US 11,699,198 B2
Methods and systems for machine-learning for prediction of grid carbon emissions
Wenbo Shi, Cambridge, MA (US)
Assigned to Singularity Energy, Inc., Cambridge, MA (US)
Filed by Singularity Energy, Inc., Cambridge, MA (US)
Filed on Jun. 6, 2022, as Appl. No. 17/833,511.
Application 17/833,511 is a continuation of application No. 16/879,303, filed on May 20, 2020, granted, now 11,398,000.
Claims priority of provisional application 62/850,361, filed on May 20, 2019.
Prior Publication US 2022/0358606 A1, Nov. 10, 2022
Int. Cl. G06Q 50/06 (2012.01); G06N 20/00 (2019.01); G06N 3/08 (2023.01)
CPC G06Q 50/06 (2013.01) [G06N 3/08 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method of machine-learning for prediction of grid carbon emissions, the method comprising:
receiving, by a computing device and from a first local grid monitoring device monitoring a first local grid, a plurality of first power output quantities of a plurality of power generators in the first local grid;
receiving, by the computing device and from the first local grid monitoring device monitoring the first local grid, a plurality of first power consumption quantities of a plurality of power consumers in the first local grid;
comparing, by the computing device, the plurality of first power consumption quantities to a consumption baseline;
estimating, by the computing device, an avoided emissions as a function of the comparison;
generating, by the computing device, a plurality of courses of action, wherein each of the plurality of courses of action are optimized for maximizing the estimated avoided emissions;
training, by the computing device, an emission projection machine-learning process using training data entries, wherein the training data entries comprise correlations of past power output quantities and past power consumption quantities with reported carbon emission data;
generating, using the emission projection machine-learning process, a first plurality of projected carbon emission rates, wherein each of the first plurality of carbon emission rates is generated as a function of a course of action of the plurality of courses of action, the first plurality of power consumption quantities and the first plurality of power output quantities; and
displaying, by the computing device on a user interface, a graphical comparison of the first plurality of projected carbon emission rates.