Seite - 197 - in Short-Term Load Forecasting by Artificial Intelligent Technologies
Bild der Seite - 197 -
Text der Seite - 197 -
Energies2018,11, 1948
2.2. TheWindPowerModel
The WT used in this paper was a commercial product, JPS-200, which is equipped with
apermanentmagnet synchronousgenerator thathasa ratingpowerof200W[21]. Awindpower
system and a theoretical model are developed to estimatewind power fromwind speed based
on experimental responses. The experimentswere conductedusing an industrial fan,whichhad
amaximumwindspeedof about 10m/s. Thewindpower systemstructure is shown inFigure2.
Wemeasured theACcurrent andvoltage fromawind turbine and recorded theDCcurrent and
voltage fromawindcontroller.
ŘŪůťġŵŶųţŪůŦġ ńŰůŵųŰŭŭŦųġ ŃŢŵŵŦųźġ
ŎŦŢŴŶųŦŮŦůŵġ ġ
ńŪųŤŶŪŵŴġ
Ĵġ
IJġ ĵġ ijġ
DF,IJ烉
GF,ij烉
DF9Ĵ烉
GF9ĵ烉
Figure2.Measurementof thewindpower.
TheWTwas testedunder steadywindandvaryingwindconditions. The time responses are
showninFigure3a,where theresponseschangeslowlywithsteadywind,butquicklywithvarying
wind. Fromthecomparisonof thewindspeedandACpower,as illustrated inFigure3b, thewind
powercanbetheoreticallydescribedusingthe followingequation:
Pac=0.11574V3wind (1)
where Pac andVwind represent the power and speed, respectively, of thewind. The experimental
resultsshowthat thewindpowercanbepredictedfromthewindspeedwithmaximumrootmean
square errors of 7.64Wand17.32Wfor steady andvaryingwind, respectively. TheWTreached
itsmaximumtheoretical power of 200Wwhen thewind speedwasgreater than 12m/s. We set
thebatteryvoltageat12V.TheenergyconversionrelationshipbetweenACandDCwindpower is
showninFigure3c,where thechargingoperation isdividedinto threezonesaccordingto thewind
turbinevoltageVac: (1)nocharging(whenVac<4.3V),where thewindcontrollerdoesnotcharge the
battery; (2) linearcharging(when4.3V≤Vac<8V),where theDCchargingvoltage increases linearly;
and(3)stablecharging(whenVac≥8V),where theDCchargingvoltage is14.3V.Theconversionof
ACandDCpowercanbedescribedas follows:
PDC=0.70973Pac−3.0958=0.0821V3wind−3.0958 (2)
as illustrated inFigure 3c. Therefore, givenwind speeddata, thewind turbineDCpower canbe
calculatedby (1) and (2). Equations (1) and (2) canbeapplied tobuild thewindpowermodule in
Figure2 for thesimulationandoptimizationanalyses.
197
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