Integrated Local Search Technique With Reptile Search Algorithm for Solving Large‐Scale Bound Constrained Global Optimization Problems

Abstract

The Reptile Search Algorithm (RSA) is a powerful modern optimization technique that effectively solves intricate problems across various fields. Despite its notable success, the local search aspect of RSA requires enhancement to overcome issues such as limited solution variety, a pattern of falling into local optimal traps, and the possibility of early convergence. In response to these challenges, this research introduces an innovative paradigm that melds the robust and time‐honoured local search technique, Simulated Annealing (SA), with RSA, christened henceforth as SARSA. This amalgamation aims to tackle the qualities of both strategies, synergistically improving their optimization capabilities. We utilize a broad and thorough assessment system to survey the viability and strength of SARSA. A comprehensive cluster of benchmark issues sourced from the CEC 2019 benchmark suite and an assorted set of real‐world challenges drawn from the CEC 2011 store is utilized as the test bed. This fastidiously curated testbed guarantees an intensive examination of SARSA's execution over a wide range of issues and complexities. Our observational discoveries substantiate that SARSA beats the foundational RSA and a few related calculations reported within the existing body of writing, in this manner setting up SARSA as a critical progression in optimization calculations. The prevalent execution illustrated by SARSA highlights its potential for broad application and underscores its utility in handling complex optimization issues viably.