Sains Malaysiana 47(2)(2018): 419-426

http://dx.doi.org/10.17576/jsm-2018-4702-25

 

Load Forecasting using Combination Model of Multiple Linear Regression with Neural Network for Malaysian City

(Peramalan Beban menggunakan Model Gabungan bagi Regresi Linear Berganda dengan Rangkaian Neuron untuk Bandaraya di Malaysia)

 

Nur Arina Bazilah Kamisan¹, Muhammad Hisyam Lee¹*, Suhartono Suhartono², Abdul Ghapor Hussin³ & Yong Zulina Zubairi⁴

¹Fakulti Sains, Universiti Teknologi Malaysia, 81310 Johor Bahru, Johor Darul Takzim, Malaysia

 

²Jalan Raya ITS, Keputih, Sukolilo, Kota SBY, Jawa Timur 60111, Indonesia

 

³Universiti Pertahanan Nasional Malaysia, Kem Sungai Besi, 57000 Kuala Lumpur, Malaysia

 

⁴Universiti Malaya, Jalan Universiti, 50603 Kuala Lumpur, Wilayah Persekutuan, Malaysia

 

Received: 1 May 2016/Accepted: 16 August 2017

 

 

Abstract

Forecasting a multiple seasonal data is differ from a usual seasonal data since it contains more than one cycle in a data. Multiple linear regression (MLR) models have been used widely in load forecasting because of its usefulness in the forecast a linear relationship with other factors but MLR has a disadvantage of having difficulties in modelling a nonlinear relationship between the variables and influencing factors. Neural network (NN) model, on the other hand, is a good model for modelling a nonlinear data. Therefore, in this study, a combination of MLR and NN models has proposed this combination to overcome the problem. This hybrid model is then compared with MLR and NN models to see the performance of the hybrid model. RMSE is used as a performance indicator and a proposed graphical error plot is introduce to see the error graphically. From the result obtained this model gives a better forecast compare to the other two models.

Keywords: Error plot; hybrid model; neural network; regression model; residuals

 

Abstrak

Peramalan berganda data bermusim adalah berbeza daripada peramalan data bermusim biasa kerana ia mengandungi lebih daripada satu kitaran dalam satu data. Model berganda regresi linear (MLR) telah digunakan secara meluas dalam ramalan beban kerana kegunaannya dalam meramalkan hubungan linear dengan faktor lain tetapi MLR mempunyai kelemahan iaitu mempunyai kesukaran dalam memodelkan hubungan linear antara pemboleh ubah dan faktor yang mempengaruhi. Model rangkaian neural (NN) di sisi lain, adalah model yang baik dalam pemodelan data linear. Oleh itu, dalam kajian ini gabungan MLR dan NN model dicadangkan gabungan ini untuk mengatasi masalah tersebut. Model hibrid ini kemudiannya dibandingkan dengan MLR dan NN model untuk melihat prestasi model hibrid. RMSE digunakan sebagai penunjuk prestasi dan plot ralat grafik diperkenalkan untuk melihat ralat secara grafik. Daripada keputusan yang diperoleh model ini memberikan ramalan yang lebih baik berbanding dengan dua model yang lain.

Kata kunci: Model hibrid; model regresi; plot ralat; rangkaian neural; sisa

 

References

Basheer Shukur, O., Salem Fadhil, N., Hisyam Lee, M. & Hura Ahmad, M. 2014. Electricity load forecasting using hybrid of multiplicative double seasonal exponential smoothing model with artificial neural network. Jurnal Teknologi (Sciences and Engineering). 69(2): 65-70.

Bates, J.M. & Granger, C.W.J. 1969. The combination of forecasts. J. Oper. Res. Soc. 20(4): 451-468.

Bowerman, B.L., O'Connell, R.T. & Koehler, A.B. 2005. Forecasting, Time Series, and Regression: An Applied Approach. 4th ed. Pacific Grove: Thomson Brooks/Cole.

Chakhchoukh, Y., Panciatici, P. & Mili, L. 2011. Electric load forecasting based on statistical robust methods. IEEE Transactions on Power Systems 26(3): 982-991.

Chatfield, C. 2005. Time-series forecasting. Significance 2(3): 131-133.

Chatfield, C. 2000. Time-Series Forecasting. Boca Raton: Chapman & Hall/CRC.

