Improved modelling of electric loads for enabling demand response by applying physical and data-driven models

project RESPONSE

Pekka Koponen (Corresponding author), Seppo Hänninen, Harri Niska, Mikko Kolehmainen, Antti Mutanen, Antti Rautiainen, Pertti Järventausta, Hannu Koivisto

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

Accurate load and response forecasts are a critical
enabler for high demand response penetrations and optimization
of responses and market actions. Project RESPONSE studies and
develops methods to improve the forecasts. Its objectives are to
improve 1) load and response forecast and optimization models
based on both data- driven and physical modelling, and their
hybrid models, 2) utilization of various data sources such as
smart metering data, weather data, measurements from
substations etc., and 3) performance criteria of load forecasting.
The project applies, develops, compares, and integrates various
modelling approaches including partly physical models, machine
learning, modern load profiling, autoregressive models, and
Kalman-filtering. It also applies non-linear constrained
optimization to load responses. This paper gives an overview of
the project and the results achieved so far.
Original languageEnglish
Title of host publicationIEEE International Energy Conference ENERGYCON 2018
Subtitle of host publicationTowards Self-healing, Resilient and Green Electric Power and Energy Systems
PublisherInstitute of Electrical and Electronic Engineers IEEE
Number of pages6
ISBN (Electronic)978-1-5386-3669-5
ISBN (Print)978-1-5386-1283-5
DOIs
Publication statusPublished - 3 Jun 2018
MoE publication typeA4 Article in a conference publication
EventIEEE International Energy Conference, ENERGYCON 2018 - Limassol, Cyprus
Duration: 3 Jun 20187 Jun 2018
http://www.energycon2018.org/

Conference

ConferenceIEEE International Energy Conference, ENERGYCON 2018
Abbreviated titleENERGYCON 2018
CountryCyprus
CityLimassol
Period3/06/187/06/18
Internet address

Fingerprint

Electric loads

Keywords

  • forecasting
  • machine learning
  • physically based models
  • hybrid models
  • active demand
  • optimization

Cite this

Koponen, P., Hänninen, S., Niska, H., Kolehmainen, M., Mutanen, A., Rautiainen, A., ... Koivisto, H. (2018). Improved modelling of electric loads for enabling demand response by applying physical and data-driven models: project RESPONSE. In IEEE International Energy Conference ENERGYCON 2018: Towards Self-healing, Resilient and Green Electric Power and Energy Systems [19] Institute of Electrical and Electronic Engineers IEEE. https://doi.org/10.1109/ENERGYCON.2018.8398794
Koponen, Pekka ; Hänninen, Seppo ; Niska, Harri ; Kolehmainen, Mikko ; Mutanen, Antti ; Rautiainen, Antti ; Järventausta, Pertti ; Koivisto, Hannu. / Improved modelling of electric loads for enabling demand response by applying physical and data-driven models : project RESPONSE. IEEE International Energy Conference ENERGYCON 2018: Towards Self-healing, Resilient and Green Electric Power and Energy Systems. Institute of Electrical and Electronic Engineers IEEE, 2018.
@inproceedings{fa9f328764ae4da8b152ff4bfc85d638,
title = "Improved modelling of electric loads for enabling demand response by applying physical and data-driven models: project RESPONSE",
abstract = "Accurate load and response forecasts are a criticalenabler for high demand response penetrations and optimizationof responses and market actions. Project RESPONSE studies anddevelops methods to improve the forecasts. Its objectives are toimprove 1) load and response forecast and optimization modelsbased on both data- driven and physical modelling, and theirhybrid models, 2) utilization of various data sources such assmart metering data, weather data, measurements fromsubstations etc., and 3) performance criteria of load forecasting.The project applies, develops, compares, and integrates variousmodelling approaches including partly physical models, machinelearning, modern load profiling, autoregressive models, andKalman-filtering. It also applies non-linear constrainedoptimization to load responses. This paper gives an overview ofthe project and the results achieved so far.",
keywords = "forecasting, machine learning, physically based models, hybrid models, active demand, optimization",
author = "Pekka Koponen and Seppo H{\"a}nninen and Harri Niska and Mikko Kolehmainen and Antti Mutanen and Antti Rautiainen and Pertti J{\"a}rventausta and Hannu Koivisto",
year = "2018",
month = "6",
day = "3",
doi = "10.1109/ENERGYCON.2018.8398794",
language = "English",
isbn = "978-1-5386-1283-5",
booktitle = "IEEE International Energy Conference ENERGYCON 2018",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
address = "United States",

