An Intelligent Overcurrent Protection Algorithm Of Distribution Systems With Inverter Based Distributed Energy Resources

To facilitate renewable energy, distributed energy resources (DERs) have been significantly integrated into distribution systems through power electronics-based inverters. The control of these inverters can limit the fault currents fed from DERs during a short-circuit (SC) fault. The resulting SC current can be too low to trigger conventional overcurrent relays on distribution feeders, leading to a protection failure (should operate but does not). To address this issue, this paper proposes an intelligent overcurrent protection scheme, which applies a machine learning algorithm innovatively, i.e., the radial basis function neural network (RBFNN), to learn and detect the SC fault currents fed by inverter based DERs (IBDERs) intelligently based on the features of their time series data. This algorithm can be implemented in the microprocessor of a digital relay on a distribution feeder to online detect the SC faults of distribution systems with IBDERs fast and accurately. Numerical simulation has been performed in a distribution system benchmark with IBDER integration to verify the effectiveness of the proposed algorithm.