研究人员开发了一个面向决策的强化学习（DF-RL）框架，以改进在出发时间未知的情况下电动汽车（EV）的充电控制。该方法端到端地训练一个预测器和一个充电策略控制器，允许预测器接收关于其对控制器决策影响的反馈。与基线相比，DF-RL方法在充电决策方面表现更优，总奖励提高了高达14%，未供应能量减少了55%。 AI
影响 这项研究通过优化电动汽车充电计划，可能导致更高效、更稳定的电网。
排序理由 该集群包含一篇详细介绍强化学习新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.19199v1 Announce Type: cross Abstract: The recent growth of EV adoption poses challenges for power systems, including increased peak demand and potential grid instability. Smart control of EV charging -- e.g., based on reinforcement learning (RL) -- can alleviate these…
The recent growth of EV adoption poses challenges for power systems, including increased peak demand and potential grid instability. Smart control of EV charging -- e.g., based on reinforcement learning (RL) -- can alleviate these issues by learning temporal and contextual patter…