Multi-objective learner performance-based behavior algorithm with five multi-objective real-world engineering problems

TL;DR

This paper introduces a novel multi-objective optimization algorithm inspired by student transfer processes, demonstrating superior performance over existing algorithms on benchmarks and real-world engineering problems.

Contribution

A new multi-objective optimization algorithm based on learner performance transfer, validated against benchmarks and real-world problems, outperforming existing methods.

Findings

The algorithm produces a diverse set of non-dominated solutions.

It outperforms MOWCA, NSGA-II, and MODA in most test cases.

Statistical analysis confirms its effectiveness.

Abstract

In this work, a new multiobjective optimization algorithm called multiobjective learner performance-based behavior algorithm is proposed. The proposed algorithm is based on the process of transferring students from high school to college. The proposed technique produces a set of non-dominated solutions. To judge the ability and efficacy of the proposed multiobjective algorithm, it is evaluated against a group of benchmarks and five real-world engineering optimization problems. Additionally, to evaluate the proposed technique quantitatively, several most widely used metrics are applied. Moreover, the results are confirmed statistically. The proposed work is then compared with three multiobjective algorithms, which are MOWCA, NSGA-II, and MODA. Similar to the proposed technique, the other algorithms in the literature were run against the benchmarks, and the real-world engineering problems utilized in the paper. The algorithms are compared with each other employing descriptive, tabular, and graphical demonstrations. The results proved the ability of the proposed work in providing a set of non-dominated solutions, and that the algorithm outperformed the other participated algorithms in most of the cases.