Simultaneous multi-controller fusion via genetic algorithm-optimized weighted summation for variable-speed wind turbine control

Although individual controllers have been frequently studied across several research fields, the synergistic combination of multiple control strategies is still mostly unexplored. This paper introduces and develops an advanced hybrid parallel controller (HPC) in which Proportional-integral (PI), Sliding Mode (SMC), and Backstepping (BSC) controllers operate concurrently and contribute simultaneously to the generation of the optimal signal command through weighted-summation. The motivation stems from an extensive concept that the suggested HPC architecture benefits from the complementary nature of these controllers, where each controller’s strengths compensate for the others’ weaknesses. PI offers a null steady-state error, SMC ensures excellent robustness and fast disturbance rejection, and BSC delivers Lyapunov-based stability for nonlinear dynamics. The HPC’s performance is evaluated using four manually configured weight settings designed to compare HPC’s performance to that of pure controllers and investigate the effect of weight distribution on HPC’s control behavior. Subsequently, a genetic algorithm (GA) is applied to determine the optimal weight distribution. Extensive Matlab/Simulink simulations have been carried out on a 1.5 MW wind turbine under different operating conditions. The results demonstrate that the developed HPC outperforms all pure controllers with an ITAE improvement ranging from 58 to 75.57%, while the GA-optimized HPC (HPC-GA) further outperforms all manually tuned configurations, showing more than 83% reduction in ITAE, with physically significant trends: SMC and BSC contributions increase with parameter changes, on the other hand PI contribution decreases until complete elimination at the most disturbing conditions, demonstrating that the GA serves as a discovery mechanism for HPC.