ABSTRACT
As one of the most classical intelligent algorithms, particle swarm optimization (PSO) has been extensively used to deal with various optimization issues. Compared with other algorithms, PSO has merit of being simple to implement, but at the same time, it is difficult to get tradeoff between global and local search, so it does not handle optimization problems with multi-peaks well, and it is easy to entrap into local optimal. Hence, an adaptive PSO based on competitive and balanced learning strategy (APSO-CB) is put forward in the work. First, chaotic inertia weight and time-varying acceleration factors are leveraged in exploration state to speed up convergence process. Second, the competitive and balanced learning mechanism is exploited to update velocity for particles, competition and average mechanism can alleviate the situation that PSO is easy to entrap into local optimal in late stage of evolution. Next, adaptive location renewal mechanism is applied to trade off exploration and exploitation. Finally, APSO-CB is tested based on CEC2013 test suite and compared with five competitive PSOs. Experiments indicate that APSO-CB markedly outperforms other PSO variants.
CCS CONCEPTS • Computing methodologies • Artificial intelligence • Search methodologies
Index Terms
- Adaptive Particle Swarm Optimization based on Competitive and Balanced Learning Strategy
Recommendations
A Particle Swarm Optimization Algorithm Based on Genetic Selection Strategy
ISNN 2009: Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part IIIThe standard particle swarm optimization algorithm (simply called PSO) has many advantages such as rapid convergence. However, a major disadvantage confronting the PSO algorithm is that they often converge to some local optimization. In order to avoid ...
Particle swarm optimisation with multi-strategy learning
To ease the conflict between diversity and convergence rate encountered by Particle Swarm Optimisation (PSO), a multi-strategy learning PSO Algorithm (Multi-strategy Learning PSO, MSLPSO) is proposed. The proposed method can effectively preserve the ...
Particle Swarm Optimization from Theory to Applications
Particle swarm optimization PSO is considered one of the most important methods in swarm intelligence. PSO is related to the study of swarms; where it is a simulation of bird flocks. It can be used to solve a wide variety of optimization problems such ...
Comments