Electricity Market Prediction Using Improved Neural Network

General analysis of Electricity markets shows that development and improvement of predicting price solutions play a vital role in increasing the profit of generators and also causes better and high operation for consumers. Also long-term prediction of market declaration in power system is one of the most essential and fundamental needs of any decision making in market including generation expansion planning (GEP) which has brought about uncertainties due to restructuring. In this paper an improved neural network with back propagations error mechanism is applied to predict market price. The proposed initial neural network is a three layer Perceptron that back propagations error algorithm using Lumberg-Markwart and apply to speed up its training and accuracy. To reduce error and improve proposed neural network operation, a multiple neural network is presented using classification of input data with fuzzy methods and finally from PJM electricity market data used to validate proposed method. Results demonstrate that the introduced solution has an exact and reliable prediction of market clearing price not only in short-time scheduling by electricity generating companies, but also in long-term scheduling, including generating development scheduling. Key word: Neural network, Electricity market, Price prediction, Fuzzy logic, Lumberg-Markwart back propagation method.

[1]  Y.-y. Hong,et al.  Locational marginal price forecasting in deregulated electricity markets using artificial intelligence , 2002 .

[2]  Zuyi Li,et al.  Market Operations in Electric Power Systems : Forecasting, Scheduling, and Risk Management , 2002 .

[3]  J. Contreras,et al.  Forecasting Next-Day Electricity Prices by Time Series Models , 2002, IEEE Power Engineering Review.

[4]  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).

[5]  D. Gan,et al.  Price forecasting using an integrated approach , 2004, 2004 IEEE International Conference on Electric Utility Deregulation, Restructuring and Power Technologies. Proceedings.

[6]  B. Ramsay,et al.  Prediction of system marginal price in the UK Power Pool using neural networks , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[7]  A.J. Conejo,et al.  Day-ahead electricity price forecasting using the wavelet transform and ARIMA models , 2005, IEEE Transactions on Power Systems.

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

[9]  A.M. Gonzalez,et al.  Modeling and forecasting electricity prices with input/output hidden Markov models , 2005, IEEE Transactions on Power Systems.

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

[11]  M. P. Moghaddam,et al.  A price guideline for generation expansion planning in competitive electricity markets , 2005, IEEE Power Engineering Society General Meeting, 2005.