Agile Predict

Model	Parameter	<1d n=672	1d n=672	2d n=672	3d n=672	4d n=672	5d n=672	6d n=672	7d n=672	8d n=636	9d n=615	10d n=615	11d n=615	12d n=580	13d n=336
AgilePredict	MAE	0.08	2.58	4.83	5.40	5.29	5.65	6.05	6.22	6.12	6.63	6.74	6.05	5.65	6.80
AgilePredict	RMSE	0.45	4.21	7.73	8.93	9.09	9.51	9.96	10.01	10.16	10.69	10.79	9.95	8.48	9.50
AgilePredict	Bias	+0.08	+1.44	+1.22	+1.43	+1.49	+1.86	+1.97	+1.63	+1.43	+1.64	+1.55	+1.42	+1.35	+2.55

Model	Offset	n	MAE	RMSE	Bias
AgilePredict	<1d	672	0.08	0.45	+0.08
AgilePredict	1d	672	2.58	4.21	+1.44
AgilePredict	2d	672	4.83	7.73	+1.22
AgilePredict	3d	672	5.40	8.93	+1.43
AgilePredict	4d	672	5.29	9.09	+1.49
AgilePredict	5d	672	5.65	9.51	+1.86
AgilePredict	6d	672	6.05	9.96	+1.97
AgilePredict	7d	672	6.22	10.01	+1.63
AgilePredict	8d	636	6.12	10.16	+1.43
AgilePredict	9d	615	6.63	10.69	+1.64
AgilePredict	10d	615	6.74	10.79	+1.55
AgilePredict	11d	615	6.05	9.95	+1.42
AgilePredict	12d	580	5.65	8.48	+1.35
AgilePredict	13d	336	6.80	9.50	+2.55

Compare AgileForecast

Compare X2R

Prediction Offset

Date Window

Start Date

End Date

Showing 672 actual prices and 672 predictions for 1d ahead.

This chart compares the actual agile price with predictions made for the selected lead time.

The prediction offset is measured from when the forecast was created to the price slot being predicted.

MAE is the average absolute error, in p/kWh.

RMSE is similar but gives more weight to larger errors.

Bias is the average signed error, so positive means predictions were too high and negative means they were too low.