A Reinforcement Learning approach for a Decision Support System for logistics networks

Rabe, Markus; Dross, Felix

doi:10.1109/wsc.2015.7408317

Cited by 34 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 summarizes these findings. Rabe and Dross [22] SimChain  DW feeds the simulation model with data  Simulation results sent to the DW These results show the usage that is given to the combined use of simulation and the data integration capabilities of structures such as DWs. From these, 3 main usages can be highlighted: (1) use analytics to extract additional information from simulation results stored in a DWs; (2) use DWs to feed data to the simulation model; and (3) use the DWs to integrate simulation results.…”

Section: Simulation and Structures To Store And Integrate Datamentioning

confidence: 99%

See 1 more Smart Citation

On the use of simulation as a Big Data semantic validator for supply chain management

Vieira

Dias

Santos

et al. 2020

Simulation Modelling Practice and Theory

View full text Add to dashboard Cite

Simulation stands out as an appropriate method for the Supply Chain Management (SCM) field. Nevertheless, to produce accurate simulations of Supply Chains (SCs), several business processes must be considered. Thus, when using real data in these simulation models, Big Data concepts and technologies become necessary, as the involved data sources generate data at increasing volume, velocity and variety, in what is known as a Big Data context. While developing such solution, several data issues were found, with simulation proving to be more efficient than traditional data profiling techniques in identifying them. Thus, this paper proposes the use of simulation as a semantic validator of the data, proposed a classification for such issues and quantified their impact in the volume of data used in the final achieved solution. This paper concluded that, while SC simulations using Big Data concepts and technologies are within the grasp of organizations, their data models still require considerable improvements, in order to produce perfect mimics of their SCs. In fact, it was also found that simulation can help in identifying and bypassing some of these issues.

show abstract

Section: Simulation and Structures To Store And Integrate Datamentioning

confidence: 99%

“…Rabe and Dross [22] proposed a framework comprised of a DW and a simulation model. The main purpose was to use simulation to predict changes that would occur to specific changes in the logistics network of a company.…”

Section: Simulation and Structures To Store And Integrate Datamentioning

confidence: 99%

On the use of simulation as a Big Data semantic validator for supply chain management

Vieira

Dias

Santos

et al. 2020

Simulation Modelling Practice and Theory

View full text Add to dashboard Cite

show abstract

“…Another example is given by Rabe et al [12], where Reinforcement Learning was used alongside a simulationbased Decision Support System for logistics networks. Here, the actions of an agent were modelled through ML, to identify and select principles on which decision-making policies should be carried out by the agent.…”

Section: Related Work 1combining Machine Learning and Simulationmentioning

confidence: 99%

On the Usage of Deep Learning for Modelling Energy Consumption in Simulation Models

Woerrlein¹,

Straßburger²

2020

SNE

View full text Add to dashboard Cite

With the increasing availability of data, the desire to interpret that data and use it for behavioral predictions arises. Traditionally, simulation has used data about the real system for input data analysis or within datadriven model generation. Automatically extracting behavioral descriptions from the data and representing it in a simulation model is a challenge for these approaches. Machine learning on the other hand has proven successful in extracting knowledge from large data sets and transforming it into more useful representations. Combining simulation approaches with methods from machine learning seems, therefore, promising. Representing some aspects of a real system by a traditional simulation model and others by a model generated from machine learning, a hybrid system model (HSM) is generated. This paper discusses such HSMs and suggests a specific HSM incorporating a deep learning method for predicting the power consumption of machining jobs.

show abstract

“…According to the authors, the use of both technologies allowed the best parameters for the system to be determined. Rabe and Dross (2015) proposed a framework comprised by a DW and a simulation model, with the purpose of using simulation to predict changes that would occur to specific changes in specific logistics operations in a network of a company. In this framework, the main DW measured KPIs, while a copy of such DW was created to store simulation results.…”

Section: Simulation Using Data Storage Structuresmentioning

confidence: 99%

Simulation of an automotive supply chain using big data

Vieira

Dias

Santos

et al. 2019

Computers & Industrial Engineering

View full text Add to dashboard Cite

Supply Chains (SCs) are dynamic and complex networks that are exposed to disruption, which have consequences hard to quantify. Thus, simulation may be used, as it allows the uncertainty and dynamic nature of systems to be considered. Furthermore, the several systems used in SCs generate data with increasingly high volumes and velocities, paving the way for the development of simulation models in Big Data contexts. Hence, contrarily to traditional simulation approaches, which use statistical distributions to model specific SC problems, this paper proposed a Decision-Support System, supported by a Big Data Warehouse (BDW) and a simulation model. The first stores and integrates data from multiple sources and the second reproduces movements of materials and information from such data, while it also allows risk scenarios to be analyzed. The obtained results show the model being used to reproduce the historical data stored in the BDW and to assess the impact of events triggered during runtime to disrupt suppliers in a geographical range. This paper also analyzes the volume of data that was managed, hoping to serve as a milestone for future SC simulation studies in Big Data contexts. Further conclusions and future work are also discussed.

show abstract

A Reinforcement Learning approach for a Decision Support System for logistics networks

Cited by 34 publications

References 18 publications

On the use of simulation as a Big Data semantic validator for supply chain management

On the use of simulation as a Big Data semantic validator for supply chain management

On the Usage of Deep Learning for Modelling Energy Consumption in Simulation Models

Simulation of an automotive supply chain using big data

Contact Info

Product

Resources

About