English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Improving system-level resiliency of networked microgrids is an importantaspect with increased population of inverter-based resources (IBRs). This paper(1) presents resilient control design in presence of adversarial cyber-events,and proposes a novel federated reinforcement learning (Fed-RL) approach totackle (a) model complexities, unknown dynamical behaviors of IBR devices, (b)privacy issues regarding data sharing in multi-party-owned networked grids, and(2) transfers learned controls from simulation to hardware-in-the-looptest-bed, thereby bridging the gap between simulation and real world. Withthese multi-prong objectives, first, we formulate a reinforcement learning (RL)training setup generating episodic trajectories with adversaries (attacksignal) injected at the primary controllers of the grid forming (GFM) inverterswhere RL agents (or controllers) are being trained to mitigate the injectedattacks. For networked microgrids, the horizontal Fed-RL method involvingdistinct independent environments is not appropriate, leading us to developvertical variant Federated Soft Actor-Critic (FedSAC) algorithm to grasp theinterconnected dynamics of networked microgrid. Next, utilizing OpenAI Gyminterface, we built a custom simulation set-up in GridLAB-D/HELICSco-simulation platform, named Resilient RL Co-simulation (ResRLCoSIM), to trainthe RL agents with IEEE 123-bus benchmark test systems comprising 3interconnected microgrids. Finally, the learned policies in simulation worldare transferred to the real-time hardware-in-the-loop test-bed set-up developedusing high-fidelity Hypersim platform. Experiments show that thesimulator-trained RL controllers produce convincing results with the real-timetest-bed set-up, validating the minimization of sim-to-real gap.

Resilient Control of Networked Microgrids using Vertical Federated Reinforcement Learning: Designs and Real-Time Test-Bed Validations