Development of Neural Network Prediction Model of Energy Consumption

In the oil and gas industry, energy prediction can help the distributor and customer to forecast the outgoing and incoming gas through the pipeline. It will also help to eliminate any uncertainties in gas metering for billing purposes. The objective of this paper is to develop Neural Network Model for energy consumption and analyze the performance model. This paper provides a comprehensive review on published research on the energy consumption prediction which focuses on structures and the parameters used in developing Neural Network models. This paper is then focused on the parameter selection of the neural network prediction model development for energy consumption and analysis on the result. The most reliable model that gives the most accurate result is proposed for the prediction. The result shows that the proposed neural network energy prediction model is able to demonstrate an adequate performance with least Root Mean Square Error.

Authors:

• Maryam Jamela Ismail
• Rosdiazli Ibrahim
• Idris Ismail

Keywords:

• Energy Prediction
• Multilayer Feedforward
• Levenberg-Marquardt
• Root Mean Square Error (RMSE)

References:

[1] H. R.Maier and G. C.Dandy, "Neural network for the prediction and
forecasting of water resources variables: a review of modelling issues
and applications," Environmental Modelling & Software, vol. 15, 2000,
pp. 101-124.
[2] P. Benardos and G. Vosniakos, "Optimizing feedforward artificial neural
network architecture," Engineering Applications of Artificial
Intelligence, vol. 20, Apr. 2007, pp. 365-382.
[3] M. N Jamal, M. E Ibrahim, and A. N Salam, "Multilayer Perceptron
Neural Network (MLPs) For Analyzing the Properties of Jordan Oil
Shale," World Applied Sciences Journal, vol. 5, 2008, pp. 546-552.
[4] D. Ivezić, "Short-Term Natural Gas Consumption
Forecast," FME Transactions, vol. 34, 2006, pp. 165-169.
[5] R. Kizilaslan and B. Karlik, "Comparison neural networks models for
short term forecasting of natural gas consumption in Istanbul,"
Applications of Digital Information and Web Technologies, 2008.
ICADIWT 2008., 2008, pp. 448-453.
[6] K. Kavaklioglu, H. Ceylan, H.K. Ozturk, and O.E. Canyurt, "Modeling
and prediction of Turkey's electricity consumption using Artificial
Neural Networks," Energy Conversion and Management, vol. 50, Nov.
2009, pp. 2719-2727.
[7] D. Peharda, M. Delimar, and S. Loncaric, "Short term hourly forecasting
of gas consumption using neural networks," Information Technology
Interfaces, 2001. ITI 2001. Proceedings of the 23rd International
Conference on, 2001, pp. 367-371.
[8] A. Khotanzad and H. Elragal, "Natural gas load forecasting with
combination of adaptive neural networks," Neural Networks, 1999.
IJCNN '99. International Joint Conference on, 1999, pp. 4069-4072
vol.6.
[9] R. Brown and I. Matin, "Development of artificial neural network
models to predict daily gas consumption," Industrial Electronics,
Control, and Instrumentation, 1995., Proceedings of the 1995 IEEE
IECON 21st International Conference on, 1995, pp. 1389-1394 vol.2.
[10] P. Musilek, E. Pelikán, T. Brabec, and M. Simunek, "Recurrent Neural
Network Based Gating for Natural Gas Load Prediction System," Neural
Networks, IJCNN'06, 2006, pp. 3736-3741.
[11] Nguyen Hoang Viet and J. Mandziuk, "Neural and fuzzy neural
networks for natural gas consumption prediction," Neural Networks for
Signal Processing, 2003. NNSP'03. 2003 IEEE 13th Workshop on, 2003,
pp. 759-768.
[12] R. Brown, P. Kharouf, Xin Feng, L. Piessens, and D. Nestor,
"Development of feed-forward network models to predict gas
consumption," Neural Networks, 1994. IEEE World Congress on
Computational Intelligence., 1994 IEEE International Conference on,
1994, pp. 802-805 vol.2.
[13] A. Khotanzad, H. Elragal, and T. Lu, "Combination of artificial neuralnetwork
forecasters for prediction of natural gas consumption," Neural
Networks, IEEE Transactions on, vol. 11, 2000, pp. 464-473.
[14] L. Xu, W. Zhou, X. Li, and S. Tang, "Wet Gas Metering Using a
Revised Venturi Mete and Soft-Computing Approximation Techniques,"
IEEE Transactions on Instrumentation and Measurement, vol. 60, Mar.
2011.
[15] J. Fidalgo and M. Matos, "Forecasting Portugal Global Load with
Artificial Neural Networks," Artificial Neural Networks - ICANN 2007,
Springer Berlin / Heidelberg, 2007, pp. 728-737.
[16] A. Bakirtzis, J. Theocharis, S. Kiartzis, and K. Satsios, "Short term load
forecasting using fuzzy neural networks," Power Systems, IEEE
Transactions on, vol. 10, 1995, pp. 1518-1524.
[17] Z. Li, G. Zhang, D. Li, X. Liu, S. Mei, and J. Wu, "Neural network
prediction of energy demand and supply in China," Proceedings of the
Institution of Civil Engineers - Energy, vol. 160, 2007, pp. 145-149.
[18] L.M. Saini, "Peak load forecasting using Bayesian regularization,
Resilient and adaptive backpropagation learning based artificial neural
networks," Electric Power Systems Research, vol. 78, Jul. 2008, pp.
1302-1310.
[19] B. Kermanshahi and H. Iwamiya, "Up to year 2020 load forecasting
using neural nets," International Journal of Electrical Power & Energy
Systems, vol. 24, Nov. 2002, pp. 789-797.
[20] H. Hippert, C. Pedreira, and R. Souza, "Neural networks for short-term
load forecasting: a review and evaluation," Power Systems, IEEE
Transactions on, vol. 16, 2001, pp. 44-55.
[21] J.J. Moré, "The Levenberg-Marquardt algorithm: Implementation and
theory," Numerical Analysis, Springer Berlin / Heidelberg, 1978, pp.
105-116.
[22] G. Welch and G. Bishop, An Introduction to the Kalman Filter,
University of North Carolina Chapel Hill, 2006.
[23] D.J.C. MacKay, "Bayesian Interpolation," Neural Computation, vol. 4,
1992, pp. 415-447.
[24] M. Riedmiller and H. Braun, "A direct adaptive method for faster
backpropagation learning: the RPROP algorithm," Neural Networks,
1993., IEEE International Conference on, 1993, pp. 586-591 vol.1.
[25] P. Baldi, "Gradient descent learning algorithm overview: a general
dynamical systems perspective," Neural Networks, IEEE Transactions
on, vol. 6, 1995, pp. 182-195.