AI-Enabled Networked Microgrids for Resilient Fault Protection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing power infrastructures are vulnerable to weather events, cyber-attacks, and difficult to meet energy demands, with distributed energy resources often not providing reliable resilience due to sensitive trip-off settings, and networked microgrids face challenges in control, scalability, and cybersecurity, making them expensive and difficult to implement.
Innovation Solution
An AI-Grid system and methods for AI-enabled, programmable, resilient, and networked microgrids, utilizing neural reachability, ODE-Net, barrier-based neural simplex, active fault management, and traveling wave protection to provide secure, reliable, and fault-tolerant algorithms for resilient networked systems, enabling scalable and self-protecting microgrids.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If distributed energy resources are interconnected to power grids, then energy generation capacity increases, but reliability during grid contingencies deteriorates due to sensitive trip-off settings
Solution Approach 1:
The patent introduces an AI-enabled control system as an intermediary between distributed energy resources and the power grid. This mediator uses machine learning models to predict grid conditions and adjusts operational parameters proactively, preventing unnecessary trip-offs while maintaining reliability during contingencies.
Solution Approach 2:
The system performs preliminary actions by using AI models to predict future grid states and pre-adjust operational parameters of distributed energy resources. This proactive approach prevents reactive trip-offs during grid contingencies, maintaining both capacity and reliability.
2Reliability
If networked microgrids are implemented to improve resilience, then coordination of distributed energy systems improves, but system complexity and implementation cost increase
Solution Approach 1:
The patent implements a universal AI-enabled control platform that can manage multiple microgrids and distributed energy resources with a single system architecture. This multi-functional approach reduces overall complexity compared to implementing separate control systems for each microgrid while maintaining resilience benefits.
3Reliability
If traditional protection systems are used in microgrids, then hardware protection is provided, but scalability and configurability are limited
Solution Approach 1:
The patent replaces traditional hardware-based protection systems with AI-enabled software-defined protection mechanisms. This substitution allows for flexible configuration and scaling through software updates rather than hardware modifications, maintaining protection capabilities while improving adaptability.
Solution Approach 2:
The protection system is made dynamic through AI algorithms that can adapt protection parameters in real-time based on changing grid conditions and configurations. This dynamic approach enables scalability and configurability without requiring fixed hardware architectures.
Data Source
AI summary
AI grid system and method for networked microgrids, including one or more of the following operations: neural reachability for dynamically verifying behavior of the microgrids; neural ordinary differential equations net (ODE-Net) for modeling states of the microgrids; barrier-based neural simplex for assuring runtime safety and control of neural controllers of the microgrids; grid forming for enabling one or more of passivity, stability, and scalability guarantees in the microgrids; active fault management for providing federated learning to active fault management of the microgrids and/or inverter-based resources; neural dynamic state estimation for estimating the states of the microgrids using ODE-Net with application of Kalman filters; traveling wave protection for processing reflected traveling wave signals in time-frequency domain; and integration and operational visualization for providing visualization of an operational status of the grid system and statuses of the associated microgrids, and providing execution and results of execution of the one or more operations.