Learning Based Resilient Control and Vulnerability Management for Wide Area Damping Control with Cyber and Physical Structures
Bibliographic record
Abstract
Low-frequency oscillations (LFOs) limit power transmission between interconnected power systems, focusing especially on inter-area oscillations.While power system stabilizers (PSSs) effectively manage inner-area oscillations, inter-area oscillations remain a significant challenge.This is compounded by cyber uncertainties including uncertain time delays and random DoS attacks in wide-area signal transmissions through remote phasor measurement units (PMUs) operating over wireless channels, affecting both the reliability and security of power system operations. InnovativeReinforcement Learning (RL) algorithms and deep reinforcement learning (DRL) are proposed to secure communication channels and stabilize cyber-physical systems under these conditions, without requiring prior knowledge of the specific cyber uncertainties.A key innovation is the development of a model-free RL based Wide-Area damping controller (WADC), which evolves into a more advanced DRL based version.This version employs the Deep Deterministic Policy Gradient (DDPG) method to refine controller policies.The training process integrates cyber and physical layer data, including random time delays, to enhance the effectiveness of the stabilization process.Additionally, a coordinated WADC scheme is designed to address multi-mode LFOs effectively.For modes with minor disturbances, it proposes a DRL-based WADC i equipped with an LSTM delay compensator, allowing the DRL agent to adapt to dynamic power system conditions by designing optimal stabilization voltage action sets.For significant disturbances, it recommends a robust DRL-based WADC that features continuous online training using a minimax DRL algorithm aimed at optimizing performance under worst-case scenarios.This approach not only improves robustness but also utilizes a combination of cyber and physical system metrics within the agent's state set to enrich training data, ensuring more effective stabilization and reducing training costs.To defend against uncertain cyber attacks on the communication channels from PMUs to WADCs, the thesis proposes an incomplete information stochastic game (IISG) based optimal cyber-layer intrusion detection system (IDS).This IDS employs a Bayesian-based method to update beliefs about the nature of the input signals, distinguishing between genuine PMU signals and potential threats.This strategy is designed to minimize unnecessary defensive actions, to optimize system response to actual threats and to enhance overall security measures within the power systems.
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) | 0.000 | 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 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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".