US 12,394,980 B1
Real time AI/IoT dynamics economics modeling for renewable energy generation and management
Camilo Mejia, Houston, TX (US); Rebecca Nye, London (GB); Meisong Yan, Houston, TX (US); and Oscar Martinez, Bogota (CO)
Assigned to Enovate AI Corporation, The Woodlands, TX (US)
Filed by Enovate AI Corporation, The Woodlands, TX (US)
Filed on Nov. 12, 2024, as Appl. No. 18/944,842.
Int. Cl. H02J 3/00 (2006.01); G06Q 10/0631 (2023.01); G06Q 50/06 (2024.01); H02J 3/38 (2006.01); H02S 10/12 (2014.01)
CPC H02J 3/003 (2020.01) [G06Q 10/0631 (2013.01); G06Q 50/06 (2013.01); H02J 3/004 (2020.01); H02J 3/381 (2013.01); H02S 10/12 (2014.12); H02J 2203/20 (2020.01); H02J 2300/10 (2020.01); H02J 2300/26 (2020.01); H02J 2300/28 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A system for real-time economic modeling and optimization for integrated power generation and distribution, comprising:
a controller configured to collect real-time multi-frequency data from multiple energy sources and IoT sensors;
an database configured to integrate the collected data with energy production cost components and market information and weather information from external data sources; and
a processing server comprising a physics-based model and a machine learning model, configured to;
apply the physics-based model to the integrated data to simulate energy production processes and establish baseline Levelized Cost of Energy (LCOE) estimates,
apply the machine learning model to the integrated data to refine the baseline LCOE estimates by identifying patterns in historical operational data and current market conditions, and calculate real-time LCOE based on current operational expenditure (OPEX) and market conditions, predict profitability, and assess risk, and
generate operational adjustment recommendations for the energy production based on at least one of the LCOE and predicted profitability.