dietz, Gerald T. Gardner, Jonathan Gilligan, Paul C. Stern, and Michael P. Vandenbergh. Household actions can provide a behavioral wedge to rapidly reduce us car- bon emissions. Proceedings of the National Academy of Sciences (PNAS), 2009.","title":"Household actions can provide a behavioral wedge to rapidly reduce us carbon emissions","authors":"Thomas Dietz, Gerald T Gardner, Jonathan Gilligan, Paul C Stern, Michael P Vandenbergh","year":"2009","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gardner and Stern, 2008] Gerald T. Gardner and Paul C. Stern. The short list: The most effective actions U.S. households can take to curb climate Change. Environment: Science and Policy for Sustainable Development, 2008.","title":"The short list: The most effective actions U.S. households can take to curb climate Change","authors":"Gerald T Gardner, Paul C Stern","year":"2008","venue":"Environment: Science and Policy for Sustainable Development","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ghahramani and Jordan, 1997] Zoubin Ghahramani and Michael I. Jordan. Factorial Hidden Markov Models. Ma- chine Learning, 1997.","title":"Factorial Hidden Markov Models","authors":"Zoubin Ghahramani, Michael I Jordan","year":"1997","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hart, 1992] George W. Hart. Nonintrusive Appliance Load Moni- toring. Proceedings of the IEEE, 1992.","title":"Nonintrusive Appliance Load Monitoring","authors":"George W Hart","year":"1992","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Johnson and Willsky, 2013] Matthew J. Johnson and Alan S. Will- sky. Bayesian nonparametric hidden semi-Markov models. Jour- nal of Machine Learning Research (JMLR), 2013.","title":"Bayesian nonparametric hidden semi-Markov models","authors":"Matthew J Johnson, Alan S","year":"2013","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kelly and Knottenbelt, 2015] Jack Kelly and William Knottenbelt. Neural NILM: Deep neural networks applied to energy Disaggre- gation. In ACM International Conference on Embedded Systems for Energy-Efficient Built Environments (BuildSys), 2015.","title":"Neural NILM: Deep neural networks applied to energy Disaggregation","authors":"Knottenbelt Kelly, Jack Kelly, William Knottenbelt","year":"2015","venue":"ACM International Conference on Embedded Systems for Energy-Efficient Built Environments","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kim et al., 2011] Hyungsul Kim, Manish Marwah, Martin Arlitt, Geoff Lyon, and Jiawei Han. Unsupervised disaggregation of low frequency power measurements. In SIAM International Confer- ence on Data Mining (SDM), 2011.","title":"Unsupervised disaggregation of low frequency power measurements","authors":"Hyungsul Kim, Manish Marwah, Martin Arlitt, Geoff Lyon, Jiawei Han","year":"2011","venue":"SIAM International Conference on Data Mining (SDM)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kolter and Jaakkola, 2012] J. Zico. Kolter and Tommi Jaakkola. Approximate inference in additive factorial HMMs with appli- cation to energy disaggregation. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2012.","title":"Approximate inference in additive factorial HMMs with application to energy disaggregation","authors":"Kolter, ; ] J Jaakkola, Zico, Tommi Kolter, Jaakkola","year":"2012","venue":"International Conference on Artificial Intelligence and Statistics (AISTATS)","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kolter and Johnson, 2011] J Zico Kolter and Matthew J Johnson. Redd: A public data set for energy disaggregation research. KDD Workshop on Data Mining Applications in Sustainability, 2011.","title":"Redd: A public data set for energy disaggregation research","authors":"Johnson ; ] J Zico Kolter, Matthew J Kolter, Johnson","year":"2011","venue":"KDD Workshop on Data Mining Applications in Sustainability","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kouki et al., 2015] Pigi Kouki, Shobeir Fakhraei, James Foulds, Magdalini Eirinaki, and Lise Getoor. HyPER: A flexible and extensible probabilistic framework for hybrid recommender sys- tems. In ACM Conference on Recommender Systems (RecSys), 2015.","title":"HyPER: A flexible and extensible probabilistic framework for hybrid recommender systems","authors":"Pigi Kouki, Shobeir Fakhraei, James Foulds, Magdalini Eirinaki, Lise Getoor","year":"2015","venue":"ACM Conference on Recommender Systems (RecSys)","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lange and Bergés, 2016] Henning Lange and Mario Bergés. BOLT: Energy disaggregation by online binary matrix