Power Plant Setpoint Optimization Using Marginal Effect Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current control schemes for power generating assets, such as wind turbines, are inflexible and do not effectively manage trade-offs between energy production, component damage, and risk of failure, leading to suboptimal economic operation.
Innovation Solution
A supervisory control system with independent applications and a central optimizer module that generates marginal effect maps to determine optimal operational setpoints for power generating assets, considering factors like energy production, component damage, and failure modes, to optimize economic value.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If traditional control schemes are used for power generating assets, then the control implementation is simple, but the economic value optimization is insufficient due to inability to manage trade-offs between energy production, component damage, and failure risk
Solution Approach 1:
The control system is segmented into multiple independent applications, each responsible for specific functions such as power production optimization, component health monitoring, and failure risk assessment. This modular architecture allows complex optimization tasks to be divided into manageable segments while maintaining overall system coordination through the central optimizer.
Solution Approach 2:
The central optimizer module acts as an intermediary that receives inputs from multiple independent applications, processes them through marginal effect maps, and generates coordinated control setpoints. This intermediary structure enables the system to manage trade-offs between conflicting objectives by synthesizing information from various specialized applications.
2Productivity
If frequent setpoint communication is implemented to optimize economic value, then the optimization responsiveness improves, but the communication and processing load increases
Solution Approach 1:
The system implements partial optimization by focusing computational resources on the most critical trade-offs and marginal effects at any given time, rather than continuously optimizing all parameters. The marginal effect maps enable the system to identify and act only on the most impactful setpoint adjustments, reducing unnecessary communication and processing overhead.
Solution Approach 2:
The system dynamically changes communication and processing parameters based on operational conditions. The marginal effect maps allow the optimizer to adapt the frequency and detail of setpoint communications according to the current state of the power generating assets, maintaining high responsiveness when needed while reducing load during stable operating conditions.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for operating a power generating plant having one or more power generating assets includes receiving, via a plurality of independent applications of a supervisory controller, a plurality of operational parameters relating to the one or more power generating assets in the power generating plant. The method also includes generating, via the plurality of independent applications of the supervisory controller, a plurality of marginal effect maps based on the plurality of operational parameters. The method further includes receiving, via a central optimizer module, the plurality of marginal effect maps from the plurality of independent applications and determining one or more operational setpoints for the power generating asset(s) based on the marginal effect maps to optimize an economic value of operating the one or more power generating assets. Moreover, the method includes communicating the operational setpoint(s) to the power generating asset(s).