Stochastic Programming Models for Production Planning Under Supply Chain Disruptions

Abstract

The issue of supply chain disruptions is a major challenge to manufacturers in terms of cost, efficiency, and overall performance. The paper gives the use of Stochastic Programming Models (SPM) in the reduction of the impact of such disruptions on production planning. The uncertain conditions included in the proposed models, like the fluctuation of demands, shortage of materials used, and delays during production, enable manufacturers to make the best decisions when there is uncertainty. The approach applies probabilistic distributions to model uncertainty and the use of scenario-based Optimization to estimate the outcomes when different situations occur. The findings have shown that the Stochastic Programming Models are able to lower the production cost by 15-20 % relative to the traditional deterministic models, and make production responsive and flexible. The models also enhance a 25 % improvement in the customer demand to be met, even when the supply chain is disrupted. The hybrid method decreases the Latency by 50 %, enhances throughput by 33 %, and realizes an average rate of resource utilization at 85 %. These advances bring out the importance of using stochastic programming to optimize resource allocation and production scheduling. The results show that the combination of stochastic programming and Optimization leads to improved resilience and continuity of production activities that provide improved management of uncertainty. Moreover, the hybrid Model, compared to the conventional approach, is superior in areas of performance by saving in costs (15%), efficiency of production (90%), and resource utilization (85%). Future studies will entail the improvement of the models in terms of multi-stage decision making and look into the applicability in real-time to scale in a variety of manufacturing environments.