Multi-agent system approach applied to a manufacturer’s supply chain using global objective function and learning concepts

Henriques, Rafaella de Souza

doi:10.1007/s10845-017-1300-z

Cited by 6 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The supply chain production inventory system is designed by the traditional single-level sub-chain system, but for large enterprises, the production inventory system is a network system composed of multi-level sub-chains, which is more in line with the research on modern supply chain systems. Therefore, multi-agent is widely used in research on supply chain systems [2][3][4]. The control theory has been widely used in supply chain management.…”

Section: Introductionmentioning

confidence: 99%

Secure Change Control for Supply Chain Systems via Dynamic Event Triggered Using Reinforcement Learning under DoS Attacks

Fan,

Zhang,

Xiong

et al. 2024

Electronics

View full text Add to dashboard Cite

In this paper, a distributed secure change control scheme for supply chain systems is presented under denial-of-service (DoS) attacks. To eliminate the effect of DoS attacks on supply chain systems, a secure change compensation is designed. A distributed policy iteration method is established to approximate the coupled Hamilton–Jacobi–Isaacs (HJI) equations. Based on the established reinforce–critic–actor (RCA) structure using reinforcement learning (RL), the reinforced signals, performance indicators, and disturbance input are proposed to update the traditional time-triggered mechanism, and the control input is proposed to update the dynamic event-triggered mechanism (DETM). Stability is guaranteed based on the Lyapunov method under secure change control. The simulation results for supply chain systems show the effectiveness of the secure change control scheme and verify the results.

show abstract

Section: Introductionmentioning

confidence: 99%

Secure Change Control for Supply Chain Systems via Dynamic Event Triggered Using Reinforcement Learning under DoS Attacks

Fan,

Zhang,

Xiong

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Previous examples demonstrate the positive impact of MAS on the automation of small-scale LSCM tasks, which play key roles in supply chain networks. For instance, MAS can be used to select suppliers based on ordering synergies (Yu and Wong, 2015), to establish collaborative supply chain management (Fu and Fu, 2015), to optimize process scheduling in the supply chain (Jiang et al , 2018; Leusin et al , 2018; Yu et al , 2017) and to support decision-making in logistics networks (Blos et al , 2018; Souza Henriques, 2019).…”

Section: Introductionmentioning

confidence: 99%

The impact of multiagent systems on autonomous production and supply chain networks: use cases, barriers and contributions to logistics network resilience

Nitsche

Brands

Treiblmaier

et al. 2023

SCM

View full text Add to dashboard Cite

Purpose Academics and practitioners have long acknowledged the potential of multiagent systems (MAS) to automate and autonomize decision-making in logistics and supply chain networks. Despite the manifold promises of MAS, industry adoption is lagging behind, and the exact benefits of these systems remain unclear. This study aims to fill this knowledge gap by analyzing 11 specific MAS use cases, highlighting their benefits, clarifying how they can help enhance logistics network resilience and identifying existing barriers. Design/methodology/approach A three-stage Delphi study was conducted with 18 industry experts. In the first round, these experts identified 11 use cases of MAS and their potential benefits, as well as any barriers that could hinder their adoption. In the second round, they assessed the identified use cases with regard to their potential to enhance logistics network resilience and improve organizational productivity. Furthermore, they estimated the complexity of MAS implementation. In the third round, the experts reassessed their evaluations in light of the evaluations of the other study participants. Findings This study proposes 11 specific MAS use cases and illustrates their potential for increasing logistics network resilience and enhancing organizational performance due to autonomous decision-making in informational processes. Furthermore, this study discusses important barriers for MAS, such as lack of standardization, insufficient technological maturity, soaring costs, complex change management and a lack of existing use cases. From a theoretical perspective, it is shown how MAS can contribute to resilience research in supply chain management. Practical implications The identification and assessment of diverse MAS use cases informs managers about the potential of this technology and the barriers that need to be overcome. Originality/value This study fills a gap in the literature by providing a thorough and up-to-date assessment of the potential of MAS for logistics and supply chain management. To the best of the authors’ knowledge, this is the first study to investigate the relevance of MAS for logistics network resilience using the Delphi method.

show abstract

“…These communication acts are carried out through communication, coordination, and negotiation protocols between agents (Kalia and Singh, 2015;Viroli et al, 2015). In a supply chain context, MAS consider each of the individual objectives of the supply chain actors but, at the same time, share resources and capabilities that seek a primary common objective (de Souza Henriques, 2019;Hu et al, 2022;Serna-Urán et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Integrating Multi-agent System and Microsimulation for Dynamic Modeling of Urban Freight Transport

Gómez-Marín¹,

Mosquera²,

Serna-Urán³

2023

Period. Polytech. Transp. Eng.

View full text Add to dashboard Cite

This work aims to apply an integration between a multi-agent system and microsimulation to take advantage of the large amount of data generated in urban freight transport to improve the overall performance of the urban supply chain without forgetting the principles of autonomy that govern each of its actors, responding to the different dynamic scenarios that may arise in the operational context. The integration framework produces a satisfactory communication process in those modeling methods measured by two indexes: throughput and latency. The results of this integration show a robust response to dynamic scenarios and allow reacting to the different quantity of changes without dismissing the search for optimum solutions.

show abstract

Multi-agent system approach applied to a manufacturer’s supply chain using global objective function and learning concepts

Cited by 6 publications

References 7 publications

Secure Change Control for Supply Chain Systems via Dynamic Event Triggered Using Reinforcement Learning under DoS Attacks

Secure Change Control for Supply Chain Systems via Dynamic Event Triggered Using Reinforcement Learning under DoS Attacks

The impact of multiagent systems on autonomous production and supply chain networks: use cases, barriers and contributions to logistics network resilience

Integrating Multi-agent System and Microsimulation for Dynamic Modeling of Urban Freight Transport

Contact Info

Product

Resources

About