An improved building load forecasting method using a combined least square support vector machine and modified artificial bee colony

Abstract

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.