Neutrino‐like particle for particle swarm optimization

Abstract

The real‐world optimal problems frequently encountered by various industries are the nonlinear constrained optimization problems (NCOPs), where the constraints represent the limitations of practical resources. Many researchers have attempted to improve particle swarm optimization (PSO) in the past decades; however, in solving the NCOPs, the PSO‐based approaches often cause premature convergences. The problem‐specific constraints frequently generate many infeasible regions that block the movements of particles. The particles' behavior causes the exploration abilities of particles that tend to weaken along with time. The decreasing of exploration ability often comes from the particle becoming stagnant or moving unusefully. This study proposes a neutrino‐like particle (NLP) with adaptive NLP hyperparameters that simulate the natural neutrino behavior. The proposed NLPs can be embedded in the PSO‐based approaches for overcoming premature convergence. The experiment results demonstrate that all referenced PSO‐based methods with the NLPs improved significantly compared with those without the NLPs to solve the NCOPs. All referenced PSO‐based methods that embedded the NLPs also significantly outperform four recent strong algorithms in most IEEE CEC 2020 benchmark problems. Therefore, the proposed NLPs with adaptive NLP hyperparameters can effectively solve the premature convergences, reinforce the exploration ability, and maintain the exploitation capability for solving the NCOPs over the whole evolution process.

Novel multiobjective particle swarm optimization based on ranking and cyclic distance strategy

“…That is, through the aggregation method, MOPs are transformed into several scalar optimization subproblems for optimization. In NLPPSO, Lu et al 31 propose a neutrino‐like particle with adaptive NLP hyperparameters to simulate the behavior of natural neutrinos. The proposed NLPs can be embedded into PSO‐based methods to overcome premature convergence.…”

Energy Dispatching Based on an Improved PSO-ACO Algorithm

“…On this basis, they combined PSO with correlation-guided clustering to propose a new three-phase hybrid feature selection algorithm, which reduced the computational cost, improved the algorithm search speed in high-dimensional data, and efectively solved the constrained problems of evolutionary algorithms in high-dimensional data feature selection [36]. Lu et al [37] proposed PSO integrating neutrino-like particles, which can enhance its global search ability in nonlinear constrained optimization problems and avoid premature convergence.…”

Fireworks algorithm based on search space partition

“…Particle swarm optimization 26 and ant colony optimization 27 are the most classical and efficient methods. Novel algorithms or improved methods are emerging in recent years, inspired from garra rufa, 3 gorilla, 4 bacterium, 28 neutrino, 29 and cellular genetic 30 …”