The objective of thermal unit commitment is to schedule the on or off status and the real power outputs of units and minimize the system production cost during the period while simultaneously satisfying operational constraints. In this thesis, the Real Genetic Algorithms (RGA) and the Hybrid Taguchi-Genetic Algorithm (HTGA) approaches are presented to solve the thermal unit commitment problem, and comparison with the results obtained using GA. Then this thesis applied the systematic reasoning ability of the Taguchi method operated after mutation can promote the RGA efficiency. The objective of Taguchi method is to improve the quality of offsprings by optimizing themselves to generate a better result, because the offsprings produced randomly by crossover and mutation process is not necessary better than the parents. This method can not only enhance the neighborhood search, but can also search the optimum solution quickly to advance convergence. Finally, it will be shown that the HTGA outperforms RGA by comparing simulation results of unit commitment.