- author = "Alberto Bartoli and Giorgio Davanzo and Andrea {De Lorenzo} and Eric Medvet",
- title = "GP-based Electricity Price Forecasting",
- booktitle = "Proceedings of the 14th European Conference on Genetic Programming, EuroGP 2011",
- year = "2011",
- month = "27-29 " # apr,
- editor = "Sara Silva and James A. Foster and Miguel Nicolau and Mario Giacobini and Penousal Machado",
- series = "LNCS",
- volume = "6621",
- publisher = "Springer Verlag",
- address = "Turin, Italy",
- pages = "37--48",
- organisation = "EvoStar",
- keywords = "genetic algorithms, genetic programming",
- isbn13 = "978-3-642-20406-7",
-
DOI = "
doi:10.1007/978-3-642-20407-4_4",
-
abstract = "The electric power market is increasingly relying on
competitive mechanisms taking the form of day-ahead
auctions, in which buyers and sellers submit their bids
in terms of prices and quantities for each hour of the
next day. Methods for electricity price forecasting
suitable for these contexts are crucial to the success
of any bidding strategy. Such methods have thus become
very important in practice, due to the economic
relevance of electric power auctions.
In this work we propose a novel forecasting method based on Genetic Programming. Key feature of our proposal is the handling of outliers, i.e., regions of the input space rarely seen during the learning. Since a predictor generated with Genetic Programming can hardly provide acceptable performance in these regions, we use a classifier that attempts to determine whether the system is shifting toward a difficult-to-learn region. In those cases, we replace the prediction made by Genetic Programming by a constant value determined during learning and tailored to the specific subregion expected.
We evaluate the performance of our proposal against a challenging baseline representative of the state-of-the-art. The baseline analyses a real-world dataset by means of a number of different methods, each calibrated separately for each hour of the day and recalibrated every day on a progressively growing learning set. Our proposal exhibits smaller prediction error, even though we construct one single model, valid for each hour of the day and used unmodified across the entire testing set. We believe that our results are highly promising and may open a broad range of novel solutions.",
- notes = "Part of \cite{Silva:2011:GP} EuroGP'2011 held in conjunction with EvoCOP2011 EvoBIO2011 and EvoApplications2011",
