Logo image
Development and Specification of a Reference Architecture for Agent-Based Systems
Journal article   Open access   Peer reviewed

Development and Specification of a Reference Architecture for Agent-Based Systems

William C Regli, Israel Mayk, Christopher T Cannon, Joseph B Kopena, Robert N Lass, William M Mongan, Duc N Nguyen, Jeff K Salvage, Evan A Sultanik and Kyle Usbeck
IEEE transactions on systems, man, and cybernetics. Systems, v 44(2)
Feb 2014
url
https://doi.org/10.1109/tsmcc.2013.2263132View
Published, Version of Record (VoR)Open Access (License Unspecified) Open
url
https://doi.org/10.1109/TSMCC.2013.2263132View
Published, Version of Record (VoR) Open

Abstract

Abstracts Agents Computer architecture Concrete distributed artificial intelligence (AI) multiagent Object oriented modeling reference model reverse engineering software architecture software engineering Software systems Unified modeling language
The recent growth of agent-based software systems was achieved without the development of a reference architecture. From a software engineering standpoint, a reference architecture is necessary to compare, evaluate, and integrate past, current, and future agent-based software systems. The agent systems reference architecture (ASRA) advances the agent-based system development process by providing a set of key interaction patterns for functional areas that exist between the layers and protocols of agent-based systems. Furthermore, the ASRA identifies the points for interoperability between agent-based systems and increases the level of discussion when referring to agent-based systems. This paper presents methodology, grounded in software forensics, to develop the ASRA and provides an overview of the resulting architectural representation. The methodology uses an approach based on software engineering techniques adapted to study agent frameworks-the libraries and tools for building agent systems. The resulting ASRA can serve as an abstract representation of the components necessary for facilitating comparison, integration, and interoperation of software systems composed of agents.

Metrics

15 Record Views
3 citations in Scopus

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types
Industry collaboration
Domestic collaboration
Web of Science research areas
Automation & Control Systems
Computer Science, Cybernetics
Logo image