Simulated Annealing Aided Artificial Hummingbird Optimizer for Infinite Impulse Response System Identification

Abstract

Infinite impulse response (IIR) systems, with their ability to model intricate system behaviors, have proven to be a powerful class of digital filters. However, accurately identifying the optimal filter parameters for system emulation remains a challenge. Metaheuristic algorithms have emerged as effective tools for parameter optimization in IIR filter design, allowing for the exploration of parameter spaces and the discovery of suitable filter sets. This paper introduces a novel adaptive algorithm, named simulated annealing aided artificial hummingbird optimizer (AHA-SA), which combines the strengths of the artificial hummingbird algorithm (AHA) and simulated annealing (SA). The synergistic integration of AHA and SA in the AHA-SA optimizer enables efficient search space exploration, rapid convergence, and the attainment of precise solutions. Extensive experiments demonstrate the superiority of the AHA-SA optimizer over competitive algorithms, both in terms of solution quality and convergence speed. The proposed optimizer presents a promising solution for optimization problems in various domains, with its simplicity, intuitive workflow, and potential for widespread adoption.