Albino Marques

Better KBS for real-time applications in power system control centers: the experience of SPARSE project

Modern Power System Control Centers must operate and control medium and large electrical networks that usually cover a large geographic area. The accomplishment of these tasks has been made possible due to important developments in computer and communication technologies. Nowadays, complex Power Systems require a very accurate and efficient control that makes Control Centers especially important. These centers are equipped with SCADA (Supervisory Control and Data Acquisition) systems allowing to acquire information about the Power System and its transmission to Control Centers in real-time. Due to the symbolic nature of the reasoning involved in some control tasks, Artificial Intelligence techniques appeared as a promising solution. Some years ago, some of the most important electrical utilities around the world began to develop knowledge-based applications to incorporate in their Control Centers. These applications deal with the information available in the Control Center and help operators in decision making. On the other hand, the duration of this kind of project is still rather long and the total number of deployed systems all over the world is still very low. This paper deals with what we consider the most important points for the success of Artificial Intelligence applications in Control Centers.

SPARSE—an expert system for alarm processing and operator assistance in substations control centers

In case of occurrence of an incident in an electrical network, several hundreds of messages per minute may be presented to Control Center operators. This makes very difficult the identification of the fault and to decide about the required actions in order to minimize the consequences of the incident and to restore the service.This paper describes an expert system named SPARSE that provides on-line assistance to the operators of Substation Control Centers (SCC) of the portuguese electrical transmission network. SPARSE performs intelligent alarm processing and provides advice regarding operator actions. This system has been developed by the Faculty of Engineering of University of Porto in a joint project with Electricidade de Portugal, EDP, S.A., the utility that deals with power generation, transmission and distribution in Portugal.

Role of antimicrobial stewardship programmes in children: a systematic review

The United Nations and the World Health Organization have designated antimicrobial resistance (AMR) as a major health priority and developed action plans to reduce AMR in all healthcare settings. Establishment of institutional antimicrobial stewardship programmes (ASPs) is advocated as a key intervention to reduce antibiotic consumption in hospitals and address high rates of multi-drug-resistant (MDR) bacteria. PUBMED and the Cochrane Database of Systematic Reviews (January 2007-March 2017) were searched to identify studies reporting the effectiveness of ASPs in general paediatric wards and paediatric intensive care units (PICUs) for reducing antibiotic consumption, use of broad-spectrum/restricted antibiotics, and antibiotic resistance and healthcare-associated infections (HAIs). Neonatal units and antifungal agents were excluded. Of 2509 titles and abstracts, nine articles were eligible for inclusion in the final analysis. All studies reported a reduction in the use of broad-spectrum/restricted antibiotics or antibiotic consumption. One study reported a reduction in HAIs in a PICU, and another study evaluated bacterial resistance, showing no effect following ASP implementation. Prospective audit on antibiotic use was the most common ASP core component (eight of nine studies). Antibiotic pre-authorization was described in two studies. Other described interventions were the provision of guidelines or written information (five of nine studies), and training of healthcare professionals (one study). There is limited evidence for a reduction in antibiotic consumption and use of broad-spectrum/restricted agents following ASP implementation specifically in PICUs. Data evaluating the impact of ASPs on HAIs and AMR in PICUs are lacking. In addition, there is limited information on effective components of a successful ASP in PICUs.

Training Scenarios Generation Tools for an ITS to Control Center Operators

In the last two decades, Intelligent Tutoring Systems (ITS) have proven to be highly effective as learning aids. However, few tutoring systems have made a successful transition to the industrial environment so far. Among the factors that make this transition difficult is the maintenance of such systems. In particular, the preparation of the learning material to the tutoring sessions constitutes a time-consuming task. Usually, in the industrial environment there is not a staff exclusively dedicated to training tasks. This is the case of the electrical sector, where the preparation of training sessions is accomplished with co-operation of the most experienced operators. As this task requires the participation of very busy people that are daily involved in the operation of the power system, it may be difficult to accomplish.

User modelling concerning control centre operators training

Typically, the user models used in intelligent tutors tend to be tightly controlled by the system, due to the constraints imposed by the specific nature of the tutoring process. Therefore, no control by the user himself is usually allowed over his/her models contents. In order to make the evaluation of the tutoring process a cooperative task, adequate techniques should, be devised. This paper describes early attempts to build a user model module for an intelligent tutor to be used in the training of electrical network control centre operators. It attempts to address the different requirements of the distinct phases of this tutoring environment. An example of how this user model data can drive the tutoring process is presented.

Man-machine interaction in power system control centers

User interfaces of power system control centers applications are a key factor for the performance of the whole system. This paper presents the experience of daily use of the Portuguese SCADA applications and points out some important issues to consider in the specification of the user interface for new control center applications. The inclusion of knowledge-based applications in the control centers is considered as an important experience that may help in the evolution towards more intelligent user interfaces. Examples concerning a software package that is being developed for display building and information presentation are included.<<ETX>>

VERITAS-an application for knowledge verification

Knowledge management is one of the most important goals of any organization. Therefore, several automatic tools are used for that purpose, e.g. Knowledge Based Systems (KBS), Experts Systems, Data Mining Applications and Computer Aided Decision Systems. The validation and verification (V&V) process is fundamental in order to ensure the quality of used knowledge. The usage of automatic verification tools can be a reliable, inexpensive and reusable way to overcome the constant growth of the Knowledge Bases, the shortening of development times and the costs of Validation, specially field tests. This paper addresses the verification of Knowledge Based Systems, focussing on VERITAS, a verification tool initially developed to verify a KBS used to assist operators of Portuguese Transmission Control Centers in incident analysis and power restoration VERITAS performs knowledge base structural analysis allowing the detection of knowledge anomalies.

Enabling client-server explanation facilities in a real-time expert system

Although expert systems have been increasingly applied for solving power system problems in the past decade, their capabilities have not been fully used. Their ability to provide explanations concerning their knowledge and inference process is one good example of misuse of expert system possibilities. In the case of expert systems designed for real-time operation, the introduction of effective explanation features poses important constraints that must be taken into account. This paper presents an explanation mechanism that has been designed and implemented to be used by SPARSE, an expert system for intelligent alarm processing and power restoration aid which is running on-line in a Portuguese transmission control center.

Validation and Verification of Knowledge-Based Systems for Power System Control Centres

During the last years, electrical utilities began to install intelligent applications in order to assist Control Centres operators. The SPARSE is a Knowledge-Based System used in the Portuguese Transmission Network for operator assistance in incident analysis and power restoration. The Verification and Validation (V&V) process must assure the reliability of these applications, even under incident conditions. This paper addresses the Validation and Verification of Knowledge-Based Systems (KBS) in general, focussing particularly on the V&V of SPARSE. Validation and Verification are presented in a complementary perspective, stressing its relation with the KBS developing stages. VERITAS is an automatic verification tool initially developed to verify SPARSE Knowledge Base. Although its initial goal was the SPARSE verification, the tool was developed with generic verification purposes and domain independent approach. Hence it is able to perform knowledge base structural analysis allowing the detection of knowledge anomalies at low cost, especially with big knowledge bases. VERITAS is currently being used in the verification of several Knowledge Based and Data Mining systems.

Intelligent training in control centres based on an ambient intelligence paradigm

This article describes a new approach in the Intelligent Training of Operators in Power Systems Control Centres, considering the new reality of Renewable Sources, Distributed Generation, and Electricity Markets, under the emerging paradigms of Cyber-Physical Systems and Ambient Intelligence. We propose Intelligent Tutoring Systems as the approach to deal with the intelligent training of operators in these new circumstances.