Behind-the-Meter Solar Generation Disaggregation using Consumer Mixture Models
Abstract
To facilitate deep penetration of solar energy in smart grids, we need high observability of solar generation at the edges of the grid. Current advanced metering infrastructures (AMI) only monitor the aggregated measurements from net-metered households, but disaggregated consumption and solar generation components are required for grid optimizations. We propose an unsupervised disaggregation model for disaggregating solar generation from AMI measurements without the need of training data. The model requires only AMI measurements from consumers in a region and the solar irradiance as input, and models the consumption of consumers by neighboring households without rooftop photovoltaics (PV) to perform the disaggregation. We evaluate our results on a real life dataset from Austin, Texas. We show that our model is able to disaggregate consumption and solar generation measurements with 42.24% and 31.67% less mean squared error, respectively, in comparison to a baseline technique that uses supervised learning. This shows that our model is capable of disaggregating historical data even if the dataset has no training data and only contains minimal exogenous data.
- Authors:
-
- Department of Computer Science, University of Southern California, Los Angeles, CA
- Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA
- US Army Research Lab, Playa Vista, CA
- Publication Date:
- Research Org.:
- Univ. of Southern California, Los Angeles, CA (United States)
- Sponsoring Org.:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Geothermal Technologies Office; USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office
- OSTI Identifier:
- 1607577
- Report Number(s):
- EE0008003-5
- DOE Contract Number:
- EE0008003
- Resource Type:
- Conference
- Resource Relation:
- Conference: 2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 14 SOLAR ENERGY; Behind-the-meter, Disaggregation, Solar Energy
Citation Formats
Cheung, Chung Ming, Zhong, Wen, Xiong, Chuanxiu, Srivastava, Ajitesh, Kannan, Rajgopal, and Prasanna, Viktor K. Behind-the-Meter Solar Generation Disaggregation using Consumer Mixture Models. United States: N. p., 2017.
Web. doi:10.1109/SmartGridComm.2018.8587539.
Cheung, Chung Ming, Zhong, Wen, Xiong, Chuanxiu, Srivastava, Ajitesh, Kannan, Rajgopal, & Prasanna, Viktor K. Behind-the-Meter Solar Generation Disaggregation using Consumer Mixture Models. United States. https://doi.org/10.1109/SmartGridComm.2018.8587539
Cheung, Chung Ming, Zhong, Wen, Xiong, Chuanxiu, Srivastava, Ajitesh, Kannan, Rajgopal, and Prasanna, Viktor K. 2017.
"Behind-the-Meter Solar Generation Disaggregation using Consumer Mixture Models". United States. https://doi.org/10.1109/SmartGridComm.2018.8587539. https://www.osti.gov/servlets/purl/1607577.
@article{osti_1607577,
title = {Behind-the-Meter Solar Generation Disaggregation using Consumer Mixture Models},
author = {Cheung, Chung Ming and Zhong, Wen and Xiong, Chuanxiu and Srivastava, Ajitesh and Kannan, Rajgopal and Prasanna, Viktor K.},
abstractNote = {To facilitate deep penetration of solar energy in smart grids, we need high observability of solar generation at the edges of the grid. Current advanced metering infrastructures (AMI) only monitor the aggregated measurements from net-metered households, but disaggregated consumption and solar generation components are required for grid optimizations. We propose an unsupervised disaggregation model for disaggregating solar generation from AMI measurements without the need of training data. The model requires only AMI measurements from consumers in a region and the solar irradiance as input, and models the consumption of consumers by neighboring households without rooftop photovoltaics (PV) to perform the disaggregation. We evaluate our results on a real life dataset from Austin, Texas. We show that our model is able to disaggregate consumption and solar generation measurements with 42.24% and 31.67% less mean squared error, respectively, in comparison to a baseline technique that uses supervised learning. This shows that our model is capable of disaggregating historical data even if the dataset has no training data and only contains minimal exogenous data.},
doi = {10.1109/SmartGridComm.2018.8587539},
url = {https://www.osti.gov/biblio/1607577},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Sun Oct 29 00:00:00 EDT 2017},
month = {Sun Oct 29 00:00:00 EDT 2017}
}