Agent-based Negotiation Research Articles

The Framework of Agent-based Negotiation Platform for Foundries Cooperating in Supply Chain

Abstract This paper concerns the domain of contracts in the metallurgy and heavy industry, that are the form of deals making between cooperating companies being suppliers and consumers of some goods. From a general point of view cooperation enables for small companies to realize orders that are too large for an individual producer, but contract negotiations, further scheduling and support of production are usually too difficult and complicated. This paper presents a proposition of an information system, that should make cooperation between companies more available. Such system should be distributed among cooperating producers, what is the reason for choosing of the agent technology as the main software paradigm. This system should also support interchanging of information in many norms and technical standards, what results in the use of ontology concerning metallurgy and heavy industry.

Agent-based negotiation mechanism for multi-project human resource allocation

Economic globalization has resulted in distributed product development. Companies must effectively integrate and allocate interdisciplinary designers who are geographically dispersed. The matrix-based organization structure is an effective model for multi-project human resource allocation because it satisfies the prescribed total cost constraint and fulfills the requirements of individual disciplines. This study proposes a novel negotiation mechanism for allowing design resources in a distributed environment with nontransparent information. The mechanism was used to consider competitive and cooperative relationships among the entities involved in resource allocation. Price-based negotiation was adopted for the competitive relationship and the Borda count was used in the cooperative relationship. In addition, multi-agent technology was applied to implement the proposed mechanism as an automatic and effective operation. Real cases of distributed product development were used to demonstrate how the negotiation mechanism works and to validate the mechanism’s effectiveness.

Agent-based multi-issue negotiation algorithm and strategy of technology innovation platform

To solve the problem of technology docking negotiation of technology innovation platform, the Agent-based multi-issue negotiation algorithm and strategy were analyzed and designed with reference to the technology of IntelliSense Agent. In the practical application environment of technology docking on technology innovation platform, the data of history technology docking proposals were fully used and the technology docking benefits of both the technology trading sides was fully considered, and then the Agent-based multi-issue negotiation algorithm was designed. Based on this algorithm, the technology docking strategy and the proposed solution in technology docking negotiation were designed and proposed. Thus, the optimality of comprehensive benefits was ensured and the " win-win" benefits situation was reached by the two trading sides in the technology docking negotiation. Through practical examples of technology docking on the technology innovation platform, the applicability, rationality, feasibility and effectiveness of this negotiation algorithm and negotiation strategy in its practical application environment were exemplified.

An Agent-based Negotiation Model Selector for Managing Negotiation Processes in Corrective and Preventive Actions: A Conceptual Framework

Negotiation is an important process of management in any organizations especially if it involves quality management such as in corrective and preventive actions (CPA). The ability of software agent to implement automated negotiation can help organizations resolve or avoid conflicts. While many negotiation models have been developed, studies in intelligent selection of integrated negotiation models are still lacking. This paper proposes a conceptual framework for an agent-based negotiation model selector engine to resolve conflicts in the CPA activities. Several software agents will be involved to operate the proposed engine, in order to assist organizations in resolving conflicts and maintaining high quality management.

Tasks for agent-based negotiation teams: Analysis, review, and challenges

An agent-based negotiation team is a group of interdependent agents that join together as a single negotiation party due to their shared interests in the negotiation at hand. The reasons to employ an agent-based negotiation team may vary: (i) more computation and parallelization capabilities; (ii) unite agents with different expertise and skills whose joint work makes it possible to tackle complex negotiation domains; (iii) the necessity to represent different stakeholders or different preferences in the same party (e.g., organizations, countries, and married couple). The topic of agent-based negotiation teams has been recently introduced in multi-agent research. Therefore, it is necessary to identify good practices, challenges, and related research that may help in advancing the state-of-the-art in agent-based negotiation teams. For that reason, in this article we review the tasks to be carried out by agent-based negotiation teams. Each task is analyzed and related with current advances in different research areas. The analysis aims to identify special challenges that may arise due to the particularities of agent-based negotiation teams.

An agent-based negotiation model on price and delivery date in a fashion supply chain

Price and due-date negotiation between supply chain members is a critical issue. Motivated by industrial practice, we consider in this paper a make-to-order fashion supply chain in which the downstream manufacturer and the upstream supplier are cooperative on due-date and competitive on price. We propose a two-phase negotiation agenda based on such characteristics, and aim to find an optimal solution to deal with the negotiation problem considering production cost and mutual benefit. We build an analytical negotiation model for a manufacturer-supplier pair, discuss their utilities, and examine the Pareto efficiency frontier from the theoretical perspective. After that, from an application perspective, we build an agent-based two-phase negotiation system where agents are used to represent the two parties to enhance communication. In the cooperative phase, a simulated annealing based intelligent algorithm is employed to help the manufacturer agent and the supplier agent search tentative agreement on due dates which can minimize the total supply chain cost. In the competitive phase, the two parties bargain on the pricing issue using concession based methods. They adjust the reservation value and aspiration value for pricing accordingly based on the integrated utility and the result of the previous phase. Simulation results show that, the proposed negotiation approach can achieve optimal utility of agents and reach a win-win situation for the bilateral parties. Sensitivity analysis is conducted to further generate insights on how different parameters affect the performance of the proposed system.

