Seite - 88 - in Short-Term Load Forecasting by Artificial Intelligent Technologies
Bild der Seite - 88 -
Text der Seite - 88 -
Energies2019,12, 57
Threestandardloadprofiles [43,44],as illustrated inFigure5,wereappliedto the loadmodule
to investigate the impacts of loads on the optimization of the hybrid power system. The 61-day
historicaldatawereusedforsimulationandoptimizationanalyses. Table3 illustrates thestatistical
dataof these loadprofiles,where thehouseholdhadthe largesthistoricallypeakandtheofficehadthe
largestdailyaveragepeak,while the laboratory loadhadthegreatestenergyconsumption. Therefore,
weusedthese three typical loads todemonstratehowloadcharacteristicscanaffect theperformance
optimizationof thehybridpowersystem.
ȱ
(a)ȱ61Ȭdayȱhistoricalȱdataȱ (b)ȱDailyȱaverageȱ[43,44]ȱ
WLPH KU
8VHU /RDG DYHUDJH
+RXVH
2IILFH
/DE
Figure5.Threestandard loadprofiles.
Table3.Thestatisticaldataof loadprofiles [39].
Household Lab Office
Historicpeak(W) 6220 3395 5333
Dailyaveragepeak(W) 1237 1811 2178
Dailyaverage (kWh) 19.96 30.41 22.32
3.DesignOptimizationof theHybridPowerSystem
Thehybridpowermodelwasapplied topredict systemresponsesunderdifferent conditions,
suchastheuseofvaryingcomponentsandloads.Wedefinedthreeindexestoevaluatetheperformance
of thehybridpowersystem: cost, reliability,andsafety,asdescribedbythe following:
(1) Systemcost: thesystemcost J(b, s,w) consistedof twoparts, Ji and Jo, as follows[39]:
J(b, s,w) = Ji(b, s,w) + Jo(b, s,w) (2)
where Jiand Jo indicatetheinitialandoperationcosts, respectively. Thesubscriptsb,s,andwrepresent
thenumbersofbatteries,PVarrays,andWTsinunitsof100Ah,1kW,and3kW,respectively. The initial
cost Jiaccountedfor the investment in thecomponents, suchas thePEMFC,powerelectricdevices,
PVarrays,WT,hydrogenelectrolyzer, chemicalhydrogengenerator,andbatteryset, as follows:
Ji(b, s,w) =∑kJki(b, s,w) (3)
wherek=PEMFC,DC,solar,WT,HE,CHG,andbatt, respectively.
Theoperationcost Jo includedthehydrogenconsumptionandthemaintenanceof theWTandPV
arrays,as in the following:
Jo(b, s,w) =∑ lJlo(b, s,w) (4)
where l=NaBH4,WT,andsolar, respectively.
88
Short-Term Load Forecasting by Artificial Intelligent Technologies
- Titel
- Short-Term Load Forecasting by Artificial Intelligent Technologies
- Autoren
- Wei-Chiang Hong
- Ming-Wei Li
- Guo-Feng Fan
- Herausgeber
- MDPI
- Ort
- Basel
- Datum
- 2019
- Sprache
- englisch
- Lizenz
- CC BY 4.0
- ISBN
- 978-3-03897-583-0
- Abmessungen
- 17.0 x 24.4 cm
- Seiten
- 448
- Schlagwörter
- Scheduling Problems in Logistics, Transport, Timetabling, Sports, Healthcare, Engineering, Energy Management
- Kategorie
- Informatik