Predicting plug loads with occupant count data through a deep learning approach
Abstract
Predictive control has gained increasing attention for its ability to reduce energy consumption and improve occupant comfort in buildings. The plug loads prediction is a key component for the predictive building controls, as plug loads is a major source of internal heat gains in buildings. This study proposed a novel method to apply the Long-Short-Term-Memory (LSTM) Network, a special form of Recurrent Neural Network, to predict plug loads. The occupant count and the time have been confirmed to drive the plug load profile and thus selected as the features for the plug load prediction. The LSTM network was trained and tested with ground truth occupant count data collected from a real office building in Berkeley, California. Results from the LSTM network markedly improve the prediction accuracy compared with traditional linear regression methods and the classical Artificial Neural Network. 95% of 1-hour predictions from LSTM network are within ±1 kW of the actual plug loads, given the average plug loads during the office hour is 8.6 kW. The CV(RMSE) of the predicted plug load is 11% for the next hour, and 20% for the next eight hours. Lastly, we compared four prediction approaches with the office building we monitored: LSTM vs.more »
- Authors:
-
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Building Technology and Urban Systems Div.
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Sponsoring Org.:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE), Energy Efficiency Office. Building Technologies Office
- OSTI Identifier:
- 1526615
- Alternate Identifier(s):
- OSTI ID: 2325445
- Grant/Contract Number:
- AC02-05CH11231
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Energy (Oxford)
- Additional Journal Information:
- Journal Name: Energy (Oxford); Journal Volume: 181; Journal Issue: C; Journal ID: ISSN 0360-5442
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION; 97 MATHEMATICS AND COMPUTING; Plug loads; Prediction; Predictive control; Long Short Term Memory Network; Occupant count; Deep learning
Citation Formats
Wang, Zhe, Hong, Tianzhen, and Piette, Mary Ann. Predicting plug loads with occupant count data through a deep learning approach. United States: N. p., 2019.
Web. doi:10.1016/j.energy.2019.05.138.
Wang, Zhe, Hong, Tianzhen, & Piette, Mary Ann. Predicting plug loads with occupant count data through a deep learning approach. United States. https://doi.org/10.1016/j.energy.2019.05.138
Wang, Zhe, Hong, Tianzhen, and Piette, Mary Ann. Thu .
"Predicting plug loads with occupant count data through a deep learning approach". United States. https://doi.org/10.1016/j.energy.2019.05.138. https://www.osti.gov/servlets/purl/1526615.
@article{osti_1526615,
title = {Predicting plug loads with occupant count data through a deep learning approach},
author = {Wang, Zhe and Hong, Tianzhen and Piette, Mary Ann},
abstractNote = {Predictive control has gained increasing attention for its ability to reduce energy consumption and improve occupant comfort in buildings. The plug loads prediction is a key component for the predictive building controls, as plug loads is a major source of internal heat gains in buildings. This study proposed a novel method to apply the Long-Short-Term-Memory (LSTM) Network, a special form of Recurrent Neural Network, to predict plug loads. The occupant count and the time have been confirmed to drive the plug load profile and thus selected as the features for the plug load prediction. The LSTM network was trained and tested with ground truth occupant count data collected from a real office building in Berkeley, California. Results from the LSTM network markedly improve the prediction accuracy compared with traditional linear regression methods and the classical Artificial Neural Network. 95% of 1-hour predictions from LSTM network are within ±1 kW of the actual plug loads, given the average plug loads during the office hour is 8.6 kW. The CV(RMSE) of the predicted plug load is 11% for the next hour, and 20% for the next eight hours. Lastly, we compared four prediction approaches with the office building we monitored: LSTM vs. ARIMA, with occupant counts vs. without occupant counts. It was found, the prediction error of the LSTM approach is around 4% less than the ARIMA approach. Using occupant counts as an exogenous input could further reduce the prediction error by 5%-6%. The findings of this paper could shed light on the plug load prediction for building control optimizations such as model-predictive control.},
doi = {10.1016/j.energy.2019.05.138},
journal = {Energy (Oxford)},
number = C,
volume = 181,
place = {United States},
year = {Thu May 23 00:00:00 EDT 2019},
month = {Thu May 23 00:00:00 EDT 2019}
}
Web of Science