Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Using Dynamic Double Machine Learning for Guided District Heating Forecasting and Physical Parameter Extraction

Smertinas, Justinas LU (2022) In Master's Theses in Mathematical Sciences MASM02 20221
Mathematical Statistics
Abstract
This thesis’ main goals were to provide accurate forecasts and informative physical parameter estimates for energy use of the district heating in the Tingbjerg neighborhood, Copenhagen. Our work is aimed as a contribution for future work towards efficient on-demand energy production.
We applied Dynamic Double Machine Learning to estimate the causal effects of weather observations on energy use. These results were used as a reference for feature selection for Dense-LSTM and ARMAX models. Dense-LSTM networks were used for 24 (hour) step ahead predictive modeling. ARMAX models were employed for physical characteristic estimation.
According to Dynamic DML, we have found the most impactful weather observations to be ambient temperature, solar... (More)
This thesis’ main goals were to provide accurate forecasts and informative physical parameter estimates for energy use of the district heating in the Tingbjerg neighborhood, Copenhagen. Our work is aimed as a contribution for future work towards efficient on-demand energy production.
We applied Dynamic Double Machine Learning to estimate the causal effects of weather observations on energy use. These results were used as a reference for feature selection for Dense-LSTM and ARMAX models. Dense-LSTM networks were used for 24 (hour) step ahead predictive modeling. ARMAX models were employed for physical characteristic estimation.
According to Dynamic DML, we have found the most impactful weather observations to be ambient temperature, solar radiation, wind speed, rainfall and relative humidity, in this order. We found Dense-LSTM networks to be superior to their LSTM counterpart and provide highly accurate predictions. Lastly, by using ARMAX models we were able to extract informative physically
interpretable parameters such as heat loss coefficients, solar gain and diurnal curves, all of which describe heat demand of different building groups under 24hr period. (Less)
Please use this url to cite or link to this publication:
author
Smertinas, Justinas LU
supervisor
organization
alternative title
Kausal Maskininlärning för Prediktion och Fysikalisk Förståelse av Fjärrvärmesystem
course
MASM02 20221
year
type
H2 - Master's Degree (Two Years)
subject
keywords
Double Machine Learning, Time Series, District Heating, ARMAX, Forecasting, Solar Gain, Diurnal Effects
publication/series
Master's Theses in Mathematical Sciences
report number
LUNFMS-3114-2022
ISSN
1404-6342
other publication id
2022:E57
language
English
id
9095300
date added to LUP
2022-08-15 17:51:48
date last changed
2022-08-15 18:21:37
@misc{9095300,
  abstract     = {{This thesis’ main goals were to provide accurate forecasts and informative physical parameter estimates for energy use of the district heating in the Tingbjerg neighborhood, Copenhagen. Our work is aimed as a contribution for future work towards efficient on-demand energy production.
We applied Dynamic Double Machine Learning to estimate the causal effects of weather observations on energy use. These results were used as a reference for feature selection for Dense-LSTM and ARMAX models. Dense-LSTM networks were used for 24 (hour) step ahead predictive modeling. ARMAX models were employed for physical characteristic estimation.
According to Dynamic DML, we have found the most impactful weather observations to be ambient temperature, solar radiation, wind speed, rainfall and relative humidity, in this order. We found Dense-LSTM networks to be superior to their LSTM counterpart and provide highly accurate predictions. Lastly, by using ARMAX models we were able to extract informative physically
interpretable parameters such as heat loss coefficients, solar gain and diurnal curves, all of which describe heat demand of different building groups under 24hr period.}},
  author       = {{Smertinas, Justinas}},
  issn         = {{1404-6342}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Master's Theses in Mathematical Sciences}},
  title        = {{Using Dynamic Double Machine Learning for Guided District Heating Forecasting and Physical Parameter Extraction}},
  year         = {{2022}},
}