Full-Model-Free Adaptive Graph Deep Deterministic Policy Gradient Model for Multi-Terminal Soft Open Point Voltage Control in Distribution Systems

High renewable energy penetration induces sharply-fluctuating feeder power, leading to voltage deviation in active distribution systems. To prevent voltage violations, multi-terminal soft open points (M-SOPs) have been integrated into the distribution systems to enhance voltage control flexibility. However, the M-SOP control model recalculated in real-time cannot adapt to the rapid fluctuations of PVs, fundamentally limiting the voltage controllability of M-SOPs. To address this issue, a full-model-free adaptive graph deep deterministic policy gradient framework (FAG-DDPG) is proposed for M-SOP voltage control. Specifically, the attention-based adaptive graph convolutional network (AGCN) is leveraged to extract the complex correlation features of nodal information to improve the policy learning ability. Then, the AGCN-based surrogate model is trained to replace the power flow calculation to achieve model-free control. Furthermore, the DDPG algorithm allows FAG-DDPG to learn an M-SOP optimal control strategy by continuous interactions with the surrogate model. Numerical tests have been performed on modified IEEE 33-, 123-node, and a real 76-node distribution system. The effectiveness and generalization ability are demonstrated by the proposed model's results.