Towards efficient identification of fractional-order systems

This study focuses on the efficient identification of fractional-order chaotic systems, particularly under challenging conditions where the time step, iteration time, orders, parameters, initial values, and system structure are all unknown. Unlike previous work, our approach emphasizes the complexities introduced by the unknown time step and iteration time. We introduce a novel differential evolution (DE) variant, termed global and local search using success-history based parameter adaptation for differential evolution (GL-SHADE), to tackle this problem in both noiseless and noisy environments. Comprehensive simulations show that GL-SHADE outperforms other comparative algorithms by delivering both higher precision and faster convergence under these uncertain conditions, highlighting the potential of advanced DE techniques in complex system identification.