An Improved Bird Swarm Algorithm with Adaptive Characteristics
Chao Zhou, Lei Mei, Ryad Chellali, Yongkun Zhao · 2018
Bird swarm algorithm (BSA) is a new heuristic intelligent algorithm, which has been successfully applied in many fields.In view of the shortcomings of bird swarm algorithm which is easy to fall into local optimum and premature convergence.I propose an improved bird swarm algorithm (IBSA).Firstly, the initial population is constructed by chaos optimization algorithm, so that the initial solution is uniformly distributed in the solution space, thus improving the diversity of the population.Secondly, by introducing inertial weights, nonlinear adjustment of cognitive and social coefficients can be trade-off bird local and global search ability.Finally, a disturbance strategy is added to the forging position of the birds.Thus, the diversity of population in the late iteration period is enhanced, and the ability to jump out of the local optimum is improved.Through the simulation experiments of several benchmark functions and compared with other intelligent algorithms, the results show that the improved bird swarm algorithm (IBSA) has better convergence speed and optimization precision, which proves its superiority.