Page - 363 - in Short-Term Load Forecasting by Artificial Intelligent Technologies
Image of the Page - 363 -
Text of the Page - 363 -
Energies2018,11, 1253
Figure7.Relationshipbetweendaytypeanddaily loadofEVchargingstation.
4.CaseStudy
TheselectedEVchargingstation in thispaper iscomposedof5 largepowerchargerswhichcan
beusedbybatterieswithhighcapacity inasinglebox,orseriesbatterieswith lowcapacity in three
boxes, and10smallpowerchargers that canbeonlyemployedbyabatterywith lowcapacity ina
singlebox. The loaddataevery30minfrom1June2016to30November2017arecollectedfromthe
chargingstation. Thedata from1June2016 to29November2017areselectedas trainingset, andthe
remainingdataon30November2017areutilizedas test set.
4.1. InputSelectionandProcessing
Accordingto theanalysisof the loadcharacteristics forEVchargingstation, ten influential factors
includingseasonalcategory,maximumtemperature,minimumtemperature,weathercondition,day
type,andthe loadsat thesamemoment in thepreviousfivedaysareselectedas input in thispaper.
The input featuresarediscussedas follows: (a) theseasoncanbedividedinto fourcategories: spring
(March,AprilandMay), summer(June, JulyandAugust), autumn(September,October,November)
andwinter (December, JanuaryandFebruary),whicharesetas{1,2,3,4}. (b)Weatherconditionsare
decomposedinto twotypes: sunnyandcloudydays,valuedat1,andrainyandsnowydays,valuedat
0.5. (c)Dayscanbedivided intoworkdays (MondaytoFriday)andweekends (SaturdayandSunday).
Whenquantifying thedaytype,workdaysarevaluedat1,andweekendsat0.5. Because thecollecting
data isnotpublicallyavailable, statisticallysignificantparametersarepresented inTable1.
Table1.Statisticallysignificantparametersof thecollectingdata.
Statistics TotalDays MaximumLoad(MW) MinimumLoad
(MW) Maximum
Temperature (◦C) MinimumTemperature
(◦C)
Value 547 5.212 0.006 36 −13
Statistics Numberofdaysinspring(day) Numberofdays
insummer(day) Numberofdays
inautumn(day) Numberofdays in
winter (day) Numberofprecipitation
days (day)
Value 92 184 182 89 76
Thetemperatureandloaddatashouldbenormalized inaccordancewithEquation(11).
Y={yi}= xi−xminxmaxxmin i=1,2,3, . . . ,n (11)
363
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