}

Koponen, P, Hänninen, S, Niska, H, Kolehmainen, M, Mutanen, A, Rautiainen, A, Järventausta, P & Koivisto, H 2018, Improved modelling of electric loads for enabling demand response by applying physical and data-driven models: project RESPONSE. in IEEE International Energy Conference ENERGYCON 2018: Towards Self-healing, Resilient and Green Electric Power and Energy Systems., 19, Institute of Electrical and Electronic Engineers IEEE, IEEE International Energy Conference, ENERGYCON 2018, Limassol, Cyprus, 3/06/18. https://doi.org/10.1109/ENERGYCON.2018.8398794

Improved modelling of electric loads for enabling demand response by applying physical and data-driven models : project RESPONSE. / Koponen, Pekka (Corresponding author); Hänninen, Seppo; Niska, Harri; Kolehmainen, Mikko; Mutanen, Antti; Rautiainen, Antti; Järventausta, Pertti; Koivisto, Hannu.

IEEE International Energy Conference ENERGYCON 2018: Towards Self-healing, Resilient and Green Electric Power and Energy Systems. Institute of Electrical and Electronic Engineers IEEE, 2018. 19.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Improved modelling of electric loads for enabling demand response by applying physical and data-driven models

T2 - project RESPONSE

AU - Koponen, Pekka

AU - Hänninen, Seppo

AU - Niska, Harri

AU - Kolehmainen, Mikko

AU - Mutanen, Antti

AU - Rautiainen, Antti

AU - Järventausta, Pertti

AU - Koivisto, Hannu

PY - 2018/6/3

Y1 - 2018/6/3

N2 - Accurate load and response forecasts are a criticalenabler for high demand response penetrations and optimizationof responses and market actions. Project RESPONSE studies anddevelops methods to improve the forecasts. Its objectives are toimprove 1) load and response forecast and optimization modelsbased on both data- driven and physical modelling, and theirhybrid models, 2) utilization of various data sources such assmart metering data, weather data, measurements fromsubstations etc., and 3) performance criteria of load forecasting.The project applies, develops, compares, and integrates variousmodelling approaches including partly physical models, machinelearning, modern load profiling, autoregressive models, andKalman-filtering. It also applies non-linear constrainedoptimization to load responses. This paper gives an overview ofthe project and the results achieved so far.

AB - Accurate load and response forecasts are a criticalenabler for high demand response penetrations and optimizationof responses and market actions. Project RESPONSE studies anddevelops methods to improve the forecasts. Its objectives are toimprove 1) load and response forecast and optimization modelsbased on both data- driven and physical modelling, and theirhybrid models, 2) utilization of various data sources such assmart metering data, weather data, measurements fromsubstations etc., and 3) performance criteria of load forecasting.The project applies, develops, compares, and integrates variousmodelling approaches including partly physical models, machinelearning, modern load profiling, autoregressive models, andKalman-filtering. It also applies non-linear constrainedoptimization to load responses. This paper gives an overview ofthe project and the results achieved so far.

KW - forecasting

KW - machine learning

KW - physically based models

KW - hybrid models

KW - active demand

KW - optimization

UR - http://www.scopus.com/inward/record.url?scp=85050244199&partnerID=8YFLogxK

U2 - 10.1109/ENERGYCON.2018.8398794

DO - 10.1109/ENERGYCON.2018.8398794

M3 - Conference article in proceedings

SN - 978-1-5386-1283-5

BT - IEEE International Energy Conference ENERGYCON 2018

PB - Institute of Electrical and Electronic Engineers IEEE

ER -

Koponen P, Hänninen S, Niska H, Kolehmainen M, Mutanen A, Rautiainen A et al. Improved modelling of electric loads for enabling demand response by applying physical and data-driven models: project RESPONSE. In IEEE International Energy Conference ENERGYCON 2018: Towards Self-healing, Resilient and Green Electric Power and Energy Systems. Institute of Electrical and Electronic Engineers IEEE. 2018. 19 https://doi.org/10.1109/ENERGYCON.2018.8398794