Adaptive Remedial Action Scheme Tool for Power Grid Reliability

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The design, testing, and implementation of Remedial Action Schemes (RAS) in power systems are time-consuming and labor-intensive, requiring extensive manual effort and relying on conservative, engineer-experienced-based coefficient settings, which limits their adaptability and efficiency in real-time operations.

Innovation Solution

The development of a transformative Remedial Action Scheme Tool (TRAST) that uses advanced mathematical methods, high-performance computing, and machine learning to adaptively set RAS parameters based on real-time operation conditions, integrating utility data analysis and power engineering domain knowledge to simplify and accelerate the RAS design, review, testing, and validation process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional manual methods are used for RAS design and parameter setting, then engineering experience and conservative approaches ensure system reliability, but the process becomes extremely time-consuming and labor-intensive

Engineering Contradiction:

Improvepower system reliabilityVSAvoidRAS design and validation time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical engineering processes with automated computational systems. Machine learning models and high-performance computing algorithms automatically perform RAS design, parameter optimization, and validation that previously required extensive manual engineering effort, thereby reducing time loss while maintaining reliability through data-driven approaches

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service through autonomous RAS design capabilities. The automated toolset performs self-validation, self-optimization, and selfconfiguration of remedial action schemes without requiring continuous human intervention, allowing the system to serve itself in the design and validation process while ensuring reliability through built-in verification mechanisms

Inventive Principle:

Principle #25Self-service

2Stability of the object's composition

If conservative engineer-experienced-based coefficient settings are used, then system stability is maintained, but adaptability and efficiency in real-time operations are limited

Engineering Contradiction:

Improvepower system stabilityVSAvoidRAS adaptability to real-time conditions

Core Design Contradiction:

Stability of the object's compositionVSAdaptability or versatility

Solution Approach 1:

The patent transforms static conservative coefficient settings into dynamic adaptive parameters. Machine learning models continuously learn from real-time power system operations and automatically adjust RAS parameters according to current system conditions, enabling the system to maintain stability while adapting to changing operational environments in real-time

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system implements parameter changes by automatically optimizing RAS coefficients based on learned patterns from historical and real-time data. The machine learning models identify optimal parameter values that balance stability requirements with adaptability needs, dynamically adjusting parameters rather than using fixed conservative values

Inventive Principle:

Principle #35Parameter changes

3Reliability

If extensive manual testing and validation are performed, then RAS performance is thoroughly verified, but the complexity and labor requirements increase significantly

Engineering Contradiction:

ImproveRAS performance verificationVSAvoidRAS design process complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces complex manual testing and validation procedures with automated computational verification systems. High-performance computing algorithms and machine learning models automatically simulate diverse power system scenarios, perform comprehensive validation, and verify RAS performance without requiring extensive manual testing effort, thereby reducing process complexity while maintaining thorough verification

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The automated validation system performs multiple functions simultaneously - it tests RAS performance across diverse scenarios, validates parameter settings, verifies compliance with reliability standards, and optimizes parameters all through a single integrated computational process, reducing overall process complexity compared to separate manual testing procedures

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11042132B2Transformative remedial action scheme tool (TRAST)

Publication Date: 2021.06.22 BATTELLE MEMORIAL INST

AI summary

Techniques and apparatuses are described that enable transformative Remedial Action Scheme (RAS) analyses and methodologies for a bulk electric power system, including methods of designing, reviewing, revising, testing, implementing, verifying, or validating a RAS. An improved RAS improves operation of the power system, including performance, reliability, control, and asset utilization. The example methodologies discussed—also referred to as a transformative Remedial Action Scheme tool (TRAST)—provide an end-to-end solution for adaptively setting RAS parameters based on realistic and near real-time operation conditions to improve power grid reliability and grid asset utilization, by leveraging utility data analysis and employing dynamic simulations and machine learning to significantly simplify and shorten the entire RAS process.