An Improved Building Load Forecasting Method using a combined Least Square Support Vector Machine and modified Artificial Bee Colony

This paper presents an improved building load forecasting method using a combined Least Square Support Vector Machine and modified Artificial Bee Colony. The main contribution of the proposed method is the improvement in the exploitation capability of the standard Artificial Bee Colony, in which a different probability selection has been introduced. This was achieved by changing the standard probability selection with the clonal selection algorithm. The results from two other methods were compared with the results from the proposed method to validate the performance of the proposed forecasting method. The accuracy of the proposed method was evaluated using the Mean Absolute Error, Mean Absolute Percentage Error and Root Mean Square Error. It was found that the proposed method had improved the accuracy by more than 50 % compared to the other methods. The results of the study showed that the proposed method has great potential to be used as an accurate forecasting method.

[1]  Y. Yusof,et al.  Application of LSSVM by ABC in energy commodity price forecasting , 2014, 2014 IEEE 8th International Power Engineering and Optimization Conference (PEOCO2014).

[2]  Dervis Karaboga,et al.  AN IDEA BASED ON HONEY BEE SWARM FOR NUMERICAL OPTIMIZATION , 2005 .

[3]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[4]  Amir H. Mohammadi,et al.  Experimental Study and Modeling of Ultrafiltration of Refinery Effluents Using a Hybrid Intelligent Approach , 2013 .

[5]  Wei-Chiang Hong,et al.  Electric load forecasting by seasonal recurrent SVR (support vector regression) with chaotic artific , 2011 .

[6]  Omar S. Soliman,et al.  LSSVM-ABC Algorithm for Stock Price prediction , 2014, ArXiv.

[7]  Youshen Xia,et al.  A prediction fusion method for reconstructing spatial temporal dynamics using support vector machines , 2006, IEEE Transactions on Circuits and Systems II: Express Briefs.

[8]  Terry R. Rakes,et al.  The effect of sample size and variability of data on the comparative performance of artificial neural networks and regression , 1998, Comput. Oper. Res..

[9]  Fernando José Von Zuben,et al.  Learning and optimization using the clonal selection principle , 2002, IEEE Trans. Evol. Comput..

[10]  Bilal Babayigit,et al.  A modified artificial bee colony algorithm for numerical function optimization , 2012, 2012 IEEE Symposium on Computers and Communications (ISCC).

[11]  Saleh M. Al-Alawi,et al.  Forecasting monthly electric load and energy for a fast growing utility using an artificial neural network , 1995 .

[12]  Sylvain Robert,et al.  State of the art in building modelling and energy performances prediction: A review , 2013 .

[13]  B. Dong,et al.  Applying support vector machines to predict building energy consumption in tropical region , 2005 .

[14]  Mohammad Ali Ahmadi,et al.  Prediction breakthrough time of water coning in the fractured reservoirs by implementing low parameter support vector machine approach , 2014 .

[15]  Chi-Man Vong,et al.  Prediction of automotive engine power and torque using least squares support vector machines and Bayesian inference , 2006, Eng. Appl. Artif. Intell..

[16]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.