Electrolyzer Plant Control Using Two-Model Operating Point Refinement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for controlling electrolyzer plants often result in non-ideal operating points due to inaccurate modeling, leading to inefficiencies, wear, and contractual or cost issues, as they require complex models and frequent recalculations to account for changing conditions, which can be computationally expensive and resource-intensive.
Innovation Solution
A method involving a two-model approach, where a less computationally expensive long-term planning model determines initial operating points and a more accurate short-term model simulates and refines these points, adjusting parameters and boundary conditions to ensure optimal operation within predetermined requirements, thereby improving accuracy without excessive resource consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If complex models with frequent recalculations are used to improve accuracy, then prediction accuracy improves, but computational resources and time consumption increase
Solution Approach 1:
The patent segments the modeling task into two distinct models: a first model for long-term planning (coarse time steps) and a second model for short-term simulation (fine time steps). This segmentation allows each model to be optimized for its specific purpose, reducing overall computational complexity while maintaining accuracy where needed.
Solution Approach 2:
The patent implements a dynamic modeling approach where the level of model detail and calculation frequency adapts to the time horizon and operational context. The first model operates at lower resolution for long-term planning, while the second model provides higher resolution for short-term critical periods, dynamically adjusting computational resources based on needs.
2Measurement precision
If complex models with frequent recalculations are used to improve accuracy, then prediction accuracy improves, but computational time increases
Solution Approach 1:
By segmenting the time horizon into long-term (first model) and short-term (second model) components, the patent avoids applying high computational effort across the entire planning period. The second model is only activated for specific short-term simulations, dramatically reducing total computational time while maintaining accuracy for critical periods.
Solution Approach 2:
The patent applies the more accurate second model only partially - specifically for short-term simulations within the long-term plan - rather than using it continuously. This partial application of high-accuracy modeling achieves necessary precision where it matters most without the excessive computational cost of continuous high-accuracy simulation.
3Measurement precision
If complex models with frequent recalculations are used to improve accuracy, then prediction accuracy improves, but available computing resources are exceeded
Solution Approach 1:
The patent segments computational resources allocation by creating two models with different resource requirements. The first model consumes fewer resources for long-term planning, while the second model consumes more resources only when needed for short-term simulation, ensuring total resource usage remains within available limits while achieving necessary accuracy.
Solution Approach 2:
The patent changes key parameters of the modeling approach - specifically the time step resolution and model detail level - depending on the planning horizon and operational context. This allows the system to adapt computational intensity to match available resources while maintaining adequate accuracy for decision-making.
Data Source
Figure 1a~1b
Figure 2
Figure 3
AI summary
The invention provides a computer-implemented method for controlling operation of an electrolyzer plant. The method comprises determining, by means of a first model, first operating points of the electrolyzer plant for a predetermined first period of time, simulating, by means of a second model, operation of the electrolyzer plant for the first operating points for a predetermined second period of time that is shorter than and comprised in the first period of time, the second model being a model having higher prediction accuracy for the operation of the electrolyzer plant than the first model, and determining whether the simulated operation meets a predetermined requirement. The method comprises, upon determining that the simulated operation does not meet the predetermined requirement, adjusting one or more parameters and/or one or more boundary conditions of the first model, and upon determining that the simulated operation meets the predetermined requirement, setting the first operating points as target operating points for the predetermined second period of time.