No abstract

The high number of devices with limited computational resources as well as limited communication resources are two characteristics of the Industrial Internet of Things (IIoT). With Industry 4.0 emerges a strong demand for data processing in the edge, constrained primarily by the limited available resources. In industry, deep reinforcement learning (DRL) is increasingly used in robotics, job shop scheduling and supply chain. In this work, DRL is applied for intelligent resource allocation for industrial edge devices. An optimal usage of available resources of the IIoT devices should be achieved. Due to the structure of IIoT systems as well as security aspects, multi-agent systems (MASs) are preferred for decentralized decision-making. In our study, we build a network from physical and virtualized representative IIoT devices. The proposed approach is capable of dealing with several dynamic changes of the target system. Three aspects are considered when evaluating the performance of the MASs: overhead due to the MASs, improvement of the resource usage of the devices as well as latency and error rate. In summary, the agents’ resource usage with respect to traffic, computing resources and time is very low. It was confirmed that the agents not only achieve the desired results in training but also that the learned behavior is transferable to a real system.

No abstract

In the classical Euclidean Steiner minimum tree (SMT) problem, we are given a set of points in the Euclidean plane and we are supposed to find the minimum length tree that connects all these points, allowing the addition of arbitrary additional points. We investigate the variant of the problem where the input is a set of line segments. We allow these segments to have length 0, i.e., they are points and hence we generalize the classical problem. Furthermore, they are allowed to intersect such that we can model polygonal input. As in the GeoSteiner approach of Juhl et al. (Math Program Comput 10(2):487–532, 2018) for the classical case, we use a two-phase approach where we construct a superset of so-called full components of an SMT in the first phase. We prove a structural theorem for these full components, which allows us to use almost the same GeoSteiner algorithm as in the classical SMT problem. The second phase, the selection of a minimal cost subset of constructed full components, is exactly the same as in GeoSteiner approach. Finally, we report some experimental results that show that our approach is more efficient than the approximate solution that is obtained by sampling the segments.