Research on Dual-Objective Robust Optimization Based on Monte Carlo Simulation and Simulated Annealing Algorithm

This paper presents a study on dual-objective robust optimization leveraging Monte Carlo simulation and Simulated Annealing (SA) algorithm, with a focus on addressing uncertainties and interconnectedness in product portfolios. By incorporating product substitutability and complementarity, a model is developed using a combination of dual-objective robust optimization, Grey Relational Analysis (GRA), and Monte Carlo simulation. GRA optimizes product mix, formulating dual-objective functions aimed at maximizing revenue and minimizing risk. The robust optimization framework handles fluctuations in prices, production volumes, and costs. Monte Carlo simulation evaluates model stability across various scenarios, achieving a stability rate of approximately 68%. The solution to this optimization problem is obtained using the Simulated Annealing algorithm. Results indicate an overall improvement in benefits by approximately 3.8%, accompanied by a significant enhancement in revenue stability and risk resilience.