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

2026-01-16

AI Summary

This work addresses the challenge of restoring critical loads after extreme events, which is complicated by renewable energy uncertainty, limited dispatchable resources, and the nonlinear dynamics of power grids. Conventional reinforcement learning (RL) methods suffer from poor generalization and require extensive retraining across varying outage scenarios. To overcome these limitations, the paper proposes a Meta-Guided Gradient-Free Reinforcement Learning framework (MGF-RL), which uniquely integrates first-order meta-learning with evolutionary strategies to learn transferable initial policies from historical blackout experiences—enabling efficient policy adaptation without gradient computation. Theoretical analysis establishes a sublinear regret bound dependent on task similarity. Experiments on IEEE 13- and 123-node test systems demonstrate that MGF-RL outperforms standard RL, MAML, and model predictive control in terms of restoration reliability, speed, and adaptation efficiency, while requiring significantly fewer fine-tuning samples.

Technology Category

• Machine Learning: Reinforcement Learning
• Search and Optimization: Metareasoning and Metaheuristics
• Planning, Routing, and Scheduling: Planning/Scheduling and Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Social networks and social learning
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• grid resilience
• critical load restoration
• renewable uncertainty
• distribution grid
• adaptive control

Innovation

• meta-reinforcement learning
• gradient-free optimization
• distribution grid resilience
• critical load restoration
• evolutionary strategies