The purpose of this study is to introduce a novel swarm intelligence optimization algorithm, termed Anolis Optimizer (ANO), which emulates the behavior of Anolis lizards in their quest for optimal territorial habitat locations, thereby addressing optimization problems.
The ANO utilizes a three-stage framework. First, the population dynamically divides into invaders and defenders, simulating Anolis’s territory awareness. Second, territory exploration employs an exploration operator mimicking the invaders’ movement. Finally, territory competition incorporates violent disputes via competition/escape operators, while dewlap conversion and escape operators simulate non-violent competition; uninvaded defenders undergo free movement modeling.
Evaluation results across the 23 classical test functions, as well as CEC 2017, CEC 2021 and CEC2022 benchmark suites, demonstrate that ANO achieves a 60.8% optimization rate, significantly outperforming the best result (39.2%) among 10 comparative algorithms. The algorithm exhibits exceptional performance in solving unimodal, fixed-dimensional multimodal and hybrid composition functions, with progressively enhanced convergence stability in later iterations. And it performs outstandingly in engineering optimization problems.
This study pioneers the first competitive algorithm based on Anolis territorial behavior, establishing a dynamically decoupled population architecture that enables real-time agent role partitioning and innovatively developing a multi-attack coordination mechanism. This work delivers the inaugural lizard-competition-behavior-driven optimization paradigm in swarm intelligence, overcoming the inherent limitations of abstract single-mode competition in existing algorithms, thereby establishing new theoretical foundations for engineering optimization problems. The source code is currently available for public from: https://www.mathworks.com/matlabcentral/fileexchange/181614-anolis-optimizer-ano
