Table 2 Numerical performance of DRN under different mini-batch sizes on ISO-NE dataset.

From: Mini-batch size sensitivity in deep residual networks for short-term load forecasting: an empirical study

Batch size

MAPE

MAE

MSE

RMSE

NMSE

R

R2

8

0.017522

0.011186

0.000316

0.017790

0.020999

0.989625

0.979001

16

0.017290

0.011209

0.000332

0.018218

0.022023

0.988990

0.977977

32

0.017182

0.011138

0.000308

0.017548

0.020432

0.989767

0.979568

64

0.016695

0.010805

0.000306

0.017502

0.020326

0.989806

0.979674

128

0.020716

0.013228

0.000397

0.019932

0.026360

0.987876

0.973640

256

0.021941

0.014209

0.000482

0.021965

0.032011

0.984289

0.967989

512

0.025728

0.016785

0.000668

0.025841

0.044309

0.978411

0.955691

Back to article page