US 12,272,949 B2
Systems and methods for power generation forecasting using text mining and feature engineering
Robert Leffler, Portland, ME (US)
Assigned to CARRIER CORPORATION, Palm Beach Gardens, FL (US)
Filed by Carrier Corporation, Palm Beach Gardens, FL (US)
Filed on Jul. 12, 2022, as Appl. No. 17/811,991.
Claims priority of provisional application 63/203,526, filed on Jul. 27, 2021.
Prior Publication US 2023/0032443 A1, Feb. 2, 2023
Int. Cl. H02J 3/00 (2006.01); G01W 1/10 (2006.01); H02J 3/14 (2006.01)
CPC H02J 3/004 (2020.01) [G01W 1/10 (2013.01); H02J 3/144 (2020.01)] 18 Claims
OG exemplary drawing
 
1. A system for power generation forecasting in a microgrid, the system comprising:
at least one processor;
a controller configured to send a control signal to a component outside of the system; and
memory storing instructions executable by the at least one processor, the instructions when executed cause the system to:
obtain weather information comprising a text description of weather events;
extract, from the obtained weather information, at least a text description of a first weather event and a text description of a second weather event;
generate, via a prediction module, one or more features indicative of a condition of one or more components of the power generation system based on the text description of the first weather event;
update, via the prediction module, the one or more features based on the text description of the second weather event or one or more parameters; and
determine, via the prediction module, future power generation by the power generation system based on the updated one or more features.