Physics Informed Learning-Based Frequency Regulation and Virtual Inertia Control for Renewable Energy Generators in Power Systems
Bibliographic record
Abstract
The increasing penetration of inverter-interfacing renewable energy-based distributed generators in the electrical power grid can help meet increasing global electricity demand, reduce greenhouse gas emissions, and lower dependency on depleting fossil fuels. However, due to the intermittency and randomness of renewable energy sources such as solar PV and wind, power electronics converters are utilized to provide power conditioning and are now displacing the conventional synchronous generators in the electric power grids with the direct consequences of a reduction in the overall system inertia and lower frequency response capability of the interconnected systems. The absence of inertia support and adequate frequency response capacity may cause recurring frequency deviations, power quality problems, power loss, instability issues and eventual blackouts. This research demonstrates novel solutions to these challenges by implementing a deep reinforcement learning algorithm to achieve model-free control designs. Specifically, this research investigated the dynamic behavior of the electric power grid with integrated renewable energy generators and demonstrated a data-driven deep reinforcement learning framework with optimization-based virtual inertia and damping control for distributed inverter-based generators that guarantee frequency stability and enable the integrated renewable energy generators to participate in primary frequency regulation. Firstly, a twin delayed deep deterministic policy gradient (TD3) algorithm-based virtual inertia control for power grids with energy storage systems (ESSs) is proposed. Secondly, the inertia contribution and the effect of wind variability and fault ride-through capability of a grid-connected variable speed doubly fed induction generator (DFIG) wind turbine was studied. Thirdly, a learning-based predictive virtual inertia control is proposed for frequency regulation in low-inertia power grids. This approach utilized a physics-informed neural network (PINN) with a safety filter to improve model uncertainty and facilitate real-world application of deep reinforcement learning-based control systems for power grids with inverter-interfacing distributed generators.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".