Abstract

Abstract

Abstract
The emergence of Industry 4.0 is making production systems more flexible and also more dynamic. In these settings, schedules often need to be adapted in real-time by dispatching rules. Although substantial progress was made until the ???90s, the performance of these rules is still rather limited. The machine learning literature is developing a variety of methods to improve them. However, the resulting rules are difficult to interpret and do not generalise well for a wide range of settings. This paper is the first major attempt at combining machine learning with domain problem reasoning for scheduling. The idea consists of using the insights obtained with the latter to guide the empirical search of the former. We hypothesise that this guided empirical learning process should result in effective and interpretable dispatching rules that generalise well to different scenarios. We test our approach in the classical dynamic job shop scheduling problem minimising tardiness, one of the most well-studied scheduling problems. The simulation experiments include a wide spectrum of scenarios for the first time, from highly loose to tight due dates and from low utilisation conditions to severely congested shops. Nonetheless, results show that our approach can find new state-of-the-art rules, which significantly outperform the existing literature in the vast majority of settings. Overall, the average improvement over the best combination of benchmark rules is 19%. Moreover, the rules are compact, interpretable, and generalise well to extreme, unseen scenarios. Therefore, we believe that this methodology could be a new paradigm for applying machine learning to dynamic optimisation problems.

Abstract

Abstract
The Minimum Life on Receipt (MLOR) is a widely used rule that imposes the minimum remaining age a food product must be delivered by the producer to the retailer. In practice, this rule is set by retailers and it is fixed, around 2/3 of the age of products regardless their shelf life. In this work, we study single and two echelon make-to-stock production-inventory problems for fixed-lifetime perishables. Mixed-integer linear optimization models are developed considering the MLOR rule both as decision variable and fixed parameter. When the MLOR rule is a variable, it is considered either a sole decision of the producer or a collaborative decision between retailer and producer. The goal of this work is to compare the supply chain performance considering this innovative setting of optimal MLOR (as a variable) against the traditional setting of fixed MLOR rule. The computational results suggest that allowing flexible MLOR rules according to the shelf life of products and the operational requirements of the producer benefit both entities in the supply chain. In particular, reducing the MLOR requirement in up to 12% does not interfere substantially with the average freshness of products arriving to the retailer, but reduces extensively surplus/waste generation at the producer while keeping a small amount of waste at the retailer.