Adaptive aggregated predictions for renewable energy systems

Balázs Csanád Csáji, András Kovács, J. Váncza

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

The paper addresses the problem of generating forecasts for energy production and consumption processes in a renewable energy system. The forecasts are made for a prototype public lighting microgrid, which includes photovoltaic panels and LED luminaries that regulate their lighting levels, as inputs for a receding horizon controller. Several stochastic models are fitted to historical times-series data and it is argued that side information, such as clear-sky predictions or the typical system behavior, can be used as exogenous inputs to increase their performance. The predictions can be further improved by combining the forecasts of several models using online learning, the framework of prediction with expert advice. The paper suggests an adaptive aggregation method which also takes side information into account, and makes a state-dependent aggregation. Numerical experiments are presented, as well, showing the efficiency of the estimated time-series models and the proposed aggregation approach.

Original languageEnglish
Title of host publicationIEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - ADPRL 2014: 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479945535
DOIs
Publication statusPublished - Jan 14 2014
Event2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2014 - Orlando, United States
Duration: Dec 9 2014Dec 12 2014

Other

Other2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2014
CountryUnited States
CityOrlando
Period12/9/1412/12/14

Fingerprint

Agglomeration
Time series
Lighting
Stochastic models
Light emitting diodes
Controllers
Experiments

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Cite this

Csáji, B. C., Kovács, A., & Váncza, J. (2014). Adaptive aggregated predictions for renewable energy systems. In IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - ADPRL 2014: 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, Proceedings [7010625] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ADPRL.2014.7010625

Adaptive aggregated predictions for renewable energy systems. / Csáji, Balázs Csanád; Kovács, András; Váncza, J.

IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - ADPRL 2014: 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. 7010625.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Csáji, BC, Kovács, A & Váncza, J 2014, Adaptive aggregated predictions for renewable energy systems. in IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - ADPRL 2014: 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, Proceedings., 7010625, Institute of Electrical and Electronics Engineers Inc., 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2014, Orlando, United States, 12/9/14. https://doi.org/10.1109/ADPRL.2014.7010625
Csáji BC, Kovács A, Váncza J. Adaptive aggregated predictions for renewable energy systems. In IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - ADPRL 2014: 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2014. 7010625 https://doi.org/10.1109/ADPRL.2014.7010625
Csáji, Balázs Csanád ; Kovács, András ; Váncza, J. / Adaptive aggregated predictions for renewable energy systems. IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - ADPRL 2014: 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014.
@inproceedings{72d918d382974ced97465808e29988d2,
title = "Adaptive aggregated predictions for renewable energy systems",
abstract = "The paper addresses the problem of generating forecasts for energy production and consumption processes in a renewable energy system. The forecasts are made for a prototype public lighting microgrid, which includes photovoltaic panels and LED luminaries that regulate their lighting levels, as inputs for a receding horizon controller. Several stochastic models are fitted to historical times-series data and it is argued that side information, such as clear-sky predictions or the typical system behavior, can be used as exogenous inputs to increase their performance. The predictions can be further improved by combining the forecasts of several models using online learning, the framework of prediction with expert advice. The paper suggests an adaptive aggregation method which also takes side information into account, and makes a state-dependent aggregation. Numerical experiments are presented, as well, showing the efficiency of the estimated time-series models and the proposed aggregation approach.",
author = "Cs{\'a}ji, {Bal{\'a}zs Csan{\'a}d} and Andr{\'a}s Kov{\'a}cs and J. V{\'a}ncza",
year = "2014",
month = "1",
day = "14",
doi = "10.1109/ADPRL.2014.7010625",
language = "English",
isbn = "9781479945535",
booktitle = "IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - ADPRL 2014: 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Adaptive aggregated predictions for renewable energy systems

AU - Csáji, Balázs Csanád

AU - Kovács, András

AU - Váncza, J.

PY - 2014/1/14

Y1 - 2014/1/14

N2 - The paper addresses the problem of generating forecasts for energy production and consumption processes in a renewable energy system. The forecasts are made for a prototype public lighting microgrid, which includes photovoltaic panels and LED luminaries that regulate their lighting levels, as inputs for a receding horizon controller. Several stochastic models are fitted to historical times-series data and it is argued that side information, such as clear-sky predictions or the typical system behavior, can be used as exogenous inputs to increase their performance. The predictions can be further improved by combining the forecasts of several models using online learning, the framework of prediction with expert advice. The paper suggests an adaptive aggregation method which also takes side information into account, and makes a state-dependent aggregation. Numerical experiments are presented, as well, showing the efficiency of the estimated time-series models and the proposed aggregation approach.

AB - The paper addresses the problem of generating forecasts for energy production and consumption processes in a renewable energy system. The forecasts are made for a prototype public lighting microgrid, which includes photovoltaic panels and LED luminaries that regulate their lighting levels, as inputs for a receding horizon controller. Several stochastic models are fitted to historical times-series data and it is argued that side information, such as clear-sky predictions or the typical system behavior, can be used as exogenous inputs to increase their performance. The predictions can be further improved by combining the forecasts of several models using online learning, the framework of prediction with expert advice. The paper suggests an adaptive aggregation method which also takes side information into account, and makes a state-dependent aggregation. Numerical experiments are presented, as well, showing the efficiency of the estimated time-series models and the proposed aggregation approach.

UR - http://www.scopus.com/inward/record.url?scp=84946690074&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946690074&partnerID=8YFLogxK

U2 - 10.1109/ADPRL.2014.7010625

DO - 10.1109/ADPRL.2014.7010625

M3 - Conference contribution

AN - SCOPUS:84946690074

SN - 9781479945535

BT - IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - ADPRL 2014: 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -