An Improved Selfish Herd Optimization Algorithm Based on Nonlinear Inertia Weight

The Selfish Herd Optimizer (SHO) is a novel swarm intelligence algorithm with excellent performance. However, it’s accuracy is low and convergence speed is slow. In order to deal with the problems, this paper puts forward an improved Selfish Herd Optimization algorithm (NWSHO). First, aiming at the problem of uneven distribution and overlapping position of the population, a good point set is utilized to initialize pop-ulation. This strategy improves the algorithm’s stability; Second, the nonlinear inertia weight is adopted to update the position of SHO algorithm. The strategy not only bal-ances the global search and local development of the algorithm, but also accelerates the convergence speed and improves the solution accuracy. Finally, the performance of the proposed algorithm is compared with the standard SHO and other well-known swarm intelligence algorithms on two suites of benchmark functions. The results of experiment show the algorithm proposed in this paper is superior to other algorithms in precision and convergence speed. © 2023, Taiwan Ubiquitous Information CO LTD. All rights reserved.