J.Q. Feng

A multi-agent based intelligent monitoring system for power transformers in distributed substations

Power Transformers are distributed across a large number of substations, and many measures have been adopted for their onsite monitoring. Current approaches to transformer monitoring focus primarily on the sampling and display of vital parameters such as voltage and current, and that have been proved insufficient for transformer maintenance. This paper presents a new approach, based on a multi-agent system and an transformer equivalent heat circuit thermal model, which improves the quality and efficiency of distributed onsite transformer condition monitoring in power grids. The thermal model provides transformer temperature predictions and evaluation suggestions, while multi-agents playing the main roles of SCADA system maintenance, transformer autonomous diagnosis and information management.

Mobile agents for data analysis in industrial automation systems

In modern power systems and other industrial concerns, a large quantity of data is produced by condition monitoring and control systems. This data is used for a variety of purposes, and is often distributed over a number of sites. This paper describes part of a prototype system which combines mobile agents with a Foundation for Intelligent Physical Agents (FIPA)-based multi-agent system to provide remote analysis and reporting functions for data stored in power substation databases. A model of mobile agent performance in this application is derived, and a number of experimental results regarding the relative performance of mobile agents and static client-server agents are presented. These results suggest that in certain circumstances mobile agents have the potential to greatly increase the performance of this application. A comparison between using wrapper agents and direct database access for data retrieval is also performed.

Implementation of a power transformer temperature monitoring system

This paper describes the implementation of a power transformer temperature monitoring system that contains a recently developed equivalent heat circuit based thermal model. In this system, four fundamental components cooperate to perform onsite condition monitoring and intelligent analysis, including data acquisition, thermal model prediction and analysis, data storage, and HTTP services. The offline test shows that this thermal model based transformer temperature monitoring system provides useful information for transformer monitoring and maintenance.

Condition Assessment of Power System Apparatuses Using Ontology Systems

Ontology based annotation provides clear and rigorous vocabularies for applications of knowledge management. It is explicitly defined and independent of the applications implementation. This paper proposes an ontology system for the condition assessment of power substation apparatus. The proposed methodology demonstrates the capability of annotating facts and their relationships in power system operation. The promising results obtained for power system apparatus condition assessment are achieved from laboratory experiments

Multi-agent based substation automation systems

This paper presents an open architecture for developing IP network-based substation automation systems. The architecture is based on multi-agent systems and is developed with aims to allow the implementation of diverse tasks and to permit greater configurability and capability of offering intelligence for the integration of information management, condition monitoring and control of power substations.

Agent-based personal article citation assistant

Scientific researchers usually need to deal with a large number of scientific and technical articles. A handy toolkit to facilitate retrieval and identification of these articles is vital. This paper presents an agent-based personal article citation assistant (APACA). As an autonomous agent, it provides extensive and efficient assistance for users to identify most related citations in a local article repository in collaboration and interaction with other distributed personal citation assistants. Furthermore, this paper proposes an article ontology and an optimised Bayesian network method to infer the most relevant article annotation in the local article ontology using a given keywords set K.

A Broker Agent for Remote Control of Distributed Power Systems

This paper proposes an agent based distributed power system architecture. With this architecture, agents are used to represent various data sources, condition monitoring and control switchgears of an electricity substation. Particularly, a broker agent as a middle-ware, is designed to bridge the gap between a user and a device in a power system. In addition, the advantages and disadvantages of the implementation of a broker agent in this architecture are discussed after the experiments and evaluations using the remote procedure call (RPC) model. The experimental results indicate when the number of interactions is large or the latency of the network is high, a broker agent method performs better than a client-server method.

Distributed Mobile Communication Base Station Diagnosis and Monitoring Using Multi-agents

Most inherently distributed systems require self diagnosis and on-line monitoring. This is especially true in the domains of power transmission and mobile communication. Much effort has been expended in developing on-site monitoring systems for distributed power transformers and mobile communication base stations.In this paper, a new approach has been employed to implement the autonomous self diagnosis and on-site monitoring using multi-agents on mobile communication base stations.