Seite - 95 - in Short-Term Load Forecasting by Artificial Intelligent Technologies
Bild der Seite - 95 -
Text der Seite - 95 -
Energies2019,12, 57
costby$35.90,$82.60,and$50.40 for thehousehold, laboratory,andoffice, respectively, if theNaBH4
price is 10NT$/kg. Therefore, the secondoption (using extraNaBH4)will be the better choice if
thecostofNaBH4 is less than7.19,10.38,and9.62NT$/kgfor thehousehold, laboratory,andoffice,
respectively.Note that theseanalysesarebasedontheworst-caseconditions,where thebatterySOC
isat the lowestwhentheextremeweatherhappens.Hence, ingeneral, thecost shouldbe lowerand
morebenefitsarepossiblebystoringextraNaBH4with theautobatchsystem[36].
4.ResultsandConclusions
Thispaperhasdemonstratedtheoptimizationofagreenbuildingthatwasautonomousanddid
notconnecttothemaingrid. Thebuildingcanbeappliedtoremotestationsandsmall islands,whereno
gridpowerisavailable.Wediscussedtheimpactsof threetypical loadsontheoptimizationofahybrid
power system. First,webuilt ageneralhybridpowermodelbasedonagreenbuilding inTaiwan.
ThemodelconsistedofPV,WT,batteries,PEMFC,electrolyzer,andchemicalhydrogenproduction
modules. Second, we evaluated the systemperformance by applying the household, laboratory,
andoffice loadprofiles to themodel. Theresults indicatedthat thecombinationofPV,battery,PEMFC,
andchemicalhydrogenproductioncanguaranteesystemreliability.Whencomparedwith theoriginal
settings, the total system costwas greatly reduced by 38.9%, 40%, and 28.6% for the household,
laboratory, andoffice loads, respectively,while the systemreliabilitywas significantly reducedby
4.89%,24.42%,and5.08%,respectively. Third, thecostdistributionshowedsimilar results for the three
loads: thebattery, PV, andPEMFCsystemsaccounted for about 25%, 40%, and20%of the system
costs forall threecases.Note that thecurrentusageof lead-acidbattery isacompromisebetweencost
andefficiency. Forexample, applying thehybridsystemwithLiFebattery [33], theoptimal system
costsbecame2.237, 1.846, and1.853perkWhfor thehousehold, lab, andoffice loads, respectively.
That ismuch higher than the current optimal costs by the lead-acid battery. Fourth, the energy
distributions indicatedthat thePVprovidednearly99%of therequiredenergy,becauseof thecurrent
highpriceofhydrogen.Asshownin[33],hydrogenenergywillbecompatiblewhenthehydrogen
pricedrops toaboutonethirdof thecurrentprice. Finally,weevaluatedthesafetyof thesesystems
underextremeweatherconditionsandproposedtwomethods forextendingsystemsustainability:
usingasub-optimaldesignorusingmoreNaBH4. The lattermethodtendedtobemoreflexibleand
wasmore able to copewithuncertainties. For example, adding 20kgofNaBH4 will increase the
systemsafetyby3.33,2.10,and2.90days for thehousehold, laboratory,andoffice loads, respectively.
Thesefindingscanbeconsideredwhendevelopingcustomizedhybridpowersystems in the future.
Author Contributions: Conceptualization, F.-C.W.; Methodology, F.-C.W. and K.-M.L.; Software, K.-M.L.;
Validation, F.-C.W., andK.-M.L.; Formal Analysis, F.-C.W. andK.-M.L.; Investigation, F.-C.W. andK.-M.L.;
Resources,F.-C.W.andK.-M.L.;DataCuration,F.-C.W.andK.-M.L.;Writing—OriginalDraftPreparation,F.-C.W.
andK.-M.L.;Writing—ReviewandEditing, F.-C.W.;Visualization, F.-C.W. andK.-M.L.; Supervision, F.-C.W.;
ProjectAdministration,F.-C.W.;FundingAcquisition,F.-C.W.
Funding: This research was funded by theMinistry of Science and Technology, R.O.C., in Taiwan under
GrandsMOST105-2622-E-002-029 -CC3,MOST106-2622-E-002-028 -CC3,MOST106-2221-E-002-165-,MOST
107-2221-E-002-174-, andMOST107-2221-E-002-174-. This researchwasalsofinanciallysupported inpartbythe
MinistryofScienceandTechnologyofTaiwan(MOST107-2634-F-002-018),NationalTaiwanUniversity,Center
forArtificial IntelligenceandAdvancedRobotics. Theauthorswould like to thankYe-CheYangandI-MingFu
forhelpingthesimulation. Thecollaborationandtechnical supportofM-FieldTMaremuchappreciated.
Conflictsof Interest:Theauthorsdeclarenoconflictof interest.
References
1. Ceraolo,M.;Miulli,C.;Pozio,A.Modellingstaticanddynamicbehaviourofprotonexchangemembrane
fuelcellsonthebasisofelectro-chemicaldescription. J.PowerSources2003,113, 131–144. [CrossRef]
2. Gorgun,H.Dynamicmodellingofaprotonexchangemembrane(PEM)electrolyzer. Int. J.HydrogenEnergy
2006,31, 29–38. [CrossRef]
95
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