The rapid development of a new-type power system dominated by renewable energy has introduced growing complexity and variability into grid topology and dynamics, posing significant challenges for transmission interface power flow control. Traditional regulation methods based on operator experience and deterministic optimization often fail to achieve real-time optimality under such dynamic conditions. Leveraging its strong capability for autonomous learning and feature perception, deep reinforcement learning (DRL) offers a promising approach for addressing these challenges. This paper proposes a safe DRL-based control framework for online transmission interface power flow regulation. A Safe Soft Actor–Critic (SSAC) agent is developed, embedding power system security constraints directly into the decision process to ensure operational safety. A secure EMS-interactive training platform with containerized parallel learning is established to accelerate model convergence and improve adaptability to changing operating conditions. The developed SSAC agent is deployed in the Jiangsu Power Grid Energy Management System (EMS) for validation. Simulation and field test results demonstrate that the proposed method can generate control strategies online within milliseconds, achieving a 99.3% interface overload mitigation rate and 3.32% network loss reduction, outperforming conventional sensitivity-based optimization methods in both timeliness and economic efficiency. These results demonstrate strong real-time computational capability and compatibility with EMS-based dispatch workflows, indicating promising practical deployment potential for transmission interface control in renewable-dominated power systems.
Zhang et al. (2026) studied this question.