基于机群系统的一种并行优化策略

A PARALLEL OPTIMIZATION STRATEGY BASED ON CLUSTER OF WORKSTATIONS

针对大规模化工过程系统优化中计算能力不够的情况 ,用机群系统建构并行优化计算环境。在分析化工过程系统优化的特点后 ,提出了一种基于机群系统的并行优化策略 ,即将优化计算中频繁出现的梯度求解过程并行化。实际算例表明 ,此方法是行之有效的。

Current trends toward increased model detail and rigorous optimization in chemical process accelerate the need to solve very large systems. Even with the high performance computers nowadays, there still exist many difficulties for a single computer to solve large scale chemical process optimization problems. Details of cluster of workstations(COW), a relatively recently developed technology, are given to highlight its advantages compared with other approaches in parallel computing. Since gradient evaluation in chemical process optimization is the most computing expensive task, a variant splitting method utilizing cluster of workstations is proposed to solve chemical process optimization problems efficiently. Computation on optimization problem of a distillation column demonstrates the efficiency of this proposed approach.