Based on the analysis of the rolling process in iron and steel enterprises, an optimal load distribution model is established for rolling mills. The objective function is to minimize the total energy consumption. The equipment and process constraints are considered. The particle swarm optimization (PSO) is employed to get the optimal rolling reductions. The simulation of a six-frame strip demonstrates the feasibility of the proposed method in Jinan Iron & Steel Group. The experimental result shows that the proposed method is efficiency in the optimal load distribution problems.