Abstract
Increasing shares of renewables in the energy matrix is linked to increased power price fluctuations, which, in turn, increases the financial risks for electricity market participants. In this context, understanding the key factors driving the power prices and thereby improving price forecasts is increasingly important. Here we analyze the main drivers of power prices with the help of machine learning. We show how the selection of the predictors set and length of historical data affect the forecast accuracy of the power prices. Using the developed model, we project how high energy and carbon prices may affect future electricity prices.
Original language | English |
---|---|
Journal | Energy Proceedings |
Volume | 25 |
DOIs | |
State | Published - 2022 |
Event | Applied Energy Symposium, MIT A+B 2022 - Cambridge, United States Duration: 5 Jul 2022 → 8 Jul 2022 |
Keywords
- Day-Ahead Market
- Electricity Price Forecasting
- Feature Selection
- Machine Learning