Scallop Locomotion Optimizer: A Novel Optimization Technique for Global Optimization Tasks and Freezing Depth Prediction of Tunnels in Cold Regions

Abstract

This paper presents a novel nature-inspired metaheuristic algorithm, namely Scallop Locomotion Optimizer (SLO), designed to tackle global optimization problems across a diverse range of scenarios. The SLO algorithm primarily simulates the water absorption, water expulsion, and sliding locomotion behavior of scallops to achieve a balance between exploitation and exploration, thereby identifying optimal solutions within the search space. The performance of SLO is comprehensively evaluated against state-of-the-art optimization algorithms through extensive numerical experiments, utilizing the CEC2017 and CEC2022 benchmark test suites. Non-parametric statistical tests are employed to conduct a thorough statistical analysis, thereby confirming the robustness and superiority of the proposed algorithm. Additionally, SLO is applied to solve the freezing depth prediction problem for tunnels in cold regions, demonstrating its practical engineering applicability. The results indicate that SLO is a promising metaheuristic technique characterized by robust optimization capabilities and significant practical value, outperforming competing state-of-the-art methods in both numerical benchmark tests and freezing depth prediction.