The methods for power system event detection using field-recorded data from Phasor Measurement Units (PMUs) often require many labeled events, which can be costly or infeasible to obtain. We show that events in one power system can be accurately detected by reusing a small number of carefully selected labeled PMU data from another without the need for additional labeling. Our transfer learning-based approach outperforms alternative state-of-the-art conventional machine learning (ML) methods on a large PMU historical dataset. We demonstrate this approach with a use case of detecting events from historical PMU data recorded in the Eastern Interconnection in the USA by using similar labeled PMU data from the Western Interconnection. This technique may be propagated to other situations where some of the events’ data from one power system may be applied to enhance learning in another.

This paper explores how electricity systems may evolve in the 21st century. The paper focuses on some fundamental challenges facing the utilization of electricity today and for years to come. Paralleling the challenges, several directions of how new solutions may emerge are suggested. In this context, some new approaches to manage power system development and deployment are outlined.

This paper focuses on the most critical task in monitoring and control of power systems: converting data to knowledge that will facilitate control action. With expansion of smart grids, which assume wide dissemination of intelligent electronic devices (IEDs) in substations supported by extensive communications, data associated with power system events becomes abundant. The fact that new data of better quality than before exists in smart grids does not assure that better decision making will be possible. In order to convert data to actionable knowledge, certain processing needs to be performed. This processing is referred to as Translational Knowledge, i.e., the knowledge that allows transition from data collection to action. This concept is illustrated through several applications such as fault locating, alarm processing, and protective relaying.

Many power system applications, particularly those related to monitoring,control, and protection, depend on the use of field data recorded by intelligent electronic devices (IEDs) in substations. With the introduction of IEDs in the last 20 years, the amount and type of data collected in substations have dramatically increased. This paper explores the benefits of data integration and information extraction achieved by merging temporal and spatial considerations. In the new approach, time and space issues are treated consistently across all IEDs, and as a result new applications with improved performance characteristics can be defined. As an illustration, two new monitoring functions are discussed in detail: 1) automated fault analysis and 2) hierarchical state and topology estimation. Discussion ends with a description of an implementation framework that will allow development of other functions that will benefit from the merger of time and space considerations.