Wind Turbine Backup Controller for Cyberattack-Resilient Operation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Wind turbines face challenges in developing backup controllers due to cyberattacks, as model-based controllers require extensive domain knowledge and cannot be trusted when compromised, and existing dynamic models from other manufacturers are inaccessible.

Innovation Solution

A learning-based backup controller that observes and learns control actions from the supervisory controller under normal operation, allowing it to take over and adjust setpoints by predicting deltas to maintain operation until the supervisory controller is available again, providing robustness against model/parameter mismatches.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a model-based controller is used for wind turbine control, then control precision and efficiency are improved, but vulnerability to cyberattacks and model inaccessibility from other manufacturers worsens reliability

Engineering Contradiction:
Improvecontrol precisionVSAvoidcontroller reliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent creates a backup controller that copies the functionality and control logic of the primary supervisory controller. This backup controller is trained to replicate the decision-making processes and control actions of the original controller, ensuring continuity of operation when the primary controller becomes unavailable due to cyberattacks or other failures.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent transitions from model-based control parameters to data-driven learning parameters. By using machine learning models that learn from operational data rather than relying on predetermined physical models, the system adapts to different controller behaviors and maintains reliability across various manufacturing sources without requiring access to proprietary dynamic models.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If a backup controller is developed using manufacturer-specific dynamic models, then control accuracy is improved, but accessibility and ease of manufacture worsen due to model inaccessibility

Engineering Contradiction:
Improvecontrol accuracyVSAvoidbackup controller development ease
Core Design Contradiction:
Measurement precisionVSEase of manufacture

Solution Approach 1:

Instead of requiring access to proprietary dynamic models, the patent copies the operational behavior of the primary controller through data collection and machine learning training. The backup controller learns to replicate control decisions by observing input-output relationships during normal operation, eliminating the need for manufacturer-specific model access.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system performs self-training by collecting its own operational data during normal operation. The backup controller automatically learns control patterns from the primary controller's behavior without requiring external model provision, making the backup controller development process autonomous and manufacturer-agnostic.

Inventive Principle:
Principle #25Self-service

3Productivity

If extensive domain knowledge and dynamic models are required for controller development, then control performance is improved, but device complexity and development time increase

Engineering Contradiction:
Improvecontrol performanceVSAvoidcontroller development complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The backup controller system automatically collects operational data, processes it, and trains its own machine learning models without requiring extensive manual domain knowledge or complex model development. The system performs self-training by learning from the primary controller's operational patterns, significantly reducing development complexity while maintaining control performance.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces traditional model-based control mechanics with data-driven machine learning mechanics. Instead of relying on complex physical models and domain knowledge, the system uses neural networks and learning algorithms that automatically capture control relationships from operational data, simplifying the development process while maintaining or improving control performance.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

4Reliability

If the supervisory controller is compromised by cyberattacks, then system security is worsened, but continuous operation capability can be maintained through backup control

Engineering Contradiction:
Improvecontinuous operation capabilityVSAvoidcyberattack vulnerability
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system prepares a trained backup controller in advance that can immediately take over when the primary supervisory controller is compromised by cyberattacks. This pre-trained backup controller acts as a cushion against security failures, ensuring continuous operation without interruption or performance degradation when attacks occur.

Inventive Principle:
Principle #11Beforehand cushioning (Prior cushioning)

Solution Approach 2:

The backup controller replicates the primary controller's functionality and control logic, creating a security redundancy that protects against cyberattacks. When the primary controller is compromised, the copied backup controller provides a secure alternative that maintains system operation, effectively neutralizing the impact of security vulnerabilities.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP4245989B1Learning-based backup controller for a wind turbine
Publication Date: 2024.09.11 GENERAL ELECTRIC RENOVABLES ESPANA SL
  • EP4245989B1 patent drawingFigure 1
  • EP4245989B1 patent drawingFigure 2
  • EP4245989B1 patent drawingFigure 3

AI summary

A method for providing backup control for a supervisory controller of at least one wind turbine includes observing, via a learning-based backup controller of the at least one wind turbine, at least one operating parameter of the supervisory controller under normal operation. The method also includes learning, via the learning-based backup controller, one or more control actions of the at least one wind turbine based on the operating parameter(s). Further, the method includes receiving, via the learning-based backup controller, an indication that the supervisory controller is unavailable to continue the normal operation. Upon receipt of the indication, the method includes controlling, via the learning-based backup controller, the wind turbine(s) using the learned one or more control actions until the supervisory controller becomes available again. Moreover, the control action(s) defines a delta that one or more setpoints of the wind turbine(s) should be adjusted by to achieve a desired outcome.