Trading in a deregulated electricity market using machine learning
Speaker: Andrei Hryshko, ITEE
When: 2003-05-15 13:00:00
Venue: 78-622
Host: Prof. Tom Downs
Abstract:Electricity trading has emerged in recent times as a significant
activity in many countries following the deregulation of the power
industry. As with most forms of trading, the activity is influenced
by many random parameters so that the creation of a system that
effectively emulates the trading process will be very helpful.
Machine learning is an extremely powerful technique for reasoning
under uncertainty. It can be used in a range of practical
applications concerned with the prediction of the behaviour of
complex random systems.
The power of machine learning systems comes from the fact that they
are able to learn from data and to generalize on the knowledge they
acquire, that is to generate correct outputs for input data that
were not employed in the system training process. During training
the parameters of the learning system are modified so that the
machine adapts its behaviour in order to deal with the given data in
a satisfactory fashion. The machine learning technique can therefore
be considered as an information processing system, but one that
employs rather unconventional computing methods.
The goal of this work will be to create a system for trading in a
deregulated electricity market using machine learning techniques. It
is expected that various refinements, based upon statistical
methodologies, will need to be applied to achieve optimum
performance.
Biography:(biography unavailable)
Type: Ph.D confirmation
Contact:Prof. Tom Downs, seminar host (td@itee.uq.edu.au)
or Guido Governatori (ITEE seminar co-ordinator)
(guido@itee.uq.edu.au)