Microgrid allows the integration of remote sources and other flexible loads to raise security concerns. Thus, it is necessary to detect the type of fault to maintain the system's stability. Existing fault detection systems include limitations such as high detection times, inability to process noisy data and discretization issues. To address these issues, a spiking neural network with a self-organizing map is used to produce precise synaptic weights for fault detection in the microgrid. A feature exploration-based spiking neural network can accurately classify faults such as line-to-ground (LG), line-to-line (LL), double line-to-ground (DLG), and three-phase ground (TLG). To mitigate the impact of the fault, a voltage deviation estimation-based control method is used, which employs a three-degree of freedom fractional order proportional integral resonant (3DOF-FOPIR) controller. In order to stabilize the system frequency, the controller sends a control signal to the multi-level inverter based on the measured voltage deviation and fault auxiliary value. This ensures reduced distortions at the output voltage, and thus, it maintains the stability of the microgrid. As a result, when compared to graph-based convolution networks, the proposed method has a higher accuracy of 99.8 % and a lower error in system stability of 55.47 %.
Read full abstract