A multiagent architecture for supervisory and control system

Supervising and controlling the many processes involved in petroleum production is both dangerous and complex. Herein, we propose a multiagent supervisory and control system for handle continuous processes like those in chemical and petroleum industries In its architeture, there are agents responsible for managing data production and analysis, and also the production equipments. Fuzzy controllers were used as control agents. The application of a fuzzy control system to managing an off-shore installation for petroleum production onto a submarine separation process is described. © 2008 IEEE.

A multi-agent architecture for intelligent data analysis

The present study introduces a multi-agent architecture designed for doing automation process of data integration and intelligent data analysis. Different from other approaches the multi-agent architecture was designed using a multi-agent based methodology. Tropos, an agent based methodology was used for design. Based on the proposed architecture, we describe a Web based application where the agents are responsible to analyse petroleum well drilling data to identify possible abnormalities occurrence. The intelligent data analysis methods used was the Neural Network.

A multiagent based strategy for detecting attacks in databases in a distributed mode

This paper presents a distributed hierarchical multiagent architecture for detecting SQL injection attacks against databases. It uses a novel strategy, which is supported by a Case-Based Reasoning mechanism, which provides to the classifier agents with a great capacity of learning and adaptation to face this type of attack. The architecture combines strategies of intrusion detection systems such as misuse detection and anomaly detection. It has been tested and the results are presented in this paper.

Personality, emotion, and mood in agent-based group decision making

Group decision making plays an important role in organizations, especially in the present-day economy that demands high-quality, yet quick decisions. Group decision-support systems (GDSSs) are interactive computer-based environments that support concerted, coordinated team efforts toward the completion of joint tasks. The need for collaborative work in organizations has led to the development of a set of general collaborative computer-supported technologies and specific GDSSs that support distributed groups (in time and space) in various domains. However, each person is unique and has different reactions to various arguments. Many times a disagreement arises because of the way we began arguing, not because of the content itself. Nevertheless, emotion, mood, and personality factors have not yet been addressed in GDSSs, despite how strongly they influence results. Our group’s previous work considered the roles that emotion and mood play in decision making. In this article, we reformulate these factors and include personality as well. Thus, this work incorporates personality, emotion, and mood in the negotiation process of an argumentbased group decision-making process. Our main goal in this work is to improve the negotiation process through argumentation using the affective characteristics of the involved participants. Each participant agent represents a group decision member. This representation lets us simulate people with different personalities. The discussion process between group members (agents) is made through the exchange of persuasive arguments. Although our multiagent architecture model4 includes two types of agents—the facilitator and the participant— this article focuses on the emotional, personality, and argumentation components of the participant agent.

Satisfação de agentes afectivos no processo de tomada de decisão em grupo

Um dos factores mais determinantes para o sucesso de uma organização é a qualidade das decisões tomadas. Para que as decisões tomadas sejam melhores e potenciem a competitividade das organizações, sistemas como os Sistemas de Apoio à Tomada de Decisão em Grupo (SADG) têm sido fortemente desenvolvidos e estudados nas últimas décadas. Cada vez mais, estes sistemas são populados com um maior número de dados, com o objectivo de serem mais assertivos. Considera-se que com determinados dados seja possível que o sistema possa aferir a satisfação dos participantes com as decisões tomadas, tendencialmente de forma automática. Hoje em dia, as análises de satisfação com as decisões não contemplam na sua maioria factores imprescindíveis, como os emocionais e de personalidade, sendo que os modelos existentes tendem a ser incompletos. Nesta dissertação propõe-se uma metodologia que permite a um SADG aferir a satisfação do participante com a decisão, considerando aspectos como a personalidade, as emoções e as expectativas. A metodologia desenvolvida foi implementada num SADG (ArgEmotionsAgents) com uma arquitectura multiagente, composto por agentes que reflectem participantes reais e que estão modelados com a sua personalidade. De acordo com a sua personalidade, esses agentes trocam argumentos persuasivos de forma a obterem uma decisão consensual. No processo de troca de argumentos os agentes geram emoções que afectam o seu humor. A implementação da metodologia no ArgEmotionsAgents permite que, no final de uma reunião, seja possível aferir a satisfação dos agentes participantes com a decisão final e com o processo que levou à tomada de decisão. De forma a validar a metodologia proposta bem como a implementação que foi desenvolvida, foram realizadas quatro experiências em diferentes cenários. Numa primeira experiência, foi aferida a satisfação dos quatro agentes participantes. Nas experiências seguintes, um dos agentes participantes foi usado como referência e foram alteradas configurações (expectativas, personalidade e reavaliação das alternativas) para perceber de que forma os vários factores afectam a satisfação. Com o estudo concluiu-se que todos os factores considerados no modelo afectam a satisfação. A forma como a satisfação é afectada por cada um dos factores vai ao encontro da lógica apresentada no estado da arte. Os resultados de satisfação aferidos pelo modelo são congruentes.

