Deep Reinforcement Learning for Optimizing Inverter Control: Fixed and Adaptive Gain Tuning Strategies for Power System Stability

TL;DR

This paper introduces deep reinforcement learning techniques for tuning inverter controller gains, improving power system stability through fixed and adaptive strategies, with significant reductions in training time and enhanced robustness demonstrated in experiments.

Contribution

It develops novel DRL-based methods for inverter gain tuning, transforming traditional controllers into neural network policies for improved stability and adaptability in power systems.

Findings

DRL-based gain tuning reduces training time significantly.

Adaptive gain strategy improves transient stability.

Experimental results confirm enhanced robustness in real systems.

Abstract

This paper presents novel methods for tuning inverter controller gains using deep reinforcement learning (DRL). A Simulink-developed inverter model is converted into a dynamic link library (DLL) and integrated with a Python-based RL environment, leveraging the multi-core deployment and accelerated computing to significantly reduce RL training time. A neural network-based mechanism is developed to transform the cascaded PI controller into an actor network, allowing optimized gain tuning by an RL agent to mitigate scenarios such as subsynchronous oscillations (SSO) and initial transients. Two distinct tuning approaches are demonstrated: a fixed gain strategy, where controller gains are represented as RL policy (actor network) weights, and an adaptive gain strategy, where gains are dynamically generated as RL policy (actor network) outputs. A comparative analysis of these methods is provided, showcasing their effectiveness in stabilizing the transient performance of grid-forming and grid-following converters and deployment challenges in hardware. Experimental results are presented, demonstrating the enhanced robustness and practical applicability of the RL-tuned controller gains in real-world systems.