Developed several capabilities in this project that will help achieve national renewable targets and improve system reliability.

1. Chronological AC Power Flow Automated Generation Tool (C-PAGE), which has round-trip capability to bring system dispatch time series from the PCM into time-sequenced power flow runs for reliability analysis.
2. Novel Data-Driven Distributed Learning Framework for Solving the ACPF problem (DL-SAP), which can accurately predict power system conditions resulting from various operating scenarios, thus making it suitable for large, interconnected grids, useful in identifying situations where power grid may become vulnerable.
3. C-PAGE uses artificial intelligence/machine learning, combined with PCM and PF tools, to discover critical contingencies as they unfold over time accurately and rapidly.
4. Voltage stability metric to assess distance to voltage collapse for DCAT (VS-DCAT).
5. ML frameworks for fast scanning of future scenarios using trained models to intelligently identify critical scenarios that the grid operators may face in the short-/long-term planning horizons. Using the proposed frameworks, it is possible to identify critical contingencies and system operating limits among various operating conditions with less computational burden than brute force approach.
6. C-PAGE was presented to more than five organizations and teams: a) WECC Production Cost Data Subcommittee; b) BPA; c). DOE Wind Energy Technologies Office; d). PNNL/NREL Transmission Team; e) Program Development Office Manager Carl Imhoff; f) DOS Vietnam team.

Overall feedback from WECC Production Cost Data Subcommittee:

“The PNNL involvement and further development and automation of the Chronological AC Power Flow Automated Generation Tool, referenced at WECC and by the Western Planning Regions as the ‘Round Trip,’ has been invaluable.”