Data-Driven Fault Ride-Through Operation of Distributed Grid-Forming Inverters Using Multi-Agent Reinforcement Learning

Grid-forming inverters (GFMIs) are essential for future low-inertia power systems because they establish voltage and frequency rather than simply following the grid. However, compared with synchronous machines, they have limited overload and fault current capability, so providing reliable fault ride-through (FRT)/low-voltage ride-through (LVRT) behavior requires specially designed control strategies. This study proposes a multi-agent reinforcement learning inspired technique for the parameter selection of virtual synchronous generator (VSG)-controlled GFMIs through independent twin delayed deep deterministic policy gradient (TD3PG) agents, considering symmetrical and asymmetrical grid faults on the IEEE 13 bus network. The methodology utilizes power flow errors and voltage unbalance factors as key observational inputs within the MATLAB/Simulink^® 2023b environment. The policies are designed to modify the inertia and damping coefficients of the active power controller, as well as the proportional–integral gains of the reactive power controller to enhance stability in response to grid disturbances. The efficacy of this approach was evaluated against a conventional VSG control approach and VSG with virtual impedance and dynamic current saturation across multiple inverters with different power ratings. The proposed reinforcement learning assisted control embedded with current limiting consistently showed reductions in peak fault current of approximately 10–12% as well as reductions in active and reactive power settling times from around 3.50–5 s to about 1–1.50 s. In addition, it also limits fault currents to below 1.25 p.u. during disturbance intervals, thereby enabling continuous operation of inverters with a wide range of power ratings under both symmetrical and asymmetrical fault conditions.