First, you have to understand what Genetic Algorithm does and how it works before applying it to your work. GA is a global optimisation Algorithm that mimics the Darwinian theory of evolution in improving solutions iteratively until the best or optimal solution is realised. You first need to formulate a fitness function which is the function you wish to either maximise or minimise as the case may be. Then, you can use a GA solver to solve the problem or you may think of writing your code from the scratch.

The following link useful to you.

http://www.sciencedirect.com/science/article/pii/S0960148110000145

The following paper may also helpful to you.

http://www.sciencedirect.com/science/article/pii/S0960148110000145 

For exergy analysis of the same please go through the following paper.

http://www.oalib.com/paper/6133 

Wind energy technology is developing rapidly and now beginning to compete with existing fossil-fuel power production methods.The velocity deficits caused by the wakes of each turbine were calculated by using Jensen's wake model. The optimal positions of wind turbine placement are evaluated by using genetic algorithm, while sustaining the obligatory space between adjacent turbines for operation safety. It is well-known that genetic algorithms are good for global searches, but are weak for local searchesThe logical application of area dimensions and genetic algorithm improved the overall efficiency of the wind farm. It is concluded that proposed duel level optimization method outperforms the existing ones. The total wind farm area (2km X 2km) was divided into 100 identical cells, with each cell having dimensions 200m X 200m . The performance of the proposed method is compared with the results from previous studies. The simulation results showed that power output of the wind farm increase by using same area with different dimensions. It has been observed that by using the same number of wind turbines, the total efficiency of wind farm increased by 7 %.To improve the performance of finding the optimal solution in a large search space, the hybrid methodology combines a distributed genetic algorithm and steepest ascent hill-climbing local search algorithms. The hill-climbing algorithm provides a powerful strategy for searching the local optimal solution by exploring the neighborhood of the current state. In this paper, the hill-climbing algorithm is further enhanced by a heuristic method to reduce the execution time for finding the optimal value. Test results show that this proposed hybrid distributed genetic algorithm adequately demonstrates its effectiveness in solution quality and execution time.

https://www.google.co.in/url?sa=i&rct=j&q=&esrc=s&source=images&cd=&ved=0ahUKEwjdo9rir6vTAhWBK48KHYkuCGkQjRwIBw&url=http%3A%2F%2Fslideplayer.com%2Fslide%2F5371175%2F&psig=AFQjCNGcJKIaMUw_gSWzSa2qVk_FPGRY2w&ust=1492514352994907

Thanks Prem, Pascal, and sir D.B