factoriza- tion of current waveforms. In ACM International Conference on Systems for Energy-Efficient Built Environments (BuildSys), 2016.","title":"BOLT: Energy disaggregation by online binary matrix factorization of current waveforms","authors":"Bergés Lange, Henning Lange, Mario Bergés","year":"2016","venue":"ACM International Conference on Systems for Energy-Efficient Built Environments","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Li and Zha, 2016] Liangda Li and Hongyuan Zha. Household structure analysis via Hawkes processes for enhancing energy disaggregation. In International Conference on Artificial Intel- ligence (IJCAI), 2016.","title":"Household structure analysis via Hawkes processes for enhancing energy disaggregation","authors":"Zha ; Li, Liangda Li, Hongyuan Zha","year":"2016","venue":"International Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":"/proceedings/2016/363"},{"position":18,"raw":"[Makonin et al., 2015] Stephen Makonin, Fred Popowich, Ivan V. Bajic, Bob Gill, and Lyn Bartram. Exploiting HMM sparsity to perform online real-time nonintrusive load monitoring. IEEE Transactions on Smart Grid, 2015.","title":"Exploiting HMM sparsity to perform online real-time nonintrusive load monitoring","authors":"Stephen Makonin, Fred Popowich, Ivan V Bajic, Bob Gill, Lyn Bartram","year":"2015","venue":"IEEE Transactions on Smart Grid","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Makonin, 2014] Stephen William Makonin. Real-Time Embedded Low-Frequency Load Disaggregation. PhD thesis, Simon Fraser Univerity, 2014.","title":"Real-Time Embedded Low-Frequency Load Disaggregation","authors":"Stephen William, Makonin","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Murphy, 1998] Kevin Murphy. Hidden Markov Model (HMM) Toolbox for Matlab, 1998.","title":"Hidden Markov Model (HMM) Toolbox for Matlab","authors":"Kevin Murphy","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Parson et al., 2012] Oliver Parson, Siddhartha Ghosh, Mark Weal, and Alex Rogers. Non-intrusive load monitoring using prior models of general appliance types. In Artificial Intelligence (AAAI), 2012.","title":"Non-intrusive load monitoring using prior models of general appliance types","authors":"Oliver Parson, Siddhartha Ghosh, Mark Weal, Alex Rogers","year":"2012","venue":"Artificial Intelligence (AAAI)","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Shaloudegi et al., 2016] Kiarash Shaloudegi, András György, Csaba Szepesvari, and Wilsun Xu. Sdp relaxation with random- ized rounding for energy disaggregation. In Advances in Neural Information Processing Systems (NIPS), 2016.","title":"Sdp relaxation with randomized rounding for energy disaggregation","authors":"Kiarash Shaloudegi, András György, Csaba Szepesvari, Wilsun Xu","year":"2016","venue":"Advances in Neural Information Processing Systems (NIPS)","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Sridhar et al., 2015] Dhanya Sridhar, James Foulds, Marilyn Walker, Bert Huang, and Lise Getoor. Joint models of disagree- ment and stance in online debate. In Association for Computa- tional Linguistics (ACL), 2015.","title":"Joint models of disagreement and stance in online debate","authors":"Dhanya Sridhar, James Foulds, Marilyn Walker, Bert Huang, Lise Getoor","year":"2015","venue":"Association for Computational Linguistics (ACL)","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Stern, 1989] Paul C. Stern. Contributions of Psychology to Limit- ing Climate Change. American Psychologist, 1989.","title":"Contributions of Psychology to Limiting Climate Change","authors":"Paul C Stern","year":"1989","venue":"American Psychologist","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Van Houwelingen and Van Raaij, 1989] Jeannet H Van Houwelin- gen and W Fred Van Raaij. The effect of goal-setting and daily electronic feedback on in-home energy use. Journal of Consumer Research, 1989.","title":"The effect of goal-setting and daily electronic feedback on in-home energy use","authors":"Van Houwelingen, Van Raaij, ; Jeannet, H Van Houwelingen, W Fred Van Raaij","year":"1989","venue":"Journal of Consumer Research","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zeifman, 2012] Michael Zeifman. Disaggregation of home energy display data using probabilistic approach. IEEE Transactions on Consumer Electronics, 2012.","title":"Disaggregation of home energy display data using probabilistic approach","authors":"Michael Zeifman","year":"2012","venue":"IEEE Transactions on Consumer Electronics","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}