US 12,249,833 B2
Optimal power flow control via dynamic power flow modeling
Taylor Spalt, Providence, RI (US); Ning Li, Mansfield, MA (US); Marissa Hummon, Golden, CO (US); and Brandon Thayer, Richland, WA (US)
Assigned to Utilidata, Inc.
Filed by Utilidata, Inc., Providence, RI (US)
Filed on Feb. 2, 2023, as Appl. No. 18/105,047.
Application 18/105,047 is a continuation of application No. 17/200,367, filed on Mar. 12, 2021, granted, now 11,575,263.
Prior Publication US 2023/0187934 A1, Jun. 15, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H02J 3/00 (2006.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06Q 10/04 (2023.01); G06Q 50/06 (2024.01)
CPC H02J 3/003 (2020.01) [G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06Q 10/04 (2013.01); G06Q 50/06 (2013.01); H02J 3/004 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A system to control components of a utility grid, comprising:
a data processing system, comprising one or more processors and memory, to:
identify, for a model trained via machine learning based on a plurality of data samples detected by one or more devices located at one or more portions of the utility grid, a bound for an input variable to the model, a constraint on an output variable of the model, and a performance objective for the utility grid, the performance objective different from the constraint on the output variable;
determine, based on i) the model and ii) a calibration technique applied to the bound for the input variable and the constraint on the output variable to establish a relationship between at least the bound and the constraint, an adjustment to a component of the utility grid to satisfy the performance objective; and
cause the adjustment to the component of the utility grid to satisfy the performance objective.