Collecting a value (Sigma ) over all of the objective function evaluations while using GA optimizer

Question

Yaser Khojah 2019-6-10

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/466296-collecting-a-value-sigma-over-all-of-the-objective-function-evaluations-while-using-ga-optimizer

编辑： Yaser Khojah 2019-6-10

I want to collect all the values of (Sigma ) over all of the objective function evaluations. I'm not really sure how to do this but I have started creating an output function as the following code and I heard this approach will not give me what I need.

I have another approach but I do not want to do it since it will take a lot of time which is based on getting all populations. Then run my main function (Stochastic_Model_Function_TOP) on the populations and store all the results. Please note this takes a lot of time. I want to store that variable (sigma) while my optimizer is running simultaneously. Is there any an efficient way to do it.

 % the script to run the optimizer
 
 clear gaoutfunction
 options          = optimoptions('ga','OutputFcn',@gaoutfunction,'UseParallel',true);
 startTime        = tic;
 fun              = @(x)Stochastic_Model_Function_TOP(x,Pi,Pa,LogNormal_G,d,lifetime,Demand,BasePrice,HighPrice,LowPrice,dis_rate_lamda,Geo,Wells_cost,Wells_rate,DStage,Operating_Fields,row);  
         
 [xGA,fval]       = ga(fun,nvars,[],[],[],[],lowbond,upbond,[],[],options);
 time_ga_parallel = toc(startTime);
 record           = gaoutfunction();
 gapopulationhistory  = vertcat(record.Population);
 gabesthistory        = vertcat(record.Best);
 gascorehistory       = vertcat(record.Score);
 
 
 
 %% My Main function to be Optimized 
  function [objective]   = Stochastic_Model_Function_TOP(x,Pi,Pa,LogG,d,lifetime,Demand,BasePrice,HighPrice,...
  LowPrice,dis_rate_lamda,Geo,Wells_cost,Wells_rate,DStage,Operating_Fields,row)
.
.
.
..
% just showing the final part. I'm optimizng the objective and I want to show sigma and objective for each population
NPV_C        = (Revenue - CAPEX);
expectedNPV  = mean(NPV_C);
sigma        = std(NPV_C);
NewObjective = (expectedNPV + 0*sigma); 
objective    = - NewObjective;
  end 
  
  
  % the output function (I heard this is not going to work)
 function [state,options,optchanged] = gaoutfunction(options,state,flag)
    persistent state_record 
    if isempty(state_record)
      state_record = struct('Population', {}, 'Best', {}, 'Score', {});
    end
    if nargin == 0
      state = state_record;
      options = [];
      optchanged = [];
    else
      state_record(end+1) = struct('Population', state.Population, 'Best', state.Best', 'Score', state.Score);
      optchanged = false;
    end
 end
 