Optimization of virtual closed-loop supply chain under uncertainty: application of IoT

PurposeSupply chains (SCs) have been growingly virtualized in response to the market challenges and opportunities that are presented by new and cost-effective internet-based technologies today. This paper designed a virtual closed-loop supply chain (VCLSC) network based on multiperiod, multiproduct and by using the Internet of Things (IoT). The purpose of the paper is the optimization of the VCLSC network.Design/methodology/approachThe proposed model considers the maximization of profit. For this purpose, costs related to virtualization such as security, energy consumption, recall and IoT facilities along with the usual costs of the SC are considered in the model. Due to real-world demand fluctuations, in this model, demand is considered fuzzy. Finally, the problem is solved using the Grey Wolf algorithm and Firefly algorithm. A numerical example and sensitivity analysis on the main parameters of the model are used to describe the importance and applicability of the developed model.FindingsThe findings showed that the Firefly algorithm performed better and identified more profit for the SC in each period. Also, the results of the sensitivity analysis using the IoT in a VCLSC showed that the profit of the virtual supply chain (VSC) is higher compared to not using IoT due to tracking defective parts and identifying reversible products. In proposed model, chain members can help improve chain operations by tracking raw materials and products, delivering products faster and with higher quality to customers, bringing a new level of SC efficiency to industries. As a result, VSCs can be controlled, programmed and optimized remotely over the Internet based on virtual objects rather than direct observation.Originality/valueThere are limited researches on designing and optimizing the VCLSC network. This study is one of the first studies that optimize the VSC networks considering minimization of virtual costs and maximization of profits. In most researches, the theory of VSC and its advantages have been described, while in this research, mathematical optimization and modeling of the VSC have been done, and it has been tried to apply SC virtualization using the IoT. Considering virtual costs in VSC optimization is another originality of this research. Also, considering the uncertainty in the SC brings the issue closer to the real world. In this study, virtualization costs including security, recall and energy consumption in SC optimization are considered.HighlightsInvestigates the role of IoT for virtual supply chain profit optimization and mathematical optimization of virtual closed-loop supply chain (VCLSC) based on multiperiod, multiproduct with emphasis on using the IoT under uncertainty.Considering the most important costs of virtualization of supply chain include: cost of IoT information security, cost of IoT energy consumption, cost of recall the production department, cost of IoT facilities.Selection of the optimal suppliers in each period and determination of the price of each returned product in virtual supply chain.Solving and validating the proposed model with two meta-heuristic algorithms (the Grey Wolf algorithm and Firefly algorithm).

Optimized operation of large scale battery systems

In the decentralized renewable driven electric energy system, economically viable battery systems become increasingly important for providing grid-related services. End of 2016, STEAG has successfully started the commercial operation of six 15 MW large scale battery systems which have been incorporated in STEAG’s primary control pool. During the commissioning phase, extensive effort has been spent in optimizing the operational efficiency of these systems with promising results. However, the operation experience has shown that there is still significant potential for improving the system behavior as well as reducing the aging of the battery cells. By analyzing historical data of the charging power associated with the state of charge management, opportunities for significantly reducing the operational costs have been identified. By means of more involved model-based control strategies, which adequately consider the specific characteristics of the battery system, and by using mathematical optimization and artificial intelligence, adapting the state of charge management strategy to new applications, these additional cost savings can be obtained. Apart from giving insights into the operational experience with large scale battery systems, the contribution of this paper lies in proposing strategies for reducing the operational costs of the battery system using classical approaches as well as mathematical optimization and neural networks. These approaches will be illustrated by simulation results.

A Bio-Inspired Method for Mathematical Optimization Inspired by Arachnida Salticidade

This paper proposes a new meta-heuristic called Jumping Spider Optimization Algorithm (JSOA), inspired by Arachnida Salticidae hunting habits. The proposed algorithm mimics the behavior of spiders in nature and mathematically models its hunting strategies: search, persecution, and jumping skills to get the prey. These strategies provide a fine balance between exploitation and exploration over the solution search space and solve global optimization problems. JSOA is tested with 20 well-known testbench mathematical problems taken from the literature. Further studies include the tuning of a Proportional-Integral-Derivative (PID) controller, the Selective harmonic elimination problem, and a few real-world single objective bound-constrained numerical optimization problems taken from CEC 2020. Additionally, the JSOA’s performance is tested against several well-known bio-inspired algorithms taken from the literature. The statistical results show that the proposed algorithm outperforms recent literature algorithms and is capable to solve challenging real-world problems with unknown search space.

