Time Series Analysis and Data Prediction of Large Databases: An Application to Electricity Demand Prediction

Abstract:

We evaluate statistical and machine learning methods for half-hourly 1-step-ahead electricity demand prediction using Australian electricity data. We show that the machine learning methods that use autocorrelation feature selection and BackPropagation Neural Networks, Linear Regression as prediction algorithms outperform the statistical methods Exponential Smoothing and also a number of baselines. We analyze the effect of day time on the prediction error and show that there are time-intervals associated with higher and lower errors and that the prediction methods also differ in their accuracy during the different time intervals. This analysis provides the foundation for construction a hybrid prediction model that achieved lower prediction error. We also show that an RBF neural network trained by genetic algorithm can achieved better prediction results than classic one. The aspect of increased transparency of networks through genetic evolution development features and granular computation is another essential topic promoted by knowledge discovery in large databases.

• Periodical: Advanced Materials Research (Volume 811)
• Pages: 401-406
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.811.401
• Online since: September 2013
• Authors: Dusan Marcek
• Keywords: ARIMA Model, Electricity Load Forecast, Forecast Accuracy, Machine Learning (ML), RBF Neural Network, Time Series Analysis

References

[1] J.W. Taylor: Short-term electricity demand forecasting using double seasonal exponential smoothing, Journal of the Operational Research Society, Vol. 54 (2003), pp: 799-805.

DOI: 10.1057/palgrave.jors.2601589

[2] Information on www. aemo. com. au.

[3] R. Sood, I. Koprinska, V. Agelidis: Electricity load forecasting based on autocorrelation analysis, in: Proc. of. Int. Joint Conf. Neural Networks (IJCNN), Barcelona, pp.1772-1779 (2010).

DOI: 10.1109/ijcnn.2010.5596877

[4] F. Sahin: A Radial Basis Function Approach to a Color Image Classification Problem in a Real Time Industrial Application, Master's thesis, Virginia polytechnic institute, Blacksburg, (1997).

[5] R.E. Rumelhart, J.L. McClelland, & the PDP Research Group: Parallel distributed processing explorations in the microstructure of cognition. Cambridge: MIT Press (1980).

DOI: 10.21825/philosophica.82503

[6] D. Goldberg: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley Professional (1989).

[7] CH.M. Bishop: Neural Networks for Pattern Recognition. New York, Oxford University Press Inc. (1995).

[8] V. Kecman: Learning and soft computing: support vector machines, neural networks, and fuzzy logic. Massachusetts, The MIT Press (2001).

DOI: 10.1016/s0925-2312(01)00685-3

[9] A. Reyaz-Ahmed, Y-Q. Zhang, R.W. Haison: Granular Decision Tree and Evolutionary Neural SVM for Protein Secondary Structure Prediction, Journal of Computational Itelligence Systems, 2(1-4) (2009) pp.343-352.

DOI: 10.1080/18756891.2009.9727666