Agent-based Supply Chain Management Research Articles

Multi-Agents System Implementation for Supply Chain Management Making-Decision

Supply Chain Management (SCM) is a mutant and complex system which represents a competitive challenge that companies are facing. It aims to optimize the product, financial and information flows, that the company manages with its suppliers, retailers and customers. Existent computing technologies have some faults in complex systems modeling. Nevertheless, research works in multi-agent system (MAS) technology have shown that complex systems can be modeled in order to generate smart and efficient solutions. SCM is considered to be a MAS, where protagonists are represented by different agents. In addition, cooperation between actors in Agent-based SCM has been proven to be an effective mechanism for improving SCM performance. The aim of this paper is to provide a solution for decision-making problems in information systems used in SCM, where each phase in the SC has been developed as an agent allowing communication, coordination and negotiation among the agents to achieve business goals. The proposed MAS will be implemented using a Java Agent Development Framework (JADE) based on specific methods to enhance collaboration in the SCM.

Agent-based Supply Chain Management Simulator の開発

Agent-based Supply Chain Management Simulator の開発

Negotiation among autonomous computational agents: principles, analysis and challenges

Automated negotiation systems with software agents representing individuals or organizations and capable of reaching agreements through negotiation are becoming increasingly important and pervasive. Examples, to mention a few, include the industrial trend toward agent-based supply chain management, the business trend toward virtual enterprises, and the pivotal role that electronic commerce is increasingly assuming in many organizations. Artificial intelligence (AI) researchers have paid a great deal of attention to automated negotiation over the past decade and a number of prominent models have been proposed in the literature. These models exhibit fairly different features, make use of a diverse range of concepts, and show performance characteristics that vary significantly depending on the negotiation context. As a consequence, assessing and relating individual research contributions is a difficult task. Currently, there is a need to build a framework to define and characterize the essential features that are necessary to conduct automated negotiation and to compare the usage of key concepts in different publications. Furthermore, the development of such a framework can be an important step to identify the core elements of autonomous negotiating agents, to provide a coherent set of concepts related to automated negotiation, to assess progress in the field, and to highlight new research directions. Accordingly, this paper introduces a generic framework for automated negotiation. It describes, in detail, the components of the framework, assesses the sophistication of the majority of work in the AI literature on these components, and discusses a number of prominent models of negotiation. This paper also highlights some of the major challenges for future automated negotiation research.

Specifying the intertwining of cooperation and autonomy in agent-based systems

Cooperation and autonomy are two antagonistic core variables of agent-based systems, and a key challenge in designing such systems is to balance these variables appropriately. This article describes a specification schema called RNS2 that has been developed in response to this challenge. Being formally grounded in deontic logic and informally inspired by social role theory, RNS2 shows several useful features which together make it unique and distinct from related approaches. In particular, RNS2 is highly expressive and allows to specify the intertwining of cooperation and autonomy at a very precise level, and it facilitates the automated detection and resolution of autonomy-induced cooperation conflicts at design time. The application of RNS2 is illustrated in the context of an agent-based supply chain management system.

The architecture and business value of a semi-cooperative, agent-based supply chain management system

Multi-agent systems have the potential to improve supply chain management. The adoption of such systems has been limited, as their design often neglects existing organizational realities and the business value for the various stakeholders is not clear. In this paper, a multi-agent system improving supply chain management is designed and its business value is evaluated. We present the semi-cooperative architecture and evaluate the benefits using agent-based simulation. We found that the multi-agent system increases the level of flexibility in the supply chain and enables supply chain members to become more responsive. This has a positive impact on the ordering lead-time, human processing time, the inventory levels and number of stock-outs.

Agent-based supply chain management parts 1 and 2

Agent-based supply chain management parts 1 and 2

Agent-based supply chain management—2: a refinery application

The refinery business involves tasks that span several departments and process large amount of data. Among others, these include crude procurement, logistics and scheduling (storage, distillation units, etc.). Current refinery decision support systems (DSSs) fail to integrate all the decision-making processes of a refinery, to interface with other systems in place, to incorporate dynamic data from various sources and to assist different departments concurrently. In part 1 of this two-part paper, we proposed an agent-based framework for supply chain DSSs. Here, we demonstrate its application through a prototype DSS, called petroleum refinery integrated supply chain modeler and simulator or PRISMS, for crude procurement. PRISMS serves as a central DSS through which all processes of a refinery can be studied and enables integrated decisions with respect to the overall refinery business. In particular, PRISMS can be used to study the effects of internal policies of the refinery and its various departments. We illustrate this through three detailed ‘what-if’ studies that provide an insight into how the business responds to changes in policies, exogenous events and plant modifications.

Commitments for agent-based supply chain management

As supply chain networks are becoming more and more global, process coordination must be considered a crucial point for successful business management. The need for a suitable management and communication framework is thus becoming evident. We already have some examples showing that information sharing is a key-point at certain levels of a supply chain network. As there are several analogies between a company in a business network and an agent, the Multi-Agent System paradigm can be a valid approach for modelling supply chain networks. We consider commitment as a concept that underlies the whole multi-agent environment, that is, an interagent state, reflecting a business relation between two companies that make themselves represented by software agents. We present a data structure for commitments that can be used in the agent-based communication framework for the management of a supply chain. Business partnership between companies leads to the creation of a "channel" through which we can identify three different kinds of flow (products, money and information). We show how commitments that deal with these flows are related to one another and how they can affect the supply chain.