An Artificial Neural Network Approach for Short-Term Electric Prices Forecasting


Article Preview

In this paper, a forecasting system of electric price is proposed to predict the short-term electric prices for avoiding the risk due to the electricity price volatility. Based on the Back-propagation Neural Network(BPN) and Orthogonal Experimental Design(OED), a New Artificial Neural Network Approach(NANNA) is constructed in the searching process. The data cluster, including Locational Marginal Price(LMP), system load, temperature, line-flow, are first collected and embedded in the Excel Database. In order to get a better solution, the OED is used to automatically regulate the parameters during the NANNA training process. Linking the NANNA and Excel database, the NANNA retrieved the input data from Excel Database to perform and analyze the efficiency and accuracy of the predicting system until the forecasting system is convergent. Simulation results will provide the participants to obtain the maximal profits and raise its ability of market’s competition in a price volatility environment.



Edited by:

Yanwen Wu




M. T. Tsai and C. H. Chen, "An Artificial Neural Network Approach for Short-Term Electric Prices Forecasting", Advanced Materials Research, Vol. 267, pp. 985-990, 2011

Online since:

June 2011




[1] PJM Energy Management: http: /www. PJM. com/index. jsp.

[2] J. C. Cuaresma, J. Hlouskova, and M. Obersteimer, Forecasting electricity spot-prices using linear univariate time-series models, Applied Energy, vol. 77, pp.87-106, (2004).


[3] A. T. Lora, J. M. R. Santos, A. G. Expósito, J. L. M. Ramos, and J. C. R. Santos, Electricity market price forecasting based on weighted nearest neighbors techniques, , IEEE trans. on Power Systems , vol. 22 , no. 3, pp.1294-1301, August (2007).


[4] J. Contreras, F. J. Nogales, and A. J. Conejo, ARIMA models to predict next-day electricity prices, IEEE trans. on Power Systems, vol. 18, no. 3, pp.1014-1020, August (2003).


[5] P. Kosater and K. Mosler, Can Markov regime-switching models improve power-price forecasts? Evidence from German daily power prices, Applied Energy, vol. 83, pp.943-958, (2006).


[6] P. Mandal, T. Senjyu, N. Urasaki, T. Funabshi, and A. K. Srivastava, A novel approach to forecast electricity price for PJM using neural network and similar days method, IEEE trans. on Power Systems, vol. 22 , no. 4 , pp.2058-2065, November (2007).


[7] J. P. S. Catalão, S. J. P. S. Mariano, V. M. F. Mendes, and L. A. F. M. Ferreira, An artificial neural network approach for short-term electricity prices forecasting, , The 14th international conference on intelligent system applications to power systems, ISPA , Kaohsiung , Taiwan, pp.430-435, November (2007).


[8] H. T. Pao, Forecasting electricity market pricing using artificial neural networks, Energy Conversion and Management, vol. 48, pp.907-912, (2007).


[9] R. Pino, J. Parreno, A. Gomez, and P. Priore, Forecasting net-day Price of Electricity in the Spanish Energy market Using Artificial Neural Networks, Engineering Applications of Artificial Intelligence, Vol. 21, pp.53-62, (2008).


[10] Chia-Hung Lin and Ming-Chieh Tsao, Power Quality Detection with Classification Enhancible Wavelet-Probabilistic Network in a Power System, IEE Proceedings-Generation, Transmission, and Distribution, Vol. 152, No. 6, November 2005, pp.969-976.


[11] F. M. Ham and I. Kostanic, Principal of Neurocomputing for Science and Engineering, McGraw-Hill Companies, Inc., (2001).

[12] Phillip J. Ross, Taguchi Techniques for Quality Engineering, Section Edition, The McGraw-Hill Companies, Inc., 1988, pp.203-243.