Knowledge Extraction and Data Mining for the Competitive Electricity Auction Market

The transition from a vertically integrated industry to a horizontally integrated open market system changes the operational planning activities of generation companies (GENCOs). This transition, along with the strategic bidding decision process that must be employed by a GENCO, changes the objective from cost minimization to profit maximization. This change requires considering not only the technical aspects of unit operation, such as capacity limits, but also information about other market participants and the volatility of market prices. These additional factors are significant, especially in an oligopolistic market, because they influence the amount of electricity bought and sold, thus affecting net profit. This paper proposes an approach that data mines historical and current market data. The context is a deterministic four-market-participant environment. This model uses an auction simulator for 120 time periods. Results suggest that the data mining approach be extended to the reduction of epistemic uncertainty in VaR/PaR inferences using information gap theory

[1]  S. Stoft.  Power System Economics: Designing Markets for Electricity , 2002 .

[2]  J. R. Quinlan.  Learning With Continuous Classes , 1992 .

[3]  Daniel Berleant,et al.  Statool: A Tool for Distribution Envelope Determination (DEnv), an Interval-Based Algorithm for Arithmetic on Random Variables , 2003, Reliab. Comput..

[4]  G. Sheblé.  Computational Auction Mechanisms for Restructured Power Industry Operation , 1999 .

[5]  A. David,et al.  Strategic bidding in competitive electricity markets: a literature survey , 2000, 2000 Power Engineering Society Summer Meeting (Cat. No.00CH37134).

[6]  Ian H. Witten,et al.  Induction of model trees for predicting continuous classes , 1996 .

[7]  A. David,et al.  Optimal bidding strategies and modeling of imperfect information among competitive generators , 2001 .

[8]  Bruce Hannon,et al.  Modeling Dynamic Economic Systems , 1997, Modeling Dynamic Systems.

[9]  R. McAfee,et al.  Auctions and Bidding , 1986 .

[10]  Yong Wang,et al.  Using Model Trees for Classification , 1998, Machine Learning.

[11]  Daniel Ashlock,et al.  Comprehensive bidding strategies with genetic programming/finite state automata , 1999 .

[12]  S. Stoft.  Power System Economics: Designing Markets for Electricity , 2002 .

[13]  Scott Ferson,et al.  Constructing Probability Boxes and Dempster-Shafer Structures , 2003 .

[14]  W W Daniel,et al.  An introduction to decision analysis. , 1978, The Journal of nursing administration.

[15]  Fushuan Wen,et al.  Development of bidding strategies in electricity markets using possibility theory , 2002, Proceedings. International Conference on Power System Technology.

[16]  Haili Song,et al.  Optimal electricity supply bidding by Markov decision process , 2000 .

[17]  S. Ferson,et al.  Different methods are needed to propagate ignorance and variability , 1996 .

[18]  D. Berleant,et al.  Information gap decision theory as a tool for strategic bidding in competitive electricity markets , 2004, 2004 International Conference on Probabilistic Methods Applied to Power Systems.

[19]  G. Sheblé,et al.  Genetic algorithm evolution of utility bidding strategies for the competitive marketplace , 1998 .

[20]  Yakov Ben-Haim,et al.  Information-gap decision theory , 2001 .