基于分布式网络并行环境的惩罚函数法  

Penalty Function Method Based on Distributed Network Parallel Environment

作　　者：范波芹[1] 索丽生[2] 

机构地区：[1]浙江省水利厅咨询中心,浙江杭州310009 [2]中华人民共和国水利部,北京100000

出　　处：《河海大学学报（自然科学版）》2002年第2期116-118,共3页Journal of Hohai University(Natural Sciences)

摘　　要：基于PVM分布式编程环境 ,将传统的惩罚函数法加以改进 ,提出惩罚函数并行算法的概念 .该算法不但具有编程方便、可移植性强和能有效地减少计算时间等优点 ,而且通讯量少 ,对传统的惩罚函数法改动少 ,只需有一网络和PVM并行编程环境就能实现 .The conventional penalty function method is improved, and the concept of parallel arithmetic for the penalty function method is proposed. The arithmetic is easy to be programmed and transplanted, and has the merit of time saving. With a small quantity of communication and little modification of the conventional penalty function method, the arithmetic can be realized with only a network and a PVM parallel environment.

关 键 词：网络并行环境 分布式 惩罚函数法 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]