Enhancement of cascaded multi-level VSC STATCOM performance using ANN in the presence of faults

Abstract

A system can be disturbed in terms of stability when connected to a number of loads at the distribution ends or when subjected to faults. To reverse such systems to a stable state, FACTS devices such as static synchronous compensator (STATCOM) are used. In this paper, a cascaded multi-level voltage source converter (VSC) STATCOM was designed and implemented with a novel space vector pulse width modulation (SVPWM) scheme. Artificial neural network (ANN) controller was used instead of instead of Proportional-Integral (PI) controller in the proposed scheme to improve the response time (RT) and performance of STATCOM in terms of power factor (PF) and voltage amplitude during periods of voltage sag. During the implementation, two fault sources (single-line-to-ground (SLG) and line-to- line (LL) faults) were used to create voltage sag. STATCOM was subjected to performance evaluation in the presence of these disturbances via MATLAB simulation in IEEE 3-bus system. The outcome of the simulation studies showed the ANN controller to perform better than PI as it was able to rapidly recover voltage value (<1 cycle) with unity PF.