An Improvement In Load Forecasting Model Using Parametric Tuned Support Vector Machine (SVM) Kernel Based Functions

Short term load forecasting (STLF) has gained huge interest among researchers because of its applications in economics, reliability, unit commitment (UC), economic dispatch (ED) and hydro-thermal coordination (HTC) of power systems. The aim of this study is to find an accurate algorithm as it is very important for the prediction of accurate load forecast. Support Vector Machine Regression Model (SVM-R) using different kernels i-e linear, polynomial and gaussian has been used and each kernel function effectiveness and its performance has been examined on real time series using ISO-New England utility data. LibSVM using R language is utilized in this research to employ SVM-R Model. Artificial Neural Network (ANN) is utilized to compare and check the effectiveness of proposed model and its performance by considering least Mean Absolute Percentage Error.

1. Engr. Hamad Ullah Khan Bangash, Department of Electrical Engineering, University of Engineering and Technology, Peshawar, Pakistan, hamadbangash@yahoo.com

2. Dr. Amjad Ullah Khattak, Department of Electrical Engineering, University of Engineering and Technology, Peshawar, Pakistan, amjad67@gmail.com

Engr. Hamad Ullah Khan Bangash and Dr. Amjad Ullah Khattak, "An Improvement in Load Forecasting Model using Parametric Tuned Support Vector Machine (SVM) Kerne", International Journal of Engineering Works, Vol. 5 Issue 9 PP. 154-162 September 2018.

[1]     A .S. Ahmad, M.Y. Hassan, M.P. Abdullah,H.A, Rahman, F. Hussin, H. Abdullah, R. Saidur , “A review on applications of ANN and SVM for building electrical energy consumption forecasting” Renewable and Sustainable Energy Reviews, vol. 33 , pp. 102 – 109, 2014.

[2]     C. Cortes, V. Vapnik “Support-Vector Networks” Machine Learning, vol. 20, pp. 273-297, 1995.

[3]     V.N. Vapnik “The Nature of Statistical Learning Theory” NewYork, Springer Verlag, 1995.

[4]     Nahi Kandil, Vajay Sood, Maarouf Saad, “Use of ANN for STLF”, IEEE1999.

[5]     Dipti Srinivasan, Swee sien ten, C S.Chang, “Parallel Neural Network – Fuzzy expert system strategy for STLF: System implementation and performance evaluation” IEEE Transactions on Power Systems, Vol. 14, No 3 August 1999.

[6]     Ying Chen, Peter B.Luh, Che Guan, Yige Zhao, Laurnet D.Michel, Matthew A.Coolbeth, Peter B.Friedland, and Stephen J.Rourke. “Short-term load forecasting: similar day-based wavelet neural networks,” IEEE Transactions on Power Systems, Vol. 25, Pages 322-330,2010

[7]     M.A. Abu El Magd, R.D. Findlay, “New approach using ANN and Time  Series Models for STLF” Electrical and Computer Engineering, IEEE CCECE , Canadian conference, Vol. 3, Pages 1723-1726,2003.

[8]     A Asar, SR Hassnain, and AU Khattack. "A multi-agent approach to short term load forecasting problem." International journal of intelligent control and systems ,Vol. 10 , pp. 52 – 59, 2005.

[9]     S.H. Ling, H.K. Lam, F,H.F. Leung and P.K.S. Tam, “A neural fuzzy network  with optimal number of rules for STLF in an intelligent home”  IEEE Fuzzy Systems conference,2001.

[10]  Hong-Ze Li, Sen Guo, Chun-jie Li, Jing-qi Sun. "A hybrid annual power load forecasting model based on generalized regression neural network with fruit fly optimization algorithm." Knowledge-Based Systems, Vol. 37,Pages  378-387,2013

[11]  Amit Jain, and B. Satish. "Clustering based short term load forecasting using support vector machines." PowerTech, 2009 IEEE ucharest. IEEE, 2009.

[12]  J. H. Min and Y.-C. Lee, "Bankruptcy prediction using support ector machine with optimal choice of kernel function parameters," Expert systems with applications, vol. 28, pp. 603-614, 2005.

[13]  Kab Ju Hwang, “ STLF Expert System”. IEEE Transactions KOROUS, IEEE, 2001.

[14]  Ming-Guang Zhang. "Short-term load forecasting based on support vector machines regression." International Conference on Machine Learning and Cybernetics, Vol. 7, pp. 4310-4314, 2005.

[15]  Ying LC, Pan MC. “Using adaptive network based fuzzy inference system to forecast regional electricity loads” Energy Conversion and Management , vol.49, pp. 205–11, 2008

[16]  M. U. Fahad and N. Arbab “Factor Affecting Short Term Load Forecasting” Journal of Clean Energy Technologies, Vol. 2, No. 4,  pp. 305-309, October 2014.

[17]  “Long-Term Hourly Peak Demand and Energy Forecast, Electric Reliability Council of Texas, Inc., Taylor, TX, 2010, pp. 9.

[18]  M. Altalo and M. Hale,“Turning weather forecasts into business forecasts,” Environmental Finance, May 2004.

[19]  G. Franco and A. Sanstad,“Climate change and electricity demand in California,” Climatic Change, vol. 87, pp. 139-151, 2007.