A Neural Network Approach for forecoasting Price Load Curves in Electricity Markets
Masterarbeit Wirtschaftsmathematik
Supervision
Description
This thesis concentrates on the spot market for electrical power.
This is a physical market where the supply of electrical power is traded.
The prices used in this thesis have been obtained from the European
Power Exchange (EPEX) SPOT and older prices from the European Energy Exchange
(EEX) respectively. The EPEX SPOT created in 2008 from the
EEX (Leipzig) and Powernext (Paris) covers the German, French, Austrian and
Swiss market. At the EPEX SPOT it is possible to trade day-ahead or intra day. In this
thesis we concentrate on the prices for day-ahead auctions in Germany. At day-ahead
auctions the power for each single hour and for blocks of hours can be bought. The
supply and demand for this determines the prices for the next day.
Keywords
References:
- G.E.P. Box and G.M. Jenkins,
Time Series Analysis - Forecasting and Control,
San Francisco: Holden-Day, 1970.
- M. Burger, B. Klar, A. Müller and G. Schindlmayr,
A spot market model for pricing derivatives in electricity markets,
Quantitative Finance 4 (2004), 109-122.
- J.L. McClelland and D.E. Rumelhart,
Parallel distributed processing: Explorations in the microstructure of cognition,
MIT Press, Cambridge 1986.
- M. Minsky and S. Papert,
Perceptrons: An introduction to computational geometry,
MIT Press, Cambridge, Massachusetts, 1969.
- J. Shadbolt and J.G. Taylor,
Neural Networks and the Financial Markets,
Springer, 2002.
- P.J. Werbos,
Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences,
PhD thesis, Harvard University, 1974.
- P. Werneburg,
Determination of the price-load curve by using smoothing splines
under tension,
Master's thesis, University of Wuppertal, 2008.
