A5080386912- Anomaly Detection Techniques and Applications
- Smart Grid Security and Resilience
- Network Security and Intrusion Detection
- Power Systems and Technologies
- Electric Power System Optimization
- HVDC Systems and Fault Protection
- Energy Efficiency and Management
- Energy Load and Power Forecasting
- Power Systems and Renewable Energy
- Data Visualization and Analytics
- Advanced Computational Techniques and Applications
- Power Systems Fault Detection
- Electricity Theft Detection Techniques
- High-Voltage Power Transmission Systems
Huazhong University of Science and Technology
2022-2025
As a cyber-physical attack targeting power systems, False Data Injection Attack (FDIA) has raised widespread concern in recent years. Many FDIA detection approaches the literature train learning models using historical data to distinguish attacked measurements from normal ones. These typically suffer severe generalization problems. Although they can achieve good performance when similar distribution offline training and online application phases, often perform poorly an operating condition...
To improve the protection sensitivity under high-resistance faults in VSC-HVDC (Voltage Source Converter based High Voltage Direct Current Transmission) grids, a novel traveling wave scheme is proposed. Firstly, by analyzing non-fault pole current, characteristics of FCENP (First Extremum Non-Fault Pole) are revealed; it reduced fault resistance and increased distance reflected wave. Then, on FCENP, indistinguishable divided into different zones. The proposed, with corresponding auxiliary...
False Data Injection Attack (FDIA) has become a growing concern for modern cyber-physical power systems. Existing data-driven FDIA detection methods are typically based on identifying abnormal spatiotemporal correlation patterns in measurement data, whose accuracy may degrade with the continuous drift of data distributions over long-term application. In addition, use black-box models bad interpretability make it difficult to precisely locate manipulated measurements. This paper proposes...
False Data Injection Attack (FDIA) has become a growing concern in modern cyber-physical power systems. Most existing FDIA detection techniques project the raw measurement data into high-dimensional latent space to separate normal and attacked samples. These approaches focus more on statistical correlations of values are therefore susceptible distribution drifts induced by changes system operating points or types strengths, especially for localization tasks. Causal inference, other hand,...
With the ever-increasing level of bidding freedom bestowed to participants in deregulated electricity markets, strategies have become more complicated, inevitably giving rise growth market uncertainties. Despite rich literatures on Bidding Behavior Forecasting (BBF), there remains a gap enhancing performance probabilistic BBF and understanding sources uncertainties markets. This paper proposes holistic Bayesian Deep Learning (BDL) framework based Accurate Variational Inference (AVI) bridge...
With an ever-increasing number of inverter interface distributed generations (IIDGs) plugged into the distribution grids, short-circuit characteristics within network have dramatically changed. It is, therefore, necessary to perform certain verifications or recalibrations existing relay settings. The current calculation methods considering IIDG require iterative solutions, which are incompatible with non-iterative algorithms embedded in traditional setting software. This conflict can give...