Risk management in renewable energy markets
Contact person: Fred Espen Benth
Keywords: Renewable energy, wind and solar production, weather risk modeling, deep learning, stochastic processes in time and space
Research group: Risk and Stochastics
Department of Mathematics
The production of renewable energy is growing world-wide, and power markets are becoming increasingly dependent on weather factors like solar irradiation, wind and precipitation on the supply side. The demand for power is temperature-dependent. This causes power prices to change rapidly and unpredictably, and makes the modelling of financial risk in energy markets challenging. At the same time, machine learning techniques are replacing classical methods within scientific computing, with the promise of accurate results with reasonably short computational effort.
We are interested in research proposals that are directed towards the theoretical and the computational aspects of the modelling of weather factors and power prices (including multi-commodity), and their impact on systems and markets. We have in mind pricing of flexibility like batteries, use of hedging tools, assessment of renewable production and power purchase agreements, to mention some. The research proposals may span several methodological approaches within stochastic modeling, control and optimisation, and computational methods, as well as a number of application domains.
Methodological research topics:
- Neuronal stochastic differential equations for weather and price dynamics in space and time
- Assessment of weather extremes and impact of energy market and systems
- Volatility modelling and risk management in energy markets
- Deep learning for pricing of energy derivatives in finite and infinite dimensions
- Re-inforcement learning and other machine learning techniques in optimization
Application domains:
- Energy systems, energy markets, risk management and pricing
External partners:
- Statkraft
Mentoring and internship will be offered by a relevant external partner