CS Seminar on October 30th, 2023

Abstract

“Deep reinforcement learning (DRL) can be used to develop an intelligent controller that can exploit information to schedule optimally the energy hub to minimize energy costs and emissions. By posing the energy hub scheduling problem as a multidimensional continuous state and action space, the deep deterministic policy gradient (DDPG) method enables more cost-effective control strategies. The method can lead to a more efficient operation by considering nonlinear physical characteristics of the energy hub components like nonconvex feasible operating regions of combined heat and power (CHP) units, valve-point effects of power-only units,  and fuel cell dynamic efficiency. Moreover, to provide great potential for the DDPG agent to learn an optimal policy efficiently, a hybrid forecasting model based on convolutional neural networks (CNNs) and bidirectional long short-term memories (BLSTMs) is developed to overcome the risk associated with PV power generation can be highly intermittent, particularly on cloudy days.”