Abstract
This paper examines the application of artificial neural networks (ANNs) to the modelling and forecasting of electricity demand experienced by an electricity supplier. The data used in the application examples relates to the national electricity demand in the Republic of Ireland, generously supplied by the Electricity Supply Board (ESB). The paper focusses on three different time scales of interest to power boards: yearly (up to fifteen years in advance), weekly (up to three years in advance) and hourly (up to 24 h ahead). Electricity demand exhibits considerably different characteristics on these different time scales, both in terms of the underlying autoregressive processes and the causal inputs appropriate to each time scale. Where possible, the ANN-based models draw on the applications experience gained with linear modelling techniques and in one particular case, manual forecasting methods.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Al-Alawi, S. M. and Islam, S. M.: Principles of electricity demand forecasting-Part 1: Methodologies, Power Engineering J. (June 1996).
Al-Anbuky, A., Bataineh, S., and Al-Aqtash, S.: Power demand prediction using fuzzy logic, Control Engrg Practice 3(9) (1995).
Azzam-ul-Asar and McDonald, J. R.: A specification of neural network applications in the load forecasting problem, IEEE Trans. Control Systems Techn. 2(2) (June 1994).
Bowerman, B. and O'Connell, R.: Time Series Forecastig-Unified Concepts and Computer Implementations, Duxbury Press, 1987.
Box, G. and Jenkins, G.: Time Series Analysis, Forecasting and Control, Holden-Day, San Francisco, CA, 1976.
Bruce, A., Jurke, S., and Thomson, P.: Forecasting load-duration curves, J. Forecasting 13 (1994).
Bunn, D. W. and Farmer, E. D. (eds): Comparative Models for Electrical Load Forecasting, Wiley, New York, 1985.
Chakraborty, K., Mehrotra, K., Mohan, C. K., and Ranka, S.: Forecasting the behaviour of multivariate time series using neural networks, Neural Networks 5 (1992) 961-970.
Commarmond, P. and Ringwood, J. V.: Quantitative fuzzy modelling of short-time-scale electricity consumption, in: Proc. of Irish Signals and Systems Conf. (ISSC'97), Derry, June 1997.
Dorffner, G.: Neural networks for time series processing, Neural Network World 6 (1996).
El-Sharkawi, M. A., Marks II, R. J., Oh, S., and Brace, C. M.: Data partitioning for training a layered perceptron to forecast electric load, in: Proc. of the 2nd IEEE Internat. Forum on Appl. of Neural Networks to Power Systems, Yokohama, 1993.
Gunel, I. Forecasting system energy demand, J. Forecasting 6 (1987).
Harvey, A. C.: A unified view of statistical forecasting proceedures, J. Forecasting 3 (1984) 245-275.
Harvey, A. C.: Structural Time Series Models and the Kalman Filter, Cambridge Univ. Press, Cambridge, 1989.
Kermanshahi, B. S., Poskar, C. H., Swift, G., McLaren, P., Pedrycz, W., Buhr,W., and Silk, A.: Artificial neural network for forecasting daily loads of a Canadian electric utility, in: Proc. of the 2nd IEEE Internat. Forum on Appl. of Neural Networks to Power Systems, Yokohama, 1993.
Kuschewski, J. G., Hui, S., and Zak, S.: Application of feedforward neural networks to dynamical system identification and control, IEEE Trans. Control Systems Techn. 1(1) (March 1993).
Lee, K. Y., Choi, T. I., Ku, C. C., and Park, J. H.: Short-term load forecasting using diagonal recurrent neural network, in: Proc. of the 2nd IEEE Internat. Forum on Appl. of Neural Networks to Power Systems, Yokohama, 1993.
Ljung, L.: System Identification: Theory for the User, Prentice-Hall, Englewood Clifs, NJ, 1987.
Lonergan, T. and Ringwood, J. V.: Linguistic modelling of short-timescale electricity comsumption using fuzzy modelling techniques, in: Proc. of Irish DSP and Control Colloquium (IDSPCC'95), Belfast, June 1995.
Mitchell, J.: Comparing feedforward neural network models for time series prediction, in: Proc. of Conf. on Neural Computing Research and Applications, Belfast, June 1992.
Murray, F. T., Ringwood, J. V., and Austin, P. C.: Integration of multi-time-scale models in time series forecasting, Internat. J. of Systems Sci. 31(10) (2000).
Murray, F. T. and Ringwood, J. V.: Improvement of electricity consumption forecasts using temperature inputs, Simulation Practice Theory 2 (1994).
Ng, N. C. and Young, P. C.: Recursive estimation and forecasting of non-stationary time series, J. Forecasting 9 (1990).
Park, D. C., El-Sharkawi, M. A., Marks II, R. J., Atlas, L. E., and Damborg, M. J.: Electricity load forecasting using an artificial neural network, IEEE Trans. Power Systems 6(2) (May 1991).
Watson, M. W., Pastuszek, L. M., and Cody, E.: Forecasting commercial electricity sales, J. Forecasting 6 (1987).
Weigend, A. S. and Gerschenfeld, N. A.: Time Series Prediction: Forecasting the Future and Understanding the Past, Addison-Wesley, Reading, MA, 1992.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Ringwood, J.V., Bofelli, D. & Murray, F.T. Forecasting Electricity Demand on Short, Medium and Long Time Scales Using Neural Networks. Journal of Intelligent and Robotic Systems 31, 129–147 (2001). https://doi.org/10.1023/A:1012046824237
Issue Date:
DOI: https://doi.org/10.1023/A:1012046824237