An improved hunter–prey optimizer with its applications

Abstract

In recent years, metaheuristic algorithms have shown great potential in solving complex optimization problems. However, when applied to multimodal optimization problems and scenarios involving large-scale, high-dimensional, and dynamic environments, existing algorithms still have limitations. Addressing the limitations of the Hunter–prey Optimizer (HPO), characterized by low optimization accuracy and susceptibility to local optima, this paper introduces an Improved Hunter–prey Optimizer (IHPO). The main improvements of IHPO include: (1) refining the adaptive parameter C to enhance the balance between global exploration and local exploitation throughout the iteration process; (2) introducing predator search behavior early in the process to boost global search capabilities; (3) adopting a dual-population interaction strategy, effectively regulating global and local search abilities through sequential initialization, and maintaining continuous information exchange between the two evolutionary populations. To extend its utility to multi-objective optimization, this paper introduces the Multi-Objective Hunter–prey Optimizer (MOHPO) and the Multi-Objective Improved Hunter–prey Optimizer (MOIHPO). To validate the efficacy of these enhancements, simulation experiments are conducted on 23 test functions, CEC-2022, CEC-2017, and CEC-2019 test suites. The optimization performance of MOIHPO is further assessed through six multi-objective test functions, demonstrating notable advantages in terms of convergence speed, accuracy, and stability. To validate IHPO's practical application in engineering optimization, truss optimization design, and an Extreme Learning Machine (ELM) regression prediction problem are considered. The results underscore IHPO's enhanced applicability in engineering optimization scenarios. The source code of IHPO is publicly availabe at https://ww2.mathworks.cn/matlabcentral/fileexchange/177049-improved-hunter-prey-optimizer-ihpo.