Abstract
Accurate energy forecasting is becoming critical due to many reasons: i ) optimal distributed energy resources operations and dispatch, ii) fault detection and diagnostics, and iii) meeting operational energy efficiency targets. Wattile uses deep learning (DL) for the building's short-term load forecasting application. Two specific types of neural networks called, Long Short Term Memory (LSTM) and Sequence-to-Sequence (S2S) models are used to make predictions. Forecasting models are trained using online historical weather and occupancy indicator data streams from the Intelligent Campus Program's data acquisition systems at the National Renewable Energy Laboratory (NREL) for main meters and sub-meters of multiple building types. These models use probabilistic methods to provide quantile-based forecasts in addition to nominal conditional median predictions of electricity consumption.
- Developers:
-
Frank, Stephen [1] ; Petersen, Anya [1] ; Mishra, Sakshi [1] ; Kim, Janghyun [1] ; Zhang, Liang [1] ; Eslinger, Hannah [1] ; Buechler, Robert [1]
- National Renewable Energy Lab. (NREL), Golden, CO (United States)
- Release Date:
- 2020-08-26
- Project Type:
- Open Source, Publicly Available Repository
- Software Type:
- Scientific
- Programming Languages:
-
Jupyter Notebook
- Licenses:
-
BSD 3-clause "New" or "Revised" License
- Sponsoring Org.:
-
USDOEPrimary Award/Contract Number:AC36-08GO28308NREL Overhead FundsPrimary Award/Contract Number:AC36-08GO28308
- Code ID:
- 103525
- Site Accession Number:
- NREL SWR-20-94
- Research Org.:
- National Renewable Energy Laboratory (NREL), Golden, CO (United States)
- Country of Origin:
- United States
Citation Formats
Frank, Stephen, Petersen, Anya, Mishra, Sakshi, Kim, Janghyun, Zhang, Liang, Eslinger, Hannah, and Buechler, Robert.
Wattile: Probabilistic Deep Learning-based Forecasting of Building Energy Consumption [SWR-20-94].
Computer Software.
https://github.com/NREL/Wattile.
USDOE, NREL Overhead Funds.
26 Aug. 2020.
Web.
doi:10.11578/dc.20230406.3.
Frank, Stephen, Petersen, Anya, Mishra, Sakshi, Kim, Janghyun, Zhang, Liang, Eslinger, Hannah, & Buechler, Robert.
(2020, August 26).
Wattile: Probabilistic Deep Learning-based Forecasting of Building Energy Consumption [SWR-20-94].
[Computer software].
https://github.com/NREL/Wattile.
https://doi.org/10.11578/dc.20230406.3.
Frank, Stephen, Petersen, Anya, Mishra, Sakshi, Kim, Janghyun, Zhang, Liang, Eslinger, Hannah, and Buechler, Robert.
"Wattile: Probabilistic Deep Learning-based Forecasting of Building Energy Consumption [SWR-20-94]." Computer software.
August 26, 2020.
https://github.com/NREL/Wattile.
https://doi.org/10.11578/dc.20230406.3.
@misc{
doecode_103525,
title = {Wattile: Probabilistic Deep Learning-based Forecasting of Building Energy Consumption [SWR-20-94]},
author = {Frank, Stephen and Petersen, Anya and Mishra, Sakshi and Kim, Janghyun and Zhang, Liang and Eslinger, Hannah and Buechler, Robert},
abstractNote = {Accurate energy forecasting is becoming critical due to many reasons: i ) optimal distributed energy resources operations and dispatch, ii) fault detection and diagnostics, and iii) meeting operational energy efficiency targets. Wattile uses deep learning (DL) for the building's short-term load forecasting application. Two specific types of neural networks called, Long Short Term Memory (LSTM) and Sequence-to-Sequence (S2S) models are used to make predictions. Forecasting models are trained using online historical weather and occupancy indicator data streams from the Intelligent Campus Program's data acquisition systems at the National Renewable Energy Laboratory (NREL) for main meters and sub-meters of multiple building types. These models use probabilistic methods to provide quantile-based forecasts in addition to nominal conditional median predictions of electricity consumption.},
doi = {10.11578/dc.20230406.3},
url = {https://doi.org/10.11578/dc.20230406.3},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20230406.3}},
year = {2020},
month = {aug}
}