In order to forecast the electricity price of the day ahead Dutch market I am using neural networks and real data from 2007-2011.
I constructed the X matrix as you said in the webinar for load forecasting and proved with different combinations. The one with gives me the lower MAPE value consists of 8 inputs (Hour dayOfWeek isWorkingDay prevWeekSameHourPrice prevDaySameHourPrice prev24HrAvePrice prevDayNGPrice prevWeekAveNGPrice), but I can't reduce this value more than 11%.
I need to achieve better accuracy but I don't know whar should I change. Could you send me an example of who to forecast the day ahead electricity price? My email is firstname.lastname@example.org