An agent-based simulator for quantifying the cost of uncertainty in production systems

Product-mix problems, where a range of products that generate different incomes compete for limited set production resources, are key to the success many organisations. In their deterministic forms, these simple optimisation problems; however, consideration stochasticity may turn them into analytically and/or computationally intractable problems. Thus, simulation becomes powerful approach providing efficient solutions real-world product-mix this paper, we develop simulator exploring cost uncertainty in systems using Petri nets and agent-based techniques. Specifically, implement stochastic version Goldratt's PQ problem incorporates volume mix customer demand. Through statistics, derive regression models link net profit level variability mix. While decreases as grows, find system is able effectively accommodate certain when Drum-Buffer-Rope mechanism. regard, reveal more robust than uncertainty. Later, analyse cost-benefit trade-off reduction, which has important implications professionals. This analysis help optimise profitability investments. observe mitigating should be given higher costs reducing low, while efforts best concentrated on alleviating under high costs.