ExaModelsPower.jl: A GPU-Compatible Modeling Library for Nonlinear Power System Optimization
This work addresses efficiency issues for power system operators by enabling faster optimization through GPU acceleration, though it is incremental as it builds on existing tools.
The paper tackles the computational challenges of power system optimization by introducing ExaModelsPower.jl, a GPU-compatible modeling library for nonlinear AC optimal power flow, and shows that GPU solvers achieve up to two orders of magnitude speedups on problems with over 20,000 variables.
As GPU-accelerated mathematical programming techniques mature, there is growing interest in utilizing them to address the computational challenges of power system optimization. This paper introduces ExaModelsPower.jl, an open-source modeling library for creating GPU-compatible nonlinear AC optimal power flow models. Built on ExaModels.jl, ExaModelsPower.jl provides a high-level interface that automatically generates all necessary callback functions for GPU solvers. The library is designed for large-scale problem instances, which may include multiple time periods and security constraints. Using ExaModelsPower.jl, we benchmark GPU and CPU solvers on open-source test cases. Our results show that GPU solvers can deliver up to two orders of magnitude speedups compared to alternative tools on CPU for problems with more than 20,000 variables and a solution precision of up to $10^{-4}$, while performance for smaller instances or tighter tolerances may vary.