Yuan Zhang

Lu An, Jie Duan, Yuan Zhang et al.

Microgrids are self-sufficient small-scale power grid systems that can employ renewable generation sources and energy storage devices and can connect to the main grid or operate in a stand-alone mode. Most research on energy-storage management in microgrids does not take into account the dynamic nature of the problem and the need for fully-distributed, multi-step scheduling. First, we address these requirements by extending our previously proposed \textit{multi-step cooperative distributed energy scheduling} (CoDES) algorithm to include both purchasing power from and selling the generated power to the main grid. Second, we model the microgrid as a multi-agent system where the agents (e.g. households) act as players in a cooperative game and employ a distributed algorithm based on the Nash Bargaining Solution (NBS) to fairly allocate the costs of cooperative power management (computed using CoDES) among themselves. The dependency of the day-ahead power schedule and the costs on system parameters, e.g., the price schedule and the user activity level (measured by whether it owns storage and renewable generation devices), is analyzed for a three-agent microgrid example.

Yuan Zhang, Jasper Hoffmann, Joschka Boedecker

Learning-based techniques have become popular in both model predictive control (MPC) and reinforcement learning (RL). Probabilistic ensemble (PE) models offer a promising approach for modelling system dynamics, showcasing the ability to capture uncertainty and scalability in high-dimensional control scenarios. However, PE models are susceptible to mode collapse, resulting in non-robust control when faced with environments slightly different from the training set. In this paper, we introduce the $\textbf{u}$ncertainty-$\textbf{d}$riven rob$\textbf{u}$st $\textbf{c}$ontrol (UDUC) loss as an alternative objective for training PE models, drawing inspiration from contrastive learning. We analyze the robustness of UDUC loss through the lens of robust optimization and evaluate its performance on the challenging Real-world Reinforcement Learning (RWRL) benchmark, which involves significant environmental mismatches between the training and testing environments.