| Popis: |
This paper proposes an innovative algorithm-based control model for improving the doubly fed induction generator (DFIG) system’s low-voltage ride-through (LVRT) capabilities. The Mountain Gazelle optimization (MGO) algorithm is combined with an adaptive neuro-fuzzy inference system (ANFIS)-based proportional-integral (PI) regulator, called the MGOANFIS-PI approach. In the proposed method, the data set of an MGO-based PI regulator is used after rectification to train the MGOANFIS controller, so updating the ANFIS technique improves MGO’s searching behavior. The implemented control method ensures LVRT capability on grid-tied wind conversion plants based on DFIG in case of a malfunction or a voltage drop. Multiple metrics relating to LVRT are monitored in the proposed system, comprising current, active, and reactive power and voltages. The objective to be achieved, which is resolved through the cascaded MGOANFIS-based PI scheme, is defined. Based on the collected data, ANFIS performs and anticipates the optimal control signal from converters on the rotor and network sides. The MGOANFIS-PI methodology effectively handles system performance and voltage instability during four fault circumstances. The LVRT functionality of the DFIG system and the power quality are enhanced with the assistance of the proposed methodology. Simulations are carried out using MATLAB/Simulink framework. Two test systems are examined: the IEEE 39 bus and the 9 MW wind power plant (WPP) test systems. The WPP’s ability to withstand grid voltage sags is analyzed as part of an effectiveness assessment. The relevance and efficacy of the proposed MGOANFIS-PI method are evaluated, and proved the better performance of the cascaded MGO-based ANFIS-PI controller when compared to PI controllers optimized by comparing it with other well-known optimization techniques, i.e., Gorilla troop optimizer, particle swarm optimization, and genetic algorithm. In the three-phase IEEE 39 bus system and the 9 MW test scheme, detailed wind power plants could persevere in the face of every fault condition. |
