Dear and greeting all researchers,
I'm interested in optimization with several kinds of algorithms as an example GA, PSO, DE, GW, and others, but in this question asking, I specified for GA only, if there any way or command or steps can make the optimization run fast with GA multi-objective as now every one known the optimization depends in the number of variables and other proprieties like the tuning of GA (generation, iteration, initial population....)?
thanks a lot in advance for any suggestions or recommendations or answers.
Particle swarm optimization
x = particleswarm(fun,nvars) x = particleswarm(fun,nvars,lb,ub) x = particleswarm(fun,nvars,lb,ub,options) x = particleswarm(problem) [x,fval,exitflag,output] = particleswarm(___)
Dear Salah
There are certain things you could do:
1) You can try reducing the population size to decrease the computational time of the GA or any other evolutionary optimization algorithm. The computational time of the GA algorithm increases exponentially with population size.
2) You can define lower bounds and upper bounds if you know that the parameter to be optimized lies in a bounded range.
- Badges
- Science topic
- Similar topics
- Biological Science
- Kinesiology
- Running