Hardware-in-the-Loop Real-Time Transient Emulation of Large-Scale Renewable Energy Installations Based on Hybrid Machine Learning Modeling
Bibliographic record
Abstract
For the integration of large-scale renewable energy resources into power grids, the complex and dynamic behavior of inverter-based resources (IBRs), such as wind farms, photovoltaic (PV) arrays, and battery energy storage systems (BESSs), poses significant challenges. Traditional models often fall short of feasibly simulating these resources at scale. This article introduces a hybrid machine learning approach, employing multilayer perceptrons (MLPs) and gated recurrent units (GRUs), to effectively simulate IBRs. The hybrid models combine MLPs and GRUs to capture the transients of IBRs. An extensive dataset, including environmental data, load profiles, and fault instances, was used for training and validation. The source of this dataset was the computational electromagnetic transient (EMT) models of IBRs and validated results. A test system was developed to integrate a microgrid comprising batched ML-based IBR modules into a large-scale ac–dc system, which is based on the IEEE 118-bus system. The system is deployed on a field-programmable gate array (FPGA) board, highlighting the viability of real-time, hardware-accelerated emulations. The results show that the hybrid ML methodology accurately represents large-scale IBRs and predicts transient behaviors in integrated grids, offering crucial insights for the future planning, operation, and control of ac–dc grids, especially those with high renewable energy integration.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".