DATA SELECTION TEST METHOD FOR BETTER PREDICTION OF BUILDING ELECTRICITY CONSUMPTION
DOI:
https://doi.org/10.11113/jt.v78.8715Keywords:
Electricity prediction, data selection, prediction accuracyAbstract
The issue of obtaining an accurate prediction of electricity consumption has been widely discussed by many previous works. Various techniques have been used such as statistical method, time-series, heuristic methods and many more. Whatever the technique used, the accuracy of prediction depends on the availability of historical data as well as the proper selection of the data. Even the data is exhaustive; it must be selected so that the prediction accuracy can be improved. This paper presented a test method named Data Selection Test (DST) method that can be used to test the historical data to select the correct data set for prediction. The DST method is demonstrated and tested on practical electricity consumption data of a selected commercial building. Three different prediction methods are used (ie. Moving Average, MA, Exponential Smoothing, ES and Linear Regression, LR) to evaluate the prediction accuracy by using the data set recommended by the DST method. Â
References
Tenaga, S., 2012. National Energy Balance. Suruhanjaya Tenaga (Energy Commission): Putrajaya, Malaysia.
Ben-Nakhi AF, Mahmoud MA, 2004. Cooling Load Prediction For Building Using General Regression Neural Networks. Energy Conversion and Management. 45(13-14): 2127-41.
Wong SL, Wan KKW, Lam TNT, 2010. Artificial Neural Networks For Energy Analysis Of Office Building With Daylighting. Applied Energy. 87(2): 551-7.
Aydinalp M, Urgusal VI, Fung AS, 2002. Modeling Of The Appliance, Lighting, And Space Cooling Energy Consumption In The Residential Sector Using Neural Networks. Applied Energy. 71(2): 87-110.
Languang Z., Jing H., Jinxiang P., and Fengzhong Z., 2012. Electrical Energy Demand Forecasting With GRNN For Energy Saving Strategy, Applied Mechanics and Materials 198-199: 639-643.
Victor M., Gareth A. Taylor, and Arthur E., 2014. A Novel Econometrics Model For Peak Demand Forecasting, IEEE.
Kang J., Hong S., and Jian C., 2011. Forecasting Building Energy Consumption Using Neural Networks And Hybrid Neuro-Fuzzy System: A Comparative Study, Energy and Buildings 43: 2893-2899.
Ahmad S. A., Muhammad Y. H., and Md. Shah M., 2012. Application Of Hybrid GMDH And Least Square Support Vector Machine In Energy Consumption Forecasting, IEEE, International Conference on Power and Energy (PECon).
S. Mohammadi, H. Keivani, M. Bakhshi, A. Mohammadi, M. R. Askari, and F. Kavehnia, Demand Forecasting Using Time Series Modeling and ANFIS Estimator.
Arindrajit Pal, JyotiPrakash Singh, ParamarthaDutta, 2013. The Path Length Prediction of MANET Using Moving Average Model, Procedia Technology. 10: 882-889.
Everette S. Gardner Jr., 2006. Exponential Smoothing: The State Of The Art—Part II, International Journal of Forecasting, 22(4): 637-666.
Shalabh. 2013. A Revisit To Efficient Forecasting In Linear Regression Models, Journal of Multivariate Analysis. 114: 161-170.
Downloads
Published
Issue
Section
License
Copyright of articles that appear in Jurnal Teknologi 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.
