Jeremy Pitt

Communication Protocols in Multi-agent Systems: A Development Method and Reference Architecture

The meaning of a communicative act in a multi-agent system can be characterised at a number of different levels. We argue that only one level of meaning is common across all applications: what we call the action-level semantics given by protocols or conversation policies. We define a general semantic framework for specifying the semantics of a class of Agent Communication Languages (ACLs) based on protocols. We then introduce sACL, a small ACL, and show how the action-level semantics of this language can be integrated with an intentional semantics. This enables us to specify the meaning of an individual communicative act in the context of the conversation in which it occurs, and to customise sACL for different application domains. We describe a development method for defining an ACL for a particular application, and give a reference architecture for the method using the Beliefs-Desires-Intentions (BDI) agent architecture.

Connected communities from the standpoint of multi-agent systems

We study the provision of software agents for connected communities, a class of applications aiming to augment the way people interact and socialize in geographically co-located communities such as neighbourhoods. Following a number of experiments that we have carried out in this area, we propose a multi-agent architecture and we study how to instantiate it in order to design a specific connected community system. We further report on the research challenges, the opportunities and risks raised by agent-based connected communities.

Designing Agent Communication Languages for Multi-agent Systems

To provide inter-operability between heterogeneous agents in open systems, a commonly understood agent communication language (ACL) is used. To ensure that it is commonly understood, a formal semantics for the ACL is required. In this paper, we explore ideas from the semantics of natual language dialogues for defining the meaning of ACL messages. Using a general semantic framework for characterising the semantics of a class of ACLs in terms of protocols, we introduce a method for designing an ACL for a particulaj application. We illustrate this idea with respect to a small ACL called sACL. The advajitages of this approach are that the specification is considerably less complex and more general, the potentieil for interoperability is improved, and verification of compliance to the semantics is easier.

FIPA-compliant agents for real-time control of Intelligent Network traffic

Abstract Autonomy, adaptability, scalability, and flexible communications are all attributes of agents and multi-agent systems which suggest that they may offer timely solutions for dealing with the growing complexity of the tasks of traffic control and resource management in telecommunications networks. However, if agent-based solutions to network management problems are to be successful then it will be important that heterogeneous agents and agent platforms inter-operate in accordance with internationally accepted standards. Although standards of this nature are being developed, they are not tailored specifically to the needs of the telecommunications domain, with the result that important issues, such as support for the operation of agent systems in real-time constrained environments, do not seem to be adequately addressed. We present two agent-based systems for control of traffic load and resource allocation in Intelligent Networks. One of these strategies is based on the concepts of `Market-based Control, the other on the concepts of `Ant Colony Optimisation. Using the market-based strategy as an example we show that enhancements to existing FIPA specifications would be required to implement these strategies in order to satisfy their real-time operation constraints. We also suggest a number of potential enhancements to FIPA specifications that would alleviate some of the identified problems.

Responsible agent behavior: a distributed computing perspective

Software agents that are autonomous, communicative, and possibly intelligent processes raise new questions for developers of distributed systems. Specifically, what is responsible agent behavior, and who, as the owner, is legally responsible for it? The answers involve an understanding of human-agent interaction, agent-oriented middleware, and social behavior. Some software agents will have a sufficiently large number of internal states to be capable of seemingly intelligent behavior. Hence, an agents future external behavior cannot be guaranteed on the basis of its past behavior, even if that behavior has been monitored over time. Complete compliance tests of intelligent agents, therefore, may not be achievable because of the (possibly) large number of internal states. Thus, the best we can say is that an agent has not exhibited noncompliant behavior yet. Communication between agents implies a contract between owners, and the complexity of agents implies possibly unpredictable behavior. Therefore, an appropriate legal framework is required to underwrite the consequences of communicative actions and to provide safeguards against unlawful activities. The legal implications of agent technology require new ways of thinking about working with an agent, new requirements for agent-oriented middleware, and additional types of social behavior to be considered when designing a multiagent system.

A semantic framework for specifying agent communication languages

The paper presents a hybrid semantic framework for the specification of agent communication languages (ACL), unifying intentional semantics with protocol based approaches to provide a more expressive framework. A richer state description based on publicly expressed mental attitudes is introduced. The state description also allows agents to be assigned certain roles in a protocol. Together, this moves to a more workflow-oriented approach, in which conversations are guided by protocols but the effect of individual communicative acts is highly sensitive to the context in which it occurs. We evaluate the usefulness of this framework as a standard for ACLs.

A multi-agent system for intelligent network load control using a market-based approach

Contemporary shifts in the nature of intelligent networks (IN) have both made the problem of IN load control increasingly important and have pointed towards agent technology as an appropriate solution to that problem. In this paper we present a multi-agent system, comprised of intelligent, autonomous and self-interested agents, which makes use of a market-based approach to perform real-time control of IN traffic. The algorithm is assessed against the benchmark automatic call capping (ACG) algorithm; the agent implementation is assessed in terms of its suitability to market-based IN load control. Simulation results show that the algorithm is capable of better performance in terms of generated network revenue when compared against ACG. We conclude that the engineering abstraction provided by agents, coupled with the distribution of autonomous decision-making, give a better granularity for fine-grained control of network components.

Agent-Oriented Middleware for Integrating Customer Network Services

There are a variety of forces causing previously disparate networks and services to be unified or integrated, including cost-reduction, ease of configuration and ease of maintenance. Communication networks of the future will consist of a wide variety of inter-linked computer networks, giving customers access to a huge range of potentially competing network services. From a customer perspective, the unification and integration of heterogeneous networks means that a service user (or value added service provider) can access any service from anywhere at any time. Examples of how services are coalescing include a diverse range of services from unified messaging services (incorporating FAX, voice-mail, voice and email) to the diversification of services offered by supermarkets.

A Computational Economy for IN Load Control Using a Multi-Agent System

Intelligent Networks (IN) are used in telecommunication networks to provide services that require a decision-making network element. The Service Control Point (SCP) can be overloaded when the number of service requests exceeds the SCPs designed capacity. Traditional IN load control algorithms assume a single service network model or use a centralized controller to find a solution. In this paper we propose and investigate a market-based model, in the form of a computational economy, for solving the distributed IN load control problem for a multi-service network. We investigate two algorithms, one price-oriented and the other resource-oriented, for finding the competitive equilibrium for this economy. We conclude that the price-oriented approach generally performs better and allows a greater level of distributed-decision making but suffers from an infeasible solution in real-time systems. Furthermore, we study a realization of this model as a multi-agent system (MAS) and investigate the communication overhead associated with running auctions for services.

IN Load Control Using a Competitive Market-Based Multi-agent System

Intelligent Networks (IN) are used in telecommunication networks to provide services that require a decision-making network element. This element is the Service Control Point (SCP). An overload of an SCP can result in a great reduction in the Quality of Service (QoS) provided by the IN. While traditional IN load control algorithms assume a single service network model or make use of a centralized controller, in this paper we propose and investigate a market-based model for solving the distributed IN load control problem for a multi-service network, where any service can be provided by any SCP. Furthermore, we study a realization of this model based on a multi-agent system (MAS) and finally draw conclusions as to both its efficiency and effectiveness.