智能机器调度员的原理和原型

Automatic Operator for Power Systems: Principle And Prototype

在Dyliacoo博士所提出的概念基础上,阐述了智能机器调度员(AO)的基本原理和应用模式,提出了面向电网安全主题的精细规则挖掘的研究课题。提出了关键技术,包括:挖掘主题的定义方法、海量训练样本的在线生成和高性能数据挖掘算法。开发了AO的原型系统,给出了基于集群机的硬件配置设计和软件功能模块结构,介绍了软件功能、算法和人机界面。最后针对某省级电力系统,对AO原型系统进行了测试和分析,验证了在线挖掘的可行性和应用效果。

Based on the concept of automatic operator (AO) proposed by doctor Dyliacoo, principle and application mode of AO are clarified in this paper. Research topic named as data mining of fine rules for power system operation is presented for mining potential economic profit insuring of security of power systems. The key technologies is proposed, including methods of definition of mining topics, online acquirement of extra large amount of training samples, and algorithms of data mining with high performance. The prototype system of AO is developed, and its PC-cluster based hardware configuration and software structure are introduced. Functions, algorithms and MMI adopted in the prototype system are presented in details. Finally, tests are carried out for a real-life provincial power system, the feasibility and efficiency of the prototype system are verified.