Table 9.

Time series forecasting results under accelerated conditions.

Dataset	Metric	CNN [15]	Deep RNNs [38]	LSTM [17]	Transformer [31]	Informer
I-I	MAE	$4.9994\times {10}^{-3}$	$4.9735\times {10}^{-3}$	$5.2031\times {10}^{-3}$	$6.1465\times {10}^{-3}$	$4.9413\times {10}^{-3}$
	MSE	$5.2178\times {10}^{-5}$	$5.9317\times {10}^{-5}$	$5.1365\times {10}^{-5}$	$6.9594\times {10}^{-5}$	$4.5778\times {10}^{-5}$
	RMSE	$7.2234\times {10}^{-3}$	$7.7017\times {10}^{-3}$	$7.1670\times {10}^{-3}$	$8.3423\times {10}^{-3}$	$6.7659\times {10}^{-3}$
	Running Time (s)	480	2475	400	4252	155
O-I	MAE	$2.2311\times {10}^{-3}$	$2.1050\times {10}^{-3}$	$2.3986\times {10}^{-3}$	$2.1532\times {10}^{-3}$	$1.7147\times {10}^{-3}$
	MSE	$9.5604\times {10}^{-6}$	$9.5604\times {10}^{-6}$	$1.0922\times {10}^{-5}$	$8.9571\times {10}^{-6}$	$6.2589\times {10}^{-6}$
	RMSE	$3.0920\times {10}^{-3}$	$3.0825\times {10}^{-3}$	$3.3048\times {10}^{-3}$	$2.9928\times {10}^{-3}$	$2.5018\times {10}^{-3}$
	Running Time (s)	480	2625	400	4344	166
R-I	MAE	$2.9234\times {10}^{-3}$	$3.2357\times {10}^{-3}$	$2.8091\times {10}^{-3}$	$2.6975\times {10}^{-3}$	$2.1812\times {10}^{-3}$
	MSE	$1.5228\times {10}^{-5}$	$1.8761\times {10}^{-5}$	$1.3894\times {10}^{-5}$	$1.3384\times {10}^{-5}$	$9.5485\times {10}^{-6}$
	RMSE	$3.9023\times {10}^{-3}$	$4.3314\times {10}^{-3}$	$3.7274\times {10}^{-3}$	$3.6584\times {10}^{-3}$	$3.0901\times {10}^{-3}$
	Running Time (s)	480	2775	400	4293	158