Federated Learning Forecasting for Strengthening Grid Reliability and Enabling Markets for Resilience
This work addresses grid reliability for power systems with distributed energy resources, but it appears incremental as it combines existing methods like federated learning and market mechanisms.
The authors tackled the problem of improving power grid reliability and resilience against cyber-physical attacks by proposing a distributed scheme combining federated learning for attack detection and a local electricity market for mitigation, validated on a real-world solar PV-rich grid with simulation results showing feasibility and successful mitigation.
We propose a comprehensive approach to increase the reliability and resilience of future power grids rich in distributed energy resources. Our distributed scheme combines federated learning-based attack detection with a local electricity market-based attack mitigation method. We validate the scheme by applying it to a real-world distribution grid rich in solar PV. Simulation results demonstrate that the approach is feasible and can successfully mitigate the grid impacts of cyber-physical attacks.