Deadlocks represent situations in which two participants are waiting for each other to finish an activity so that neither of them will ever finish. Deadlocks can occur in complex computer-integrated systems, such as flexible and selforganizing production systems. As deadlocks bring production to halt, methods for deadlock control in production systems are widely studied. Yet most algorithms proposed are not suited for the use in decentral multi-agent systems, as they require central control or can not handle concurrency. Other algorithms can be used in a decentral fashion but assume that only one type of product will be manufactured at a time. But in times of mass customization, where customers choose a product from a variety of options, support for several product types is required. To meet both the requirements of mass customization and decentral multi-agent systems, we present a new decentralized approach for avoiding deadlocks in a self-organizing production cell, where several types of products are being manufactured in parallel. Our approach is based solely on local knowledge and does not assume central control. We evaluate our approach in terms of effectiveness and message overhead to conclude that it avoids starvation and deadlocks with a reasonable message overhead.

No abstract

Cutting and Packing problems are occurring in different industries with a direct impact on the revenue of businesses. Generally, the goal in Cutting and Packing is to assign a set of smaller objects to a set of larger objects. To solve Cutting and Packing problems, practitioners can resort to heuristic and exact methodologies. Lately, machine learning is increasingly used for solving such problems. This paper considers a 2D packing problem from the furniture industry, where a set of wooden workpieces must be assigned to different modules of a trolley in the most space-saving way. We present an experimental setup to compare heuristics, constraint optimization, and deep reinforcement learning for the given problem. The used methodologies and their results get collated in terms of their solution quality and runtime. In the given use case a greedy heuristic produces optimal results and outperforms the other approaches in terms of runtime. Constraint optimization also produces optimal results but requires more time to perform. The deep reinforcement learning approach did not always produce optimal or even feasible solutions. While we assume this could be remedied with more training, considering the good results with the heuristic, deep reinforcement learning seems to be a bad fit for the given use case.