摘要
机器人与机器学习的新闻编辑每日新闻-机器学习的新研究是一篇报道的主题。根据NewsRx记者从加州沃特卢市发回的新闻报道，研究表明：“家庭对电动汽车(EVs)和太阳能光伏(PV)发电的采用正在迅速而显著地增加。公用事业面临着有效管理电动汽车和光伏资源以帮助减轻对电网运营的不良影响的挑战。”对这项研究的财政支持来自nserc-alliance/oce-vip。我们的新闻编辑从沃特卢大学的研究中获得了一句话：“现有的解决这些问题的方法依赖于准确但难以预测的电动汽车和电动汽车的行为，客户的详细知识，以及网格结构。”本文针对这些实际问题,与致力于解决这些问题的工业界合作,提出了一种基于数据驱动的两级配电网电动汽车充电智能控制器,该控制器是一个深度强化学习(DRL)agent。它协调连接到具有高光伏发电普及率的现实住宅馈线的多辆电动汽车的充电速率。第一级协调配电中压(MV)级的累计电动汽车负载，以提供需求响应(DR)服务；在低压(LV)级，旨在最大限度地提高电动汽车出发时的充电状态，同时避免MV/LV配电变压器RS的过载。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting originating from Waterloo, Ca nada, by NewsRx correspondents, research stated, “The adoption of Electric Vehic les (EVs) and solar Photovoltaic (PV) generation by households is rapidly and si gnificantly increasing. Utilities are facing the challenge of efficiently managi ng EV and PV resources to help mitigate the undesirable effects on grid operatio n.” Financial support for this research came from NSERC-Alliance/OCE-VIP. Our news editors obtained a quote from the research from the University of Water loo, “Existing approaches to solve these issues depend on accurate but hard to p redict behavior of EVs and PVs, detailed knowledge of customers, and grid infras tructure, all of which complicate the effective deployment of these resources. M otivated by these practical challenges and in collaboration with industry partne rs working on addressing these issues, this paper proposes a two-level data-driv en smart controller for EV charging in distribution systems. The controller is m odeled as a Deep Reinforcement Learning (DRL) agent, which coordinates the charg ing rates of multiple EVs connected to a realistic residential feeder with high penetration of PV generation. The first level coordinates the aggregated EV load at distribution Medium Voltage (MV) level to provide Demand Response (DR) servi ces; at the Low Voltage (LV) level it aims to maximize the EVs’ state of charge at departure while avoiding the overloading of the MV/LV distribution transforme rs.”
NETL
NSTL