Harmony search-based multi-objective optimization model for multi-site order planning with multiple uncertainties and learning effects

• We establish the mathematical model for multi-site order planning with multiple uncertainties and learning effects.
• We develop a novel harmony search-based multi-objective optimization model.
• The proposed harmony search-based Pareto optimization process is superior to the NSGA-II-based process.

This paper addresses a multi-objective multi-site order planning problem in make-to-order manufacturing with the consideration of various real-world features such as production uncertainties and learning effects. A novel harmony search-based multi-objective optimization model, mainly integrating a harmony search based Pareto optimization (HSPO) process and a Monte Carlo simulation process, is developed to tackle this problem. A series of experiments are conducted to evaluate the effectiveness of the proposed model based on real industrial data. Results demonstrate that (1) the proposed model can effectively solve the problem investigated; and (2) the HSPO process can generate the optimization performance superior to those generated by a multi-objective genetic algorithm (NSGA-II)-based process and an industrial method.