Alexandre Forel (TUM, AdONE)
Integrated stochastic optimization of production planning and raw material management
In the agrochemical industry, tactical production planning is done using uncertain sales forecasts as demand depends on unpredictable parameters such as meteorological conditions during the next growing season. In order to deal with the high uncertainty, forecasts are periodically updated and the production plan is implemented in a rolling-horizon fashion. However, the flexibility of the production in each month is limited by the availability of raw material. In particular, the active ingredient synthesis has long lead-times and strongly limits short-term changes. Since the active ingredient delivery depends on our production plan, the long-term decisions of today restrict the short-term flexibility of tomorrow.
Our approach includes the decisions of both production planning and raw material procurement in order to ensure the flexibility of production in rolling horizon. We formulate scenario-based stochastic models with varying level of recourse and flexibility. The models are evaluated through rolling horizon simulations and the performances measured in terms of inventory cost, customer satisfaction and stability of the production plans.
Date: 08.01.2020, starting at 2 p.m.
Location: City campus Z 538