Contact person: Fred Espen Benth
Keywords: Renewable energy, signatures, deep learning, volatility modelling, calibration
Research group: Risk and Stochastics
Department of Mathematics
The production of renewable energy is growing world-wide, and power production is becoming increasingly dependent on weather factors like solar irradiation, wind and precipitation, all of which are hard to forecast. 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. Already within energy markets, machine learning has shown great potential in terms of price forecasting, load and demand forecasting, but also for option pricing and hedging.
We are interested in research proposals that are directed towards the theoretical and the computational aspects of the modelling of environmental factors and their impact on energy systems and markets. The research proposals may span several methodological approaches within stochastic control, optimisation, and computational methods, as well as a number of application domains.
Methodological research topics:
- Neuronal stochastic differential equations for weather and price dynamics
- Assessment of weather extremes and impact of energy market and systems
- Data driven methods for price dynamics via deep learning towards arbitrage free pricing
- Volatility modelling and risk management in energy markets
- Deep learning/Machine learning for pricing of energy derivatives in finite and infinite dimensions
Application domains:
- Energy systems, energy markets, risk assessments
- Derivatives pricing
- Sustainability
External partner:
- Statkraft
