Renewable energy sources, such as wind and solar power, are increasingly being integrated into smart grid systems. However, when compared to traditional energy resources, the unpredictability of renewable energy generation poses significant challenges for both electricity providers and utility companies. Furthermore, the large-scale integration of distributed energy resources (such as PV systems) creates new challenges for energy management in microgrids. To tackle these issues, we propose a novel framework with two objectives: (i) combating uncertainty of renewable energy in smart grid by leveraging time-series forecasting with Long-Short Term Memory (LSTM) solutions, and (ii) establishing distributed and dynamic decision-making framework with multi-agent reinforcement learning using Deep Deterministic Policy Gradient (DDPG) algorithm. The proposed framework considers both objectives concurrently to fully integrate them, while considering both wholesale and retail markets, thereby enabling efficient energy management in the presence of uncertain and distributed renewable energy sources. Through extensive numerical simulations, we demonstrate that the proposed solution significantly improves the profit of load serving entities (LSE) by providing a more accurate wind generation forecast. Furthermore, our results demonstrate that households with PV and battery installations can increase their profits by using intelligent battery charge/discharge actions determined by the DDPG agents.

翻译：风能和太阳能等可再生能源正日益融入智能电网系统。然而，与传统能源相比，可再生能源发电的不可预测性给电力供应商和公用事业公司带来了重大挑战。此外，分布式能源资源（如光伏系统）的大规模并网为微电网的能源管理带来了新问题。为解决这些问题，我们提出了一种具有双重目标的新型框架：（i）利用长短期记忆（LSTM）网络的时间序列预测方法，消除智能电网中可再生能源的不确定性；（ii）采用深度确定性策略梯度（DDPG）算法的多智能体强化学习构建分布式动态决策框架。该框架同步考虑并整合批发与零售市场中的这两个目标，从而在存在不确定性和分布式可再生能源的情况下实现高效的能源管理。通过大量数值模拟，我们证明所提出的方案通过提供更精准的风电出力预测，显著提升了负荷服务实体（LSE）的利润。此外，结果表明，配备光伏和电池的家庭可通过DDPG智能体确定的智能充放电策略增加收益。