.png){kind=icon}
.png){kind=icon}
Return
Adaptive hierarchical update particle swarm optimization algorithm with a multi-choice comprehensive learning strategy
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-021-02413-3.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Since many PSO variants are easily trapped in local optima from which they can barely break free, this paper proposes an adaptive hierarchical update particle swarm optimization (AHPSO) algorithm. The new term local optimum early warning is first defined to reflect the risk of being trapped in a local optimum. It plays a key role in the global coordinated control to determine the paradigm evolution direction and adjust the trajectory of particles in different risk environments. After that, the adaptive hierarchical update method generates two-layer and three-layer update formulas for the global exploration subpopulation and the local exploitation subpopulation, respectively, in order to improve the capability to resist the temptation of local optima. Consisting of the weighted synthesis sub-strategy and the mean evolution sub-strategy, the multi-choice comprehensive learning strategy is then employed to develop the most suitable learning paradigm to guide the motion path. Moreover, 18 benchmark functions and one real-world optimization problem are employed to evaluate the AHPSO against eight typical PSO variants. According to the experimental results, the AHPSO outperformed other methods in solving different types of functions by yielding high solution accuracy and high convergence speed.
Keywords:
Local optima early warning
Adaptive hierarchical update
Multi-choice
Weighted synthesis sub-strategy
Mean evolution sub-strategy
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.