A multi-agent-based negotiation approach for parallel machine scheduling with multi-objectives in an electro-etching process

Electro-etching is a critical process in producing aluminium foil, and it always involves many parallel machines with three distinct voltages. Therefore, production scheduling involves these parallel machines and their eligibility. In this paper, an agent-based negotiation approach is proposed to develop a distributed parallel machine scheduling application in this manufacturing environment. The agent-based system consists of types of agent, i.e. job agents, machine agents and management agents, to represent jobs, machines and supervisors, respectively. To establish job allocations, job agents and machine agents have to bid interactively. Negotiation protocol and bid decision models are developed for negotiations between job agents and machine agents. The management agent plays a centralised controller and system coordinator role. The main function of the management agent is to manage the negotiation process between job agents and machine agents to ensure that the global objectives of the system, such as minimising total job tardiness and flow time, balancing machine loading and maximising total revenue, can be achieved. Experiments are conducted to evaluate the performance of the proposed system. The results show that the proposed agent-based scheduling mechanism will provide an integrated process plan and parallel eligible machine scheduling solutions with better global performance.

육상화물운송시장에서 기회비용을 고려한 협상방법론 연구

As a way to allocate lots of orders to many participants for vehicle allocation problem, this study has used an agent negotiation based reverse auction model. This agent negotiation provides coordination functions allowing all participants to make a profit, and accomplishing Pareto optimum solution from the viewpoint of a whole trucking cargo transportation network. In order to build a strategic cooperation relationship based on information sharing, this agent negotiation provides a coordination mechanism in which all the participants including consignors, brokerage firms, and car owners are able to attain their own profits, and also that ensure a competitive market. This study has tried to prove that the result of an agent-based negotiation is the Pareto optimal solution under the present market environment. We established a mathematical formulation for a comparison with the Integer Programming model, and analysing e-Marketplace, structure of shipping expenses and brokerage system in the trucking cargo transportation industry.

Studying the impact of negotiation environments on negotiation teams’ performance

In this article we study the impact of the negotiation environment on the performance of several intra-team strategies (team dynamics) for agent-based negotiation teams that negotiate with an opponent. An agent-based negotiation team is a group of agents that joins together as a party because they share common interests in the negotiation at hand. It is experimentally shown how negotiation environment conditions like the deadline of both parties, the concession speed of the opponent, similarity among team members, and team size affect performance metrics like the minimum utility of team members, the average utility of team members, and the number of negotiation rounds. Our goal is identifying which intra-team strategies work better in different environmental conditions in order to provide useful knowledge for team members to select appropriate intra-team strategies according to environmental conditions.

Agent-Based Cloud Computing

Agent-based cloud computing is concerned with the design and development of software agents for bolstering cloud service discovery, service negotiation, and service composition. The significance of this work is introducing an agent-based paradigm for constructing software tools and testbeds for cloud resource management. The novel contributions of this work include: 1) developing Cloudle: an agent-based search engine for cloud service discovery, 2) showing that agent-based negotiation mechanisms can be effectively adopted for bolstering cloud service negotiation and cloud commerce, and 3) showing that agent-based cooperative problem-solving techniques can be effectively adopted for automating cloud service composition. Cloudle consists of 1) a service discovery agent that consults a cloud ontology for determining the similarities between providers' service specifications and consumers' service requirements, and 2) multiple cloud crawlers for building its database of services. Cloudle supports three types of reasoning: similarity reasoning, compatibility reasoning, and numerical reasoning. To support cloud commerce, this work devised a complex cloud negotiation mechanism that supports parallel negotiation activities in interrelated markets: a cloud service market between consumer agents and broker agents, and multiple cloud resource markets between broker agents and provider agents. Empirical results show that using the complex cloud negotiation mechanism, agents achieved high utilities and high success rates in negotiating for cloud resources. To automate cloud service composition, agents in this work adopt a focused selection contract net protocol (FSCNP) for dynamically selecting cloud services and use service capability tables (SCTs) to record the list of cloud agents and their services. Empirical results show that using FSCNP and SCTs, agents can successfully compose cloud services by autonomously selecting services.

