Reinforcement Learning for Optimal Primary Frequency Control: A Lyapunov Approach

TL;DR

This paper introduces a Lyapunov-based reinforcement learning method to design neural network controllers for inverter-connected resources, ensuring grid stability and outperforming traditional linear droop controls.

Contribution

It develops a neural network controller structure with stability guarantees using Lyapunov functions, tailored for nonlinear grid dynamics involving renewable resources.

Findings

Controllers outperform linear droop methods

Neural network controllers guarantee stability by construction

Local information suffices for effective control

Abstract

As more inverter-connected renewable resources are integrated into the grid, frequency stability may degrade because of the reduction in mechanical inertia and damping. A common approach to mitigate this degradation in performance is to use the power electronic interfaces of the renewable resources for primary frequency control. Since inverter-connected resources can realize almost arbitrary responses to frequency changes, they are not limited to reproducing the linear droop behaviors. To fully leverage their capabilities, reinforcement learning (RL) has emerged as a popular method to design nonlinear controllers to optimize a host of objective functions. Because both inverter-connected resources and synchronous generators would be a significant part of the grid in the near and intermediate future, the learned controller of the former should be stabilizing with respect to the nonlinear dynamics of the latter. To overcome this challenge, we explicitly engineer the structure of neural network-based controllers such that they guarantee system stability by construction, through the use of a Lyapunov function. A recurrent neural network architecture is used to efficiently train the controllers. The resulting controllers only use local information and outperform optimal linear droop as well as other state-of-the-art learning approaches.