Check out our interactive example notebooks in Google Colab to find out just how simple it is to solve multistage stochastic programming problems with QUASAR®!
What to expect in this notebook? In this example notebook, we are going to look at a classic optimization problem from operations management: aggregate planning.
Aggregate planning is a type of tactical production planning that deals with the problem of building up and adjusting capacity to ensure uninterrupted production over a time horizon that ranges from several months to years. The objective of aggregate planning is to maximize capacity utilization while minimizing operational cost from backlogs and holding inventory under uncertain product demand. An optimal aggregate production plan minimizes inventory, minimizes workforce fluctuations, maximizes production rates, and maximizes asset utilization.
Conventional aggregate planning uses long-term sales forecasts to capture fluctuations in product demand but ignores forecast errors as well as other sources of uncertainty. The problem with ignoring uncertainty is that the resulting plan not only conveys a false sense of security about what is going to happen in the future, but moreover, the decisions that result from the plan do not properly balance the risk of having too much versus too little capacity.
Despite this obvious deficiency, aggregate planning tools that account for demand uncertainty are hard to find, which is likely due to the inherent difficulty of solving the underlying optimization problem. With QUASAR, introducing parameter uncertainty into aggregate planning is a no-brainer, as you will see in this example.
Any QUASAR® model can be transformed into a fully-fledged software solution for end users with QUASAR® Cloud.