Pinning Decision in Interconnected Systems with Communication Disruptions under Multi-Agent Distributed Control Topology

In this study, we propose a decision-making strategy for pinning-based distributed multi-agent (PDMA) automatic generation control (AGC) in islanded microgrids against stochastic communication disruptions. The target microgrid is construed as cyber-physical system, wherein the physical modeled an inverter-interfaced autonomous grid with detailed system dynamic formulation, and network topology regarded cyber-system independent of its connection. primal goal proposed method to decide minimum number generators be pinned their identities amongst all (DGs). pinning-decisions are made based on complex theories using genetic algorithm (GA), purpose synchronizing regulating frequencies voltages generator bus-bars PDMA structure, i.e., without resorting central AGC agent. Thereafter, mapping pinning decision constructed deep-learning (DL) technique, so that pinning-decision can nearly instantly upon detecting new after approach verified 10-generator, 38-bus through time-domain simulation transient stability analysis. Simulations show making achieve robust frequency active channels.