Easy Particle Swarm Optimization for Nonlinear Constrained Optimization Problems

Particle swarm optimization (PSO) is a popular stochastic approach for solving practical optimal problems from industries due to its effective performance and few hyperparameters. Nonlinear constrained optimization (NCO) problems frequently cause multiple optimal regions and can cause many infeasible regions in the search space. The state-of-the-art approaches for handling the infeasible regions generated by problems' constraints either block particles' paths or penalize NCO problems' objective values based on the standard updating velocity formula. The standard updating velocity formula introduces difficulties for particles in searching the undiscovered optimal solutions separated by infeasible regions and being mutually restrained on directions by social and cognitive factors. Afterward, the particles cause premature convergence and difficulty searching the undiscovered optimal regions to improve their solutions. Observing the biological ant colony and inspired by lazy ant behavior, this study proposes an easy particle that simulates the lazy ant to diversify the moving direction. Finally, this study integrates the proposed easy particles with referenced PSO-based approaches for solving NCO problems. The experiment results show that the proposed easy particles can effectively reinforce exploration abilities and improve the performances of all referenced PSO-based algorithms to reduce the status of premature convergence in solving NCO problems.

Automated summary

Particle swarm optimization (PSO) is a popular stochastic approach for solving practical optimal problems due to its effective performance and few hyperparameters. This study proposes easy particles inspired by lazy ant behavior to diversify moving directions and improve the exploration abilities of all referenced PSO-based algorithms in solving nonlinear constrained optimization (NCO) problems to reduce premature convergence.