An Adaptive Neuro-Fuzzy Controller to Enhance Power Sharing in Distributed Energy Resources Applications

In inverter-interfaced microgrids, droop control techniques are essential for regulating active and reactive power exchange. However, their performance is compromised by the varying impedance of the feeder and the slow response to dynamic load changes, leading to power-sharing inaccuracies. This paper proposes an Adaptive Neuro-Fuzzy Inference System (ANFIS)-based virtual impedance controller to address this issue and enhance active and reactive power sharing. The proposed controller dynamically adjusts a virtual voltage to compensate for impedance mismatches, modifying the reference voltage of the inverter. This enables precise power tracking with minimal deviation from the defined reference values and a faster response under transient conditions, including startup and external disturbances. The ANFIS framework integrates fuzzy logic and neural networks, eliminating the limitations of manual and separate tuning in conventional controllers and improving performance in nonlinear systems. The controller’s performance is validated on an IEEE 39-bus test system under various scenarios, including charging, discharging, and transient disturbances. It is tested with three battery sizes (1 MW, 96 kW, and 75 kW) under the same controller setup to assess scalability. Training with per-unit data ensures scalability across different battery capacities and distributed generators. The results are compared to traditional methods to demonstrate the controller’s superior effectiveness.