How to restructure my objective function to optimise using genetic algorithm?

Hello

I am solving an optimisation problem where i am minimising total cost from retailer pov. Ive attached my objective function

I need to use genetic algorithm to generate values of order qty placed by retailer. I managed to get a code snippet for it. will this be alrght? how can i use the optimiser task for this purpose?

note: mainfile and ModifiedWorking are same thing in different forms

I managed to get this code:

% geneticAlgorithm.m

function optimizedQB = geneticAlgorithm(D, SB, T, hcr, scr, pcr, ecr, populationSize, mutationRate)
    
        % Define genetic algorithm parameters
        populationSize = 50;
        generations = 100;
        mutationRate = 0.1;
        
        % Main loop for genetic algorithm
        bestQB = zeros(1, T);
        
        for generation = 1:generations
            % Generate initial population
            population = randi(SB, populationSize, T);
        
            % Evaluate fitness (total cost) for each individual in the population
            fitness = zeros(1, populationSize);
            for i = 1:populationSize
                QB = population(i, :);
                fitness(i) = calculateTotalCost(D, SB, QB, hcr, scr, pcr, ecr);
            end
        
            % Select individuals for crossover
            [~, sortedIndices] = sort(fitness);
            selectedPopulation = population(sortedIndices(1:populationSize/2), :);
        
            % Crossover
            crossoverPopulation = crossover(selectedPopulation);
        
            % Mutate
            mutatedPopulation = mutate(crossoverPopulation, mutationRate, SB);
        
            % Elitism: Replace worst individuals with the best from the previous generation
            population = [population(sortedIndices(1:populationSize/2), :); mutatedPopulation];
        
            % Find the best QB from the current generation
            [~, bestIndex] = min(fitness);
            bestQB = population(bestIndex, :);
end

Answer 1

[Catalytic]

Follow this example -

https://www.mathworks.com/help/gads/ga-nonlinear-constraint-problem-based.html

[Gauri]

thank you for your comment, but i wasnt able to draw an analogy between the article and the code i have to work with. My main doubt is how to implement genetic algorithm inside the for loop. i cant find a way to seperate the genetic algorithm outside the loop. Do you have any advice on that?

[Matt J]

Your post doesn't mention any difficulties with a for loop... I don't see why that would be the main problem. There is no fundamental difference between running ga once or within a loop. My suggestion would be that you first get ga running on a single instance of the optimization without the loop. Then, come back to us with that code if wrapping it in a loop is somehow breaking things.