Page - 208 - in Short-Term Load Forecasting by Artificial Intelligent Technologies
Image of the Page - 208 -
Text of the Page - 208 -
Energies2018,11, 1948
declines fromNT$28 toNT$9 (NT$1)per batch, the systemcostdrops fromNT$1685 toNT$1662
(NT$1088)perday. Second, theenergysupplyratiobythePEMFCincreases to19.6%(59.5%)when
thehydrogenprice isNT$9orNT$1perbatch. Under this scenario, the systemtends tousemore
hydrogen energy, as the cost is competitivewith that of other renewable energies. Last, the stack
pricehas little influenceon the systemcostbecause it is considered in the initial cost (from10k to
180k). Forexample,whenthehydrogenprice isgreater thanNT$11/batchandthePEMFCstackcost
drops fromNT$180ktoNT$90k, thesystemcostdrops fromNT$1685 toNT$1667perday.Whenthe
hydrogencost isNT$9(NT$1)perbatchandthePEMFCstackpricedrops fromNT$180ktoNT$90k,
thesystemcostdrops fromNT$1662(NT$1088) toNT$1615(NT$999)perday.
+\GURJHQ SULFH SHU EDWFK 17' EDWFK N
N
N
N
N
N
N
N
Figure11.The influenceofhydrogenpricesonsystemcosts.
4.Conclusions
Thispaperdemonstrated theoptimizationofhybridpowersystems.Wedevelopedageneral
hybrid power model that consisted of solar cells, a WT, a fuel cell, hydrogen electrolysis,
chemicalhydrogengeneration,andbatteries. Themodelparametersare tunedbasedonexperimental
data, so that system responses under different operation conditions can be predicted without
conducting individual experiments. Then, the performance of four hybrid systems under three
typical loadswasevaluatedbycalculatingsystemcostsandreliability. Theresults showedthat the
costs and reliability of all the systemswere effectively improved by optimizing the system sizes.
The hybrid systemwith the solar panels andbattery sets achieved the lowest costs, aswind and
hydrogenenergyarerelativelyexpensiveatpresent. Last, the impactsof stackandhydrogenpriceson
systemcostswasanalyzed. Theresults indicatedthathydrogenpriceshadamoresubstantial influence
thanthestackpriceonsystemcosts,andthathydrogenenergywouldbecompetitivewhenitsprice
fell toaboutone-thirdof thecurrentprice. In futureresearch, the impactofcostofothercomponents,
suchas thePVandWT,canbeanalyzedinasimilarway.
Author Contributions: Conceptualization, F.-C.W.; Methodology, F.-C.W. and Y.-S.H.; Software, Y.-S.H.;
Validation,F.-C.W.,Y.-S.H.andY.-Z.Y.;FormalAnalysis,F.-C.W.andY.-S.H.; Investigation,F.-C.W.andY.-S.H.;
Resources,F.-C.W.andY.-S.H.;DataCuration,F.-C.W.,Y.-S.H.,andY.-Z.Y.;Writing-OriginalDraftPreparation,
Y.-S.H.; Writing-Review and Editing, F.-C.W.; Visualization, F.-C.W., Y.-S.H., Y.-Z.Y.; Supervision, F.-C.W.;
ProjectAdministration,F.-C.W.;FundingAcquisition,F.-C.W.
208
Short-Term Load Forecasting by Artificial Intelligent Technologies
- Title
- Short-Term Load Forecasting by Artificial Intelligent Technologies
- Authors
- Wei-Chiang Hong
- Ming-Wei Li
- Guo-Feng Fan
- Editor
- MDPI
- Location
- Basel
- Date
- 2019
- Language
- English
- License
- CC BY 4.0
- ISBN
- 978-3-03897-583-0
- Size
- 17.0 x 24.4 cm
- Pages
- 448
- Keywords
- Scheduling Problems in Logistics, Transport, Timetabling, Sports, Healthcare, Engineering, Energy Management
- Category
- Informatik