Monte Carlo construction of cubature on Wiener space

In this paper, we investigate application of mathematical optimization to construction of a cubature formula on Wiener space, which is a weak approximation method of stochastic differential equations introduced by Lyons and Victoir (Proc R Soc Lond A 460:169–198, 2004). After giving a brief review on the cubature theory on Wiener space, we show that a cubature formula of general dimension and degree can be obtained through a Monte Carlo sampling and linear programming. This paper also includes an extension of stochastic Tchakaloff’s theorem, which technically yields the proof of our primary result.

Expert-enhanced machine learning for cardiac arrhythmia classification

We propose a new method for the classification task of distinguishing atrial fibrillation (AFib) from regular atrial tachycardias including atrial flutter (AFlu) based on a surface electrocardiogram (ECG). Recently, many approaches for an automatic classification of cardiac arrhythmia were proposed and to our knowledge none of them can distinguish between these two. We discuss reasons why deep learning may not yield satisfactory results for this task. We generate new and clinically interpretable features using mathematical optimization for subsequent use within a machine learning (ML) model. These features are generated from the same input data by solving an additional regression problem with complicated combinatorial substructures. The resultant can be seen as a novel machine learning model that incorporates expert knowledge on the pathophysiology of atrial flutter. Our approach achieves an unprecedented accuracy of 82.84% and an area under the receiver operating characteristic (ROC) curve of 0.9, which classifies as “excellent” according to the classification indicator of diagnostic tests. One additional advantage of our approach is the inherent interpretability of the classification results. Our features give insight into a possibly occurring multilevel atrioventricular blocking mechanism, which may improve treatment decisions beyond the classification itself. Our research ideally complements existing textbook cardiac arrhythmia classification methods, which cannot provide a classification for the important case of AFib↔AFlu. The main contribution is the successful use of a novel mathematical model for multilevel atrioventricular block and optimization-driven inverse simulation to enhance machine learning for classification of the arguably most difficult cases in cardiac arrhythmia. A tailored Branch-and-Bound algorithm was implemented for the domain knowledge part, while standard algorithms such as Adam could be used for training.

Image Segmentation by Pairwise Nearest Neighbor Using Mumford-Shah Model

Mumford-Shah model has been used for image segmentation by considering both homogeneity and the shape of the segments jointly. It has been previously optimized by complex mathematical optimization methods like Douglas-Rachford, and a faster but sub-optimal k-means. However, they both suffer from fragmentation caused by non-convex segments. In this paper, we present hierarchical algorithm called Pairwise nearest neighbor (PNN) to optimize the Mumford-Shah model. The merge-based strategy utilizing the connectivity of the pixels prevents isolated fragments to be formed, and in this way, reaches better quality in case of images containing complex shapes.

Deep Reinforcement Learning for UAV Trajectory Design Considering Mobile Ground Users

A network composed of unmanned aerial vehicles (UAVs), serving as base stations (UAV-BS network), is emerging as a promising component in next-generation communication systems. In the UAV-BS network, the optimal positioning of a UAV-BS is an essential requirement to establish line-of-sight (LoS) links for ground users. A novel deep Q-network (DQN)-based learning model enabling the optimal deployment of a UAV-BS is proposed. Moreover, without re-learning of the model and the acquisition of the path information of ground users, the proposed model presents the optimal UAV-BS trajectory while ground users move. Specifically, the proposed model optimizes the trajectory of a UAV-BS by maximizing the mean opinion score (MOS) for ground users who move to various paths. Furthermore, the proposed model is highly practical because, instead of the locations of individual mobile users, an average channel power gain is used as an input parameter. The accuracy of the proposed model is validated by comparing the results of the model with those of a mathematical optimization solver.