Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: Evaluating performance of different generative adversarial networks for large-scale building power demand prediction

Journal Article · · Energy and Buildings
 [1];  [2];  [2];  [2]; ORCiD logo [3];  [2]
  1. Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
  2. University of Colorado, Boulder, CO (United States)
  3. Pennsylvania State University, University Park, PA (United States); National Renewable Energy Lab. (NREL), Golden, CO (United States)
+ Show Author Affiliations

We report as an unsupervised-learning data-driven model, Generative Adversarial Networks (GANs) have recently attracted a lot of attention for various applications. There is potential to apply GANs for large-scale building power demand prediction, which is needed for power grid operation. However, there are many GAN variations and it is unclear which GAN is suitable for this application. To answer this question, this paper identifies five promising GANs (Original GAN, cGAN, SGAN, InfoGAN, and ACGAN) and evaluates their performance for predicting building power demand at a large scale. Physics-based building energy models are developed to generate training and reference data. A new evaluation indicator that combines accuracy and reproducibility is proposed to evaluate the performance of different GANs in predicting building power demand. The results show that SGAN and InfoGAN are not suitable because they cannot control the number of generated building samples for different building types. The prediction performance among the Original GAN, cGAN, and ACGAN can vary depending on training sample sizes and number of building types. If the training sample size is sufficiently large, Original GAN and cGAN can predict building power demand more accurately than ACGAN with the same number of samples. If training samples are limited, Original GAN provides better accuracy than cGAN and ACGAN. When the number of building types increase, the prediction accuracy increases for cGAN, decreases for ACGAN, and remains the same for Original GAN. As a result, cGAN and Original GAN are recommended for large-scale building power demand prediction.

Research Organization:
National Renewable Energy Laboratory (NREL), Golden, CO (United States); Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Sponsoring Organization:
USDOE Office of Energy Efficiency and Renewable Energy (EERE)
Grant/Contract Number:
AC05-76RL01830; AC36-08GO28308
OSTI ID:
1876878
Report Number(s):
NREL/JA-5500-83477; PNNL-SA-166754; MainId:84250; UUID:708e4d39-f3a9-473a-aac4-1f0d47edd81d; MainAdminID:64878
Journal Information:
Energy and Buildings, Journal Name: Energy and Buildings Vol. 269; ISSN 0378-7788
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (19)

Calibrating building energy models using supercomputer trained machine learning agents: CALIBRATING BEMS USING SUPERCOMPUTER TRAINED ML AGENTS
  • Sanyal, Jibonananda; New, Joshua; Edwards, Richard E.
  • Concurrency and Computation: Practice and Experience, Vol. 26, Issue 13 https://doi.org/10.1002/cpe.3267
journal March 2014
Daily power demand prediction for buildings at a large scale using a hybrid of physics-based model and generative adversarial network journal February 2022
Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques journal August 2014
Automatic generation and simulation of urban building energy models based on city datasets for city-scale building retrofit analysis journal November 2017
Data-driven Urban Energy Simulation (DUE-S): A framework for integrating engineering simulation and machine learning methods in a multi-scale urban energy modeling workflow journal September 2018
An integrated data-driven framework for urban energy use modeling (UEUM) journal November 2019
A novel semi-supervised data-driven method for chiller fault diagnosis with unlabeled data journal March 2021
Data-driven Urban Energy Simulation (DUE-S): Integrating machine learning into an urban building energy simulation workflow journal December 2017
DUE-B: Data-driven urban energy benchmarking of buildings using recursive partitioning and stochastic frontier analysis journal March 2018
Data driven parallel prediction of building energy consumption using generative adversarial nets journal March 2019
Generating realistic building electrical load profiles through the Generative Adversarial Network (GAN) journal October 2020
A semi-supervised approach to fault detection and diagnosis for building HVAC systems based on the modified generative adversarial network journal September 2021
Comparing Generative Adversarial Networks architectures for electricity demand forecasting journal September 2021
Tuning machine learning models for prediction of building energy loads journal May 2019
Development of new baseline models for U.S. medium office buildings based on commercial buildings energy consumption survey data journal May 2020
Digital Signal Modulation Classification With Data Augmentation Using Generative Adversarial Nets in Cognitive Radio Networks journal January 2018
Prediction of electric power consumption for commercial buildings
  • Cherkassky, Vladimir; Roy Chowdhury, Sohini; Landenberger, Volker
  • 2011 International Joint Conference on Neural Networks (IJCNN 2011 - San Jose), The 2011 International Joint Conference on Neural Networks https://doi.org/10.1109/IJCNN.2011.6033285
conference July 2011
Transactive Control of Commercial Buildings for Demand Response journal January 2017
Introduction to Semi-Supervised Learning journal January 2009

Similar Records

Related Subjects

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
Generative adversarial networks
hybrid model
EnergyPlus
building power demand prediction
large scale
building
data-driven model
generative adversarial networks
power demand prediction