TITLE:
A Resiliency Assessment of Predictive Power Outage Integration in Energy-Transactive Networked Microgrids Architectures
AUTHORS:
Mohamed Abaas, Pritpal Singh, Ross A. Lee
KEYWORDS:
Machine Learning, Networked Microgrids, Resiliency, Energy Trading, Blockchain
JOURNAL NAME:
Journal of Power and Energy Engineering,
Vol.14 No.9,
September
15,
2026
ABSTRACT: The reliability of the U.S. electric system underpins virtually every sector of the modern U.S. economy. Reliable electricity access is essential for daily activities, and disruptions can critically affect facilities, potentially leading to life-threatening situations. For example, Hurricane Maria in 2017 caused a prolonged outage in Puerto Rico, underscoring the need to strengthen grid resilience. The centralized architecture of the current power grid presents vulnerabilities that can be mitigated through decentralized approaches, such as networked microgrids. Significant progress has been achieved in the development of networked microgrid systems. This paper presents a patented framework that integrates power outage prediction with blockchain‑based trading to enhance system resilience. The predictive model increases the demand offered for trading when a power outage is predicted. This research evaluates the impact of a machine‑learning‑based outage prediction model on the resilience of a secure transactive platform for networked microgrids. Preliminary results show a 36% increase in resiliency compared with similar systems that operate without such a prediction model.