A new algorithm for normal and large-scale optimization problems: Nomadic People Optimizer
Metaheuristic algorithms have received much attention recently for solving different optimization and engineering problems. Most of these methods were inspired by nature or the behavior of certain swarms, such as birds, ants, bees, or even bats, while others were inspired by a specific social behavi...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2019
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/29726/1/Salih-Alsewari2020_Article_ANewAlgorithmForNormalAndLarge.pdf http://umpir.ump.edu.my/id/eprint/29726/ https://link.springer.com/article/10.1007/s00521-019-04575-1 https://doi.org/10.1007/s00521-019-04575-1(0123456789().,-volV)(0123456789(). ,- volV) |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Metaheuristic algorithms have received much attention recently for solving different optimization and engineering problems. Most of these methods were inspired by nature or the behavior of certain swarms, such as birds, ants, bees, or even bats, while others were inspired by a specific social behavior such as colonies, or political ideologies. These algorithms faced an important issue, which is the balancing between the global search (exploration) and local search (exploitation) capabilities. In this research, a novel swarm-based metaheuristic algorithm which depends on the behavior of nomadic people was developed, it is called ‘‘Nomadic People Optimizer (NPO)’’. The proposed algorithm simulates the nature of these people in their movement and searches for sources of life (such as water or grass for grazing), and how they have lived hundreds of years, continuously migrating to the most comfortable and suitable places to live. The algorithm was primarily designed based on the multi-swarm approach, consisting of several clans and each clan looking for the best place, in other words, for the best solution depending on the position of their leader. The algorithm is validated based on 36 unconstrained benchmark functions. For the comparison purpose, six well-established nature-inspired algorithms are performed for evaluating the robustness of NPO algorithm. The proposed and the benchmark algorithms are tested for large-scale optimization problems which are associated with high-dimensional variability. The attained results demonstrated a remarkable solution for the NPO algorithm. In addition, the achieved results evidenced the potential high convergence, lower iterations, and less time-consuming required for finding the current best solution. |
|---|