An ANN-based risk assessment method for carbon pricing

This paper proposes an efficient method for risk assessment of carbon pricing with artificial neural network (ANN). The global warming is of main concern in the world. The power industry wants to make generation planning more flexible through the emission trading system. In this paper, an ANN-based method is proposed to predict one-step-ahead carbon pricing. As ANN, the radial base function network (RBFN) is used to approximate the nonlinear function of time-series carbon pricing. To improve the performance of RBFN, this paper makes use of preconditioned RBFN in a way that DA (deterministic annealing) clustering classifies learning data into some clusters and RBFN is constructed at each cluster. In addition, DA clustering is used to determine the center vectors of the Gaussian function in RBFN. Also, the Monte Carlo simulation is applied to the risk assessment of carbon pricing with the RBFN model. The risk of one-step-ahead carbon pricing is evaluated in probability. The proposed method is successfully applied to real data of the carbon pricing market.

[1]  D. K. Ranaweera,et al.  Application of radial basis function neural network model for short-term load forecasting , 1995 .

[2]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[3]  Carbon Risk Management , 2006, 2006 International Conference on Probabilistic Methods Applied to Power Systems.

[4]  B. Ramsay,et al.  A neural network based estimator for electricity spot-pricing with particular reference to weekend and public holidays , 1998, Neurocomputing.

[5]  J. Contreras,et al.  ARIMA Models to Predict Next-Day Electricity Prices , 2002, IEEE Power Engineering Review.

[6]  Peter E. Hart,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[7]  Carlos E. Pedreira,et al.  Neural networks for short-term load forecasting: a review and evaluation , 2001 .

[8]  Marco van Akkeren,et al.  A GARCH forecasting model to predict day-ahead electricity prices , 2005, IEEE Transactions on Power Systems.

[9]  David S. Broomhead,et al.  Multivariable Functional Interpolation and Adaptive Networks , 1988, Complex Syst..

[10]  Geoffrey C. Fox,et al.  A deterministic annealing approach to clustering , 1990, Pattern Recognit. Lett..

[11]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[12]  A. Gjelsvik,et al.  Generation scheduling in a deregulated system. The Norwegian case , 1999 .

[13]  C. Rodriguez,et al.  Energy price forecasting in the Ontario competitive power system market , 2004, IEEE Transactions on Power Systems.

[14]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[15]  T. Dillon,et al.  Electricity price short-term forecasting using artificial neural networks , 1999 .

[16]  A. Papalexopoulos,et al.  Forecasting power market clearing price and quantity using a neural network method , 2000, 2000 Power Engineering Society Summer Meeting (Cat. No.00CH37134).