Electricity Load Demand Forecast using Fast Ensemble-Decomposed Model

Nuramirah Akrom, Zuhaimy Ismail


Electricity load demand forecasting is a complex process since the pattern of electricity load demand data sets varies. To overcome this problem, a fast ensemble-decomposed model was proposed in this work. Firstly, two data sets of electricity load demand, which are electricity consumption and electricity production, were decomposed into two Intrinsic Mode Functions (IMFs). Secondly, the different values of ensemble trials are employed into fast ensemble-decomposed model. Then, the second IMF was used as the intrinsic prediction trend for the actual electricity load demand data sets. Lastly, the second IMF was compared with the actual electricity load demand time series data and the intrinsic prediction trend of the second IMF was forecasted. Simulation results revealed that the FED model better than the ARIMA and ANN methods and different values of ensembles trials do effect forecast accuracy.


Fast Ensemble-Decomposed Model (FED); Electricity load demand; Electricity consumption; Electricity production; Forecasting

Full Text:


Copyright (c) 2018 Journal of Science and Technology

ISSN : 2229-8460

e-ISSN : 2600-7924


Creative Commons License
This OJS site and its metadata are licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.