F. Sivianes

PeMMAS: A Tool for Studying the Performance of Multiagent Systems Developed in JADE

This paper describes the performance measurement for multiagent systems (PeMMAS) tool, a system designed to study and measure the performance of any multiagent system (MAS) developed in JADE. The tool itself is another MAS which is deployed and coexists alongside the one being studied. This characteristic allows us to adapt PeMMAS to any scenario in which MAS deployment in JADE is used. PeMMAS extracts information from the target MAS regarding the use of system resources, the flight time for comprehensive messages according to agent type, as well as the processing time for actions. After processing this information, PeMMAS sends a report to the final user for subsequent analysis.

Facilitating Decision Making and Maintenance for Power Systems Operators through the Use of Agents and Distributed Embedded Systems

This article examines the improvements provided when multimedia information in traditional SCADAS are included in electric facility management and maintenance. Telecontrol use in the electric sector, with the fundamental objective of providing increased and improved service to the operators who manage these systems, is also described. One of the most important contributions is the use of an agent network that is distributed around the electric facility. Through the use of multi-agent technology and its placement in embedded systems, to the authors design a system with a degree of intelligence and independence to optimize data collection and provide reaction proposals for the operator. The proposed agent-based architecture is also reviewed in this article, as are the design of an example agent and the results obtained in a pilot experience using the proposed hardware platform.

Managing emergency response operations for electric utility maintenance

One of the most important criteria used to measure the quality of service in the electric utility industry is the uninterrupted service supplied to the customers. So, preventive maintenance is very relevant to avoid failures in the electric utility network. However, when failure is inevitable, it is very important that emergency repair operations are accomplished as soon as possible so the operators can avoid high-risk situations. Service unavailability can be decreased, reducing the frequency of power interruptions, number of customers affected per interruption, and duration of the interruption. A MAS for managing maintenance and emergency response operations in the electric utility industry was presented. The proposed system has the capability to support maintenance operations and make planning decisions.

Multiple intelligences in a MultiAgent System applied to telecontrol

This paper presents a control system, based on artificial intelligence technologies, that implements multiple intelligences. This system aims to support and improve automatic telecontrol of solar power plants, by either automatically triggering actuators or dynamically giving recommendations to human operators. For this purpose, the development of a MultiAgent System is combined with a variety of inference systems, such as Expert Systems, Neural Networks, and Bayesian Networks. This diversity of intelligent technologies is shown to result in an efficient way to mimic the reasoning process in human operators.

Innovative learning and teaching methodology in electronic technology area: A case of study in Computer Science University degrees

This paper describes an experience that has been carried out by several professors in different subjects. Our experience is framed within the First Plan in Teaching of the University of Seville. All involved subjects belong to the electronic technology area and from three Computer Science degrees. We propose to use, in a combined way, some learning techniques: cooperative learning as complement to traditional learning, role-playing technique and jigsaw technique. We have considered a base methodology but in each subject a variant of it has been accomplished. We have used several evaluation techniques, such as reciprocal evaluation, electronic portfolio and check lists. Applying our methodology helps us to detect learning problems before the term ends. Also, in tune with the framework of the European Higher Education Area (EHEA), our methology gives a boost to develop transversal competences as important as work (or study) management, empathy and understanding of other members in a workgroup, conflict resolution, capacity to make decisions as well as coordinate and communicate with other members in a workgroup and also with the professor.

Architecture for Multiagent-Based Control Systems

This paper presents a multiagent architecture that covers the new requirements for the new control systems such as the distribution and decentralisation of system elements, the definition of communications between these elements, the fast adaptation in the control and organizational changes. The agents in this architecture can cooperate and coordinate to achieve a global goal, encapsulate the hardware interfaces and make the control system easily adapt to different requirements through configuration. Finally, the proposed architecture is applied to a control system of a solar power plant, obtaining a preliminary system that achieve the goals of simplicity, scalability, flexibility and optimization of communications system.

Remote Controlling and Monitoring of Safety Devices Using Web-Interface Embedded Systems

To date, access control systems have been hardware-based platforms, where software and hardware parts were uncoupled into different systems. The Department of Electronic Technology in the University of Seville, together with ISIS Engineering, have developed an innovative embedded system that provides all needed functions for controlling and monitoring remote access control systems through a built-in web interface. The design provides a monolithic structure, independence from outer systems, easiness in management and maintenance, conformation to the highest standards in security, and straightforward adaptability to applications other than the original one. We have accomplished it by using an extremely reduced Linux kernel and developing web and purpose-specific logic under software technologies with an optimal resource use.

Simulation and Implementation of a Neural Network in a Multiagent System

This paper presents the simulation and the implementation of a model of a neural network applied to a multiagent system by using the Neuroph framework. This tool enables several tests to be carried out and verify which structure is the best structure of our neural network for a specific application. In our case, we simulated the neural network for a sun-tracking control system in a solar farm. Initial implementation shows good results in performance, thereby providing an alternative to traditional solar-tracking systems.

Multiagent system powered by neural network for positioning control of solar panels

This paper presents a model of neural network for position control of solar panels in multiagent-based control systems. This neural network is integrated within agents in order to optimize and predict the best positioning of solar panels depending on the position of the sun and other variables. The agents in this system can cooperate and coordinate to achieve a sun tracking system optimized, simple and adaptive.

Automatic surveillance in power system telecontrol applying embedded and multi-agent system technologies

We have designed, implemented and deployed a system called IDOLO [1] [9]. This system was born within a research project with the main goal of adding audiovisual information to the usually text-based Human-Machine Interfaces (HMI) used on Supervisory Control And Data Acquisition (SCADA) systems. IDOLO system is based on well-known hardware and software solutions, such as Ethernet networks or MPEG codecs, resulting in a flexible and extendable system that has successfully been deployed in a real electrical facility. Now our effort is focused on developing this system inside an embedded system by using the last technology. This is in order to provide a black box that includes the same functionality of IDOLO system and automatic surveillance as well. We are basing our work on different kinds of embedded systems and we are modeling its autonomous surveillance behavior by using Multi-Agent System technology.