A genetic algorithm for supply planning optimization under correlated uncertain demand

Supply planning optimization is one of the most important issues for manufactures and scholars. Supply is planned to meet the future demand. Under the uncertainty of demand, profit is maximized and opportunity loss is minimized. In real case, however, the demands of products are usually correlated. Hence, in this paper, a method is proposed for supply planning optimization under the correlated and uncertainty demand. Correlated random numbers are introduced to Monte Carlo simulation to meet the real case. The supply planning is multi-objective, thus genetic algorithm is employed. In order to search the optimal solutions effectively and efficiently, GENOCOP system is utilized to initialize population. The algorithm is tested on real data, and a wonderful performance is shown.