Improvement of differential evolution variants with nonlinear population adjustment and parameter adaption

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 126945 - 126945

Опубликована: Фев. 1, 2025

Язык: Английский

NLAPSMjSO-EDA: A Nonlinear Shrinking Population Strategy Algorithm for Elite Group Exploration with Symmetry Applications

Symmetry, Год журнала: 2025, Номер 17(2), С. 153 - 153

Опубликована: Янв. 21, 2025

This work effectively modifies APSM-jSO (a novel jSO variant with an adaptive parameter selection mechanism and a new external archive updating mechanism) to offer (single objective real-parameter optimization: Algorithm jSO) version called NLAPSMjSO-EDA. There are three main distinctions between NLAPSMjSO-EDA APSM-jSO. Firstly, in the linear population reduction strategy, number of individuals eliminated each generation is insufficient. results higher inferior remaining, since total iterations fixed, these will also consume iteration counts for their evolution. Therefore, it essential allocate more elite promote emergence superior individuals. The nonlinear strategy addresses this issue. Secondly, we have introduced Estimation Distribution (EDA) sample generate from population, aiming produce higher-quality that can drive iterative evolution population. Furthermore, enhance algorithmic diversity, increased initial during subsequent experiments ensure diverse early while maintaining constant iterations. Symmetry plays role design performance inherently introduces form asymmetry mimics natural evolutionary processes, favoring reducing influence ones. asymmetric yet balanced approach ensures dynamic equilibrium exploration exploitation, aligning principles symmetry optimization. Additionally, incorporation EDA utilizes probabilistic sampling structural coherence promoting diversity. Such applications algorithm not only improve but provide insights into balancing components. NLAPSMjSO-EDA, evaluated on CEC 2017 benchmark suite, significantly outperforms recent differential algorithms. In conclusion, enhances overall APSM-jSO, establishing itself as outstanding combining code has been open-sourced.

Язык: Английский

Auxiliary population-assisted differential evolution for multi-area economic dispatch considering valve point effects

Energy, Год журнала: 2025, Номер unknown, С. 136982 - 136982

Опубликована: Июнь 1, 2025

Язык: Английский