Future of Buildings: Graduate Insights and Innovations

“Building-domain GenAI Application: Conditional generative adversarial network (cGAN) for generating building load profiles with photovoltaics and electric vehicles”
Presenter: Yuewei Li, fifth-year Ph.D. candidate in Mechanical and Aerospace Engineering, affiliated with Built Environment Science and Technology (BEST) Lab

In recent years, the adoption of distributed energy resources (DERs) has increased significantly. However, most existing load forecasting and energy modeling techniques do not adequately account for the variability introduced by DERs, which poses challenges for accurate energy management and grid planning. To address this gap of the growing need for realistic building load profiles that consider the integration of DERs, particularly solar photovoltaic (PV) and electric vehicles (EVs), we use a conditional Generative Adversarial Network (cGAN) to generate load profiles that reflect the dynamic impacts of DERs under various conditions, such as seasonal variations and PV and EV adoption scenarios. The proposed cGAN approach offers a scalable and data-driven solution to generate realistic building load profiles under different DER conditions. This method provides utility companies, researchers, and policymakers with synthetic datasets for comprehensive analysis, supporting energy management, demand response planning, and DER policy design. By offering a flexible tool for large-scale load profile generation, our study contributes to more effective integration of DERs within energy systems.

Hosted by the ASHRAE Student Branch at Syracuse University, “Future of Buildings: Graduate Insights and Innovations” presentations are held every other Thursday at 727 E. Washington St. Lunch is provided and free parking is available onsite. Please RSVP to attend.

Learn more Register now