ABSTRACT
Residential buildings constitute roughly one-fourth of the total energy use across the globe. Numerous studies have shown that providing an energy breakdown increases residents' awareness of energy use and can help save up to 15% energy. A significant amount of prior work has looked into source-separation techniques collectively called non-intrusive load monitoring (NILM), and most prior NILM research has leveraged high-frequency household aggregate data for energy breakdown. However, in practice most smart meters only sample hourly or once every 15 minutes, and existing NILM techniques show poor performance at such a low sampling rate.
In this paper, we propose a TreeCNN model for energy breakdown on low frequency data. There are three key insights behind the design of our model: i) households consume energy with regular temporal patterns, which can be well captured by filters learned in CNNs; ii) tree structure isolates the pattern learning of each appliance that helps avoid magnitude variance problem, while preserves relationship among appliances; iii) tree structure enables the separation of known appliance from unknown ones, which de-noises the input time series for better appliance-level reconstruction. Our TreeCNN model outperformed seven existing baselines on a public benchmark dataset with lower estimation error and higher accuracy on detecting the active states of appliances.
- Jose´ Alcalá, Oliver Parson, and Alex Rogers. 2015. Detecting anomalies in activities of daily living of elderly residents via energy disaggregation and cox processes. In Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments. Google ScholarDigital Library
- K Carrie Armel, Abhay Gupta, Gireesh Shrimali, and Adrian Albert. 2013. Is disaggregation the holy grail of energy efficiency? The case of electricity. Energy Policy 52(2013), 213-234.Google ScholarCross Ref
- Sean Barker, Sandeep Kalra, David Irwin, and Prashant Shenoy. 2013. Empirical characterization and modeling of electrical loads in smart homes. In IEEE IGCC. Arlington, VA, USA.Google Scholar
- Nipun Batra, Yiling Jia, Hongning Wang, Kamin Whitehouse, 2018. Transferring Decomposed Tensors for Scalable Energy Breakdown across Regions. AAAI (2018).Google Scholar
- Nipun Batra, Jack Kelly, Oliver Parson, Haimonti Dutta, William Knottenbelt, Alex Rogers, Amarjeet Singh, and Mani Srivastava. 2014. NILMTK: An Open Source Toolkit for Non-intrusive Load Monitoring. In Fifth International Conference on Future Energy Systems. Cambridge, UK. arXiv:1404.3878 Google ScholarDigital Library
- Nipun Batra, Amarjeet Singh, and Kamin Whitehouse. 2016. Gemello: Creating a Detailed Energy Breakdown from Just the Monthly Electricity Bill. In SIGKDD 2016. Google ScholarDigital Library
- Nipun Batra, Hongning Wang, Amarjeet Singh, and Kamin Whitehouse. 2017. Matrix Factorisation for Scalable Energy Breakdown.. In AAAI. 4467-4473. Google ScholarDigital Library
- Mario E Berges, Ethan Goldman, H Scott Matthews, and Lucio Soibelman. 2010. Enhancing electricity audits in residential buildings with nonintrusive load monitoring. Journal of industrial ecology 14, 5 (2010), 844-858.Google ScholarCross Ref
- George William Hart. 1992. Nonintrusive appliance load monitoring. Proc. IEEE 80, 12 (1992), 1870-1891.Google ScholarCross Ref
- Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning. Google ScholarDigital Library
- Jack Kelly and William Knottenbelt. 2015. Neural NILM: Deep neural networks applied to energy disaggregation. In Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments. ACM, 55-64. Google ScholarDigital Library
- Jihyun Kim, Thi-Thu-Huong Le, and Howon Kim. 2017. Nonintrusive load monitoring based on advanced deep learning and novel signature. Computational intelligence and neuroscience 2017 (2017).Google Scholar
- J. Z. Kolter, S. Batra, and A. Y. Ng. 2010. Energy Disaggregation via Discriminative Sparse Coding. In NIPS 2010. Vancouver, BC, Canada. Google ScholarDigital Library
- J. Z. Kolter and T. Jaakkola. 2012. Approximate Inference in Additive Factorial HMMs with Application to Energy Disaggregation. In Proceedings of the International Conference on Artificial Intelligence and Statistics. La Palma, Canary Islands.Google Scholar
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097-1105. Google ScholarDigital Library
- Roderick JA Little. 1988. Missing-data adjustments in large surveys. Journal of Business & Economic Statistics 6, 3 (1988), 287-296.Google Scholar
- Oliver Parson, Grant Fisher, April Hersey, Nipun Batra, Jack Kelly, Amarjeet Singh, William Knottenbelt, and Alex Rogers. 2015. Dataport and NILMTK: A building data set designed for non-intrusive load monitoring. In GlobalSIP 2015. IEEE.Google ScholarCross Ref
- Oliver Parson, Siddhartha Ghosh, Mark J Weal, and Alex Rogers. 2012. Non-Intrusive Load Monitoring Using Prior Models of General Appliance Types.. In AAAi. Google ScholarDigital Library
- Adam Paszke, Sam Gross, Soumith Chintala, and Gregory Chanan. 2017. Pytorch.Google Scholar
- Luis Pe´rez-Lombard, Jose´ Ortiz, and Christine Pout. 2008. A review on buildings energy consumption information. Energy and buildings 40, 3 (2008), 394-398.Google Scholar
- Staff Report. 2017. 2017 Assessment of Demand Response and Advanced Metering.Google Scholar
- Jeffrey M Wooldridge. 2007. Inverse probability weighted estimation for general missing data problems. Journal of Econometrics 141, 2 (2007), 1281-1301.Google ScholarCross Ref
- Mingjun Zhong, Nigel Goddard, and Charles Sutton. 2015. Latent Bayesian melding for integrating individual and population models. In NIPS 2015. Google ScholarDigital Library
Recommendations
Active Collaborative Sensing for Energy Breakdown
CIKM '19: Proceedings of the 28th ACM International Conference on Information and Knowledge ManagementResidential homes constitute roughly one-fourth of the total energy usage worldwide. Providing appliance-level energy breakdown has been shown to induce positive behavioral changes that can reduce energy consumption by 15%. Existing approaches for ...
Circuit-Level Load Monitoring for Household Energy Management
The first requirement for any intelligent household energy management system is to accurately measure home energy use. Whole-home energy measurement is cheap and easy to set up because it requires only one sensor where the home connects to the power ...
Management of Household Energy Saving and Its Green Alternatives: Information of Chinese Energy Consumption Patterns
Given the significant growth potential in households' energy consumption in China, studying household consumption behavior becomes even more valuable. This study explores factors influencing the shift in households' energy-saving preferences from ...
Comments