Input-convex neural network modeling for battery optimization in power systems
Abstract
Battery energy storage systems (BESS) play an increasingly vital role in integrating renewable generation into power grids due to their ability to dynamically balance supply. Grid-tied batteries typically employ power converters, where part-load efficiencies vary non-linearly. This non- linearity poses challenges for optimization, particularly in ensuring computational tractability. In this poster, a data-driven approach is introduced with the input-convex neural network (ICNN) to approximate the nonlinear efficiency with a convex function. This relaxed ICNN method is applied to battery optimization problems. Specifically, ICNN-based method appears to be promising for future battery optimization with desirable feasibility and optimality outcomes.
Primary Faculty Mentor Name
Matthew I. Aho
Status
Graduate
Student College
College of Engineering and Mathematical Sciences
Program/Major
Electrical Engineering
Primary Research Category
Engineering and Math Science
Input-convex neural network modeling for battery optimization in power systems
Battery energy storage systems (BESS) play an increasingly vital role in integrating renewable generation into power grids due to their ability to dynamically balance supply. Grid-tied batteries typically employ power converters, where part-load efficiencies vary non-linearly. This non- linearity poses challenges for optimization, particularly in ensuring computational tractability. In this poster, a data-driven approach is introduced with the input-convex neural network (ICNN) to approximate the nonlinear efficiency with a convex function. This relaxed ICNN method is applied to battery optimization problems. Specifically, ICNN-based method appears to be promising for future battery optimization with desirable feasibility and optimality outcomes.
