Page - 385 - in Short-Term Load Forecasting by Artificial Intelligent Technologies

Energies2018,11, 1138 Residentcustomersmayincreaseelectricityconsumptiononweekendsbutbusinesscustomersmay not. Thesearesomeobviousreasonswhyweshouldconsider theenvironment factors. Table 8. ComparedMAPEs for nine customers in three categorieswithmulti-sourcedata or only loaddata. Customer Category Feeder MAPEwithMulti-SourceData MAPEwithonlyLoadData 37148000 1 2 10.80% 15.09% 51690000 1 7 9.25% 15.06% 37165000 1 7 11.12% 16.50% 53990001 2 2 10.07% 18.56% 54265001 2 3 11.91% 17.36% 54265002 2 3 10.76% 15.99% 31624001 3 35 13.56% 15.89% 41661001 3 34 12.23% 16.46% 76242001 3 33 9.98% 17.33% D 6DPSOLQJ 3RLQWV 6DPSOLQJ 3HULRG PLQXWHV E 6DPSOLQJ 3RLQWV 6DPSOLQJ 3HULRG PLQXWHV F 6DPSOLQJ 3RLQWV 6DPSOLQJ 3HULRG PLQXWHV G 6DPSOLQJ 3RLQWV 6DPSOLQJ 3HULRG PLQXWHV $FWXDO ORDG )RUHFDVWLQJ ORDG ZLWK PXOWL VRXUFH GDWD )RUHFDVWLQJ ORDG ZLWK ORDG GDWD Figure13.Comparisoncurveofactual loadandforecastingloadofCustomer53990001withorwithout multi-sourcedata: (a–d) the results for the same fourdays inNovember2013as theexperiment in Figure12. It canbeconcludedfromthe twoexperiments that theMAPEsarefloating inacertaindegree. ThemaximalMAPEsofall samples in theconditionsof the twoexperimentsare showninTable9. ThemaximalMAPEwithoutclusteringandwithonlyloaddataissignificantlylargerthantheproposed methodwithclusteringandmulti-sourcedata. ThemaximalMAPEofproposedmethodis15.12%, which isacceptable for loadforecastingof individualcustomers. Table9.MaximalMAPEs indifferentconditions. Conditions ForecastwithoutClustering ForecastwithonlyLoadData ProposedMethod MaximalMAPE 30.25% 21.87% 15.12% 385