Pattern sequence-based energy demand forecast using photovoltaic energy records

研究成果: Conference contribution

8 引用 (Scopus)

抄録

Considering recent trends in energy technology development, consumer's energy demand could be influenced by the renewable energy supply in any way. A simple extension of pattern sequence-based forecasting (PSF) enables us to predict demand curves based on the correlated bidimensional time-series by using co-occurrence patterns of energy supply and demand. However, prediction accuracy of PSF deeply depends on the clustering result, which is used for pattern matching. In this paper, a promising clustering method based on nonnegative tensor factorization is applied for this task and evaluated experimentally from the viewpoint of prediction accuracy.

元の言語English
ホスト出版物のタイトル2012 International Conference on Renewable Energy Research and Applications, ICRERA 2012
DOI
出版物ステータスPublished - 2012
イベント1st International Conference on Renewable Energy Research and Applications, ICRERA 2012 - Nagasaki
継続期間: 2012 11 112012 11 14

Other

Other1st International Conference on Renewable Energy Research and Applications, ICRERA 2012
Nagasaki
期間12/11/1112/11/14

Fingerprint

Pattern matching
Factorization
Tensors
Time series

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment

これを引用

Fujimoto, Y., & Hayashi, Y. (2012). Pattern sequence-based energy demand forecast using photovoltaic energy records. : 2012 International Conference on Renewable Energy Research and Applications, ICRERA 2012 [6477299] https://doi.org/10.1109/ICRERA.2012.6477299

Pattern sequence-based energy demand forecast using photovoltaic energy records. / Fujimoto, Yu; Hayashi, Yasuhiro.

2012 International Conference on Renewable Energy Research and Applications, ICRERA 2012. 2012. 6477299.

研究成果: Conference contribution

Fujimoto, Y & Hayashi, Y 2012, Pattern sequence-based energy demand forecast using photovoltaic energy records. : 2012 International Conference on Renewable Energy Research and Applications, ICRERA 2012., 6477299, 1st International Conference on Renewable Energy Research and Applications, ICRERA 2012, Nagasaki, 12/11/11. https://doi.org/10.1109/ICRERA.2012.6477299
Fujimoto Y, Hayashi Y. Pattern sequence-based energy demand forecast using photovoltaic energy records. : 2012 International Conference on Renewable Energy Research and Applications, ICRERA 2012. 2012. 6477299 https://doi.org/10.1109/ICRERA.2012.6477299
Fujimoto, Yu ; Hayashi, Yasuhiro. / Pattern sequence-based energy demand forecast using photovoltaic energy records. 2012 International Conference on Renewable Energy Research and Applications, ICRERA 2012. 2012.
@inproceedings{f00f559502c3490cb998a516db41e319,
title = "Pattern sequence-based energy demand forecast using photovoltaic energy records",
abstract = "Considering recent trends in energy technology development, consumer's energy demand could be influenced by the renewable energy supply in any way. A simple extension of pattern sequence-based forecasting (PSF) enables us to predict demand curves based on the correlated bidimensional time-series by using co-occurrence patterns of energy supply and demand. However, prediction accuracy of PSF deeply depends on the clustering result, which is used for pattern matching. In this paper, a promising clustering method based on nonnegative tensor factorization is applied for this task and evaluated experimentally from the viewpoint of prediction accuracy.",
author = "Yu Fujimoto and Yasuhiro Hayashi",
year = "2012",
doi = "10.1109/ICRERA.2012.6477299",
language = "English",
isbn = "9781467323284",
booktitle = "2012 International Conference on Renewable Energy Research and Applications, ICRERA 2012",

}

TY - GEN

T1 - Pattern sequence-based energy demand forecast using photovoltaic energy records

AU - Fujimoto, Yu

AU - Hayashi, Yasuhiro

PY - 2012

Y1 - 2012

N2 - Considering recent trends in energy technology development, consumer's energy demand could be influenced by the renewable energy supply in any way. A simple extension of pattern sequence-based forecasting (PSF) enables us to predict demand curves based on the correlated bidimensional time-series by using co-occurrence patterns of energy supply and demand. However, prediction accuracy of PSF deeply depends on the clustering result, which is used for pattern matching. In this paper, a promising clustering method based on nonnegative tensor factorization is applied for this task and evaluated experimentally from the viewpoint of prediction accuracy.

AB - Considering recent trends in energy technology development, consumer's energy demand could be influenced by the renewable energy supply in any way. A simple extension of pattern sequence-based forecasting (PSF) enables us to predict demand curves based on the correlated bidimensional time-series by using co-occurrence patterns of energy supply and demand. However, prediction accuracy of PSF deeply depends on the clustering result, which is used for pattern matching. In this paper, a promising clustering method based on nonnegative tensor factorization is applied for this task and evaluated experimentally from the viewpoint of prediction accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84876140439&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876140439&partnerID=8YFLogxK

U2 - 10.1109/ICRERA.2012.6477299

DO - 10.1109/ICRERA.2012.6477299

M3 - Conference contribution

AN - SCOPUS:84876140439

SN - 9781467323284

BT - 2012 International Conference on Renewable Energy Research and Applications, ICRERA 2012

ER -