An improved polar lights optimization algorithm for global optimization and engineering applications

The study proposes an enhanced, high-caliber Population Evolution Polar Lights Optimization (IPLO) algorithm to address the shortcomings of the existing Polar Lights Optimization (PLO) method. These include issues like insufficient diversity in the population, a lack of speed in convergence, and an uneven balance between local optimization and global search. In the IPLO, a pseudo-random lens SPM chaos initialization (PRLS-CI) strategy is proposed for population initialization, aiming to enhance the quality and diversity of the initial population. To strike a successful balance between global exploration and local search, a reinforcement learning approach is suggested that combines adaptive dynamics with a reward loss function centered on exploration. Furthermore, the adaptive t-distribution mutation strategy is employed to enhance population diversity, accelerating the convergence speed of IPLO. In addition, the simplex method is used to construct diversified geometric search paths, improving the utilization efficiency of the population’s peripheral individuals. A comparison between the proposed IPLO and well-known optimization algorithms, as well as their improved versions, shows that IPLO outperforms other algorithms and their improved versions on multiple benchmark functions, specifically in terms of faster convergence speed and higher solution accuracy. The validation outcomes on the CEC2017, CEC 2019, and CEC 2022 benchmark functions, along with four engineering design issues, further substantiate the efficacy of the IPLO algorithm in tackling intricate real-world optimization tasks. Compared to PLO, IPLO improves convergence accuracy by 66.7%, increases convergence speed by 69.6%, and enhances stability by 99.9%. © The Author(s) 2025.