Increasing the Resolution of Wide-Area Situational Awareness of the Power Grid through Event Unmixing

Energy infrastructure is a critical underpinning of modern society. To ensure its safe and healthy operation, a wide-area situational awareness system is essential to provide high-resolution understanding of the system dynamics such that proper actions can be taken in time in response to power system disturbances and to avoid cascading blackouts. This paper focusses on the high resolution or finer-scale analysis of data obtained through the North American frequency monitoring network (FNET) to reveal hidden information. In the power grid, events seldom occur in an isolated fashion. Cascading events and simultaneous events are more common and realistic. We present a new conceptual framework in event analysis, referred to as event unmixing, where we consider real-world events as a mixture of more than one constituent root event. This concept is a key enabler for the analysis of events to go beyond what are immediately detectable in the system. We interpret the event formation process from spectral mixing perspective and present innovative unsupervised unmixing algorithms to unravel complex events.