US 11,900,031 B2
Systems and methods of composite load modeling for electric power systems
Yishen Wang, San Jose, CA (US); Xinan Wang, San Jose, CA (US); Haifeng Li, Jiangsu (CN); Chunlei Xu, Jiangsu (CN); Di Shi, San Francisco, CA (US); You Lin, San Jose, CA (US); Siqi Wang, San Jose, CA (US); Zhiwei Wang, San Jose, CA (US); Jing Cao, Nanjing (CN); Bo Guo, Nanjing (CN); and Zhengyang Ding, Nanjing (CN)
Assigned to State Grid Smart Research Institute Co., Ltd., Beijing (CN); State Grid Corporation of China Co., Ltd, Beijing (CN); State Grid Jiangsu Electric Power Co., Ltd., Jiangsu (CN); State Grid Shandong Electric Power Company, Shangdong (CN); and State Grid Jiangsu Electric Power Co., Ltd., Information and Communication Branch, Nanjing (CN)
Filed by State Grid Smart Grid Research Institute Co., Ltd., Beijing (CN); State Grid Corporation of China Co. Ltd, Beijing (CN); State Grid Jiangsu Electric Power Co., LTD., Jiangsu (CN); and State Grid Shandong Electric Power Company, Shandong (CN)
Filed on Aug. 14, 2020, as Appl. No. 16/994,512.
Claims priority of provisional application 62/887,167, filed on Aug. 15, 2019.
Prior Publication US 2021/0049314 A1, Feb. 18, 2021
Int. Cl. G06F 30/27 (2020.01); G06F 119/06 (2020.01)
CPC G06F 30/27 (2020.01) [G06F 2119/06 (2020.01)] 22 Claims
OG exemplary drawing
 
1. A method for generating a load model having composite load components for an electric power system, the method comprising:
acquiring state information at a bus of the electric power system;
acquiring a training event record; and
generating the load model by sequentially executing steps of:
determining a final load component composition for a predetermined composite load model structure referencing to both the state information and the training event record; and
determining a plurality of final load parameters corresponding to the final load component composition and the predetermined load model structure also referencing to both the state information and the training event record
wherein the determining the final load component composition comprises:
initializing a plurality of load component compositions;
optimizing the plurality of the initial load component compositions with a machine learning agent to generate a predetermined number of top load component compositions;
calculating quantile loss for each of the top load component compositions with a predefined quantile level; and
selecting one of the top load component compositions that has the lowest quantile loss as the final load component composition.