Fuzzy adaptive particle swarm optimization.pdf

Fuzzy Adaptive Particle Swarm Optimization Abstract Yuhui Shi EDS Embedded Systems Team 1401 E. Hoffer Street Kokomo, IN 46902, USA Y uhui.shi@ and Russell C. Eberhart Department of Electrical and Computer Engineering Purdue School of Engineering and Technology 799 W. Michigan Street Indianapolis, IN 46202 Eberhart@ particles are manipulated according to the following equation (Shi and Eberhart I998a, I998b): I n this paper, a fuzzy system is implemented to dynamically adapt the inertia weight of the particle swarm optimization algorithm (PSO). Three benchmark functions with asymmetric initial range settings are selected as the test functions. The same fuzzy system has been applied to all the three test functions with different dimensions. The experimental results illustrate that the fuzzy adaptive PSO i s a promising optimization method, which is especially useful for optimization problems with a dynamic environment. 1 Introduction Particle swam optimization is a population-based evolutionary algorithm. It is similar to other population- based evolutionary algorithms in that the algorithm is initialized with a population of random solutions. It is unlike most of other population-based evolutionary algorithms (Goldberg 1989, Fogel 1994, Rechenberg 1994, Koza 1992), however, in that PSO is motivated by the simulation of social behavior instead of survival of the fittest, and each candidate solution is associated with a velocity (Eberhart and Kennedy 1995, Kennedy and Eberhart 1995, Eberhart, Dobbins and Simpson 1996, Kennedy 1997). The candidate solutions, called particles, then “fly” through the search space. The velocity is constantly adjusted according to the corresponding particle’s experience and the particle’s companions’ experience. It is expected that the particles will move towards better solution areas. Mathematically, the 0-7803-6657-3/01/$10.00 2001 IEEE 101 where cI and c2 are positive constants, and rand