Optimization methods






E. Zitzler, M. Laumanns and L. Thiele


Institut für Technische Informatik und Kommunikationsnetze, ETH Zürich–Switzerland




Strenght Pareto Evolutionary Algorithms (SPEA2)


[1] E. Zitzler, M. Laumanns and L. Thiele. "Spea2: Improving the strength Pareto evolutionary algorithm", Technical Report 103, Gloriastrasse 35, CH-8092 Zurich, Switzerland, May 2001.

Description of the method

Like NSGA-II, the modified Strength Pareto Evolutionary Algorithm (SPEA2) is one of the most important multi-objective evolutionary algorithms that use elitism approach.

Concerning fitness assignment schemeof SPEA2, for each individual is assigned a raw fitness calculated on basis of the strength value of solutions who dominate it. To discriminate between individuals having identical raw fitness values additional density information is incorporated. To form the next generation, SPAEA2 combines offspring and current population. Subsequently, the best individuals in terms of nondominance and diversity are chosen. For diversity preservation. SPEA2 uses a truncation procedure that requires a computational complexity of O(M 2 log M) where M=N+N', N is the population size, and N' is the archive population size.