Page - 407 - in Short-Term Load Forecasting by Artificial Intelligent Technologies

Energies 2018,11, 242 4.3.3. ExperimentalResults For the testing data of the retail store, parts of the prediction results of the five predictors constructed by utilizing the energy-consuming pattern are illustrated in Figure 9. Furthermore, forbettervisualization, thepredictionerrorhistogramsof thefivepredictorsareshowninFigure10. It isobviousthatthemorethepredictionerrorsfloataroundzero, thebettertheforecastingperformance of thepredictorwillbe. Then, to examine the superiorityof thehybridmodel for the retail store energyconsumption prediction, thefivepredictionmodels are compared consideringdifferentdata types (theoriginal andresidualdata). Theoriginaldatameans that thepredictorsare learnedusing theoriginaldata series,while theresidualdatameansthat thepredictorsareconstructedbyboththeenergy-consuming patternandtheresidualdataseries. Experimental resultsaredemonstrated indetail inTable3. D 0'%1 $FWXDO YDOXH H 695 $FWXDO YDOXH E %311 $FWXDO YDOXH G (/0 $FWXDO YDOXH F *5%)11 $FWXDO YDOXH 7LPH RI IRXU WHVWLQJ GD\V RQH XQLW PLQXWHV 7LPH RI IRXU WHVWLQJ GD\V RQH XQLW PLQXWHV 7LPH RI IRXU WHVWLQJ GD\V RQH XQLW PLQXWHV 7LPH RI IRXU WHVWLQJ GD\V RQH XQLW PLQXWHV 7LPH RI IRXU WHVWLQJ GD\V RQH XQLW PLQXWHV Figure9.Partsofpredictionresultsofthefivepredictorsconstructedbyutilizingtheenergy-consuming pattern: (a)hybridDBNmodel; (b)BPNN;(c)GRBFNN;(d)ELM;and(e)SVR. 407