A Single-Source Multiprocessing Parallelism for Heterogeneous Acceleration of Power System Dynamic Simulation

Today's scientific software in the power system domain highly relies on CPU-based multi-core clusters. However, the rise of heterogeneous computing requires that parallel applications be executed on various hardware from different vendors. Thus, efficient solutions are emerging using compiler directives, communication protocols, high-level libraries, and execution policies. Power system dynamic simulation (DS) is critical to predicting and identifying real-time physical stability constraints with inevitable system component failures. This paper explores a multiprocessing heterogeneous solution for parallel DS. We design a single-source code realized through Message Passing Interface (MPI) and array computing at a high level. The performance test of a 30-second simulation on the largest 36864-bus-12288-generator system indicates that the program run with pure CPU-based parallelism finishes the computation in 14.6 seconds on a personal computer, and the program's CPU+GPU acceleration (hybrid switch) reaches more speedup with 2.33 seconds on a cluster node. The proposed solution significantly improves computational performance with high portability and adaptiveness to various hardware environments.