Modelagem e implementação da interface para apresentação de comportamentos animados e emotivos de um agente pedagógico animado

A popularização da Internet e o crescimento da educação à distância tornaram possível a criação de softwares e cursos à distância, disponíveis na WWW. Atualmente, a Inteligência Artificial (IA) vem sendo utilizada para aumentar a capacidade de ambientes de educação à distância, diminuindo a desistência pela falta de estímulos externos e de interação entre colegas e professores. Este trabalho encontra-se inserido no ambiente colaborativo suportado por computador, definido no projeto “Uma Proposta de Modelo Computacional de Aprendizagem à Distância Baseada na Concepção Sócio-Interacionista de Vygotsky” chamado MACES (Multiagent Architecture for an Collaborative Educational System). Sua principal proposta, como parte do projeto do grupo, é desenvolver e implementar a interface animada do personagem para os agentes pedagógicos animados Colaborativo e Mediador que operam no ambiente de aprendizado colaborativo proposto pelo grupo. O personagem desenvolvido chama-se PAT (Pedagogical and Affective Tutor). A interface do personagem foi desenvolvida em Java, JavaScript e usa o Microsoft Agent para a movimentação. O Resin 2.1.6 (semelhante ao Tomcat que também foi usado de teste) é o compilador de servlet usado na execução de Java Servlet’s e tecnologias jsp – que monta páginas HTML dinamicamente. Esta montagem é feita no servidor e enviada para o browser do usuário. Para definir a aparência do personagem foram feitas entrevistas com pedagogas, psicólogas, psicopedagogas e idéias tiradas de entrevistas informais com profissionais que trabalham com desenho industrial, propaganda, cartoon e desenho animado. A PAT faz parte da interface do MACES e promove a comunicação entre esse ambiente e o usuário. Portanto, acredita-se que a PAT e os recursos da Inteligência artificial poderão aumentar a capacidade de ambientes de educação à distância, tornando-os mais agradáveis, assim como diminuir a desistência pela falta de estímulos externos e de interação com colegas e professores.

Uma arquitetura baseada em agentes para configuração dinâmica de aplicações inteligentes em ambiente foundation fieldbus

The industrial automation is directly linked to the development of information tecnology. Better hardware solutions, as well as improvements in software development methodologies make possible the rapid growth of the productive process control. In this thesis, we propose an architecture that will allow the joining of two technologies in hardware (industrial network) and software field (multiagent systems). The objective of this proposal is to join those technologies in a multiagent architecture to allow control strategies implementations in to field devices. With this, we intend develop an agents architecture to detect and solve problems which may occur in the industrial network environment. Our work ally machine learning with industrial context, become proposed multiagent architecture adaptable to unfamiliar or unexpected production environment. We used neural networks and presented an allocation strategies of these networks in industrial network field devices. With this we intend to improve decision support at plant level and allow operations human intervention independent

Engineering Agent Systems for Decision Support

This paper discusses how agent technology can be applied to the design of advanced Information Systems for Decision Support. In particular, it describes the different steps and models that are necessary to engineer Decision Support Systems based on a multiagent architecture. The approach is illustrated by a case study in the traffic management domain.

Multiagent System Architecture for Short-term Operation of Integrated Microgrids

The forthcoming smart grids are comprised of integrated microgrids operating in grid-connected and isolated mode with local generation, storage and demand response (DR) programs. The proposed model is based on three successive complementary steps for power transaction in the market environment. The first step is characterized as a microgrid’s internal market; the second concerns negotiations between distinct interconnected microgrids; and finally, the third refers to the actual electricity market. The proposed approach is modeled and tested using a MAS framework directed to the study of the smart grids environment, including the simulation of electricity markets. This is achieved through the integration of the proposed approach with the MASGriP (Multi-Agent Smart Grid Platform) system.

