Cluster-Based Optimization of an Evacuation Process Using a Parallel Bi-Objective Real-Coded Genetic Algorithm

摘要

This work presents a novel approach to the design of a decision-makingsystem for the cluster-based optimization of an evacuation process using a Parallelbi-objective Real-Coded Genetic Algorithm (P-RCGA). The algorithm is based onthe dynamic interaction of distributed processes with individual characteristics thatexchange the best potential decisions among themselves through a global population.Such an approach allows the HyperVolume performance metric (HV metric) asreflected in the quality of the subset of the Pareto optimal solutions to be improved.The results of P-RCGA were compared with other well-known multi-objective geneticalgorithms (e.g., e -MOEA, NSGA-II, SPEA2). Moreover, P-RCGA was aggregatedwith the developed simulation of the behavior of human agent-rescuers in emergencythrough the objective functions to optimize the main parameters of the evacuationprocess.