Particle swarm optimization with state-based adaptive velocity limit strategy

Velocity limit (VL) has been widely adopted in many variants of particle swarm optimization (PSO) to prevent particles from searching outside the solution space. Several adaptive VL strategies have introduced with which performance PSO can be improved. However, existing simply adjust their based on iterations, leading unsatisfactory results because incompatibility between and current state particles. To deal this problem, a novel variant state-based velocity strategy (PSO-SAVL) is proposed. In proposed PSO-SAVL, adaptively adjusted evolutionary estimation (ESE) high value set for global low local state. Besides that, handling modified improve capability avoiding optima. The good PSO-SAVL experimentally validated wide range benchmark functions 50 dimensions. satisfactory scalability high-dimension large-scale problems also verified. Besides, merits are verified experiments. Sensitivity analysis relevant hyper-parameters conducted, insights how select these discussed.