Reaching Unanimous Agreements Within Agent-Based Negotiation Teams With Linear and Monotonic Utility Functions

In this article, an agent-based negotiation model for negotiation teams that negotiate a deal with an opponent is presented. Agent-based negotiation teams are groups of agents that join together as a single negotiation party because they share an interest that is related to the negotiation process. The model relies on a trusted mediator that coordinates and helps team members in the decisions that they have to take during the negotiation process: which offer is sent to the opponent, and whether the offers received from the opponent are accepted. The main strength of the proposed negotiation model is the fact that it guarantees unanimity within team decisions since decisions report a utility to team members that is greater than or equal to their aspiration levels at each negotiation round. This work analyzes how unanimous decisions are taken within the team and the robustness of the model against different types of manipulations. An empirical evaluation is also performed to study the impact of the different parameters of the model.

A Concept toward Negotiation Support for Value Management on Sustainable Construction

Decision making for value-based design in Value Management (VM) is very complicated due to the involvement of many parties. In such situation where the designer, project manager, facility manager and others are involved in choosing a single alternative from a set of solutions, a negotiation support is required to evaluate and rank the solution before engaging into negotiation. This paper presents a conceptual model of negotiation support for VM. It consists of developing the appropriate research approach, methodology of negotiation and agent-based negotiation in VM. The research objectives are to find a theoretical basis and research approach for negotiation support methodology on VM, to develop a decision model for technical solution options in a satisfying function/cost preferences, to investigate negotiation style and outcome and analyze the correlation between them for the basis of scenarios on the agent system, to develop a model for agreement options and coalition algorithms on value-based decision, to validate the coalition algorithms and introduce an initial model of Negotiation Support for Value Management (NSVM). A triangulation methodology has been used to fulfill the objectives. It combines simultaneous triangulation by using case studies and survey methods and sequential triangulation in which results of one method are essential in planning the next method (theoretical mapping, survey research, focus group, case study and conceptual modeling). The methodology is based on a theoretical approach which consists of value-based decision nature in construction VM, multicriteria group decision making, game theory, negotiation theory, and agent-based development. This methodology combines value analysis method using Function Analysis System Technique (FAST); Life Cycle Cost analysis, group decision analysis method based on Analytical Hierarchy Process (AHP), and Game theory-based agent system to develop a negotiation support. The negotiation support bridges theoretical gap between automated design in construction domain and automated negotiation in information technology domain by providing a structured methodology which can lead to systematic support system and automated negotiation for VM process. It will contribute to the Value Management body of knowledge as an advanced method for creativity and analysis phase, since the practice of this knowledge is teamwork based.

Knowledge representation for multi-agent negotiations in virtual enterprises

A virtual enterprise (VE) involves the coordination of collaborative partners in the supply chain network. To seek the market opportunity, the VE initiator and the VE partners have to negotiate with each other to achieve mutual gains as well as ultimate customer satisfaction. Messages sent and received by the counterparts during the negotiation process are considered as negotiation knowledge. However, it is difficult for different companies involved in the VE to recognise the heterogeneous knowledge on their own, especially in an agent-based negotiation system. Thus, semantic interoperability is an important issue in a VE. The objective of this research is to propose an ontology-based knowledge representation approach to provide a semantic interoperable environment to realise automatic negotiations in the VE. The contribution of this article is twofold. On the one hand, an ontology-based knowledge representation scheme is established for VE partners’ ontology construction, matching and integration. On the other hand, two agent interaction protocols are developed for the multi-agent system (MAS) to retrieve semantic correspondences and conduct bid negotiations.

Applying hybrid case-based reasoning in agent-based negotiations for supply chain management

In recent years, enormous research effort has been spent on the development of multi-agent systems to automate buyer–seller negotiations in supply chain management (SCM) applications. In many of these agent-based negotiation systems, the negotiation process is restricted to the stage when agents interact to exchange bargaining offers; activities in the pre-bargaining and post-bargaining stages are ignored. With a more comprehensive perspective, the negotiation lifecycle comprises a number of phases including the pre- and post-bargaining phases, in addition to the phase when participants interact to bargain. In this paper, a hybrid case-based reasoning approach is applied in the pre- and post-negotiation phases to support adaptive negotiation strategy for buyer–seller negotiations in SCM applications. When a new negotiation problem arrives, a similar previous negotiation case is retrieved from the case database and its solutions are recommended for inferring the negotiation parameters. The recommended parameters have to be adjusted to suit the new negotiation problem. Subsequent to negotiation completion, negotiation parameters and the negotiation outcome are analyzed and evaluated. After the evaluation, the new negotiation case, including the problem descriptions and solutions, is retained in the case database for future applications.

