Multi-step-ahead Multivariate Predictors: A Comparative Analysis

Marzia Cescon; Rolf Johansson

Multi-step-ahead Multivariate Predictors: A Comparative Analysis

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

136 Downloads (Pure)

Abstract

The focus of this article is to undertake a comparative analysis of multi-step-ahead linear multivariate predictors. The approach considered for the estimation will be based on geometrically reliable linear algebra tools, resorting to subspace identification methods. A crucial issue is quantification of both bias error and variance affecting the estimate of the prediction for increasing values of the look ahead when only a small number of samples is available. No complete theory is available so far, nor sufficient numerical experience. Therefore, the analysis of this paper aims at shading some lights on the topic providing some insights and help to develop some intuitions.

Original language	English
Title of host publication	Proc. 49th IEEE Conf. Decision and Control (CDC2010)
Pages	2837-2842
Publication status	Published - 2010
Event	49th IEEE Conference on Decision and Control - Atlanta, Georgia, United States Duration: 2010 Dec 15 → …

Conference

Conference	49th IEEE Conference on Decision and Control
Country/Territory	United States
City	Atlanta, Georgia
Period	2010/12/15 → …

Subject classification (UKÄ)

Control Engineering

Access to Document

CDC2010MCRJ

DIAdvisor
Ståhl, F. (Researcher), Rönn, M. (Researcher), Cescon, M. (Researcher) & Johansson, R. (PI)
2008/03/01 → 2012/02/29
Project: Research

Cite this

@inproceedings{02d433349d444e44a31d156cf72c5c17,

title = "Multi-step-ahead Multivariate Predictors: A Comparative Analysis",

abstract = "The focus of this article is to undertake a comparative analysis of multi-step-ahead linear multivariate predictors. The approach considered for the estimation will be based on geometrically reliable linear algebra tools, resorting to subspace identification methods. A crucial issue is quantification of both bias error and variance affecting the estimate of the prediction for increasing values of the look ahead when only a small number of samples is available. No complete theory is available so far, nor sufficient numerical experience. Therefore, the analysis of this paper aims at shading some lights on the topic providing some insights and help to develop some intuitions.",

author = "Marzia Cescon and Rolf Johansson",

year = "2010",

language = "English",

pages = "2837--2842",

booktitle = "Proc. 49th IEEE Conf. Decision and Control (CDC2010)",

note = "49th IEEE Conference on Decision and Control ; Conference date: 15-12-2010",

}

TY - GEN

T1 - Multi-step-ahead Multivariate Predictors: A Comparative Analysis

AU - Cescon, Marzia

AU - Johansson, Rolf

PY - 2010

Y1 - 2010

N2 - The focus of this article is to undertake a comparative analysis of multi-step-ahead linear multivariate predictors. The approach considered for the estimation will be based on geometrically reliable linear algebra tools, resorting to subspace identification methods. A crucial issue is quantification of both bias error and variance affecting the estimate of the prediction for increasing values of the look ahead when only a small number of samples is available. No complete theory is available so far, nor sufficient numerical experience. Therefore, the analysis of this paper aims at shading some lights on the topic providing some insights and help to develop some intuitions.

AB - The focus of this article is to undertake a comparative analysis of multi-step-ahead linear multivariate predictors. The approach considered for the estimation will be based on geometrically reliable linear algebra tools, resorting to subspace identification methods. A crucial issue is quantification of both bias error and variance affecting the estimate of the prediction for increasing values of the look ahead when only a small number of samples is available. No complete theory is available so far, nor sufficient numerical experience. Therefore, the analysis of this paper aims at shading some lights on the topic providing some insights and help to develop some intuitions.

M3 - Paper in conference proceeding

SP - 2837

EP - 2842

BT - Proc. 49th IEEE Conf. Decision and Control (CDC2010)

T2 - 49th IEEE Conference on Decision and Control

Y2 - 15 December 2010

ER -

Multi-step-ahead Multivariate Predictors: A Comparative Analysis

Abstract

Conference

Subject classification (UKÄ)

Access to Document

Fingerprint

Projects

DIAdvisor

Cite this