大地网平差的网格计算实现

Grid Computing on Large-Scale Geodetic Network Adjustment

利用网格的高性能计算、传输和存储能力,解决大规模大地网观测数据量庞大而分散、平差中大型线性方程组存储和解算困难的问题。由Helmert分区法,推导了适合网格计算的并行计算平差公式。搭建了网格计算环境并进行了实验,实验结果验证了网格计算的优越性。

To solve the problems of computing and storage of large amounts of geodetic data in Largescale Geodetic Network, grid computing is introduced. Helmert Blocking Method is used for breaking up a least squares adjustment problem which is too large to be managed as a single computation and is divided into many smaller computational tasks for parallel computing. Finally, the paper constructs the environment of grid computing in which experiment is done to improve the superiority of grid computing.