The emergence of microgrids (MGs) has provided a promising solution for decarbonizing and decentralizing the power grid, mitigating the challenges posed by climate change. However, MG operations often involve considering multiple objectives that represent the interests of different stakeholders, leading to potentially complex conflicts. To tackle this issue, we propose a novel multi-objective reinforcement learning framework that explores the high-dimensional objective space and uncovers the tradeoffs between conflicting objectives. This framework leverages exogenous information and capitalizes on the data-driven nature of reinforcement learning, enabling the training of a parametric policy without the need for long-term forecasts or knowledge of the underlying uncertainty distribution. The trained policies exhibit diverse, adaptive, and coordinative behaviors with the added benefit of providing interpretable insights on the dynamics of their information use. We employ this framework on the Cornell University MG (CU-MG), which is a combined heat and power MG, to evaluate its effectiveness. The results demonstrate performance improvements in all objectives considered compared to the status quo operations and offer more flexibility in navigating complex operational tradeoffs.

翻译：微电网（MG）的出现为电力系统的脱碳化和去中心化提供了有前途的解决方案，有助于缓解气候变化带来的挑战。然而，微电网运行往往涉及多个目标，这些目标代表了不同利益相关者的利益，可能导致潜在的复杂冲突。为解决这一问题，我们提出了一种新颖的多目标强化学习框架，该框架探索高维目标空间并揭示冲突目标之间的权衡。该框架利用外部信息，并充分发挥强化学习数据驱动特性的优势，使得无需长期预测或了解潜在不确定性分布即可训练参数化策略。经过训练的策略展现出多样性、自适应性和协调性行为，并且额外提供了关于其信息使用动态的可解释性洞察。我们将该框架应用于康奈尔大学微电网（CU-MG）（一种热电联供微电网）以评估其有效性。结果表明，与现状运行相比，所有考虑的目标均实现了性能提升，并在处理复杂运行权衡方面提供了更高的灵活性。