Improving agent-based negotiation efficiency in construction supply chains: A relative entropy method

This research presents a relative entropy method for improving agent-based negotiation efficiency (REANE) in a construction supply chain. REANE provides a path forward to help negotiators reach an acceptable solution when other methods fail; the key insight is the use of relative entropy to measure the relative degree of consensus among parties and hence minimize necessary compromises. An illustrative example is presented to show the application of REANE. The REANE method aggregates the preference information of negotiators in CSC twice. First, a compromise group preference order is ascertained using preference information, which is newly provided by negotiators, and compromise preference information (formed previously in the agent-based auto-negotiation process). Second, group preferences are aggregated by employing a relative entropy model, which is established based on entropy theory, while, considering the multiple attributes of negotiation in a construction supply chain. The method of REANE fulfills the necessary requirement of group decision-making, i.e., maximizing the preference consistency of decision-making groups and minimizing the utility gaps between every negotiator's preference and the group's preference.

The agent-based negotiation process for B2C e-commerce

B2C e-commerce is becoming more widespread as more people come to recognize its convenience and its ability to rapidly respond to requests and as more products and services become available. However, many electronic marketplaces, especially in the business-to-consumer, are in essence some kind of search engine where buyers look for the best product in a database of products offered by sellers. Usually, such e-marketplaces do not use agent technology at all although agents could significantly improve the services provided both for the buyers and the sellers. Further, negotiation capabilities are essential for B2C e-commerce systems. In an automated negotiation, intelligent agents engage in broadly similar processes to achieve the same end. In more detail, the agents prepare bids for and evaluate offers on behalf of the parties they represent with the aim of obtaining the maximum benefit for their users. Nevertheless, in the current situation, price is the only criterion by which agents are created. This factor is easy to measure and automate. However, the criteria for advanced transactions need to be elaborated, for example, details of giveback and dividend. In this paper, we present a multiple-attributes negotiation model for B2C e-commerce, which deploys intelligent agents to facilitate autonomous and automatic on-line buying and selling by intelligent agents while quickly responding to consumers. These include a 4-phase model, information collection, search, negotiation, and evaluation. We also apply fuzzy theory and analytical hierarchy process to develop the system interface to facilitate the user inputs. Finally, an example of the notebook purchasing process is illustrated.

BTO supply chain configuration via agent-based negotiation

This paper presents a constraint-based contract net protocol for agent-based configuration of a Build-To-Order (BTO) supply chain. Applicability of BTO supply chain configuration using intelligent agents has been proved in many research works. Mainly this is due to the fact that both agent-based systems and supply chains consist of a number of independent units that have to collaborate in order to achieve the goal set. Here presented negotiation protocol is a development of the contract net protocol. The latter has been extended with iterative negotiation process, constraint-based information exchange/processing and other features. This allowed improving solutions, but the negotiation time increased. The analysis of the negotiation time for the modified protocol showed that it linearly depends on the product complexity (number of product components) and quadratically on the being configured supply chain complexity (number of suppliers).

Negotiation Behaviors in Agent-Based Negotiation Support Systems

Prior research on negotiation support systems (NSS) has paid limited attention to the information content in the observed bid sequences of negotiators as well as on the cognitive limitations of individual negotiators and their impacts on negotiation performance. In this paper, we assess the performance of human subjects in the context of agent-based NSS, and the accuracy of an exponential functional form in representing observed human bid sequences. We then predict the reservation values of negotiators based on their observed bids. Finally, we study the impact of negotiation support systems in helping users realize superior negotiation outcomes. Results indicate that an exponential function is a good model for observed bids.

Adapting an agent-based negotiation protocol for a collaborative network of CBM service providers

The only way to minimize maintenance cost and contemporarily maximize plant availability is to perform a condition based maintenance (CBM) strategy for the main critical equipments of the system. This kind of maintenance requires a condition monitoring system and expert skills in order to forecast the degradation phenomenon. Very often these type of competences and the relative maintenance activities are managed by external service providers. So the actual configuration of the maintenance services of a factory is composed by a network of medium and small enterprise that work coordinating by a main contractor without any real integration or cooperation able to improve service efficiency. In this paper we suggest an approach to achieve a condition based maintenance in legacy plants, without peculiar exceptions for the technology involved, maintained through a collaborative network of enterprises. A demonstration unit was built as a test case for the functioning of the expert system to manage the condition based maintenance and the network of skills involved. In the present work, we present a widening regarding the negotiation mechanism that is one the most important issue of the expert system for the collaborative network management.

Model checking communicative agent-based systems

Model checking is a formal technique used to verify communication protocols against given properties. In this paper, we propose a new model checking algorithm aims at verifying systems designed as a set of autonomous interacting agents. These software agents are equipped with knowledge and beliefs and interact with each other according to protocols governed by a set of logical rules. We present a tableauased version of this algorithm and provide the soundness, completeness, termination and complexity results. A case study about an agent-based negotiation protocol and its implementation are also described.