Load forecasting in power system

• Main Author: Lee, Yunfeng
• Other Authors: Ponnuthurai Nagaratnam Suganthan
• Format: Final Year Project
• Language: English
• Published: 2014
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Control engineering
• Online Access: http://hdl.handle.net/10356/60489
• Institution: Nanyang Technological University

Load forecasting had been a focal point of research throughout many countries. It played a vital role in the electrical industry such as economic dispatch, planning and operation of electrical utilities, energy transfer scheduling and many more. Thus, an accurate load forecasting would enable a correct anticipation of power needed to supply the demand. In order to achieve that, Support Vector Regression (SVR) model, hybridizing with Empirical Mode Decomposition (EMD), Complementary Ensemble Empirical Mode Decomposition (CEEMD) and Complete Ensemble Empirical Mode Decomposition Adaptive Noise (CEEMDAN) methods were compared with 6 other models to determine which model would give the best performance. The load data of the New South Wales (Australia) would be used for our research in this paper. Despite inconclusive results in terms of the best model, the results proved that CEEMDAN method had enabled the improvement of load forecasting performance.