Additional Calendars
Calendar Views
All
Athletics
Conferences and Meetings
Law School
Special Events

ECE Seminar-Topic: Deep Learning Applications in Energy Storage Management and Renewable Energy Resources Integration

When: Tuesday, November 29, 2022
2:00 PM - 3:00 PM
Where: Science and Engineering Building 285 Old Westport Road, Dartmouth, MA
Cost: Free
Description: Speaker:
Dr. Hussein Abdeltawab
Penn State University
Behrend College

Location: Science & Engineering Building (SENG), Room 118

Zoom Teleconference: Abdeltawab-Research Presentation


Abstract:
Renewable energy (RE) resources have attracted extensive attention worldwide. However, due to their intermittency, RE resources could pose considerable challenges to the optimal operation of the energy systems despite their low carbon footprint. As a result, accurate RE forecasting and efficient operation of RE-integrated energy systems has gained paramount interest in the research community. The rapid growth of deep learning (DL) techniques can contribute to precise forecasting and optimal management of such systems, as will be discussed in this presentation. First, the DL forecasting techniques will include; Investigating a light detection and ranging (LiDAR)-aided deep learning model to learn the powerful spatial-temporal characteristics from the input wind fields and using sky images in PV irradiance estimation. Second, Deep reinforcement learning (DRL) is utilized in optimizing the compressed air energy storage (CAES) energy arbitrage in the presence of a solar irradiance forecasting model. Another application is applying the deep deterministic policy gradient (DDPG) framework to develop an intelligent controller to optimally schedule a multi-carrier energy hub. Finally, Twin Delayed DDPG (TD3) is utilized for optimal model-free management of the battery swapping station.

The Seminars is open to the public free of charge.

*For further information, please contact Dr. John Buck at 508.999.9237, or by via email at jbuck@umassd.edu.
Topical Areas: General Public, University Community, College of Engineering, Electrical and Computer Engineering