OPTIMAL HANKEL-NORM APPROXIMATION APPROACH TO MODEL-REDUCTION OF LARGE-SCALE MARKOV-CHAINS

被引:4
|
作者
CHEN, GR
CHUI, CK
YU, YQ
机构
[1] TEXAS A&M UNIV SYST,DEPT MATH,COLL STN,TX 77843
[2] TEXAS A&M UNIV SYST,DEPT ELECT ENGN,COLL STN,TX 77843
[3] UNIV CALIF IRVINE,DEPT ELECT & COMP ENGN,IRVINE,CA 92717
基金
美国国家科学基金会;
关键词
D O I
10.1080/00207729208949383
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A model reduction problem of certain large-scale Markov chains under an optimal criterion for Hankel-norm approximation is discussed. The multi-dimensional Markov chain under investigation is assumed to have a finite-dimensional stationary state-transition matrix, which is first reformulated as a multi-input/multi-output (MIMO) linear time-invariant (LTI) stochastic system. Consequently, the resulting large-scale MIMO LTI stochastic system has a closed-form best approximant in the Hankel-norm from a specified class of stable lower-dimensional MIMO LTI systems.
引用
收藏
页码:1289 / 1297
页数:9
相关论文
共 45 条