Table 4 Combined weight allocation and error value summary results of each model.

From: An innovative MGM–BPNN–ARIMA model for China’s energy consumption structure forecasting from the perspective of compositional data

Model

Weight

CRMSE (%)

CMAPE (%)

MGM(1,1)

–

7.928

4.296

BPNN

–

8.352

4.833

ARIMA

–

6.092

3.323

MGM-BPNN

(0.514, 0.487)

6.416

3.593

BPNN-ARIMA

(0.268, 0.732)

5.885

3.226

MGM-ARIMA

(0.165, 0.835)

5.914

3.214

MGM-BPNN-ARIMA

(0.181, 0.275, 0.544)

5.739

3.150

Back to article page