Skip to main content

Table 7 Comparison of the different approaches

From: Accurate prediction of different forecast horizons wind speed using a recursive radial basis function neural network

S. No Various Wind Speed Prediction Approaches Methodology Year Performance Metrics Parametric Values Training Computation Time in sec
1 Anurag More & Deo M C Approach NN with Cascade Algorithm 1995 MSE 0.0015 280
2 Perez Li era et al. Approach NN with BP Algorithm 1998 MSE 6.3334e-04 305
3 Selcuk Nogay H et al. Approach MLP with BP Algorithm 2012 MSE 1.7244e-05 186
4 Vigneswaran T & Dhivya S Approach GRNN 2012 MSE 0.0236 253
MAPE 1.1545
5 Gnana Sheela K & Deepa S N Approach RBF 2013 MSE 7.1052e-06 152
MAE 0.0010
MAPE 0.0131
6 Chuanan Yao et al. Approach LCWNN 2013 MSE 0.0070 137
RMSE 0.0834
MAPE 0.4408
7 Ramesh Babu N & Arulmozhivarman P Approach WT - NN 2013 MSE 1.0656e-04 148
RMSE 0.0103
MAE 0.0029
MAPE 0.0361
8 Qinghua Hu et al. Approach Ensemble GPCA 2014 MSE 0.0087 195
9 Ramesh Babu N & Arulmozhivarman P Approach NARX 2014 MSE 0.0335 252
RMSE 0.1830
10 Wenyu Zhang et al. Approach SSA 2014 MAE 0.0733 224
RMSE 0.1031
MAPE 0.9050
11 Madhiarasan M & Deepa S N IBPN 2015 MSE 5.1014e-05 140
RMSE 0.0071
MAE 2.9832e-04
MRE 3.6823e-05
MAPE 0.0037
12 Proposed Approach RRBFNN   MSE 1.6166e-12 72
RMSE 1.2715e-05
MAE 8.2352e-07
MRE 1.0165e-07
MAPE 1.0165e-05