Aggregately Regularized Multi-task Matrix Factorization for Household Energy Breakdown
- 830 Downloads
Household energy breakdown aims to disaggregate the monthly energy consumption into appliance level usage. It is an important but challenging issue due to the cost of hardware deployments. Existing approaches shed light on decomposing the energy in a non-intrusive way and utilizing matrix factorization. However, traditional matrix factorization methods overlook the relations among appliances and aggregations. In this paper, we propose an novel aggregately regularized Multi-task model, Non-negative Matrix Factorization (MultiNMF), to address this issue. By combining the per-appliance tasks with regularizations, MultiNMF can simultaneously infer the appliance level energy usage for users. The model is evaluated on both synthetic and real world datasets with different settings, and the experimental results demonstrate the effectiveness of our approach.
This work was supported in part by the National Natural Science Foundation of China (Grant No.61802124), and the Fundamental Research Funds for the Central Universities (2019MS126).
- 1.Abdi, M.H., Okeyo, G.O., Mwangi, R.W.: Matrix factorization techniques for context-aware collaborative filtering recommender systems: a survey. Comput. Inf. Sci. 11(2), 1–10 (2018)Google Scholar
- 3.Batra, N., Singh, A., Whitehouse, K.: Gemello: creating a detailed energy breakdown from just the monthly electricity bill. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, pp. 431–440, 13–17 August 2016Google Scholar
- 4.Batra, N., Wang, H., Singh, A., Whitehouse, K.: Matrix factorisation for scalable energy breakdown. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, pp. 4467–4473, 4–9 February 2017Google Scholar
- 5.Debruin, S., Ghena, B., Kuo, Y.S., Dutta, P.: Demo: powerblade a low-profile, true-power, plug-through energy meter. In: Proceedings of the ACM Conference on Embedded Networked Sensor Systems, pp. 463–464 (2015)Google Scholar
- 7.Gupta, S., Reynolds, M.S., Patel, S.N.: Electrisense: single-point sensing using EMI for electrical event detection and classification in the home. In: Proceedings of the 12th International Conference on Ubiquitous Computing, UbiComp 2010, Copenhagen, Denmark, pp. 139–148, 26–29 September 2010Google Scholar
- 9.Kim, Y., Schmid, T., Charbiwala, Z., Srivastava, M.B.: ViridiScope: design and implementation of a fine grained power monitoring system for homes. In: Proceedings of the 11th International Conference on Ubiquitous Computing, UbiComp 2009, pp. 245–254 (2009)Google Scholar
- 11.Lee, D.D., Seung, H.S.: Algorithms for non-negative matrix factorization. In: Proceedings of the Neural Information Processing Systems 2000, Denver, pp. 556–562 (2000)Google Scholar
- 13.Parson, O., et al.: Dataport and NILMTK: a building data set designed for non-intrusive load monitoring. In: Proceedings of the 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015, Orlando, pp. 210–214, 14–16 December 2015Google Scholar