Multi-objective evolutionary algorithms (MOEAs) are any of the paradigms of evolutionary computing (e.g., genetic algorithms, evolutionary strategies, etc.) used to solve problems requiring optimization of two or more potentially conflicting objectives, without resorting to the reduction of the objectives to a single objective by the means of a weighted sum.
MULTI-OBJECTIVE EVOLUTIONARY OPTIMIZATION
The main ideas of evolutionary algorithms (EAs) are derived from the principles of variation and selection that are the foundation of Darwinian evolution (Beyer 2001). An evolutionary algorithm operates on a population of individuals, every one of which represents a candidate solution to a given optimization problem. Each individual is assigned a fitness value, which represents the “quality” of that potential solution. Solutions evolve by replication and become…
Particle Swarm Optimization, Evolutionary Algorithm, Neuronal Model, Strength Pareto Evolutionary Algorithm, Parameter Search Space