Abstract:

Aiming at limitations of traditional Photovoltaic Hosting Capacity （PHC） assessment methods， such as over-reliance on detailed physical models and high computational complexity， as well as challenge of improving accuracy and stability of deep reinforcement learning methods in policy optimization， a model-free PHC assessment method combining attention mechanism and deep reinforcement learning was proposed. In the method， a Deep Neural Network （DNN） was constructed to predict node voltages and was combined with Soft Actor-Critic （SAC） algorithm for PHC assessment， and intrinsic correlation between state-action pairs was focused on by the interactive attention mechanism adaptively， so as to improve Q-value estimation accuracy and training stability. Case study was conducted in a real power distribution network and the proposed method was compared with the DIgSILENT-based physical modeling method and the model-free method without attention mechanism. Experimental results demonstrate that the proposed method achieves Normalized Mean Absolute Error （NMAE） of 0.045 2， Normalized Root Mean Square Error （NRMSE） of 0.061 8， Mean Absolute Percentage Error （MAPE） of 5.93%， and coefficient of determination （R²） of 0.930 5， and the maximum voltage deviation of ±3 V， verifying the validity of this method.

Key words: Photovoltaic Hosting Capacity (PHC), deep reinforcement learning, attention mechanism, model-free method, DIgSILENT, Soft Actor-Critic (SAC) algorithm

摘要：

针对传统光伏接入容量（PHC）评估方法对详细物理模型的过度依赖和高计算复杂性，以及深度强化学习方法在策略优化中的精度和稳定性有待提升的挑战，提出一种结合注意力机制与深度强化学习的无模型PHC评估方法。通过构建深度神经网络（DNN）预测节点电压并结合软演员-评论家（SAC）算法评估PHC，同时引入交互注意力机制自适应地关注状态-动作对之间的内在关联，提升对Q值的估计精度和训练稳定性。案例研究在一个真实配电网络中展开，并将所提方法与基于DIgSILENT的物理模型方法和无注意力机制的无模型方法对比。实验结果表明，所提方法的归一化平均绝对误差（NMAE）为0.045 2，归一化均方根误差（NRMSE）为0.061 8，平均绝对百分比误差（MAPE）为5.93%，决定系数（R²）为0.930 5，最大电压偏差在±3 V，验证了该方法的有效性。

关键词: 光伏接入容量, 深度强化学习, 注意力机制, 无模型方法, DIgSILENT, 软演员-评论家算法