Leveraging Decentralized Artificial Intelligence to Enhance Resilience of Energy Networks

TL;DR

This paper explores how decentralized AI can improve energy network resilience by defining resilience, analyzing natural hazard impacts, and proposing a distributed management strategy for better decision-making.

Contribution

It introduces a novel decentralized AI-based approach for enhancing energy network resilience and provides a high-fidelity model for strategic and preventive decision-making.

Findings

Wildfires significantly impact power system resilience.

Decentralized strategies improve management of distributed storage and demand response.

The proposed model aids utilities and policymakers in resilience planning.

Abstract

This paper reintroduces the notion of resilience in the context of recent issues originated from climate change triggered events including severe hurricanes and wildfires. A recent example is PG&E's forced power outage to contain wildfire risk which led to widespread power disruption. This paper focuses on answering two questions: who is responsible for resilience? and how to quantify the monetary value of resilience? To this end, we first provide preliminary definitions of resilience for power systems. We then investigate the role of natural hazards, especially wildfire, on power system resilience. Finally, we will propose a decentralized strategy for a resilient management system using distributed storage and demand response resources. Our proposed high fidelity model provides utilities, operators, and policymakers with a clearer picture for strategic decision making and preventive decisions.