Published: June 30, 2022

How could we predict large-scale building power demand fast and accurately? Generative Adversarial Networks (GAN), as a potential candidate, have recently attracted a lot of attention. This paper identified five promising GANs (Original GAN, cGAN, SGAN, InfoGAN, and ACGAN) and evaluates their performance for predicting building power demand at a large scale. As a result, cGAN and Original GAN are recommended.

This work has been published under the title “Evaluating Performance of Different Generative Adversarial Networks for Large-Scale Building Power Demand Prediction” in the journal Energy and Buildings. The full paper is available here.

The first author of this paper, Dr. Yunyang Ye, is the former member of the SBS Lab. He is currently a Research Scientist at Pacific Northwest National Laboratory (PNNL). His research focuses on building energy modeling, building code and standards analyses, urban scale modeling, building-to-grid integration, and energy policies.

Congratulations to Yunyang on publishing this paper!