基于机群系统的一种并行优化策略  

A PARALLEL OPTIMIZATION STRATEGY BASED ON CLUSTER OF WORKSTATIONS

作　　者：张帆[1] 邵之江[1] 仲卫涛[1] 钱积新[1] 

机构地区：[1]浙江大学系统工程研究所,浙江杭州310027

出　　处：《石油学报（石油加工）》2001年第6期56-60,共5页Acta Petrolei Sinica(Petroleum Processing Section)

基　　金：国家自然科学基金资助项目 ( 2 990 6 0 10 )

摘　　要：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.

关 键 词：优化策略 并行计算 机群系统 化工过程系统 

分 类 号：TQ02[化学工程] TQ056.8