ABSTRACT
Electric water heaters consume approximately 19% of the total energy in residential buildings and may be used as virtual batteries to provide a variety of ancillary services for the electric grid. With the proliferation of advanced metering infrastructure (AMI) smart meters, vast amounts of data have become available for non-intrusive load disaggregation. Disaggregating major appliances such as water heaters using low-resolution AMI data may assist in assessing residential virtual battery potential at a regional level. In this paper, we assess the use of a graph signal processing algorithm for non-intrusive load disaggregation of a hybrid heat pump water heater. Algorithm performance is evaluated for disaggregating the water heater signal in the presence of a variety of other loads and operational modes. Real-world data sampled in the field at a frequency of 1 minute and downsampled for the purpose of this study to 15 minutes were used to simulate typical AMI meter sampling frequency. Results demonstrate that F-measures (the harmonic mean of precision and recall values) > 0.90 are achievable for water heater disaggregation.
- EIA. Residential Energy Consumption Survey. U.S. Energy Information Administration, Washington D.C., 2015.Google Scholar
- Somani, A., Wu, D., Kalsi, K., Reiman, A., Alam, J., Fan, R., Mongird, K. and Balducci, P. Preliminary locational net-benefit analysis (LBNA) using building loads represented as virtual batteries. Pacific Northwest National Laboratory, Alexandria, VA, 2018.Google Scholar
- EIA. Annual Electric Power Industry Report. United States Energy Information Association, Washington, D.C., 2019.Google Scholar
- Parson, O., Ghosh, S., Weal, M. and Rogers, A. Non-intrusive load monitoring using prior models of general appliance types. In Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence (Toronto, Canada, 2012). 2012.Google ScholarDigital Library
- Zoha, A., Gluhak, A., Imran, M. A. and Rajasegarar, S. Non-intrusive load monitoring approaches for disaggregated energy sensing: a survey. Sensors (Basel), 12, 12 (2012), 16838--16866.Google ScholarCross Ref
- Kim, H., Marwah, M., Arlitt, M., Lyon, G. and Han, J. Unsupervised disaggregation of low frequency power measurements. In Proceedings of the 2011 SIAM International Conference on Data Mining (Mesa, Arizona, USA, 2012). 2012.Google Scholar
- Kolter, J. Z. and Jaakkola, T. Approximate Inference in Additive Factorial HMMs with Application to Energy Disaggregation. In Proceedings of the Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, 2012). PMLR. 2012.Google Scholar
- Basu, K., Debusschere, V., Bacha, S., Maulik, U. and Bondyopadhyay, S. Nonintrusive Load Monitoring: A Temporal Multilabel Classification Approach. IEEE Transactions on Industrial Informatics, 11, 1 (2015), 262--270.Google ScholarCross Ref
- Zhao, B., Stankovic, L. and Stankovic, V. On a Training-Less Solution for Non-Intrusive Appliance Load Monitoring Using Graph Signal Processing. IEEE Access, 4 (2016), 1784--1799.Google Scholar
- Zhao, B., Ye, M., Stankovic, L. and Stankovic, V. Non-intrusive load disaggregation solutions for very low-rate smart meter data. Applied Energy, 268 (2020/06/15/ 2020), 114949.Google Scholar
- Shuman, D. I., Narang, S. K., Frossard, P., Ortega, A. and Vandergheynst, P. The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains. IEEE Signal Processing Magazine, 30, 3 (2013), 83--98.Google ScholarCross Ref
- He, K., Stankovic, L., Liao, J. and Stankovic, V. Non-Intrusive Load Disaggregation Using Graph Signal Processing. IEEE Transactions on Smart Grid, 9, 3 (2018), 1739--1747.Google Scholar
- Ortega, A., Frossard, P., Kovačević, J., Moura, J. M. F. and Vandergheynst, P. Graph Signal Processing: Overview, Challenges, and Applications. Proceedings of the IEEE, 106, 5 (2018), 808--828.Google ScholarCross Ref
- Chen, S., Varma, R., Singh, A. and Kovacevic, J. Signal representations on graphs: tools and applications. CoRR (2015).Google Scholar
- Boyd, S. P. Convex optimization. Cambridge, UK New York: Cambridge University Press, Cambridge, UK New York, 2004.Google ScholarDigital Library
- Fugate, D. ORNL-NILMS Project Yarnell Station Research House. Oak Ridge, TN, 2019.Google Scholar
- Batra, N., Kelly, J., Parson, O., Dutta, H., Knottenbelt, W., Rogers, A., Singh, A. and Srivastava, M. NILMTK: an open source toolkit for non-intrusive load monitoring. In Proceedings of the Proceedings of the 5th International Conference on Future Energy Systems (Cambridge, United Kingdom, 2014). Association for Computing Machinery, New York City, USA. 2014.Google ScholarDigital Library
Index Terms
- Non-Intrusive Load Monitoring of Water Heaters Using Low-Resolution Data
Recommendations
Actual Consumption Estimation Algorithm for Occupancy Detection using Low Resolution Smart Meter Data
SENSORNETS 2017: Proceedings of the 6th International Conference on Sensor NetworksThis paper proposes an actual consumption estimation algorithm that achieves highly accurate occupancy detection using electricity consumption data derived from smart meters. In Japan, electricity consumption data on households will soon be available ...
Implications of data sampling resolution on water use simulation, end-use disaggregation, and demand management
AbstractUnderstanding the tradeoff between the information of high-resolution water use data and the costs of smart meters to collect data with sub-minute resolution is crucial to inform smart meter networks. To explore this tradeoff, we first ...
Highlights- We assess information from water use data at different time sampling resolutions.
An Approach to Outage Location Prediction Utilizing Smart Metering Data
AMS '14: Proceedings of the 2014 8th Asia Modelling SymposiumRecently, advanced and intelligent power supply networks have been proposed under the concept of Smart Grid and smart meters have been implemented all over the world as the first step. While the first purpose of smart meter installation is improvement ...
Comments