Queue Length Forecasting in Complex Manufacturing Job Shops

May, Marvin Carl; Albers, Alexander; Fischer, Marc David; Mayerhofer, Florian; Schäfer, Louis; Lanza, Gisela

doi:10.3390/forecast3020021

Cited by 10 publications

(6 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A technological system as a set of machines and production equipment with the flow of products and the probability of equipment failure (in case of failure) can serve as a mass service system. Scientists have developed a number of solutions to improve the efficiency of the production system: the method of identifying «bottlenecks» in the technological process in the conditions of Industry 4.0 [40], a model for the accurate forecasting of queue length [41], a model of a repairable mass service system [42], etc.…”

Section: Focus Of Mass Maintenance Models On Capital Resourcesmentioning

confidence: 99%

See 1 more Smart Citation

Application of Mass Service Theory to Economic Systems Optimization Problems—A Review

Galimulina,

Barsegyan

2024

Mathematics

View full text Add to dashboard Cite

An interdisciplinary approach to management allows for the integration of knowledge and tools of different fields of science into a unified methodology in order to improve the efficiency of resource management of different kinds of systems. In the conditions of global transformations, it is economic systems that have been significantly affected by external destabilizing factors. This determines the focus of attention on the need to develop tools for the modeling and optimization of economic systems, both in terms of organizational structure and in the context of resource management. The purpose of this review study is to identify the current gaps (shortcomings) in the scientific literature devoted to the issues of the modeling and optimization of economic systems using the tools of mass service theory. This article presents a critical analysis of approaches for the formulation of provisions on mass service systems in the context of resource management. On the one hand, modern works are characterized by the inclusion of an extensive number of random factors that determine the performance and efficiency of economic systems: the probability of delays and interruptions in mobile networks; the integration of order, inventory, and production management processes; the cost estimation of multi-server system operation; and randomness factors, customer activity, and resource constraints, among others. On the other hand, controversial points are identified. The analytical study carried out allows us to state that the prevailing majority of mass service models applied in relation to economic systems and resource supply optimization are devoted to Markov chain modeling. In terms of the chronology of the problems studied, there is a marked transition from modeling simple systems to complex mass service networks. In addition, we conclude that the complex architecture of modern economic systems opens up a wide research field for finding a methodology for assessing the dependence of the enterprise performance on the effect of optimization provided by using the provisions of mass service theory. This statement can be the basis for future research.

show abstract

Section: Focus Of Mass Maintenance Models On Capital Resourcesmentioning

confidence: 99%

“…Scientists see the solution to the problem of queue management as optimizing its length. So, May et al, in the example of semiconductor production using machine learning tools, offer the following heuristic approach [41]:…”

Section: Focus Of Mass Maintenance Models On Capital Resourcesmentioning

confidence: 99%

Application of Mass Service Theory to Economic Systems Optimization Problems—A Review

Galimulina,

Barsegyan

2024

Mathematics

View full text Add to dashboard Cite

show abstract

“…In recent decades, many researchers and practitioners have tried to predict stock prices using various methods, including time-series-based prediction methods [7,8], machine learningbased prediction methods [9,10], deep learning-based prediction methods [11][12][13][14], and so on. However, due to the characteristics of stock prices, such as non-linearity, high noise, and variability, it is often difficult to achieve the desired prediction results with these methods [15][16][17][18][19][20][21].…”

Section: Introductionmentioning

confidence: 99%

Time-Series Neural Network: A High-Accuracy Time-Series Forecasting Method Based on Kernel Filter and Time Attention

Zhang,

Wang,

et al. 2023

Information

View full text Add to dashboard Cite

This research introduces a novel high-accuracy time-series forecasting method, namely the Time Neural Network (TNN), which is based on a kernel filter and time attention mechanism. Taking into account the complex characteristics of time-series data, such as non-linearity, high dimensionality, and long-term dependence, the TNN model is designed and implemented. The key innovations of the TNN model lie in the incorporation of the time attention mechanism and kernel filter, allowing the model to allocate different weights to features at each time point, and extract high-level features from the time-series data, thereby improving the model’s predictive accuracy. Additionally, an adaptive weight generator is integrated into the model, enabling the model to automatically adjust weights based on input features. Mainstream time-series forecasting models such as Recurrent Neural Networks (RNNs) and Long Short-Term Memory Networks (LSTM) are employed as baseline models and comprehensive comparative experiments are conducted. The results indicate that the TNN model significantly outperforms the baseline models in both long-term and short-term prediction tasks. Specifically, the RMSE, MAE, and R2 reach 0.05, 0.23, and 0.95, respectively. Remarkably, even for complex time-series data that contain a large amount of noise, the TNN model still maintains a high prediction accuracy.

show abstract

“…The ML approaches can reveal different complex patterns defined by nonlinearity and some relationships that have difficulty discovering linear algorithms. The approaches are widely used to predict cloud services [2], health [3], energy [4], and many other real-world problems.…”

mentioning

confidence: 99%

“…In the paper Queue Length Forecasting in Complex Manufacturing Job Shops by May et al [4], the authors introduced an approach to retrospectively identify queue lengths based on transitional data. The study found that accurate queue length prediction is feasible by applying various techniques, which can enable further research and predictions.…”

mentioning

confidence: 99%