THE FORECAST OF ELECTRICAL POWER DISTRIBUTION UNIT USING SUPPORT VECTOR REGRESSION OPTIMIZED WITH GENETIC ALGORITHM
Keywords:
Support vector regression, genetic algorithm, artificial neuralnNetwork, ARIMA model, time seriesAbstract
This research applied time series forecasting with a proposed algorithm: the genetic algorithm optimizing support vector egression (GASVR). The forecasting accuracy performance of the GASVR has been compared with the techniques of an artificial neural network and an autoregressive integrated moving average to forecast the power consumption of Bangkok’s metropolitan area. Time series data in terms of the electrical power distribution nit for household electricity usage were obtained from the Metropolitan Electricity Authority of Thailand. The forecasting performance of each model is measured by the root mean square error (RMSE) and the mean absolute percentage error (MAPE) metrics. The experimental results of the RMSE and MAPE comparisons between the 3 models reveal that the GASVR model has the lowest RMSE and MAPE. Based on such results, we can conclude that the proposed GASVR algorithm, which is the support vector regression with parameter optimization by the genetic algorithm, is the most powerful model to forecast time series data in the specific domain of household power consumption.
References
Bagheripour, P., Gholami, A., Asoodeh, M., and Asadi, M.V. (2015). Support vector regression based determination of shear wave velocity. J. Petrol. Sci. Eng., 125:95-99.
Bergmeir, C. and Benítez, J.M. (2012). On the use of cross-validation for time series predictor evaluation. Inform. Sciences, 191:192-213.
Box, G.E.P. and Jenkins, G. (1990). Time Series Analysis, Forecasting and Control. Holden-Day, San Francisco, CA, USA, 500p.
Bunn, D.W. and Farmer, E.D. (1985). Comparative Models for Electrical Load Forecasting. John Wiley and Sons, New York, NY, USA, 232p.
Fan, G.F., Peng, L.L., Hong, W.C., and Fan, S. (2016). Electric load forecasting by the SVR model with differential empirical mode decomposition and autoregression. Neurocomputing, 173:958-970.
Hyndman, R.J. (2015). Forecasting Functions for Time Series and Linear Models. Melbourne, Australia: Monash University. Available from: http://github. com/robjhyndman/forecast. Accessed date: Sep 3, 2015.
Jirong, G., Mingcang, Z., and Liuguangyan, J. (2011). Housing price forecasting based on genetic algorithm and support vector machine. Expert Syst. Appl., 38:3,383-3,386.
Kaytez, F., Taplamacioglu, M.C., Cam, E., and Hardalac, F. (2015). Forecasting electricity consumption: A comparison of regression analysis, neural networks and least squares support vector machines. Electrical Power and Energy Systems, 67:431-438.
Lee, Y.S. and Tong, L.I. (2011). Forecasting time series using a methodology based on autoregressive integrated moving average and genetic programming. Knowledge-Based Systems, 24:66-72.
Metropolitan Electricity Authority. (2015). Reports of electrical distribution. Bangkok, Thailand. Available from: http://www.mea.or.th/download/ index.php#. Accessed date: Aug 12, 2015.
Meyer, D., Dimitriadou, E., Hornik, K., Weingessel, A., Leisch, F., Chang, C.C., and Lin, C.C. (2015). Misc Functions of the Department of Statistics, Probability Theory Group. Vienna, Austria: Vienna University of Technology. Available from: http://cran.r-project.org/web/packages/e1071/ index.html. Accessed date: Dec 5, 2015.
Ogcu, G., Demirel, O.F., and Zaim, S. (2012). Forecasting electricity consumption with neural networks and support vector regression. Procedia-Social and Behavioral Sciences, 58:1576-1585.
Pai, P.F. and Lin, C.S. (2005). A hybrid ARIMA and support vector machines model in stock price forecasting. Omega, 33:497-505.
Sajan, K.S., Kumar, V., and Tyagi, B. (2015). Genetic algorithm based support vector machine for on-line voltage stability monitoring. Electrical Power and Energy Systems, 73:200-208.
Wang, J., Li, L., Niu, D., and Tan, Z. (2012a). An annual load forecasting model based on support vector regression with differential evolution algorithm. Appl. Energ., 94:65-70.
Wang, X. and Meng, M. (2012). A Hybrid Neural Network and ARIMA Model for Energy Consumption Forecasting. Journal of Computers, 7(5):1,184-1,190.
Wang, Y., Wang, J., Zhao, G., and Dong, Y. (2012b). Application of residual modification approach in seasonal ARIMA for electricity demand forecasting: A case study of China. Energ. Policy, 48:284-294.
Willighagen, E. and Ballings, M. (2015). R Based Genetic Algorithm. CRAN Repository. Available from: http://github.com/egonw/genalg. Accessed date: Dec 5, 2015.
Vapnik, V. (1995). The Nature of Statistical Learning Theory. 2nd ed. Springer-Verlag, New York, Ny, USA, 314p.
Zhang, F., Deb, C., Lee, S.E., , Yang, J., and Shah, K.W. (2016). Time series forecasting for building energy consumption usingweighted Support Vector Regression with differential evolution optimization technique. Energ. Buildings, 126:94-103.
