Probabilistic forecast of electric vehicle charging demand: analysis of different aggregation levels and energy procurement

Ostermann, Adrian; Haug, Theodor

doi:10.1186/s42162-024-00319-1

Energy Informatics

Table 8 Metrics of the models for the individual sites

From: Probabilistic forecast of electric vehicle charging demand: analysis of different aggregation levels and energy procurement

Site (number of charger)	Model	nRMSE*	MASE*	R2**	PS low Q***	PS high Q***	IS***
A (3)	LinR	1.009	1.151	584.168	0.15	0	0
	Bagging	1.106	1.115	640.565	− 0.023	3.024	37.963
	GradientB	1.029	1.057	595.809	0.115	3.024	30.945
	Ada	1.067	1.356	618.029	0.048	3.024	50.004
	Random forest	1.111	1.105	643.396	− 0.032	3.024	41.262
	LSTM	1.088	1.236	629.841	0.011	1943.876	117.946
	CNN	1.172	1.252	678.441	− 0.147	666.728	117.946
	NN	1.185	1.01	686.159	− 0.173	525.407	117.947
B (4)	LinR	0.992	1.077	870.695	0.189	0	0
	Bagging	1.013	1.017	889.115	0.154	10.281	82.067
	GradientB	0.994	1.032	872.227	0.186	10.281	73.75
	Ada	0.994	1.094	872.266	0.186	10.281	89.058
	Random forest	1.031	1.034	905.217	0.123	10.283	81.927
	LSTM	1.071	1.067	940.387	0.054	1695.592	400.964
	CNN	1.164	1.19	1022.103	-0.118	926.987	400.964
	NN	1.095	1.013	961.368	0.011	1211.949	400.964
C (8)	LinR	0.954	1.149	294.785	0.116	0	0
	Bagging	0.993	0.849	307.083	0.041	1.723	16.471
	GradientB	0.989	1.042	305.84	0.049	1.617	14.012
	Ada	0.982	0.981	303.652	0.062	1.797	15.972
	Random forest	1.022	0.869	316.031	− 0.016	2.739	17.262
	LSTM	0.894	0.89	276.51	0.222	807.033	63.078
	CNN	1.057	0.802	326.657	− 0.085	234.903	63.082
	NN	1.093	0.858	337.963	− 0.162	409.187	88.649
D (14)	LinR	0.971	1.096	644.271	0.32	0	0
	Bagging	1.022	1.108	677.737	0.247	9.038	56.199
	GradientB	1.034	1.15	685.814	0.229	9.054	47.525
	Ada	1.026	1.211	680.719	0.241	9.21	57.178
	Random forest	1.027	1.112	680.964	0.24	13.526	64.093
	LSTM	1.005	1.062	666.66	0.272	1060.265	353.12
	CNN	1.071	1.241	710.662	0.172	588.897	353.132
	NN	1.044	1.035	692.421	0.214	345.821	353.13
E (145)	LinR	0.74	0.719	301.995	0.764	0	0
	Bagging	0.671	0.537	273.832	0.806	10.581	12.018
	GradientB	0.616	0.562	251.491	0.837	6.126	14.434
	Ada	0.66	0.553	269.211	0.813	10.988	12.427
	Random forest	0.691	0.547	282.057	0.794	11.293	16.224
	LSTM	1.009	1.151	584.168	0.15	0	0
	CNN	1.106	1.115	640.565	− 0.023	3.024	37.963
	NN	1.029	1.057	595.809	0.115	3.024	30.945

*Unitless, **in %, ***in W

Back to article page