You need to devise a procedure that can create a collection of random initial solutions, a "reproduction" procedure that takes a pair of "parent" solutions and creates a "child" solution from them, and a "mutation" procedure that takes a child solution and modifies it slightly. The details of these procedures will depend on the specific scheduling problem that you are trying to solve.

Refer the link may helpful for you:

For GA:

http://www.mathworks.com/help/gads/ga.html

For SA:

http://www.mathworks.com/help/gads/examples/minimization-using-simulated-annealing-algorithm.html

You need to prepare a program to execute the GA. Usually, it is the duty of the researcher to design the procedures to create an initial random solution (feasible may be), a procedure to calculate the fitness function, reproduction of solutions from the current solutions, and the overall algorithm. I think you'd better to follow the coding prepared by other researchers, then you will be able to write your own one. Use this text book: practical genetic algorithms

http://www.csbdu.in/pdf/Practical_Genetic_Algorithms.pdf

I think " Learning is acting" so if you want to know what is a GA ,you must solve a problem  (in a simple case an optimization problem) with it. write a code in your favorite  language (mine is Python). You could use search the web for simple examples of GA. When you coded some simple problems with it you know how to use it for the problem at hand.

some links that could be useful:

https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=2&cad=rja&uact=8&ved=0CCgQFjAB&url=https%3A%2F%2Fgist.github.com%2F741853&ei=tSm_U_6DIsbfOqyagKAO&usg=AFQjCNFSgJr9x-ivVI120C9rP_4UILFXRg&bvm=bv.70810081,d.ZWU

https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=2&cad=rja&uact=8&ved=0CCQQFjAB&url=http%3A%2F%2Finspyred.github.io%2F&ei=BSq_U8GPMsnhPJXlgBg&usg=AFQjCNHBTguXOamd4Pcz-ux0TX1Ph7MjXQ&bvm=bv.70810081,d.ZWU

or google : Genetic Algorithm Example in C++/Java,...

good luck

Hi . I am using Genetic algorithm in my work but I am always stuck with local optimal . I could not figure out how to avoid this issue. some people suggested using Simulated Annealing and Genetic Algorithm Optimization . if any one has an idea how I can combine both to solve my issue please help.

You might access Talbi's metaheuristics book. It has some good advice on these algorithms, and methods for avoiding becoming stuck in local optima.