Abstract

Manufacturing processes are increasingly driven by new product needs, innovations, and cost efficiency. Planning Staff and decision makers face the challenge of achieving fixed production programs and subsequently individual orders in a certain quantity and within a certain period at a guaranteed completion date. A systematic approach to scheduling and tracking resource requirements is necessary to ensure efficient flow of manufactured products. Forward- and backward-oriented planning strategies are most used by manufacturers to meet their demands for existing orders. The current application of such approaches is very time and resource intensive due to the complexity and dimension of the decision and planning problems to be considered; it is difficult to react to short-term changes within the production program. To address this gap, this paper provides a systematic litera-ture review of backward decision and planning approaches in production scenarios and presents a potential over-arching solution approach of a simulation- and machine learning-based decision support combination for operational production planning.