A Hybrid Forecasting Model Based on EMD-GASVM-RBFNN for Power Grid Investment Demand

Table 4

Summary of prediction methods and application literature based on decomposition algorithm.

Author	Forecasting object	Forecasting model	Characteristics
Antonio J. Conejo et al. [27]	Electricity Price	Wavelet-ARIMA Models	It can effectively identify and extract the internal features and laws of nonlinear non-stationary time series, and significantly improve the prediction accuracy of nonlinear non-stationary time series.
Z. A. Bashir and M. E. El-Hawary [28]	Short-Term Load Forecasting	Wavelets-PSO-Based Neural Networks
Rahmat-Allah Hooshmand et al. [29]	Short-term load forecasting	Wavelet transform and artificial neural network model
Lean Yu et al. [30]	Crude oil price	EMD-based neural network model
Chun-Fu Chen et al. [5]	Tourism demand	EMD-based neural network model
YE Lin and LIU Peng [31]	Short-term Wind Power Prediction	EMD-SVM model
Ning An et al. [32]	Electricity demand	EMD-FNN model
L. Karthikeyan and D. Nagesh Kumar [33]	Non-stationary time series	EMD-ARMA models
W.Y. Duan et al. [34]	Short-Term Wave Height	EMD-SVR model
Shouxiang Wang et al. [35]	Wind Speed	EMD-GA-BP neural network
Fan, G.-F. et al. [36].	Load Forecasting	EMD-PSO-GA-SVR