The 2012 International Joint Conference on Neural Networks (IJCNN) 2012
DOI: 10.1109/ijcnn.2012.6252648
|View full text |Cite
|
Sign up to set email alerts
|

Load profile generator and load forecasting for a renewable based microgrid using Self Organizing Maps and neural networks

Abstract: In this paper, two methods for generating the daily load profile and forecasting in isolated small communities are proposed. In these communities, the energy supply is difficult to predict because it is not always available, is limited according to some schedules and is highly dependent on the consumption behavior of each community member. The first method is proposed to be used before the implementation of the microgrid in the design state, and it includes a household classifier based on a Self Organizing Map… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
34
0
2

Year Published

2013
2013
2022
2022

Publication Types

Select...
3
3
3

Relationship

0
9

Authors

Journals

citations
Cited by 44 publications
(36 citation statements)
references
References 18 publications
0
34
0
2
Order By: Relevance
“…Although high precision, as low as 1.97% mean absolute percentage error (MAPE), has been achieved on large scale (for example national and municipal level [3]- [6]), microgrid, VPP and transformer level forecasting has only recently emerged as a research interest [7]- [10]. The results are not very encouraging, with errors ranging from 5.15% MAPE at university campus level [10], where power demand peaks at 8 MW during the day, up to 13.8% MAPE at village level, where power demand peaks at 15 kW [7].…”
Section: Introductionmentioning
confidence: 99%
“…Although high precision, as low as 1.97% mean absolute percentage error (MAPE), has been achieved on large scale (for example national and municipal level [3]- [6]), microgrid, VPP and transformer level forecasting has only recently emerged as a research interest [7]- [10]. The results are not very encouraging, with errors ranging from 5.15% MAPE at university campus level [10], where power demand peaks at 8 MW during the day, up to 13.8% MAPE at village level, where power demand peaks at 15 kW [7].…”
Section: Introductionmentioning
confidence: 99%
“…Although high precision, as low as 1.97% mean absolute percentage error (MAPE), has been achieved on large scale (for example national and municipal level (Amjady, 2007;Beccali et al, 2004;Motamedi et al, 2012;Taylor and Mcsharry, 2008)), microgrid, VPP and transformer level forecasting has only recently emerged as a research interest (Amjady and Keynia, 2010;Fatimie et al, 2010;Hernandez et al, 2014;Llanos et al, 2012;Lloret and Valencia, 2013). The results are not very encouraging, with errors ranging from and 5.15% MAPE at university campus level (Fatimie et al, 2010), where power demand peaks at 8 MW during the day, and 7.92% MAPE at university building level (Borges et al, 2011) -up to 13.8% MAPE at village level, where power demand peaks at 15 kW (Llanos et al, 2012). Short term load forecasting (STLF) has further been done at microgrid level, with forecasting errors of 3.69% MAPE (Wai et al, 2011) 6 , 6.7% MAPE (Shimoda et al, 2012), 7.92% MAPE (Chaouachi et al, 2013) and 15.12% MAPE (Chan et al, 2011).…”
Section: Power Demand Forecasting In Smart Gridsmentioning
confidence: 99%
“…Other work presents results in the non-normalised RMSE (e.g., (Espinoza et al, 2005;Llanos et al, 2012;Tidemann et al, 2013)), but NRMSE is a better way to compare forecasting accuracy, as the power demand scale between tested cases does not have to be the same when comparing accuracy rates (Wijaya et al, 2014). Therefore, even particularly high power demands are comparable with other evaluated demands, when normalised.…”
Section: Forecasting Metricsmentioning
confidence: 99%
“…At the microgrid level (small scale), prediction has been recently considered of interest [7]- [10]. Unfortunately until now prediction accuracy has seen a noticeable decrease when compared to large scale.…”
Section: Background and Related Workmentioning
confidence: 99%