Inverter-Based Resource Model Export via LSTM Training
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The integration of inverter-based resources (IBRs) into power systems poses challenges due to the lack of transparent models, limiting their usability across different software platforms for power system studies.
Innovation Solution
A method is developed to export a black-box model of an inverter-based resource or plant from one software platform to another by training a machine learning model, specifically a long short-term memory (LSTM) network, using training data generated from simulations, and then generating software code to represent this model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If black-box models are used for IBR simulation, then simulation accuracy is maintained, but model transparency and portability across software platforms are lost
Solution Approach 1:
The patent creates a transparent copy of the black-box model's behavior by training a machine learning model to replicate the IBR's response characteristics. The ML model is trained using simulation data from the black-box model, learning to reproduce the same input-output relationships while providing interpretability through its transparent structure and parameters.
2Measurement precision
If black-box models are used for IBR simulation, then simulation accuracy is maintained, but software platform portability is lost
Solution Approach 1:
The patent creates a portable copy of the black-box model's behavior by training a machine learning model to replicate the IBR's response characteristics. The ML model is trained using simulation data from the black-box model, learning to reproduce the same input-output relationships while providing interpretability through its transparent structure and parameters.
3Adaptability or versatility
If transparent machine learning models are used instead of black-box models, then model transparency and portability are improved, but model complexity increases
Solution Approach 1:
The patent replaces the complex internal structure of black-box models with a transparent machine learning model that uses standard algorithms and parameters. The ML model substitutes the proprietary black-box architecture with a universally understandable structure that can be implemented across different software platforms.
4Ease of operation
If manufacturer-provided black-box models are used, then ease of operation is maintained, but user independence and customization capability are reduced
Solution Approach 1:
The patent creates a portable copy of the black-box model's behavior by training a machine learning model to replicate the IBR's response characteristics. The ML model is trained using simulation data from the black-box model, learning to reproduce the same input-output relationships while providing interpretability through its transparent structure and parameters.
Data Source
AI summary
A method is disclosed for exporting a black-box model of an inverter-based resource or plant from a first software platform for use by a second software platform. The method comprises simulating, using the first software platform, instantaneous time-domain responses of the inverter-based resource or plant to respective conditions defined by a script, according to the black-box model. The method may further comprise generating training data from the instantaneous time-domain responses and the respective conditions. The method may further comprise, with the training data, training a machine learning model to model the inverter-based resource or plant, wherein the trained machine learning model is transparent as to its inner workings. The method may further comprise generating software code that represents the trained machine learning model in terms of software code usable for defining a custom model of the inverter-based resource or plant in the second software platform.