Advanced search
1 file | 1.98 MB Add to list

A data-driven approach using deep learning time series prediction for forecasting power system variables

Author
Organization
Abstract
This study investigates the performance of ‘Group Method of Data Handling’ type neural network algorithm in short-term time series prediction of the renewable energy and grid-balancing variables, such as the Net Regulation Volume (NRV) and System Imbalance (SI). The proposed method is compared with a Multi-layer Perceptron (MLP) neural network which is known as a universal approximator. Empirical validation results show that the GMDH performance is more accurate in compression with the most recent forecast which is provided by ELIA (Belgian transmission system operator). This study aims to practice the applicability of the polynomial GMDH-type neural network algorithm in time series prediction under a wide range of complexity and uncertainty related to the environment and electricity market.
Keywords
Renewble energy, Power system, Timeseries prediction, Group method of data handling (GMDH), Multi-layer perceptron (MLP)

Downloads

  • Kayedpour N accepted version.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 1.98 MB

Citation

Please use this url to cite or link to this publication:

MLA
Kayedpour, Nezmin, et al. “A Data-Driven Approach Using Deep Learning Time Series Prediction for Forecasting Power System Variables.” PROCEEDINGS OF 2019 IEEE 2ND INTERNATIONAL CONFERENCE ON RENEWABLE ENERGY AND POWER ENGINEERING (REPE 2019), IEEE, 2019, pp. 43–47, doi:10.1109/REPE48501.2019.9025159.
APA
Kayedpour, N., Ebneali Samani, A., De Kooning, J., Vandevelde, L., & Crevecoeur, G. (2019). A data-driven approach using deep learning time series prediction for forecasting power system variables. PROCEEDINGS OF 2019 IEEE 2ND INTERNATIONAL CONFERENCE ON RENEWABLE ENERGY AND POWER ENGINEERING (REPE 2019), 43–47. https://doi.org/10.1109/REPE48501.2019.9025159
Chicago author-date
Kayedpour, Nezmin, Arash Ebneali Samani, Jeroen De Kooning, Lieven Vandevelde, and Guillaume Crevecoeur. 2019. “A Data-Driven Approach Using Deep Learning Time Series Prediction for Forecasting Power System Variables.” In PROCEEDINGS OF 2019 IEEE 2ND INTERNATIONAL CONFERENCE ON RENEWABLE ENERGY AND POWER ENGINEERING (REPE 2019), 43–47. IEEE. https://doi.org/10.1109/REPE48501.2019.9025159.
Chicago author-date (all authors)
Kayedpour, Nezmin, Arash Ebneali Samani, Jeroen De Kooning, Lieven Vandevelde, and Guillaume Crevecoeur. 2019. “A Data-Driven Approach Using Deep Learning Time Series Prediction for Forecasting Power System Variables.” In PROCEEDINGS OF 2019 IEEE 2ND INTERNATIONAL CONFERENCE ON RENEWABLE ENERGY AND POWER ENGINEERING (REPE 2019), 43–47. IEEE. doi:10.1109/REPE48501.2019.9025159.
Vancouver
1.
Kayedpour N, Ebneali Samani A, De Kooning J, Vandevelde L, Crevecoeur G. A data-driven approach using deep learning time series prediction for forecasting power system variables. In: PROCEEDINGS OF 2019 IEEE 2ND INTERNATIONAL CONFERENCE ON RENEWABLE ENERGY AND POWER ENGINEERING (REPE 2019). IEEE; 2019. p. 43–7.
IEEE
[1]
N. Kayedpour, A. Ebneali Samani, J. De Kooning, L. Vandevelde, and G. Crevecoeur, “A data-driven approach using deep learning time series prediction for forecasting power system variables,” in PROCEEDINGS OF 2019 IEEE 2ND INTERNATIONAL CONFERENCE ON RENEWABLE ENERGY AND POWER ENGINEERING (REPE 2019), Toronto, ON, Canada, 2019, pp. 43–47.
@inproceedings{8634304,
  abstract     = {{This study investigates the performance of ‘Group Method of Data Handling’ type neural network algorithm in short-term time series prediction of the renewable energy and grid-balancing variables, such as the Net Regulation Volume (NRV) and System Imbalance (SI). The proposed method is compared with a Multi-layer Perceptron (MLP) neural network which is known as a universal approximator. Empirical validation results show that the GMDH performance is more accurate in compression with the most recent forecast which is provided by ELIA (Belgian transmission system operator). This study aims to practice the applicability of the polynomial GMDH-type neural network algorithm in time series prediction under a wide range of complexity and uncertainty related to the environment and electricity market.}},
  author       = {{Kayedpour, Nezmin and Ebneali Samani, Arash and De Kooning, Jeroen and Vandevelde, Lieven and Crevecoeur, Guillaume}},
  booktitle    = {{PROCEEDINGS OF 2019 IEEE 2ND INTERNATIONAL CONFERENCE ON RENEWABLE ENERGY AND POWER ENGINEERING (REPE 2019)}},
  isbn         = {{9781728145624}},
  issn         = {{2380-9329}},
  keywords     = {{Renewble energy,Power system,Timeseries prediction,Group method of data handling (GMDH),Multi-layer perceptron (MLP)}},
  language     = {{eng}},
  location     = {{Toronto, ON, Canada}},
  pages        = {{43--47}},
  publisher    = {{IEEE}},
  title        = {{A data-driven approach using deep learning time series prediction for forecasting power system variables}},
  url          = {{http://doi.org/10.1109/REPE48501.2019.9025159}},
  year         = {{2019}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: