Markov Model of Wind Power Time Series UsingBayesian Inference of Transition Matrix

Peiyuan Chen; Kasper Klitgaard Berthelsen; Birgitte Bak-Jensen; Zhe Chen

Markov Model of Wind Power Time Series UsingBayesian Inference of Transition Matrix

Peiyuan Chen
, Kasper Klitgaard Berthelsen
, Birgitte Bak-Jensen
, Zhe Chen

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

1393 Downloads (Pure)

Abstract

This paper proposes to use Bayesian inference of transition matrix when developing a discrete Markov model of a wind speed/power time series and 95% credible interval for the model verification. The Dirichlet distribution is used as a conjugate prior for the transition matrix. Three discrete Markov models are compared, i.e. the basic Markov model, the Bayesian Markov model and the birth-and-death Markov model. The proposed Bayesian Markov model shows the best accuracy in modeling the autocorrelation of the wind power time series.

Originalsprog	Engelsk
Titel	Proceedings of the 35^th Annual Conference of the IEEE Industrial Electronics Society (IECON)
Forlag	IEEE (Institute of Electrical and Electronics Engineers)
Publikationsdato	2009
Sider	624-629
Status	Udgivet - 2009
Begivenhed	Annual Conference of the IEEE Industrial Electronics Society - Porto, Portugal Varighed: 3 nov. 2009 → 5 nov. 2009 Konferencens nummer: 35

Konference

Konference	Annual Conference of the IEEE Industrial Electronics Society
Nummer	35
Land/Område	Portugal
By	Porto
Periode	03/11/2009 → 05/11/2009

Adgang til dokumentet

PublicationForlagets udgivne version, 428 KB

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Citationsformater

@inproceedings{4dbbbd90e30311deabf1000ea68e967b,

title = "Markov Model of Wind Power Time Series UsingBayesian Inference of Transition Matrix",

abstract = "This paper proposes to use Bayesian inference of transition matrix when developing a discrete Markov model of a wind speed/power time series and 95\% credible interval for the model verification. The Dirichlet distribution is used as a conjugate prior for the transition matrix. Three discrete Markov models are compared, i.e. the basic Markov model, the Bayesian Markov model and the birth-and-death Markov model. The proposed Bayesian Markov model shows the best accuracy in modeling the autocorrelation of the wind power time series.",

keywords = "Bayesian inference, Markov model, Parameter uncertainty, Transition matrix, Wind power time series",

author = "Peiyuan Chen and Berthelsen, \{Kasper Klitgaard\} and Birgitte Bak-Jensen and Zhe Chen",

year = "2009",

language = "English",

pages = "624--629",

booktitle = "Proceedings of the 35th Annual Conference of the IEEE Industrial Electronics Society (IECON)",

publisher = "IEEE (Institute of Electrical and Electronics Engineers)",

address = "United States",

note = "Annual Conference of the IEEE Industrial Electronics Society ; Conference date: 03-11-2009 Through 05-11-2009",

}

Chen, P, Berthelsen, KK, Bak-Jensen, B & Chen, Z 2009, Markov Model of Wind Power Time Series UsingBayesian Inference of Transition Matrix. i Proceedings of the 35^th Annual Conference of the IEEE Industrial Electronics Society (IECON). IEEE (Institute of Electrical and Electronics Engineers), s. 624-629, Annual Conference of the IEEE Industrial Electronics Society, Porto, Portugal, 03/11/2009.

Markov Model of Wind Power Time Series UsingBayesian Inference of Transition Matrix. / Chen, Peiyuan; Berthelsen, Kasper Klitgaard; Bak-Jensen, Birgitte et al.
Proceedings of the 35^th Annual Conference of the IEEE Industrial Electronics Society (IECON). IEEE (Institute of Electrical and Electronics Engineers), 2009. s. 624-629.

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - Markov Model of Wind Power Time Series UsingBayesian Inference of Transition Matrix

AU - Chen, Peiyuan

AU - Berthelsen, Kasper Klitgaard

AU - Bak-Jensen, Birgitte

AU - Chen, Zhe

N1 - Conference code: 35

PY - 2009

Y1 - 2009

N2 - This paper proposes to use Bayesian inference of transition matrix when developing a discrete Markov model of a wind speed/power time series and 95% credible interval for the model verification. The Dirichlet distribution is used as a conjugate prior for the transition matrix. Three discrete Markov models are compared, i.e. the basic Markov model, the Bayesian Markov model and the birth-and-death Markov model. The proposed Bayesian Markov model shows the best accuracy in modeling the autocorrelation of the wind power time series.

AB - This paper proposes to use Bayesian inference of transition matrix when developing a discrete Markov model of a wind speed/power time series and 95% credible interval for the model verification. The Dirichlet distribution is used as a conjugate prior for the transition matrix. Three discrete Markov models are compared, i.e. the basic Markov model, the Bayesian Markov model and the birth-and-death Markov model. The proposed Bayesian Markov model shows the best accuracy in modeling the autocorrelation of the wind power time series.

KW - Bayesian inference

KW - Markov model

KW - Parameter uncertainty

KW - Transition matrix

KW - Wind power time series

M3 - Article in proceeding

SP - 624

EP - 629

BT - Proceedings of the 35th Annual Conference of the IEEE Industrial Electronics Society (IECON)

PB - IEEE (Institute of Electrical and Electronics Engineers)

T2 - Annual Conference of the IEEE Industrial Electronics Society

Y2 - 3 November 2009 through 5 November 2009

ER -

Markov Model of Wind Power Time Series UsingBayesian Inference of Transition Matrix

Abstract

Konference

Adgang til dokumentet

AUB Link

Fingeraftryk

Citationsformater