Page - 362 - in Short-Term Load Forecasting by Artificial Intelligent Technologies

Energies2018,11, 1253 Figure5.Relationshipbetweentemperatureanddaily loadofelectricvehicle (EV)chargingstation. Dividetheweatherconditions into twocategories: sunnydaysandrainydays.Figure6 illustrates the relationship between weather conditions and the daily load of the EV charging station on 21 February and 22 February in 2017. It is sunny on 21 February and it is rainy on 22 February. It proves that snowdays can reduce thedailymaximumloadas a result of vehicle’s deceleration, which leads to thedecreaseofdailydrivingmileageandcharging.Hence, snowisanother important influential factor. Figure6.Relationshipbetweenweatherconditionanddaily loadofEVchargingstation. 3.3.DayTypes Dividethedays intoworkdays,SaturdayandSunday. Figure7describes therelationshipbetween daytypesanddaily loadof theEVchargingstationbasedonthedata from14August to20August in 2017. It isMonday toFriday from14August to18August. 19Augustand20AugustareSaturday and Sunday respectively. The loads onworkdays are slightly lower than those of theweekends. FromMonday to Friday, the use of EVs focuses on the period that people go to and fromwork, while theabundantoutdooractivitiesonSaturdayandSundayincrease theuseofEVs. Tothisend, thedaytype ischosenasan influential indicator in thispaper. 362