Chatfield, C. 1978. The Holt-Winters forecasting procedure. Journal of the Royal Statistical Society. Series C (Applied Statistics) 27(3): 264-279.

Dudek, G. 2016. Pattern-based local linear regression models for short-term load forecasting. Electric Power Systems Research 130: 139-147.

Gould, P.G., Koehler, A.B., Ord, J.K., Snyder, R.D., Hyndman, R.J. & Vahid-Araghi, F. 2008. Forecasting time series with multiple seasonal patterns. European Journal of Operational Research 191(1): 207-222.

Hahn, H., Meyer-Nieberg, S. & Pickl, S. 2009. Electric load forecasting methods: Tools for decision making. European Journal of Operational Research 199(3): 902-907.

Hyndman, R.J. & Koehler, A.B. 2006. Another look at measures of forecast accuracy. International journal of forecasting. 22(4): 679-688.

Ismail, Z., Jamaluddin, F. & Jamaludin, F. 2008. Time series regression model for forecasting malaysian electricity load demand. Asian Journal of Mathematics & Statistics 1: 139-149.

Jang, J.S.R. 1993. ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions on. Systems, Man and Cybernetics 23(3): 665-685.

Kyriakides, E. & Polycarpou, M. 2007. Short term electric load forecasting: A tutorial. In Trends in Neural Computation, edited by Chen, K. & Wang, L. Berlin Heidelberg:  Springer. 35: 391-418.

Masters, T. 1993. 19 - Evaluating performance of neural networks. In Practical Neural Network Recipies in C++. edited by Masters, T. San Francisco: Morgan Kaufmann. pp. 343-360.

Mastorocostas, P.A., Theocharis, J.B., Kiartzis, S.J. & Bakirtzis, A.G. 2000. A hybrid fuzzy modeling method for short-term load forecasting. Mathematics and Computers in Simulation 51(3-4): 221-232.

Mohamed, N. & Ahmad, M.H. 2010. Forecasting Malaysia load using a hybrid model. Paper presented at the STATISTIKA: Forum Teori dan Aplikasi Statistika.

Mohamed, N., Ahmad, M.H. & Ismail, Z. 2011. Improving short term load forecasting using double seasonal arima model. World Applied Sciences Journal 15(2): 223-231.

Mohamed, N., Ahmad, M.H. & Ismail, Z. 2010. Double seasonal ARIMA model for forecasting load demand. Matematika 26: 217-231.

Park, Y.R., Murray, T.J. & Chen, C. 1996. Predicting sun spots using a layered perceptron neural network. IEEE Trans Neural Netw. 7(2): 501-505.

Ringwood, J.V., Bofelli, D. & Murray, F.T. 2001. Forecasting electricity demand on short, medium and long time scales using neural networks. Journal of Intelligent & Robotic Systems 31(1): 129-147.

Soares, L.J. & Medeiros, M.C. 2008. Modeling and forecasting short-term electricity load: A comparison of methods with an application to Brazilian data. International Journal of Forecasting 24(4): 630-644.

Tang, Z. & Fishwick, P.A. 1993. Feedforward neural nets as models for time series forecasting. ORSA Journal on Computing 5(4): 374-385. 

Taylor, J.W. 2003. Short-term electricity demand forecasting using double seasonal exponential smoothing. The Journal of the Operational Research Society 54(8): 799-805.

Xiaojuan, L., Enjian, B., Jian'an, F. & Lunhan, L. 2010. Time-variant slide fuzzy time-series method for short-term load forecasting. Paper presented at the 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems (ICIS).

Ying, L.C. & Pan, M.C. 2008. Using adaptive network based fuzzy inference system to forecast regional electricity loads. Energy Conversion and Management 49(2): 205-211.

Zhang, G.P. 2003. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50: 159-175.

Zhang, G.P. & Qi, M. 2005. Neural network forecasting for seasonal and trend time series. European Journal of Operational Research 160(2): 501-514.

Zhang, Y., Zhou, Q., Sun, C., Lei, S., Liu, Y. & Song, Y. 2008. RBF neural network and ANFIS-based short-term load forecasting approach in real-time price environment. IEEE Transactions on Power Systems 23(3): 853-858.

 

*Corresponding author; email: mhl@utm.my