- Smart Grid Security and Resilience
- Network Security and Intrusion Detection
- Smart Grid Energy Management
- Optimal Power Flow Distribution
- Energy Load and Power Forecasting
- Microgrid Control and Optimization
- Power System Optimization and Stability
- Advanced Malware Detection Techniques
- Electricity Theft Detection Techniques
Health Innovations (United States)
2024
PG&E Corporation (United States)
2017
Reinforcement learning (RL) has been employed to devise the best course of actions in defending critical infrastructures, such as power networks against cyberattacks. Nonetheless, even case smallest grids, action space RL experiences exponential growth, rendering efficient exploration by agent practically unattainable. The current algorithms tailored grids are generally not suited when state-action size becomes large, despite trade-offs. We address large action-space problem for grid...
To safeguard electric power grids from random failures and cyberattacks, a reinforcement learning approach is developed using linear temporal logic to efficiently allocate limited resources, promising improved defense for critical cyberphysical systems.
The intermittent nature of solar PV output, installed in distribution systems, may cause voltage fluctuations on the customer side. On other hand, smart meters are widely deployed field as part grid modernization efforts. This paper presents a fuzzy logic based analytical tool to determine if problems side, or problem side was caused by PV. proposed utilizes measurement capabilities meters, estimated and many additional available data analyze fluctuation high penetrated feeders. A prototype...
This paper provides details on an innovative project to better enable dispatchable resources. Today's reactive, load-serving, and outage-mitigation focused methods are insufficient because they do not effectively manage or optimize various resources within the distribution network. Our project, a DOE ARPA-E funded grant featuring work by Arizona State University (ASU), Public Service (APS) Nexant, transforms these via active resource, load, outage-managed, market-ready methodology. It...