Toward Adaptive Grid Resilience: A Gradient-Free Meta-RL Framework for Critical Load Restoration

TL;DR

This paper introduces a gradient-free meta-reinforcement learning framework that enables rapid, adaptive critical load restoration in distribution grids with renewable uncertainties, outperforming traditional methods in speed and reliability.

Contribution

The paper presents MGF-RL, a novel meta-RL approach combining meta-learning and evolutionary strategies for scalable, transferable, and efficient grid restoration under uncertainty.

Findings

MGF-RL outperforms standard RL and model predictive control in tests.

It adapts quickly to unseen outage and renewable scenarios.

Requires fewer fine-tuning episodes than conventional RL.

Abstract

Restoring critical loads after extreme events demands adaptive control to maintain distribution-grid resilience, yet uncertainty in renewable generation, limited dispatchable resources, and nonlinear dynamics make effective restoration difficult. Reinforcement learning (RL) can optimize sequential decisions under uncertainty, but standard RL often generalizes poorly and requires extensive retraining for new outage configurations or generation patterns. We propose a meta-guided gradient-free RL (MGF-RL) framework that learns a transferable initialization from historical outage experiences and rapidly adapts to unseen scenarios with minimal task-specific tuning. MGF-RL couples first-order meta-learning with evolutionary strategies, enabling scalable policy search without gradient computation while accommodating nonlinear, constrained distribution-system dynamics. Experiments on IEEE 13-bus and IEEE 123-bus test systems show that MGF-RL outperforms standard RL, MAML-based meta-RL, and model predictive control across reliability, restoration speed, and adaptation efficiency under renewable forecast errors. MGF-RL generalizes to unseen outages and renewable patterns while requiring substantially fewer fine-tuning episodes than conventional RL. We also provide sublinear regret bounds that relate adaptation efficiency to task similarity and environmental variation, supporting the empirical gains and motivating MGF-RL for real-time load restoration in renewable-rich distribution grids.