A new cognitive-based massive alarm management system in electrical power administration

This paper presents a methodology that integrates several available techniques to manage the massive amount of alarm signals in electrical power dispatch control centres, as well as the contribution of each entity involved in the system. Artificial intelligence techniques that can be used in this problem are reviewed here based on the available information. The final objective is to find the root cause of avalanches of alarms (failure tree) and to reduce their number through grouping or clustering techniques so that the EEMUA 191 standards are followed. Even though other contributions in this topic have been made before, the alarm management problem continues to be practically unsolved for many applications in industry. Here, the integration is developed using the ontology of each system domains, i.e., the ontology corresponding to the alarms, controls, events, energy flow and trigger sequence. Additionally, in this methodology, a rule based expert system is used to treat the alarms with a neural net based approach to treat the historical database of alarms and failures.