A Deep Reinforcement Learning-Based Intelligent Grid-Forming Inverter for Inertia Synthesis by Impedance Emulation

Article Engineering, Electrical & Electronic

A Distributed Dynamic Inertia-Droop Control Strategy Based on Multi-Agent Deep Reinforcement Learning for Multiple Paralleled VSGs

Qiufan Yang et al.

Summary: In this paper, the relationship between the inertia-droop parameters distribution of multiple paralleled VSGs and oscillations is derived, and a distributed dynamic inertia-droop control strategy based on multi-agent deep reinforcement learning is proposed. The proposed approach effectively suppresses power oscillations.

IEEE TRANSACTIONS ON POWER SYSTEMS (2023)

Add to Collection

Article Automation & Control Systems

A Critical Aspect of Dynamic Stability in Autonomous Microgrids: Interaction of Droop Controllers Through the Power Network

Mohsen Eskandari et al.

Summary: This article explores the impact of the interaction between droop controllers through the power network on the dynamic stability of a networked microgrid. New models are developed to analyze the effects of power network impedance, droop controllers, and impedance characteristics of voltage source inverters. It is shown that a low X/R ratio amplifies low-frequency oscillations and that the virtual inductance loop improves dynamic performance. However, the resistive-capacitive impedance characteristics of the inverters pose stability risks. A H-infinity robust controller is proposed to stabilize the microgrid.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Add to Collection

Article Engineering, Electrical & Electronic