“…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).…”