Coalition based approach for shop floor agility – a multiagent approach

Dissertation submitted for a PhD degree in Electrical Engineering, speciality of Robotics and Integrated Manufacturing from the Universidade Nova de Lisboa, Faculdade de Ciências e Tecnologia

Ontologies for the interoperability of multiagent electricity markets simulation platforms

Electricity markets worldwide are complex and dynamic environments with very particular characteristics. These are the result of electricity markets’ restructuring and evolution into regional and continental scales, along with the constant changes brought by the increasing necessity for an adequate integration of renewable energy sources. The rising complexity and unpredictability in electricity markets has increased the need for the intervenient entities in foreseeing market behaviour. Market players and regulators are very interested in predicting the market’s behaviour. Market players need to understand the market behaviour and operation in order to maximize their profits, while market regulators need to test new rules and detect market inefficiencies before they are implemented. The growth of usage of simulation tools was driven by the need for understanding those mechanisms and how the involved players' interactions affect the markets' outcomes. Multi-agent based software is particularly well fitted to analyse dynamic and adaptive systems with complex interactions among its constituents, such as electricity markets. Several modelling tools directed to the study of restructured wholesale electricity markets have emerged. Still, they have a common limitation: the lack of interoperability between the various systems to allow the exchange of information and knowledge, to test different market models and to allow market players from different systems to interact in common market environments. This dissertation proposes the development and implementation of ontologies for semantic interoperability between multi-agent simulation platforms in the scope of electricity markets. The added value provided to these platforms is given by enabling them sharing their knowledge and market models with other agent societies, which provides the means for an actual improvement in current electricity markets studies and development. The proposed ontologies are implemented in MASCEM (Multi-Agent Simulator of Competitive Electricity Markets) and tested through the interaction between MASCEM agents and agents from other multi-agent based simulators. The implementation of the proposed ontologies has also required a complete restructuring of MASCEM’s architecture and multi-agent model, which is also presented in this dissertation. The results achieved in the case studies allow identifying the advantages of the novel architecture of MASCEM, and most importantly, the added value of using the proposed ontologies. They facilitate the integration of independent multi-agent simulators, by providing a way for communications to be understood by heterogeneous agents from the various systems.

A multiagent based shop floor transportation system simulator

Dissertação para obtenção do Grau de Mestre em Engenharia Electrotécnica e de Computadores

An agent based architecture to support monitoring in plug and produce manufacturing systems using knowledge extraction

In recent years a set of production paradigms were proposed in order to capacitate manufacturers to meet the new market requirements, such as the shift in demand for highly customized products resulting in a shorter product life cycle, rather than the traditional mass production standardized consumables. These new paradigms advocate solutions capable of facing these requirements, empowering manufacturing systems with a high capacity to adapt along with elevated flexibility and robustness in order to deal with disturbances, like unexpected orders or malfunctions. Evolvable Production Systems propose a solution based on the usage of modularity and self-organization with a fine granularity level, supporting pluggability and in this way allowing companies to add and/or remove components during execution without any extra re-programming effort. However, current monitoring software was not designed to fully support these characteristics, being commonly based on centralized SCADA systems, incapable of re-adapting during execution to the unexpected plugging/unplugging of devices nor changes in the entire system’s topology. Considering these aspects, the work developed for this thesis encompasses a fully distributed agent-based architecture, capable of performing knowledge extraction at different levels of abstraction without sacrificing the capacity to add and/or remove monitoring entities, responsible for data extraction and analysis, during runtime.

Automated monitoring of medical protocols: a secure and distributed architecture

The control of the right application of medical protocols is a key issue in hospital environments. For the automated monitoring of medical protocols, we need a domain-independent language for their representation and a fully, or semi, autonomous system that understands the protocols and supervises their application. In this paper we describe a specification language and a multi-agent system architecture for monitoring medical protocols. We model medical services in hospital environments as specialized domain agents and interpret a medical protocol as a negotiation process between agents. A medical service can be involved in multiple medical protocols, and so specialized domain agents are independent of negotiation processes and autonomous system agents perform monitoring tasks. We present the detailed architecture of the system agents and of an important domain agent, the database broker agent, that is responsible of obtaining relevant information about the clinical history of patients. We also describe how we tackle the problems of privacy, integrity and authentication during the process of exchanging information between agents.

Analysis and design of multiagent systems using MAS-CommonKADS

This article proposes an agent-oriented methodology called MAS-CommonKADS and develops a case study. This methodology extends the knowledge engineering methodology CommonKADSwith techniquesfrom objectoriented and protocol engineering methodologies. The methodology consists of the development of seven models: Agent Model, that describes the characteristics of each agent; Task Model, that describes the tasks that the agents carry out; Expertise Model, that describes the knowledge needed by the agents to achieve their goals; Organisation Model, that describes the structural relationships between agents (software agents and/or human agents); Coordination Model, that describes the dynamic relationships between software agents; Communication Model, that describes the dynamic relationships between human agents and their respective personal assistant software agents; and Design Model, that refines the previous models and determines the most suitable agent architecture for each agent, and the requirements of the agent network.