Application of a hybrid of least square support vector machine and artificial bee colony for building load forecasting

• Main Authors: Mat Daut, M. A., Hassan, M. Y., Abdullah, H., Abdul Rahman, H., Abdullah, M. P., Hussin, F.
• Format: Article
• Language: English
• Published: Penerbit UTM Press 2016
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utm.my/id/eprint/71170/1/MohammadAzharMatDaut2016_ApplicationofaHybridofLeastSquareSupport.pdf; http://eprints.utm.my/id/eprint/71170/; https://www.scopus.com/inward/record.uri?eid=2-s2.0-84973338464&doi=10.11113%2fjt.v78.8907&partnerID=40&md5=7738bfaa0eb0d41d2d5b63471e8ac927

Accurate load forecasting is an important element for proper planning and management of electricity production. Although load forecasting has been an important area of research, methods for accurate load forecasting is still scarce in the literature. This paper presents a study on a hybrid load forecasting method that combines the Least Square Support Vector Machine (LSSVM) and Artificial Bee Colony (ABC) methods for building load forecasting. The performance of the LSSVM-ABC hybrid method was compared to the LSSVM method in building load forecasting problems and the results has shown that the hybrid method is able to substantially improve the load forecasting ability of the LSSVM method.