An Analytic Model-Based Approach for Power System Alarm Processing Employing Temporal Constraint Network
- 6 October 2009
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Delivery
- Vol. 25 (4), 2435-2447
- https://doi.org/10.1109/tpwrd.2009.2032054
Abstract
The alarm-processing problem is to interpret a large number of alarms under stress conditions, such as faults or disturbances, by providing summarized and synthesized information instead of a flood of raw alarm data. Alarm timestamps represent the temporal relationship among event occurrences and consist of rich and useful information for alarm processing. However, the temporal information has not been well utilized in existing alarm-processing methods. The temporal constraint network (TCN) is a type of directed acyclic graph suitable for representing temporal logics. Based on TCN, a new analytic model is developed for alarm processing with temporal information taken into account. Three major modules are included in the developed approach or alarm processor (i.e., alarm selection, event analysis, and result evaluation). In the alarm selection module, reported alarms are divided into related groups. The function of the event analysis module is to find out what events cause the reported alarms and to estimate when these events happen. The result evaluation module is used to identify abnormal or missing alarms. Finally, two alarm-processing scenarios of an actual power system are served for demonstrating the feasibility and efficiency of the developed approach.Keywords
This publication has 29 references indexed in Scilit:
- Unsupervised Event Extraction Within Substations Using Rough ClassificationIEEE Transactions on Power Delivery, 2006
- Fault section estimation in power system using Boltzmann machinePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Abductive network model-based diagnosis system for power transformer incipient fault detectionIEE Proceedings - Generation, Transmission and Distribution, 2002
- Automated fault detection in power distribution networks using a hybrid fuzzy–genetic algorithm approachEngineering Applications of Artificial Intelligence, 2000
- NEW APPROACH TO ALARM PROCESSING IN POWER SYSTEMS BASED ON THE SET COVERING THEORY AND A REFINED GENETIC ALGORITHMElectric Machines & Power Systems, 1998
- Tabu search approach to alarm processing in power systemsIEE Proceedings - Generation, Transmission and Distribution, 1997
- Power system distributed on-line fault section estimation using decision tree based neural nets approachIEEE Transactions on Power Delivery, 1995
- Application of hierarchical neural networks to fault diagnosis of power systemsInternational Journal of Electrical Power & Energy Systems, 1993
- Tabu Search—Part IIINFORMS Journal on Computing, 1990
- Tabu Search—Part IINFORMS Journal on Computing, 1989