Wave Energy Converter Control Using Forecasted Wave Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wave energy converter (WEC) devices are typically controlled in a reactive manner, which limits their ability to adapt to changing wave conditions, resulting in suboptimal energy production and increased mechanical wear due to excessive adjustments.
Innovation Solution
Implementing a proactive control system using a computationally lightweight machine learning model that predicts wave conditions up to several days in advance, allowing for optimized tuning of WEC devices to maximize energy generation and extend service life by reducing unnecessary adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If reactive control is used to adjust WEC device resistance based on current waves, then energy production is maximized under current conditions, but the device cannot adapt to future changing wave conditions and experiences excessive mechanical wear
Solution Approach 1:
The system performs preliminary action by predicting future wave conditions using machine learning models and environmental characteristics before the waves arrive. This allows the WEC device to be proactively tuned to optimal resistance settings in advance, rather than reactively adjusting to current conditions. The prediction enables the device to be prepared for upcoming wave patterns, maximizing energy capture while reducing unnecessary adjustments and mechanical wear.
2Adaptability or versatility
If reactive control continuously adjusts resistance based on current waves, then the device responds to changing conditions, but it cannot anticipate future waves and makes excessive adjustments causing mechanical wear
Solution Approach 1:
The system performs preliminary action by predicting future wave conditions using machine learning models and environmental characteristics before the waves arrive. This allows the WEC device to be proactively tuned to optimal resistance settings in advance, rather than reactively adjusting to current conditions. The prediction enables the device to be prepared for upcoming wave patterns, maximizing energy capture while reducing unnecessary adjustments and mechanical wear.
Solution Approach 2:
The machine learning prediction system acts as an intermediary between environmental characteristics and device control. Instead of directly reacting to current wave conditions, the system uses the prediction model as a mediator to determine optimal resistance settings based on forecasted future waves. This intermediary layer filters out noise and enables smoother, more intentional adjustments that reduce mechanical wear while maintaining adaptability.
3Measurement precision
If complex prediction models are used to forecast wave conditions, then prediction accuracy improves, but computational complexity and resource requirements increase
Solution Approach 1:
The system uses computationally lightweight machine learning models that can be deployed on resource-constrained edge devices at the WEC location. Rather than relying on complex centralized models, the approach uses simpler, faster models that provide sufficient prediction accuracy for operational control decisions. These lightweight models consume minimal computational resources and can be updated or replaced as needed, balancing accuracy with device complexity constraints.
Data Source
AI summary
Embodiments for managing a wave energy converter (WEC) device by one or more processors are described. At least one environmental characteristic associated with a WEC device in a body of water is received. A prediction of wave conditions on the body of water is calculated based on the at least one environmental characteristic. A signal representative of the prediction of wave conditions is generated.