Page - 281 - in Short-Term Load Forecasting by Artificial Intelligent Technologies
Image of the Page - 281 -
Text of the Page - 281 -
Energies2018,11, 1605
2026. However, the average annual rateswill decrease in all. For the period between 1965 and
2016, the rate of increaseswas 2.2% forBPNN,1.3% forLR, 1.8% for SVR, 1.5% for bagging1.6%,
forAR2.0%forSMLE-basedSVR,2.0%forSMLE-basedBPNN,and2.1%forSMLE-basedBPNN-SVR.
Additionally, for the forecastedperiodbetween2017and2026 therateswereexpected tobe0.74%,
1.39%,1.38%,1.42%,1.39%0.13%,0.38%,and0.44, respectively.Ontheotherhand, theaverageannual
rateof totaloildemanddecreasedfrom1.8%between1965and2016 to0.91%between2017and2026.
Lastly, thesummarizedresults inTable6demonstrate that theannualgrowthratesof1-ahead
OCweremoresignificant thanthe totalaverageOCin10-aheadyears. Figure8, showstheapparent
rise in the1-aheadinbothsingleandclassicensemblemodels,andfor theSMLEmodels therewas
asuddendropfrom1- to2-aheadyears, alsonote thestability in thegrowthfrom2-aheadto10-ahead,
withclosevalues inallmodels, except forSMLE-basedBPNNwhere therewasafewdecreasing in
the 9-, 10-ahead, sequentially. Thedecrease in the rate of oil demandmaybe interpretedas there
beingotheralternativeenergies thataffectoildemand, thiswillbeachievedinthecomingdecades,
ascomparedwithallotherenergytypeconsumption.Ratesofchangesandreserves in theOCofall
themodels indicate that theSMLEschemewas thebest todetermine theactualdemandofenergy
globally,which facilitates theplanningprocess, associatedwith the issueOCprediction. Basedon
thesestudyfindings,wesuggestedsomerecommendations.
Figure7. Illustrated10-aheadconsumptionpredictionerrorsof (a) singlemodels (b) classicmodels
(c)SMLEensemblemodels.
Table6.Summaryof forecastedvaluesandCGRforOCusingallmodels from2017to2026.
Years Models
BPNN LR SVR Bagging RF 1stSMLE 2ndSMLE 3rdSMLE
2017 4279.16 4531.93 4504.13 4559.73 4531.93 4554.73 4395.00 4459.94
2018 4316.27 4595.00 4567.34 4646.02 4595.00 4737.14 4409.57 4523.12
2019 4349.24 4677.23 4650.48 4748.19 4677.23 4764.54 4426.70 4511.95
2020 4401.42 4771.37 4746.31 4819.88 4771.37 4835.67 4454.33 4530.88
2021 4448.96 4857.41 4821.93 4896.70 4857.41 4967.25 4482.28 4592.90
281
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