Abstract
The energy and power sector is a major value contributor to our society and our high
living standards. In recent times the power sector has gained increased complexity
while undergoing significant changes, with the increased share of renewable production
being one of the contributors. An increased portion of renewable contributors in the
power mix from, e.g., wind power, results in more volatile power production, increasing
the need for grid balancing, making the regulating power market more challenging
for power producers to participate in. The purpose of the regulating power market
is to compensate the gap between the planned production that has been settled in
the day-ahead market and the actual production and demand. The ability to forecast
the regulating power volumes and prices some hours in advance of the hour when
it is actually traded would enable power producers to balance their positions in the
market more optimally. This project exploits historical regulation data together with
different market data and weather data to train deep learning models to forecast future
regulation volumes. A thorough time-series analysis of regulating power volumes
revealed some predictive potential. Furthermore, Bidirectional LSTM showed satisfying
results when forecasting up to four hours into the future using data from 2016-to 2021.
No previous research was found that uses more than two years of data, no previous
research uses recent data, and no previous work has utilized deep learning to forecast
the Norwegian regulation market volumes. Additionally, this project did a deep analysis
of topographical weather images and transfer learning to evaluate the potential of
predicting regulating power volumes using weather images. Different weather forecasts,
actual weather, and weather uncertainties were all utilized. The weather data was
generally not found to have a considerable direct influence on regulation volumes.
However, the weather is considered to have an increasing influence in the future as more
volatile renewable power production is expected in the power markets. No previous
research has been found to investigate weather images in the context of the regulation
market.
living standards. In recent times the power sector has gained increased complexity
while undergoing significant changes, with the increased share of renewable production
being one of the contributors. An increased portion of renewable contributors in the
power mix from, e.g., wind power, results in more volatile power production, increasing
the need for grid balancing, making the regulating power market more challenging
for power producers to participate in. The purpose of the regulating power market
is to compensate the gap between the planned production that has been settled in
the day-ahead market and the actual production and demand. The ability to forecast
the regulating power volumes and prices some hours in advance of the hour when
it is actually traded would enable power producers to balance their positions in the
market more optimally. This project exploits historical regulation data together with
different market data and weather data to train deep learning models to forecast future
regulation volumes. A thorough time-series analysis of regulating power volumes
revealed some predictive potential. Furthermore, Bidirectional LSTM showed satisfying
results when forecasting up to four hours into the future using data from 2016-to 2021.
No previous research was found that uses more than two years of data, no previous
research uses recent data, and no previous work has utilized deep learning to forecast
the Norwegian regulation market volumes. Additionally, this project did a deep analysis
of topographical weather images and transfer learning to evaluate the potential of
predicting regulating power volumes using weather images. Different weather forecasts,
actual weather, and weather uncertainties were all utilized. The weather data was
generally not found to have a considerable direct influence on regulation volumes.
However, the weather is considered to have an increasing influence in the future as more
volatile renewable power production is expected in the power markets. No previous
research has been found to investigate weather images in the context of the regulation
market.
