GPU Accelerated DC Power Flow Analysis

Graphics processing unit (GPU) has broad prospects in computation and memory intensive realms due to its superior performances in calculation capability, memory bandwidth and power consumption, and has natural applications in computational intensive power system analyses. Direct current power flow (DCPF) is often used in power system analysis, such as power flow analysis, security analysis and contingency screening. DCPF is a problem of solving sparse linear systems. This paper uses Jacobi iteration method to solve DCPF. Numeric studies on a 900-bus system have shown that the GPU-accelerated algorithm, in compared with its counterpart CPU version, can achieve about 2.3 times speedup. This highly promising performance has demonstrated that carefully designed performance tuning in conjunction with GPU programing architecture is imperative for a GPU-accelerated application.