Performance of fuzzy approach in Malaysia short-term electricity load forecasting

• Main Authors: Mansor, Rosnalini, Zulkifli, Malina, Mat Yusof, Muhammad, Ismail, Mohd Isfahani, Ismail, Suzilah, Yip, Chee Yin
• Format: Conference or Workshop Item
• Published: 2014
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://repo.uum.edu.my/17340/; http://doi.org/10.1063/1.4903677
• Institution: Universiti Utara Malaysia

Many activities such as economic, education and manufacturing would paralyse with limited supply of electricity but surplus contribute to high operating cost. Therefore electricity load forecasting is important in order to avoid shortage or excess.Previous finding showed festive celebration has effect on short-term electricity load forecasting.Being a multi culture country Malaysia has many major festive celebrations such as Eidul Fitri, Chinese New Year and Deepavali but they are moving holidays due to non-fixed dates on the Gregorian calendar. This study emphasis on the performance of fuzzy approach in forecasting electricity load when considering the presence of moving holidays. Autoregressive Distributed Lag model was estimated using simulated data by including model simplification concept (manual or automatic), day types (weekdays or weekend), public holidays and lags of electricity load. The result indicated that day types, public holidays and several lags of electricity load were significant in the model.Overall, model simplification improves fuzzy performance due to less variables and rules.