Research Article

Multi-Swarm Multi-Objective Optimizer Based on -Optimality Criteria for Multi-Objective Portfolio Management

Algorithm 1

Pseudocode for p-MSNSGA-II.
Main steps of p-MSNSGA-II
Set the number of swarm (m), the size of each swarm (N), the lower and upper bound of p (p-lb, p-ub),
the maximum number of cycles (MCN), the number of swarm maximum cycles (SMCN)
and the number of exchange of swarms (EN)
  repeat
Initialize the sub-swarms , assign for each swarm
repeat
The initialized solutions are sorted based on non-domination
For each sub-swarm
Selection operator based on p-optimality criteria are adopted to select superior individuals
Recombination operator and mutation operator are used
Offspring swarm is created
Non-domination and crowding distance are used by and to create
If mod (I,SMCN)=0
Exchange among m sub-swarms
End if
End for
Until cycle = SMCN EN
Sub-swarms are integrated together and sorted based on non-domination
Until cycle = MCN