胡丹尔, 李子晨, 彭勇刚, 杨英杰, 朱明增, 周培. 含电动汽车充电桩的配电网深度强化学习有功–无功协调电压控制策略[J]. 电网技术, 2023, 47(12): 4985-4994. DOI: 10.13335/j.1000-3673.pst.2022.0814
引用本文: 胡丹尔, 李子晨, 彭勇刚, 杨英杰, 朱明增, 周培. 含电动汽车充电桩的配电网深度强化学习有功–无功协调电压控制策略[J]. 电网技术, 2023, 47(12): 4985-4994. DOI: 10.13335/j.1000-3673.pst.2022.0814
HU Daner, LI Zichen, PENG Yonggang, YANG Yingjie, ZHU Mingzeng, ZHOU Pei. Deep Reinforcement Learning Active-reactive Coordinated Voltage Control Strategy for Distribution Network With Electric Vehicle Charging[J]. Power System Technology, 2023, 47(12): 4985-4994. DOI: 10.13335/j.1000-3673.pst.2022.0814
Citation: HU Daner, LI Zichen, PENG Yonggang, YANG Yingjie, ZHU Mingzeng, ZHOU Pei. Deep Reinforcement Learning Active-reactive Coordinated Voltage Control Strategy for Distribution Network With Electric Vehicle Charging[J]. Power System Technology, 2023, 47(12): 4985-4994. DOI: 10.13335/j.1000-3673.pst.2022.0814

含电动汽车充电桩的配电网深度强化学习有功–无功协调电压控制策略

Deep Reinforcement Learning Active-reactive Coordinated Voltage Control Strategy for Distribution Network With Electric Vehicle Charging

  • 摘要: 新能源的高渗透率加剧了配电网的电压波动,给配电网电压控制带来新挑战。主动配电网中可控的有功和无功设备在缓解电压偏差方面发挥了重要作用。提出了一种基于多智能体强化学习的有功无功协调电压控制策略,通过协调光伏逆变器、静止无功补偿装置的无功功率和电动汽车充电桩的有功功率以减小电压偏差和网损,且不依赖于精确的潮流模型。同时提出一种基于经验增强技术并引入注意力机制的深度强化学习算法(experience augmentation multi-actor-attention-critic,EAMAAC),能够提供无偏的生成数据集,提高样本利用效率。在改进IEEE33节点测试算例的验证结果表明,所提出的控制策略和算法不仅能有效缓解电压偏差问题,并且相较于现有的强化学习算法其采样效率更高、鲁棒性更强。

     

    Abstract: The increasing penetration of the distributed power sources exacerbates the voltage violations in the distribution networks and brings new challenges to the reactive voltage control. The controllable active and reactive devices in the active distribution networks play an important role in mitigating the voltage deviations. In this paper, we propose a multi-intelligent reinforcement learning-based active-reactive coordinated voltage control strategy to adjust the reactive power of the connected PV inverters and the active power of the EV charging piles with the goal of reducing the voltage deviations and the network losses without depending on the precise flow model. The reinforcement learning algorithm using the empirical enhancement technique with the attention mechanism (EAMAAC), which provide unbiased training data to improve sample efficiency. The proposed voltage control strategy is validated on the IEEE 33-bus test case. The results show that the proposed control strategy is not only effective in mitigating the voltage deviation but also has higher and more stable sampling efficiency compared to the existing reinforcement learning algorithms.

     

/

返回文章
返回