Parametric Model Based Approach for Consumer Load Prediction
Keywords:Autoregressive, autoregressive moving average, consumer load prediction, power distribution network, Prony method.
AbstractVarious load prediction techniques have been proposed to predict consumer load which represents the activities of the consumer on the distribution network. Usually, these techniques use cumulative energy consumption data of the consumers connected to the power network to predict consumer load. However, this data fails to reveal and monitor the activities of individual consumers represented by consumer load consumption pattern. A new approach of predicting individual consumer load based on autoregressive moving average model (ARMA) is proposed in this study. Sub- optimal technique of parameter estimation based on Prony method was used to determine the model order of the ARMA models ARMA (10, 8), ARMA (8, 6) and ARMA (6, 4).Â ARMA (6, 4) was found to be appropriate for consumer load prediction with an average mean square error of 0.00006986 and 0.0000685 for weekday and weekend loads respectively. The energy consumption data acquired from consumer load prototype for one week, with 288 data points per day used in our previous work, was used and 5-minute step ahead load prediction is achieved. Furthermore, a comparison between autoregressive AR (20) and ARMA (6, 4) was carried out and ARMA (6, 4) was found to be appropriate for consumer load prediction. This facilitates the monitoring of individual consumer activities connected on the power network.
S. S. Pappas et al., â€œElectricity demand load forecasting of the Hellenic power system using an ARMA model,â€ Electr. Power Syst. Res., vol. 80, no. 3, pp. 256â€“264, 2010.
C.-N. Yu, P. Mirowski, and T. K. Ho, â€œA sparse coding approach to household electricity demand forecasting in smart grids,â€ IEEE Trans. Smart Grid, vol. 8, no. 2, pp. 738â€“748, 2017.
Y. Liu, W. Wang, and N. Ghadimi, â€œElectricity load forecasting by an improved forecast engine for building level consumers,â€ Energy, vol. 139, pp. 18â€“30, 2017.
N. Amjady and F. Keynia, â€œA new neural network approach to short term load forecasting of electrical power systems,â€ Energies, vol. 4, no. 3, pp. 488â€“503, 2011.
P. C. Chang, C. Y. Fan, and J. J. Lin, â€œMonthly electricity demand forecasting based on a weighted evolving fuzzy neural network approach,â€ Int. J. Electr. Power Energy Syst., vol. 33, no. 1, pp. 17â€“27, 2011.
E. Diaconescu, â€œThe use of NARX neural networks to predict chaotic time series,â€ WSEAS Trans. Comput. Res., vol. 3, no. 3, pp. 182â€“191, 2008.
H. K. Alfares and M. Nazeeruddin, â€œElectric load forecasting: Literature survey and classification of methods,â€ Int. J. Syst. Sci., 2002.
N. Cristianini and J. Shawe-Taylor, An introduction to support vector machines and other kernel-based learning methods. Cambridge university press, 2000.
R. P. Singh, P. X. Gao, and D. J. Lizotte, â€œOn hourly home peak load prediction,â€ in Third International Conference on Smart Grid Communications , 2012, pp. 163â€“168.
I. Koprinska, M. Rana, and V. Agelidis, â€œElectricity Load Forecasting: A Weekday-Based Approach,â€ in Artificial Neural Networks and Machine Learning â€“ ICANN 2012, vol. 7553, A. Villa, W. Duch, P. Ã‰rdi, F. Masulli, and G. Palm, Eds. Springer Berlin Heidelberg, 2012, pp. 33â€“41.
D. J. Trudnowski, S. Member, W. L. Mcreynolds, J. M. Johnson, and A. Member, â€œReal-Time Very Short-Term Load Prediction for Power-System Automatic Generation Control,â€ vol. 9, no. 2, pp. 254â€“260, 2001.
C. O. Adika and L. Wang, â€œShort term energy consumption prediction using bio-inspired fuzzy systems,â€ in North American Power Symposium (NAPS), 2012, pp. 1â€“6.
W. Yan, â€œToward automatic time-series forecasting using neural networks,â€ IEEE Trans. Neural Networks Learn. Syst., vol. 23, no. 7, pp. 1028â€“1039, 2012.
N. I. Sapankevych and R. Sankar, â€œTime series prediction using support vector machines: a survey,â€ IEEE Comput. Intell. Mag., vol. 4, no. 2, pp. 24â€“38, 2009.
C. Guan, P. B. Luh, L. D. Michel, Y. Wang, and P. B. Friedland, â€œVery Short-Term Load Forecasting: Wavelet Neural Networks With Data Pre-Filtering,â€ Power Syst. IEEE Trans., vol. 28, no. 1, pp. 30â€“41, 2013.
H. Y. Yang, H. Ye, G. Wang, J. Khan, and T. Hu, â€œFuzzy neural very-short-term load forecasting based on chaotic dynamics reconstruction,â€ Chaos, Solitons & Fractals, vol. 29, no. 2, pp. 462â€“469, 2006.
C. Y. Fok and M. I. Vai, â€œVery Short Term Load Forecasting for Macau Power System,â€ in Intelligent Computing Technology, H. De-Shuang, J. Changjun, B. Vitoantonio, and C. F. Juan, Eds. Berlin Heidelberg: Springer, 2012, pp. 538â€“546.
A. I. Abdullateef, M.-J. E. Salami, and M. F. Akorede, â€œIntelligent technique for electricity theft identification using autoregressive model,â€ LAUTECH J. Eng. Technol., vol. 12, no. 1, pp. 1â€“12, 2018.
A. I. Abdullateef, M. J. E. Salami, M. A. Musse, M. A. Onasanya, and M. I. Alebiosu, â€œNew consumer load prototype for electricity theft monitoring,â€ IOP Conf. Ser. Mater. Sci. Eng., vol. 53, no. 1, p. 12061, 2013.
B. Friedlander, â€œA recursive maximum likelihood algorithm for ARMA spectral estimation,â€ Inf. Theory, IEEE Trans., vol. 28, no. 4, pp. 639â€“646, 1982.
How to Cite
Copyright of articles that appear in Elektrika belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.