A new genetic algorithm with Lamarckian individual learning for generation scheduling

Unit commitment (UC) is an important optimization task in the daily operation planning of the utilities. In mathematical terms, UC is a nonlinear optimization problem with a varied set of constraints. The genetic algorithm (GA), as a powerful tool to achieve global optima, has been successfully used for the solution of this complex optimization problem. Nevertheless, since the GA does not effectively use all the available information, usually the searching process does not have satisfactory convergence. In this research work, in order to improve the convergence of the GA, a new local optimizer for the UC problem based on Lamarck theory in the evolution, has been proposed. This local optimizer, which tries to improve the fitness of one chromosome in the population, effectively uses the information generated in calculating the fitness. The simulation results show that by implementing this local search method in the form of a new genetic operator, the speed of convergence to the optimum solution is noticeably increased.