Multi-Agent Systems for Semantic Web Services Composition

Multi-Agent Systems for Semantic Web Services Composition

Agostino Poggi (Università degli Studi di Parma, Italy) and Paola Turci (Università degli Studi di Parma, Italy)
DOI: 10.4018/978-1-60566-650-1.ch016
OnDemand PDF Download:
List Price: $37.50


The vision which is making its way in information technology is to encapsulate organizations’ functionalities within appropriate interfaces and advertise them as one or more Web services, which could be integrated, when brought into play, in workflows. This innovative idea brings with it new outstanding opportunities but also new great issues, related mainly to the ability to automatically discover and compose Web services. Several researchers belonging to the agent community are convinced that this technical area is a natural environment in which the agent technology features can be leveraged to obtain significant advantages. This chapter is aimed at briefly recalling the major results achieved by agent community and showing how their exploitation in the area of service-orientation systems could be very promising.
Chapter Preview


The first subsection includes a brief survey of the literature in the areas of standard Web services, workflow and semantic Web services technologies with the objective of showing the scenario in which the agent possibly contribution should be set and at the same time to give a short preamble acting as a motivation and rationale of the research work done by the agent community.

There are plenty of papers on the subject of agent and multi-agent system definition. The purpose of the second subsection is not to be comprehensive but simply to establish some basic concepts.

Key Terms in this Chapter

Goal Delegation Protocol: An interaction protocol allowing an agent to delegate a goal to another agent in the form of a proposition that the delegating agent intends its delegate to bring about.

Negotiation: A process by which a group of agents come to a mutually acceptable agreement on some matter.

Multi-Agent Planning: A process that can involve agents plan for a common goal, agents coordinating the plan of others, or agents refining their own plans while negotiating over tasks or resources.

Contracting: A process where agents can assume the role of manager and contractor and where managers tries to assign tasks to the most appropriate contractors.

Organizational Structuring: A process for defining the organizational structure of a multi-agent system, i.e., the information, communication, and control relationships among the agents of the system.

Coordination: Coordination is a process in which a group of agents engages in order to ensure that each of them acts in a coherent manner.

Autonomic Computing: It is an initiative started by IBM in 2001 and it is about an approach for realizing self-managing systems, i.e. systems characterized by self-configuration, self-healing, self-optimization and self-protection properties.

Multi-Agent System: A multi-agent system (MAS) is a loosely coupled network of software agents that interact to solve problems that are beyond the individual capacities or knowledge of each software agent.

Software Agent: A software agent is a computer program that is situated in some environment and capable of autonomous action in order to meet its design objectives.

Complete Chapter List

Search this Book: