Abstract:

An improved shuffled frog leaping algorithm (Im-SFLA) was proposed for solving constrained optimization problems. In view of overcoming the defects of shuffled frog leaping algorithm (SFLA) such as slow searching speed in the late evolution and local minimum, the ideas of simulated annealing and immune vaccination were involved into basic SFLA with Guassian mutation and chaotic disturbance in the improved algorithm. The test results on standard test functions indicated that Im-SFLA could outstandingly enhance the convergence velocity and precision, effectively averted the local extreme values and the global searching performance was superior to SFLA. The static penalty function was used to transform a constrained optimization problem into an unconstrained optimization problem, and the test results on 12 constrained optimization benchmark functions showed that Im-SFLA could obtain a high solution quality and had strong robust, which was an effective algorithm for solving constrained optimization problems.

Key words: immune, shuffled frog leaping algorithm, simulated annealing, Guassian mutation, constrained optimization, chaotic disturbance