Correlation-constrained and sparsity-controlled vector autoregressive model for spatio-temporal wind power forecasting

Yongning Zhao, Lin Ye*, Pierre Pinson, Yong Tang

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

The ever-increasing number of wind farms has brought both challenges and opportunities in the development of wind power forecasting techniques to take advantage of interdependenciesbetweentensorhundredsofspatiallydistributedwind farms, e.g., over a region. In this paper, a Sparsity-Controlled Vector Autoregressive (SC-VAR) model is introduced to obtain sparse model structures in a spatio-temporal wind power forecasting framework by reformulating the original VAR model into a constrained Mixed Integer Non-Linear Programming (MINLP) problem. It allows controlling the sparsity of the coefficient matrices in direct manner. However this original SC-VAR is difficult to implement due to its complicated constraints and the lack of guidelines for setting its parameters. To reduce the complexity of this MINLP and to make it possible to incorporate prior expert knowledge to benefit model building and forecasting, the original SC-VAR is modified and a Correlation-Constrained SC-VAR (CCSC-VAR) is proposed based on spatial correlation information about wind farms. Our approach is evaluated based on a case study of very-short-term forecasting for 25 wind farms in Denmark. Comparison is performed with a set of traditional local methods and spatio-temporal methods. The results obtained show the proposed CCSC-VAR has better overall performance than both the original SC-VAR and other benchmark methods, taking into account all evaluation indicators, including sparsitycontrol ability, sparsity, accuracy and efficiency
Original languageEnglish
JournalI E E E Transactions on Power Systems
Volume33
Issue number5
Pages (from-to)5029 - 5040
ISSN0885-8950
DOIs
Publication statusPublished - 2018

Keywords

  • Wind power
  • Power system operations
  • Forecasting
  • Spatial correlation
  • Sparsity

Cite this

@article{666d3af6dffc4d99a50884b49d3a3c79,
title = "Correlation-constrained and sparsity-controlled vector autoregressive model for spatio-temporal wind power forecasting",
abstract = "The ever-increasing number of wind farms has brought both challenges and opportunities in the development of wind power forecasting techniques to take advantage of interdependenciesbetweentensorhundredsofspatiallydistributedwind farms, e.g., over a region. In this paper, a Sparsity-Controlled Vector Autoregressive (SC-VAR) model is introduced to obtain sparse model structures in a spatio-temporal wind power forecasting framework by reformulating the original VAR model into a constrained Mixed Integer Non-Linear Programming (MINLP) problem. It allows controlling the sparsity of the coefficient matrices in direct manner. However this original SC-VAR is difficult to implement due to its complicated constraints and the lack of guidelines for setting its parameters. To reduce the complexity of this MINLP and to make it possible to incorporate prior expert knowledge to benefit model building and forecasting, the original SC-VAR is modified and a Correlation-Constrained SC-VAR (CCSC-VAR) is proposed based on spatial correlation information about wind farms. Our approach is evaluated based on a case study of very-short-term forecasting for 25 wind farms in Denmark. Comparison is performed with a set of traditional local methods and spatio-temporal methods. The results obtained show the proposed CCSC-VAR has better overall performance than both the original SC-VAR and other benchmark methods, taking into account all evaluation indicators, including sparsitycontrol ability, sparsity, accuracy and efficiency",
keywords = "Wind power, Power system operations, Forecasting, Spatial correlation, Sparsity",
author = "Yongning Zhao and Lin Ye and Pierre Pinson and Yong Tang",
year = "2018",
doi = "10.1109/TPWRS.2018.2794450",
language = "English",
volume = "33",
pages = "5029 -- 5040",
journal = "I E E E Transactions on Power Systems",
issn = "0885-8950",
publisher = "Institute of Electrical and Electronics Engineers",
number = "5",

}

Correlation-constrained and sparsity-controlled vector autoregressive model for spatio-temporal wind power forecasting. / Zhao, Yongning ; Ye, Lin ; Pinson, Pierre; Tang, Yong .

In: I E E E Transactions on Power Systems, Vol. 33, No. 5, 2018, p. 5029 - 5040.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Correlation-constrained and sparsity-controlled vector autoregressive model for spatio-temporal wind power forecasting

AU - Zhao, Yongning

AU - Ye, Lin

AU - Pinson, Pierre

AU - Tang, Yong

PY - 2018

Y1 - 2018

N2 - The ever-increasing number of wind farms has brought both challenges and opportunities in the development of wind power forecasting techniques to take advantage of interdependenciesbetweentensorhundredsofspatiallydistributedwind farms, e.g., over a region. In this paper, a Sparsity-Controlled Vector Autoregressive (SC-VAR) model is introduced to obtain sparse model structures in a spatio-temporal wind power forecasting framework by reformulating the original VAR model into a constrained Mixed Integer Non-Linear Programming (MINLP) problem. It allows controlling the sparsity of the coefficient matrices in direct manner. However this original SC-VAR is difficult to implement due to its complicated constraints and the lack of guidelines for setting its parameters. To reduce the complexity of this MINLP and to make it possible to incorporate prior expert knowledge to benefit model building and forecasting, the original SC-VAR is modified and a Correlation-Constrained SC-VAR (CCSC-VAR) is proposed based on spatial correlation information about wind farms. Our approach is evaluated based on a case study of very-short-term forecasting for 25 wind farms in Denmark. Comparison is performed with a set of traditional local methods and spatio-temporal methods. The results obtained show the proposed CCSC-VAR has better overall performance than both the original SC-VAR and other benchmark methods, taking into account all evaluation indicators, including sparsitycontrol ability, sparsity, accuracy and efficiency

AB - The ever-increasing number of wind farms has brought both challenges and opportunities in the development of wind power forecasting techniques to take advantage of interdependenciesbetweentensorhundredsofspatiallydistributedwind farms, e.g., over a region. In this paper, a Sparsity-Controlled Vector Autoregressive (SC-VAR) model is introduced to obtain sparse model structures in a spatio-temporal wind power forecasting framework by reformulating the original VAR model into a constrained Mixed Integer Non-Linear Programming (MINLP) problem. It allows controlling the sparsity of the coefficient matrices in direct manner. However this original SC-VAR is difficult to implement due to its complicated constraints and the lack of guidelines for setting its parameters. To reduce the complexity of this MINLP and to make it possible to incorporate prior expert knowledge to benefit model building and forecasting, the original SC-VAR is modified and a Correlation-Constrained SC-VAR (CCSC-VAR) is proposed based on spatial correlation information about wind farms. Our approach is evaluated based on a case study of very-short-term forecasting for 25 wind farms in Denmark. Comparison is performed with a set of traditional local methods and spatio-temporal methods. The results obtained show the proposed CCSC-VAR has better overall performance than both the original SC-VAR and other benchmark methods, taking into account all evaluation indicators, including sparsitycontrol ability, sparsity, accuracy and efficiency

KW - Wind power

KW - Power system operations

KW - Forecasting

KW - Spatial correlation

KW - Sparsity

U2 - 10.1109/TPWRS.2018.2794450

DO - 10.1109/TPWRS.2018.2794450

M3 - Journal article

VL - 33

SP - 5029

EP - 5040

JO - I E E E Transactions on Power Systems

JF - I E E E Transactions on Power Systems

SN - 0885-8950

IS - 5

ER -